🎬 Awesome Seedance 2.5 Prompts + Seedance 2.5 Skill

A curated library of Seedance 2.5 video prompts plus Seedance 2.5 Skill, an installable Agent Skill that improves prompts, plans and reviews storyboards when needed, and generates controllable video. It uses Seedream 5.0 Pro for storyboard images and Seedance 2.0 as the current executable video default, switching to Seedance 2.5 only when the selected provider exposes it.

📖 Contents

• 🤔 What is Seedance 2.5?
• 🧩 Seedance 2.5 prompt guide
• 🧠 Seedance 2.5 Skill
• 🌐 Universal Video Prompt Skill
• 🚀 How to use this repository
• ⚙️ Model and execution defaults
• 🔎 Curation and provenance
• 📊 Statistics
• 🔥 Featured Prompts
• 🏷️ Browse by Category
• 📋 All Prompts
• ❓ Frequently asked questions
• 🔗 Resources
• 📄 License

🤔 What is Seedance 2.5?

Seedance 2.5 is ByteDance's next-generation multimodal video generation model, following Seedance 2.0. It is designed for reference-driven video creation, longer narrative sequences, synchronized audio and video, and precise visual control.

Launch status: Seedance 2.5 is expected to launch in August 2026. Atlas Cloud is one of the first official API launch partners for Seedance 2.5.

Published Seedance 2.5 launch material describes up to 30-second generation, native 4K output, up to 50 multimodal references, and local region editing. Treat these as announced capabilities, not universal API parameters.

Availability note: provider availability, reference limits, duration, resolution, and editing controls can differ. The Skill verifies actual model availability instead of assuming Seedance 2.5 is callable.

🧩 Seedance 2.5 prompt guide

Prompt structure used by the Skill

1. Reference binding: state what each image, video, or audio reference controls.
2. Observable action: describe visible events in temporal order, including reactions and state changes.
3. Spatial relationships: say where subjects, objects, and the camera are in relation to each other.
4. Camera and cuts: specify framing, movement, cut order, match actions, and occlusions only where they matter.
5. Visual style: define lighting, palette, texture, atmosphere, and pace.
6. Audio: define dialogue, ambience, sound effects, or music when the selected model supports them.
7. Constraints: preserve only the identities, product details, scene traits, and exclusions that are essential.

🧠 Seedance 2.5 Skill

Seedance 2.5 Skill is the name of the installable Agent Skill in this repository. It turns a creative brief, existing prompt, references, or a storyboard into a production-ready prompt, the necessary intermediate assets, an execution request, and a review loop.

Install

Install the workflow Skill, the Universal Video Prompt Skill it references, and the default Atlas Cloud execution Skill:

npx skills add AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill seedance-2-5-skill
npx skills add AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill
npx skills add AtlasCloudAI/atlas-cloud-skills --skill atlas-cloud

What it does

• Improve prompts: turn an idea, an existing prompt, or reference assets into a clearer production-ready Seedance prompt.
• Plan and review storyboards: create a Seedream 5.0 Pro storyboard only when the video needs multi-shot planning or stronger visual consistency, display it as progress, and review its quality automatically.
• Generate and review video: use the best available Seedance model, submit through the selected Atlas Cloud channel, poll the same task to completion, and check the result.

🌐 Universal Video Prompt Skill

Universal Video Prompt Skill writes one model-agnostic prompt spec and compiles it to whichever video model you can actually call. A spec records the decisions a prompt encodes — scope, locks, staging, end states — separately from the dialect that expresses them, so the same brief survives a change of model instead of being rewritten. Each model gets a measured profile covering reference syntax, limits, timing adherence, and default-bias behaviour; the Skill probes what it does not know, degrades the spec to what the model supports, and reports every degrade.

Which one to use: use Seedance 2.5 Skill for Seedance-specific writing and execution. Use Universal Video Prompt Skill when one brief has to run across several models, when you are comparing models, or when the model you want is not available yet and the work has to proceed on another one.

Install

npx skills add AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill

This Skill can be installed on its own for standalone cross-model work. A complete Seedance 2.5 Skill setup installs all three Skills shown above.

🚀 How to use this repository

1. Browse: filter by category, open a real preview when available, and copy the prompt.
2. Adapt: ask Seedance 2.5 Skill to rewrite a prompt for your subject, duration, aspect ratio, references, and continuity needs.
3. Generate: let the Skill create and show intermediate storyboards when needed, review them automatically, and submit the final image or video request through the selected Atlas channel.

⚙️ Model and execution defaults

The workflow Skill and the execution adapter are separate layers. The workflow decides what to make; the selected Atlas channel submits, polls, and retrieves the media.

Model defaults

Storyboard stills: Seedream 5.0 Pro. Executable video default: Seedance 2.0. Seedance 2.5: only when the selected provider exposes the model and its actual limits.

• Atlas Cloud Skill: default direct execution route inside an Agent conversation. If it is missing, the workflow helps install it and directs the user to obtain an API key.
• Atlas MCP: used when the user explicitly selects MCP and its generation tools are available.
• Atlas CLI / REST: used for explicit terminal, script, CI, or batch workflows.

All asynchronous jobs are polled every 2 seconds using the same prediction ID. A timeout or delayed output is not permission to submit a duplicate paid generation.

→ Get an Atlas Cloud API key

🔎 Curation and provenance

Every prompt record keeps its category, source platform, author, source link, input references, and preview video when available. Prompt text remains unchanged during README generation.

• The official and community labels describe where a prompt came from; they are not a guarantee that every prompt has been independently benchmarked across every provider or model version.
• A preview demonstrates one observed output under its original setup. Results can change with model version, provider parameters, references, aspect ratio, seed, and moderation.

📊 Statistics

🔥 Featured Prompts

No. 1: Crystal Ball Match-Cut Beat Film

• Category: Match-Cut & Creative Effects
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

Description

A beat-synced match-cut film: one crystal ball etched with a glowing 'seedance' logo stays centered while eight scenes cut seamlessly behind it.

Prompt

A fast-paced, cinematic Match-cut short film synced to a driving electronic beat. A flawless crystal ball stays fixed dead-center throughout, a glowing "seedance" logo etched inside it. The ball holds razor-sharp focus while, on every strong musical beat, the background match-cuts seamlessly: Scene 1: macro close-up, cinematic water splashing around the ball, refracting intricate light. Scene 2: a vintage morning cafe, the ball on a raw-wood table, rising coffee steam and blurred commuters beyond the window. Scene 3: golden-hour dusk, a skater youth tosses and catches the ball one-handed, street racing backward behind them in gorgeous backlit sunset. Scene 4: a frenzied music festival, hands raise the ball high, refracting dazzling stage lasers. Scene 5: a lively family party table, the ball resting center-frame, blurred figures toasting and reaching for food. Scene 6: a dim cinema, hands cupping the ball as the giant screen's faint glow drifts across its surface. Scene 7: the ball on a violently vibrating speaker diaphragm, match-cutting on the climax to a spinning DJ turntable center. Scene 8: an outdoor camping night, background becoming warm bonfire and swaying string-light bokeh. Finale: on the final downbeat the ball is hurled up out of frame; cut to pure black, a minimal white-on-black "seedance" appearing dead-center. Beat-synced match-cut editing, top-tier cinematic color grading, photoreal glass refraction, ray tracing, global illumination. Subject razor-sharp, background heavy motion blur.

No. 2: Steampunk Clockwork — 30s One-Take

• Category: One-Take Cinematography
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

Description

A 30-second steampunk miniature 3D sequence with continuous orbiting, pass-through camera moves.

Prompt

A high-end, deeply cinematic 30-second 3D motion-graphics sequence in refined steampunk and vintage-miniature style, with continuous fluid orbiting and pass-through camera moves. [0-10s] Macro close-up of an antique brass clock face that unfolds layer by layer into meshing rotating gear rings and volumetric fog. The camera pierces down through the gears; a mechanical ornithopter spirals up from a miniature canyon of stacked weathered old books. [10-20s] The camera glides forward tracking the ornithopter, seamlessly passing into a fast-spinning ornate brass zoetrope projecting galloping mechanical-horse light. The light leaps out and the scene becomes a brass floating cable car on glimmering copper rails through a forest of gears, bathed in cinematic golden-hour light. [20-30s] The camera pans elegantly down; below appears an exquisite clockwork wooden sailing ship cutting deep-blue glass-textured waves, which morph into a glowing giant moon with lantern-holding explorer silhouettes trekking a crystal-vein ridge under stars. The camera spirals smoothly back through ethereal clouds to the ticking brass clock face. Hyper-real mechanical textures, rich brass and gold tones, cinematic shallow depth of field, smooth seamless pass-through camerawork, epic fantastical adventure atmosphere.

No. 3: Windows Through Worlds (5 refs)

• Category: Multi-Image Reference
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A brand concept short driven by 5 reference images, gliding through windows into different worlds.

Prompt

A cinematic brand concept short. @image1 is the first frame; the picture trembles slightly, the camera pushes in to tree shadows rushing backward outside the window, their retreat accelerating, then abruptly cuts to @image2, speed easing as the camera glides slowly along a stream, birdsong and blossoms. The camera drops underwater — bubble sounds — as orange jellyfish drift gracefully past the lens @image3; the camera pulls back as small fish flit past and swim from the water into the window @image4, a girl looking around, watching them. The camera pulls back, defocuses, then refocuses sharp, switching to the music's rhythm: a Chinese-garden lattice window @image5 with light circling, church stained glass, an airplane porthole, a dome skylight, a bay window, louver blinds, a European dormer, a door peephole, a camera viewfinder, a bird's eye, a human eye close-up. It settles on the human eye; the eye closes, screen black, then suddenly opens — "seedance" appearing in the center of the eye on the accent beat.

No. 4: One-Take Through Six Rooms (8 refs)

• Category: Multi-Image Reference
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

One continuous take following a figure through six mood-shifting rooms, driven by 8 reference images.

Prompt

One continuous take. The camera smoothly follows a person in a black coat (reference @image1) moving left to right through six connected rooms of different tones and moods. Every room shares the same structure: white walls, light herringbone wood floor, French floor-to-ceiling windows, white sheer curtains (reference @image2) but the outside view and mood differ each time. The protagonist walks at a constant pace, passing through every open door. 0-5s room one, American-comic fight: the protagonist fights a character (@image3), who is defeated; 5-10s room two, warmth, felt-craft style, window view a sunflower field (@image4), warm-orange soft light, a painter painting sunflowers (@image5), the protagonist turning felt-style on entering; 10-15s room three, sorrow, black-and-white comic stop-motion, rain outside, cold-grey light, a person alone on the floor hugging their knees, a phone glowing with an unanswered call; on entering, the light blinks off then on, the room turns color, flowers bursting into bloom; 15-20s room four, joy, a room submerged in the sea (reference @image6), the protagonist turning transparent among coral and fish; 20-25s room five, surprise, window view a sky of fireworks (reference @image7), colorful flickering light, the protagonist swept up in a cheering crowd; 25-30s a blank white room, the protagonist snaps their fingers — snap SFX — frame goes black, "seedance" in the middle (reference @image8). Cinematic quality, high-fashion advertising style, lighting entirely determined by the window views for strong emotional contrast, no text in frame.

No. 5: Video Edit — Remove All But the Lead

• Category: Video Editing
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

Reference-video editing: erase everyone except the protagonist from a source clip.

Prompt

Video editing: remove everyone in @video1 except the protagonist.

No. 6: Multilingual Hip-Hop 'Hello' MV

• Category: Multi-Image Reference
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A seaside hip-hop MV built from one reference image; the lead raps 'hello' in 8 languages, lip-synced, hard cuts on the beat.

Prompt

Cinematic hip-hop / rap music video, photoreal quality, high-end tone, seaside setting. Build the frame from @image1: a band performs at a golden sand beach with crashing waves — a lead vocalist gripping a mic on a stand in the wet sand, one guitarist left, one right, a drummer at the back; a vast coastline behind, rolling waves, a warm golden-hour sun shimmering on the water, sea mist in the air. The lead in a red tracksuit raps to camera — lips and jaw precisely synced to every word, head punching to the beat. Bright, punchy, fast, confident rap. HARD CUT on the beat, each switch a double contrast (shot size and type change together). Lyrics (the lead sings 'hello' in each language in turn, precisely lip-synced): English "Hello", Chinese "你好", Japanese "こんにちは", Korean "안녕하세요", Portuguese "Olá", Thai "สวัสดี", Spanish "Hola", Arabic "مرحبا". 8 hard-cut shots (low-angle wide establishing; close-up rap to camera; macro guitar-string insert; 3/4 prowling orbit; lateral track at shore; drummer tilt-up; tight push on the lead; heroic full-band push-in), one language per shot. White balance 4000K, teal-and-amber grade, 35mm, shallow depth of field, film grain, sea mist, golden-hour flare. Premium feel, precise lip-sync, no subtitles, no text overlays, hard cuts only, total 20 seconds.

No. 7: Capsule Coffee Machine Setup Tutorial (6 refs)

• Category: Reference-Guided Tutorial
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A 30-second setup-and-use tutorial for a capsule coffee machine, six reference-guided steps with voiceover — from installing the water tank to the first rinse.

Prompt

A 30-second tutorial video on installing and using a capsule coffee machine. 0-2s: the opening title card reads "seedance capsule coffee machine setup tutorial". 2-5s, Step 1: install the water tank, reference @image1, medium shot from a slightly high angle, rear of the machine body, align the water tank with the slot on the back of the body and push it straight down until it clicks firmly into place, clearly showing how the tank's bottom clips align with the body's slot, the water level line visible through the tank's transparent section, voiceover "First, install the water tank. Align the tank with the slot on the back of the machine; a click means it is locked in place.". 5-9s, Step 2: install the drip tray, reference @image2, close-up front view, front bottom of the body, slide the drip tray horizontally into the guide rails at the bottom until fully seated, voiceover "Next, install the drip tray. Align the tray with the bottom rails.". 9-13s, Step 3: install the used-capsule collection box, reference @image3, close-up from a slightly low angle, the cavity beneath the drip tray, align the collection box with the recess and push it in flush with the drip tray, voiceover "Then insert the capsule collection box. Used capsules will drop down here automatically.". 13-18s, Step 4: first fill with water, reference @image4, close-up side view, the water tank at the top/back of the body, open the tank lid and pour in clean water up to the MAX water level line, then close it, emphasizing the water level line, voiceover "Open the tank lid, pour in clean water, being careful not to exceed the maximum water level line, then close the tank lid.". 18-25s, Step 5: power on, reference @image5, medium shot front view, front of the body, plug in the power cord and press the power button; the indicator light goes from blinking to steady (preheating complete), voiceover "Connect the power and press the power button. The indicator light starts blinking, which means it is preheating. When the light turns steady, the machine is ready.". 25-30s, Step 6: first rinse (without a capsule), reference @image6, medium shot moving to a close-up front-side view, without inserting a capsule press the brew button directly so hot water flows out and rinses the lines, emphasizing the "no capsule needed" note, voiceover "The last step, the first rinse. Note that this step does not require a capsule; just press the brew button. Once the rinse is done, your coffee machine is ready to use."

No. 8: Fruity Cookie Commercial (image + 6 video refs)

• Category: Multimodal Reference (image+video)
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A bright, colorful commercial for fruity cookies in four flavors — strawberry, apple, grape, orange — built from one image reference and six motion/camera video references, cut hard to a driving beat.

Prompt

A bright, colorful commercial style with fruity cookies as the hero, in four flavors — strawberry, apple, grape, and orange; strawberry flavor reference @image1. The cookies and their matching fruits are arranged in a strongly ordered geometric array; the overall frame is clean, premium, and high-energy. It opens with the fruits orbiting rapidly around the central cookie to quickly establish visual focus — reference the composition of @video1 — cutting in on a strong musical beat. Then cookies of different flavors advance toward the lens along spiral paths, forming clear spatial depth — reference the motion and camera work of @video2 — switching colors and flavors on the beat with the background music. The array of cookies pans left and right with fast plane-to-plane cuts, strawberry, apple, grape, and orange flavors alternating as the frame jump-cuts quickly to the rhythm — reference the movement of @video3. The mid-section adds up-and-down panning; the neat cookie array rises and falls vertically like a machine — reference the movement of @video4 — highlighting the beauty of order and the richness of the product. In the climax a cookie is snapped in two and the moment enters slow motion as the fruity filling bursts open, crumbs scattering, the juicy sensation and grainy impact amplified — reference the explosion effect of @video5 — then quickly returns to the fast-paced edit. The ending brings in the English text "Fresh on Seedance, made for viral vision", entering word by word in quick succession with strong rhythmic text motion and a product freeze-frame — reference @video6 — the four cookie flavors lined up neatly with the fruits bouncing in sync for a final brand-forward close, the frame full of a young, energetic, delicious, shareable ad atmosphere.

🏷️ Browse by Category

• Match-Cut & Creative Effects: 1
• One-Take Cinematography: 1
• Multi-Image Reference: 3
• Video Editing: 2
• Reference-Guided Tutorial: 1
• Multimodal Reference (image+video): 1
• Image Reference: 1
• Image Reference (Cinematic): 1
• E-commerce Livestreaming: 8
• Food & Dining: 8
• Beauty & Fashion: 6
• Digital Tech & Gadgets: 6
• Automotive: 4
• Real Estate & Home: 4
• Talking Head & Digital Humans: 6
• Short Dramas & Emotional Stories: 8
• Brand Commercials & Ads: 6
• Travel & Cultural Tourism: 6
• Pets & Animals: 5
• Kids, Education & Science: 5
• Gaming, CG & Fantasy: 5
• Animation & Cartoons: 4
• Sports & Fitness: 4
• Music, Dance & Music Videos: 4
• Festivals & Solar Terms: 5
• Nature, Astronomy & Documentaries: 4
• Anthropomorphic & Creative Memes: 2
• Film & Storytelling: 11
• Advertising & E-commerce: 8
• Knowledge & Explainer: 6
• Industrial & Manufacturing: 4
• Creative & Misc: 3
• Capability Showcase: 7

📋 All Prompts

Match-Cut & Creative Effects (1)

No. 1: Crystal Ball Match-Cut Beat Film

• Category: Match-Cut & Creative Effects
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

Description

A beat-synced match-cut film: one crystal ball etched with a glowing 'seedance' logo stays centered while eight scenes cut seamlessly behind it.

Prompt

A fast-paced, cinematic Match-cut short film synced to a driving electronic beat. A flawless crystal ball stays fixed dead-center throughout, a glowing "seedance" logo etched inside it. The ball holds razor-sharp focus while, on every strong musical beat, the background match-cuts seamlessly: Scene 1: macro close-up, cinematic water splashing around the ball, refracting intricate light. Scene 2: a vintage morning cafe, the ball on a raw-wood table, rising coffee steam and blurred commuters beyond the window. Scene 3: golden-hour dusk, a skater youth tosses and catches the ball one-handed, street racing backward behind them in gorgeous backlit sunset. Scene 4: a frenzied music festival, hands raise the ball high, refracting dazzling stage lasers. Scene 5: a lively family party table, the ball resting center-frame, blurred figures toasting and reaching for food. Scene 6: a dim cinema, hands cupping the ball as the giant screen's faint glow drifts across its surface. Scene 7: the ball on a violently vibrating speaker diaphragm, match-cutting on the climax to a spinning DJ turntable center. Scene 8: an outdoor camping night, background becoming warm bonfire and swaying string-light bokeh. Finale: on the final downbeat the ball is hurled up out of frame; cut to pure black, a minimal white-on-black "seedance" appearing dead-center. Beat-synced match-cut editing, top-tier cinematic color grading, photoreal glass refraction, ray tracing, global illumination. Subject razor-sharp, background heavy motion blur.

One-Take Cinematography (1)

No. 1: Steampunk Clockwork — 30s One-Take

• Category: One-Take Cinematography
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

Description

A 30-second steampunk miniature 3D sequence with continuous orbiting, pass-through camera moves.

Prompt

A high-end, deeply cinematic 30-second 3D motion-graphics sequence in refined steampunk and vintage-miniature style, with continuous fluid orbiting and pass-through camera moves. [0-10s] Macro close-up of an antique brass clock face that unfolds layer by layer into meshing rotating gear rings and volumetric fog. The camera pierces down through the gears; a mechanical ornithopter spirals up from a miniature canyon of stacked weathered old books. [10-20s] The camera glides forward tracking the ornithopter, seamlessly passing into a fast-spinning ornate brass zoetrope projecting galloping mechanical-horse light. The light leaps out and the scene becomes a brass floating cable car on glimmering copper rails through a forest of gears, bathed in cinematic golden-hour light. [20-30s] The camera pans elegantly down; below appears an exquisite clockwork wooden sailing ship cutting deep-blue glass-textured waves, which morph into a glowing giant moon with lantern-holding explorer silhouettes trekking a crystal-vein ridge under stars. The camera spirals smoothly back through ethereal clouds to the ticking brass clock face. Hyper-real mechanical textures, rich brass and gold tones, cinematic shallow depth of field, smooth seamless pass-through camerawork, epic fantastical adventure atmosphere.

Multi-Image Reference (3)

No. 1: Windows Through Worlds (5 refs)

• Category: Multi-Image Reference
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A brand concept short driven by 5 reference images, gliding through windows into different worlds.

Prompt

A cinematic brand concept short. @image1 is the first frame; the picture trembles slightly, the camera pushes in to tree shadows rushing backward outside the window, their retreat accelerating, then abruptly cuts to @image2, speed easing as the camera glides slowly along a stream, birdsong and blossoms. The camera drops underwater — bubble sounds — as orange jellyfish drift gracefully past the lens @image3; the camera pulls back as small fish flit past and swim from the water into the window @image4, a girl looking around, watching them. The camera pulls back, defocuses, then refocuses sharp, switching to the music's rhythm: a Chinese-garden lattice window @image5 with light circling, church stained glass, an airplane porthole, a dome skylight, a bay window, louver blinds, a European dormer, a door peephole, a camera viewfinder, a bird's eye, a human eye close-up. It settles on the human eye; the eye closes, screen black, then suddenly opens — "seedance" appearing in the center of the eye on the accent beat.

No. 2: One-Take Through Six Rooms (8 refs)

• Category: Multi-Image Reference
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

One continuous take following a figure through six mood-shifting rooms, driven by 8 reference images.

Prompt

One continuous take. The camera smoothly follows a person in a black coat (reference @image1) moving left to right through six connected rooms of different tones and moods. Every room shares the same structure: white walls, light herringbone wood floor, French floor-to-ceiling windows, white sheer curtains (reference @image2) but the outside view and mood differ each time. The protagonist walks at a constant pace, passing through every open door. 0-5s room one, American-comic fight: the protagonist fights a character (@image3), who is defeated; 5-10s room two, warmth, felt-craft style, window view a sunflower field (@image4), warm-orange soft light, a painter painting sunflowers (@image5), the protagonist turning felt-style on entering; 10-15s room three, sorrow, black-and-white comic stop-motion, rain outside, cold-grey light, a person alone on the floor hugging their knees, a phone glowing with an unanswered call; on entering, the light blinks off then on, the room turns color, flowers bursting into bloom; 15-20s room four, joy, a room submerged in the sea (reference @image6), the protagonist turning transparent among coral and fish; 20-25s room five, surprise, window view a sky of fireworks (reference @image7), colorful flickering light, the protagonist swept up in a cheering crowd; 25-30s a blank white room, the protagonist snaps their fingers — snap SFX — frame goes black, "seedance" in the middle (reference @image8). Cinematic quality, high-fashion advertising style, lighting entirely determined by the window views for strong emotional contrast, no text in frame.

No. 3: Multilingual Hip-Hop 'Hello' MV

• Category: Multi-Image Reference
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A seaside hip-hop MV built from one reference image; the lead raps 'hello' in 8 languages, lip-synced, hard cuts on the beat.

Prompt

Cinematic hip-hop / rap music video, photoreal quality, high-end tone, seaside setting. Build the frame from @image1: a band performs at a golden sand beach with crashing waves — a lead vocalist gripping a mic on a stand in the wet sand, one guitarist left, one right, a drummer at the back; a vast coastline behind, rolling waves, a warm golden-hour sun shimmering on the water, sea mist in the air. The lead in a red tracksuit raps to camera — lips and jaw precisely synced to every word, head punching to the beat. Bright, punchy, fast, confident rap. HARD CUT on the beat, each switch a double contrast (shot size and type change together). Lyrics (the lead sings 'hello' in each language in turn, precisely lip-synced): English "Hello", Chinese "你好", Japanese "こんにちは", Korean "안녕하세요", Portuguese "Olá", Thai "สวัสดี", Spanish "Hola", Arabic "مرحبا". 8 hard-cut shots (low-angle wide establishing; close-up rap to camera; macro guitar-string insert; 3/4 prowling orbit; lateral track at shore; drummer tilt-up; tight push on the lead; heroic full-band push-in), one language per shot. White balance 4000K, teal-and-amber grade, 35mm, shallow depth of field, film grain, sea mist, golden-hour flare. Premium feel, precise lip-sync, no subtitles, no text overlays, hard cuts only, total 20 seconds.

Video Editing (2)

No. 1: Video Edit — Remove All But the Lead

• Category: Video Editing
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

Reference-video editing: erase everyone except the protagonist from a source clip.

Prompt

Video editing: remove everyone in @video1 except the protagonist.

No. 2: Steam Train Bursts the Screen (video edit)

• Category: Video Editing
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A video edit that keeps the original @video1 old-cinema clip intact and adds only a steam locomotive bursting through the screen, tearing the fabric, with black-and-white snapping to full color at the moment of impact.

Prompt

Hyper-real cinematic realist style with photorealistic live-action texture, emphasizing the real-world plausibility of the physical object bursting out (the steam train); no CGI gloss / game engine / stylized 3D. Preserve @video1's original composition, projection-hall lighting, handheld camera state and natural imperfections. Source video locked: keep @video1 fully intact as the base image (the old-fashioned projection hall, the rows of hat-wearing audience seen from behind, the projector's conical beam, the screen, the ambient light, the color tone and the handheld movement all unchanged); the only additions: the train bursting out of the screen, the changes in light and shadow it brings, the tearing of the screen, and the slight physical impact on the hall and the front-row audience. Color-shift rule (the core addition): at the start strictly keep @video1's original black-and-white old-film texture (grain / scratches / flicker / monochrome); at the exact moment the locomotive truly breaks through the screen and bursts into reality, the image abruptly shifts from black-and-white to full, real color, the color spreading across the whole frame like a shockwave centered on the point where the train breaks out (the train's black steel body, the red-copper boiler, the orange-yellow steam-lamp glow, the warm brown of the wooden carriage, the white-grey steam, and the warm brown of the projection hall all coming into color accordingly); the color shift is precisely synchronized with the screen-breaking burst, after which photorealistic color is maintained to the end. Screen-tearing locked: the screen is a real white projection cloth with genuine fabric tension; as the train bursts out it is forcibly torn open along the contour of the locomotive's front, with radial rips whose edges curl back and shredded cloth fibers flying. Subject: an old-fashioned steam locomotive front bursting forcibly out of the screen, a black steel body, a cylindrical boiler, a front cowcatcher, a chimney venting white-grey steam, a bright headlamp, the metal surfaces with real wear, oil grime, rivets and wet reflections, charging forward with immense weight and inertia. Camera: fully inherits @video1's original handheld movement, not smoothed, not re-timed, not re-composed; the bursting train stays correctly locked into the screen and the hall space at all times, maintaining correct parallax, occlusion and ground-contact shadow. Sound: no music, keep only real on-scene sound effects, inheriting @video1's projection-hall ambience (the projector's clatter, the audience's stirring) and adding the sound of the cloth tearing, steam gushing, the mechanical roar of steel wheels, and the impact air blast. Total duration exactly the same as @video1; add nothing other than the train itself and its physical interactions, the screen tearing, and the color shift at the moment of the break. No slow motion, no sense of magic, no stylized horror; the final result should look like an eerie yet real image of "a train smashing through the screen, black-and-white instantly turning to color" captured by chance by a real camera in an old projection hall.

Reference-Guided Tutorial (1)

No. 1: Capsule Coffee Machine Setup Tutorial (6 refs)

• Category: Reference-Guided Tutorial
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A 30-second setup-and-use tutorial for a capsule coffee machine, six reference-guided steps with voiceover — from installing the water tank to the first rinse.

Prompt

A 30-second tutorial video on installing and using a capsule coffee machine. 0-2s: the opening title card reads "seedance capsule coffee machine setup tutorial". 2-5s, Step 1: install the water tank, reference @image1, medium shot from a slightly high angle, rear of the machine body, align the water tank with the slot on the back of the body and push it straight down until it clicks firmly into place, clearly showing how the tank's bottom clips align with the body's slot, the water level line visible through the tank's transparent section, voiceover "First, install the water tank. Align the tank with the slot on the back of the machine; a click means it is locked in place.". 5-9s, Step 2: install the drip tray, reference @image2, close-up front view, front bottom of the body, slide the drip tray horizontally into the guide rails at the bottom until fully seated, voiceover "Next, install the drip tray. Align the tray with the bottom rails.". 9-13s, Step 3: install the used-capsule collection box, reference @image3, close-up from a slightly low angle, the cavity beneath the drip tray, align the collection box with the recess and push it in flush with the drip tray, voiceover "Then insert the capsule collection box. Used capsules will drop down here automatically.". 13-18s, Step 4: first fill with water, reference @image4, close-up side view, the water tank at the top/back of the body, open the tank lid and pour in clean water up to the MAX water level line, then close it, emphasizing the water level line, voiceover "Open the tank lid, pour in clean water, being careful not to exceed the maximum water level line, then close the tank lid.". 18-25s, Step 5: power on, reference @image5, medium shot front view, front of the body, plug in the power cord and press the power button; the indicator light goes from blinking to steady (preheating complete), voiceover "Connect the power and press the power button. The indicator light starts blinking, which means it is preheating. When the light turns steady, the machine is ready.". 25-30s, Step 6: first rinse (without a capsule), reference @image6, medium shot moving to a close-up front-side view, without inserting a capsule press the brew button directly so hot water flows out and rinses the lines, emphasizing the "no capsule needed" note, voiceover "The last step, the first rinse. Note that this step does not require a capsule; just press the brew button. Once the rinse is done, your coffee machine is ready to use."

Multimodal Reference (image+video) (1)

No. 1: Fruity Cookie Commercial (image + 6 video refs)

• Category: Multimodal Reference (image+video)
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A bright, colorful commercial for fruity cookies in four flavors — strawberry, apple, grape, orange — built from one image reference and six motion/camera video references, cut hard to a driving beat.

Prompt

A bright, colorful commercial style with fruity cookies as the hero, in four flavors — strawberry, apple, grape, and orange; strawberry flavor reference @image1. The cookies and their matching fruits are arranged in a strongly ordered geometric array; the overall frame is clean, premium, and high-energy. It opens with the fruits orbiting rapidly around the central cookie to quickly establish visual focus — reference the composition of @video1 — cutting in on a strong musical beat. Then cookies of different flavors advance toward the lens along spiral paths, forming clear spatial depth — reference the motion and camera work of @video2 — switching colors and flavors on the beat with the background music. The array of cookies pans left and right with fast plane-to-plane cuts, strawberry, apple, grape, and orange flavors alternating as the frame jump-cuts quickly to the rhythm — reference the movement of @video3. The mid-section adds up-and-down panning; the neat cookie array rises and falls vertically like a machine — reference the movement of @video4 — highlighting the beauty of order and the richness of the product. In the climax a cookie is snapped in two and the moment enters slow motion as the fruity filling bursts open, crumbs scattering, the juicy sensation and grainy impact amplified — reference the explosion effect of @video5 — then quickly returns to the fast-paced edit. The ending brings in the English text "Fresh on Seedance, made for viral vision", entering word by word in quick succession with strong rhythmic text motion and a product freeze-frame — reference @video6 — the four cookie flavors lined up neatly with the fruits bouncing in sync for a final brand-forward close, the frame full of a young, energetic, delicious, shareable ad atmosphere.

Image Reference (1)

No. 1: Desert Horned Lizard & Grapefruit (3D ad)

• Category: Image Reference
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A bright, glossy 3D animated commercial: a parched desert horned lizard finds a grapefruit, bites in, and a juice tsunami turns the desert into a summer sea. Built from one character reference.

Prompt

A 3D animated commercial style, bright and translucent colors; the pulp and juice must feel intensely refreshing and impactful. The overall vibe is like a high-quality commercial animated short with a touch of exaggerated humor. The desert horned lizard character is cute, lively and expressive, reference @image1. The image texture references that soft natural light, delicate fuzz/skin texture, dreamy macro depth of field, and a realistic-yet-slightly-childlike feel from the reference image. 0-3s: a desert scorched by the blazing sun, the air shimmering with heat and the sand searing hot; a desert horned lizard lies on the scalding sand, tongue slightly out, eyes glazed, nearly dried out, swaying with every couple of steps as if about to "evaporate". 3-6s: it suddenly stops, its nose twitches, and looking down it spots a cool, plump, dew-covered grapefruit half-buried in the sand, glistening like a desert miracle; the lizard's eyes go wide in an instant. 6-8s: it pounces over, hugging the grapefruit tightly with both hands, pressing its whole face against the rind with a blissful "I'm finally alive" expression; the frame holds for 1 second, forming an exaggerated, funny memory beat. 8-11s: it looks up, opens its mouth and takes a big bite; the grapefruit rind splits open, the plump pulp shining with a translucent gloss, and the next moment the juice erupts like a tsunami. 11-16s: orange-pink, translucent, glistening grapefruit juice gushes out wildly, pouring down the dunes and rapidly flooding the entire desert; the dry yellow sand instantly turns into a cool, sparkling, fruit-scented summer sea, cacti, rocks and small dunes swallowed by the waves of juice, the lizard's expression turning from delight to terror. 16-20s: nearly drowned by the "grapefruit sea", it frantically clutches half a grapefruit like a life buoy and floats, poking its soaked head out looking dazed. 20-24s: cut to a white screen; the brand name and slogan appear dead-center: "Seedance Grapefruit — bite in for the pulp, what pours out is summer." The voiceover reads the whole line. 24-30s: cut back from white; the desert horned lizard is now lounging on the floating grapefruit, wearing tiny sunglasses and holding a cup with a straw, drifting leisurely on the "juice sea" on vacation, surrounded by floating orange pulp, little ice cubes, cool splashes and a clear blue sky; the mood shifts from "survival" to "vacation", and finally it leans back contentedly on the grapefruit as the camera pulls out and freezes on a refreshing, bright, playful summer frame.

Image Reference (Cinematic) (1)

No. 1: Drunk Man's Rooftop Fall (black-comedy short)

• Category: Image Reference (Cinematic)
• Source: official
• Author: Volcengine Ark
• Language: en
• Video: View

• Inputs:

Description

A ~30s black-comedy cinematic short: a chubby, tipsy man topples off a rooftop, grabs a lifeline, crashes through a window, and simply falls asleep. Character from one reference image; built on hard cuts between roar and total silence.

Prompt

[Drunk Man's Rooftop Fright — falls off the edge — grabs a rope through the window — passes out on the spot | black-comedy short | about 30 seconds] One-line premise: a chubby, cute, drunk middle-aged man is eating a burger and drinking beer on the rooftop of a building; as he stands up and stretches he accidentally loses his footing and falls, in his panic grabs a lifesaving rope and immediately crashes through a window into an interior, is dazed and stunned for one second, then just lies down where he is and falls fast asleep. Reference image @image1 — a chubby, cute, drunk middle-aged man: round and stocky build with a big round beer belly, short in stature, movements loose, slow and wobbly from drinking; round face, double chin, drink-flushed cheeks and nose, eyes narrowed to slits with a bleary gaze, an untrimmed ring of short stubble, messy hair, a silly, cute, carefree expression; wearing a white tank-top undershirt stained with burger sauce hanging loosely over his round belly, old jeans, shuffling along in loose slippers, always clutching a half-eaten burger in his hand. There is only this one character in the whole film, a 100% match to the reference image. Overall look: a nighttime cyberpunk mega-city, a dense forest of glass-and-steel skyscrapers, neon signs (cyan / magenta / electric blue), holographic billboards, wet reflective ground, volumetric fog, distant flying-car light trails and drones. Real live-action texture, physical cinema lenses, no 3D rendering / game engine / anime feel. The camera mixes handheld with jib / drone; after the fall the camera plunges down with him as the building's exterior wall and the neon streak upward to convey speed, 24-35mm widescreen cinematic lens texture, 180-degree shutter motion blur. Sound design is the key to the black comedy: hard-cutting repeatedly between "a huge roar" and "total silence". Real gravity throughout. Storyboard (about 30 seconds): S1 (0-4s) opening chewing big close-up (with sound) the man's face fills the screen, chewing the burger in big bites, a satisfied drunken state; S2 (4-9s) pull to a wide shot, stretching -> losing footing and falling (with sound) he wobbles to his feet and stretches big, leans back, can't keep his balance, his foot slips and he tumbles backward over the edge of the rooftop, never letting go of the burger, with a panicked "Eh——!"; S3 (9-12s) cut to a startled facial close-up (a loud scream, huge roar) drunken eyes bulging round, double chin bunched up, mouth wide in a screaming "Ahh——!!", wind howling; S4 (12-16s) cut to a long shot at eye level (total silence) seen from the building across the way, a tiny white figure plummeting straight down from the high-rise, the neon city vast and indifferent, the total silence forming a black-comedy contrast with the huge roar a second earlier; S5 (16-21s) cut to a facial close-up (screaming) -> grabbing the rope, still screaming, hands flailing in the air, he suddenly grabs a lifesaving cable, the cable snapping taut and bending under his weight with a twang, the scream cutting off abruptly as he is jerked and swings out (a brief slow motion at the moment he grabs the rope); S6 (21-26s) cut to an interior angle (quiet) -> the glass shatters -> he crashes in, the interior first quiet with only the hum of the air conditioner, the next second the glass explosively bursts inward (a brief bullet time) as the drunk man, burger and all, smashes through the window, shards flying out radially, neon light streaming in, and he crashes heavily into the room onto the floor / sofa, broken glass clinking; S7 (26-30s) ending, a startled second -> falls asleep, the man sprawled spread-eagle on the floor, covered in broken glass, still clutching the burger, slowly opens his eyes, dazed, blank and startled for a full second, looking around as if thinking "where am I?", then the drunkenness takes over and, not caring at all, he smacks his lips, tucks the burger into his arms, rolls over, lies down right there and falls fast asleep, even snoring lightly, the camera pulls out and freezes, hard cut to black. Only on-set live sound, no music, no subtitles; the core is hard cuts repeatedly between "huge roar" and "silence".

E-commerce Livestreaming (8)

No. 1: Garment On-Body Display

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the model from Image 1 (facial reference from Image 1 close-up, makeup and styling reference from Image 2 full-body shot) as the main subject, vertical 9:16, fashionable realistic style, generate a 30-second clothing display short video.

Prompt

Using the model from Image 1 (facial reference from Image 1 close-up, makeup and styling reference from Image 2 full-body shot) as the main subject, vertical 9:16, fashionable realistic style, generate a 30-second clothing display short video.
Shot 1: Medium shot, model @Image 1 stands sideways and suddenly turns, swinging the coat hem, pure color studio soft top light outlines the silhouette, camera slowly pushes in, (upbeat fashionable electronic music starts) <sound of fabric friction>.
Shot 2: Close-up, camera smoothly pans across the shoulder seam and lapel stitching details, side backlight highlights the fabric sheen.
Shot 3: Full shot, model @Image 1 naturally walks to showcase the overall silhouette and drape of the cut, camera smoothly follows.
Shot 4: Medium shot, model @Image 1 raises hand to adjust collar and looks back, camera slowly orbits half a circle.
Shot 5: Medium close-up, model @Image 1 freezes with a smile, camera slowly pulls out to end, (music concludes).
Constraints: Model's face, makeup, and styling must remain consistent with Image 1 and Image 2 throughout; studio background and top light remain fixed.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural slight movements, not be statues.

No. 2: Footwear Details

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, high-end textured realistic style, main subject is a pair of genuine leather ankle boots, generate a 30-second footwear detail short video.

Prompt

Vertical 9:16, high-end textured realistic style, main subject is a pair of genuine leather ankle boots, generate a 30-second footwear detail short video.
Shot 1: Macro close-up, ankle boots resting on a matte stone platform, camera slowly pushes in to the toe stitching, cool-toned side light sweeps across the leather, (low atmospheric electronic music starts) <sound of light leather contact>.
Shot 2: Close-up, camera orbits around the shoe body for one full circle showcasing the streamlined shape and heel curve, reflector fill light.
Shot 3: Macro close-up, fixed camera position, fingertip flips the tongue to reveal the inner lining logo and stitching.
Shot 4: Medium shot, booted foot steps down and lightly lifts the heel, camera looks down to capture the moment of contact, <sound of heel tapping ground>.
Shot 5: Close-up, camera slowly pulls out to frame the full shoe, (music concludes).
Constraints: Ankle boot style, leather texture, and color scheme must remain consistent throughout; stone platform and cool-toned lighting setup locked; prevent inconsistency between left and right shoe shapes.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural slight movements, not be statues.

No. 3: Bag Opening and Closing Demo

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, minimalist high-end realistic style, main subject is a commuter tote bag, generate a 30-second bag function demonstration short video.

Prompt

Vertical 9:16, minimalist high-end realistic style, main subject is a commuter tote bag, generate a 30-second bag function demonstration short video.
Shot 1: Medium shot, tote bag stands upright on a solid-color surface, camera slowly pushes in to the metal clasp, soft top light, (refreshing light music starts).
Shot 2: Close-up, hands unzip to open the main compartment, camera looks down to showcase internal compartments and card slots, <sound of zipper sliding>.
Shot 3: Close-up, hand places laptop and water bottle in sequence, camera smoothly pans to showcase capacity.
Shot 4: Medium shot, single hand lifts the bag to showcase handle load-bearing and structured feel, camera low-angle shot.
Shot 5: Medium shot, clasp is fastened and bag returns to position, camera slowly pulls out to end, (music concludes).
Constraints: Tote bag color, hardware, and structure must remain consistent throughout; surface and top light locked; opening/closing actions should be连贯, not jumpy.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural slight movements, not be statues.

No. 4: Jewelry

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, luxurious and exquisite realistic style, main subject is a diamond necklace, generate a 30-second jewelry display short video.

Prompt

Vertical 9:16, luxurious and exquisite realistic style, main subject is a diamond necklace, generate a 30-second jewelry display short video.
Shot 1: Macro close-up, necklace coiled on a black velvet tray, camera slowly pushes in to the main diamond, spotlight creates fire, (elegant string music starts) <subtle metallic chime>.
Shot 2: Close-up, camera orbits around the main diamond for half a circle capturing multi-angle refraction sparkles, background darkened.
Shot 3: Medium close-up, necklace worn on model's neck, camera moves up from collarbone to the pendant, soft fill light on face.
Shot 4: Macro close-up, fixed camera position, pendant sways slightly with breath, shimmering.
Shot 5: Close-up, camera slowly pulls out focusing on the fire to frame, (string music concludes).
Constraints: Necklace style, diamond cut, and setting must remain consistent throughout; black velvet background and spotlighting setup locked; neck skin tone in wearing segment should match studio segment.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural slight movements, not be statues.

No. 5: Home Appliance Display (Blender)

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, bright kitchen lifestyle realistic style, main subject is a high-speed blender, generate a 30-second home appliance demonstration short video.

Prompt

Vertical 9:16, bright kitchen lifestyle realistic style, main subject is a high-speed blender, generate a 30-second home appliance demonstration short video.
Shot 1: Medium shot, blender placed on a light-colored countertop, camera slowly pushes in to the control panel, morning light slants in, (lively lifestyle light music starts).
Shot 2: Close-up, hand pours fruit and ice into the cup, camera looks down at the cup opening, <sound of ingredients falling>.
Shot 3: Close-up, pressing the start button, blade assembly rotates at high speed to blend, camera fixed position close to the cup wall, <sound of blending roar>.
Shot 4: Medium shot, pouring smooth smoothie into a glass, camera smoothly pans following the liquid flow.
Shot 5: Medium close-up, finished smoothie and appliance body in the same frame, camera slowly pulls out to end, (music concludes).
Constraints: Blender body color, panel, and cup must remain consistent throughout; kitchen countertop and morning light locked; smoothie texture should be连贯.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural slight movements, not be statues.

No. 6: Maternity and Baby Products

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, gentle and soothing lifestyle realistic style, main subject is a baby insulated feeding bottle, generate a 30-second maternity and baby product display short video.

Prompt

Vertical 9:16, gentle and soothing lifestyle realistic style, main subject is a baby insulated feeding bottle, generate a 30-second maternity and baby product display short video.
Shot 1: Medium close-up, feeding bottle standing on a nursery soft mat, camera slowly pushes in to the anti-colic nipple, warm soft light, (gentle piano music starts).
Shot 2: Close-up, hand unscrews the cap to showcase wide-mouth design and measurement markings, camera smoothly pans, <gentle sound of cap unscrewing>.
Shot 3: Close-up, after pouring warm water, hand touches bottle body to feel constant temperature, camera fixed position.
Shot 4: Medium shot, mother holds bottle and gently shakes to test temperature before feeding, camera slowly moves up and down, <sound of water gently sloshing>.
Shot 5: Medium close-up, feeding bottle and soft plush toy framed together, camera slowly pulls out to end, (music concludes).
Constraints: Bottle color, body markings, and nipple style must remain consistent throughout; nursery warm light and soft mat background locked; maintain a soft, warm visual基调.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural slight movements, not be statues.

No. 7: Food Gift Box

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, festive and exquisite realistic style, featuring a Chinese pastry gift box. Generate a 30-second food gift box showcase short video.

Prompt

Vertical 9:16, festive and exquisite realistic style, featuring a Chinese pastry gift box. Generate a 30-second food gift box showcase short video.
Shot 1: Medium shot, a red and gold gift box rests quietly on a wooden table, the camera slowly pushes in to the gold-stamped cover, warm side lighting, (joyful Chinese-style music starts).
Shot 2: Close-up, hands slowly lift the box lid to reveal the compartmentalized pastries, camera looks down for a full view, <sound of lid opening>.
Shot 3: Macro close-up, the camera smoothly pans horizontally across the flaky crust and filling texture of each pastry compartment.
Shot 4: Medium close-up, a hand picks up a piece of pastry to show its layers, the camera slowly orbits around it.
Shot 5: Medium shot, the gift box is closed and tied with a ribbon, the camera slowly pulls back to conclude, (music concludes).
Constraints: The gift box color scheme, gold-stamped pattern, and pastry types remain consistent throughout; the wooden table and warm lighting are locked; pastry placement is coherent from start to finish.
General constraints: Keep no subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be statue-like.

No. 8: Digital Accessories (Flash Sale Style, with Captions)

• Category: E-commerce Livestreaming
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, flash sale high-contrast realistic style, featuring a pair of wireless noise-cancelling headphones. Generate a 30-second promotional flash sale short video.

Prompt

Vertical 9:16, flash sale high-contrast realistic style, featuring a pair of wireless noise-cancelling headphones. Generate a 30-second promotional flash sale short video.
Shot 1: Close-up, headphones float and rotate against a neon gradient background, camera quickly pushes in, (strong rhythmic electronic drumbeat starts) <power-on prompt sound>, 【Storewide Direct Discount ¥300】.
Shot 2: Macro close-up, camera cuts to the earcup hinge and charging contacts, hard light highlights sweep across.
Shot 3: Medium shot, camera cuts to a person wearing headphones nodding to the beat, light and shadow flicker, 【Active Noise Cancellation 40-hour Battery Life】.
Shot 4: Close-up, camera quickly pans horizontally past the charging case opening and closing, <magnetic snap sound>, 【Limited-time Flash Sale First 100 Customers】.
Shot 5: Medium close-up, headphones and price tag share the frame, camera quickly pulls back and freezes, (drumbeat concludes) 【Buy Now】.
Constraints: Headphone color and design remain consistent throughout; neon background color palette is locked; captions appear rhythmically synchronized with shot changes, maintaining high-contrast promotional feel.
General constraints: Keep no subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be statue-like.

Food & Dining (8)

No. 1: Hot Pot Served

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, steaming hot appetite-inducing realistic style, featuring a dual-flavor hot pot. Generate a 30-second hot pot serving short video.

Prompt

Vertical 9:16, steaming hot appetite-inducing realistic style, featuring a dual-flavor hot pot. Generate a 30-second hot pot serving short video.
Shot 1: Medium shot, the dual-flavor hot pot is placed on a wooden table, the red soup bubbling, camera slowly pushes in to the boiling oil bubbles, warm yellow restaurant lighting, (lively street market music starts) <soup base bubbling sound>.
Shot 2: Close-up, a hand dips tripe into the red soup with the 'seven up, eight down' motion, camera looks down as steam rises, <blanching sound>.
Shot 3: Macro close-up, camera smoothly pans horizontally across shrimp paste, freshly sliced beef, and a vegetable platter.
Shot 4: Medium close-up, chopsticks lift a slice of meat coated in red oil, camera follows upward, <oil dripping sound>.
Shot 5: Medium shot, several people raise their chopsticks together, creating a lively atmosphere, camera slowly pulls back to conclude, (music concludes).
Constraints: The dual-flavor pot style, soup color, and dish arrangement remain consistent throughout; the restaurant's warm lighting and wooden table are locked; steam and boiling state persist throughout.
General constraints: Keep no subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be statue-like.

No. 2: Coffee Latte Art

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, tranquil and artistic realistic style, featuring a handcrafted latte with latte art. Generate a 30-second coffee latte art short video.

Prompt

Vertical 9:16, tranquil and artistic realistic style, featuring a handcrafted latte with latte art. Generate a 30-second coffee latte art short video.
Shot 1: Close-up, espresso drips into the cup, camera slowly pushes in to the crema texture, natural window light, (soothing jazz music starts) <espresso dripping sound>.
Shot 2: Medium close-up, a hand holding a milk pitcher begins pouring milk foam, camera fixed at eye level looking at the liquid surface, <milk foam pouring sound>.
Shot 3: Macro close-up, camera looks down as milk foam spreads on the coffee surface forming a leaf pattern.
Shot 4: Close-up, a slight wrist flick finishes the pour, drawing the leaf veins, camera slowly orbits the rim of the cup.
Shot 5: Medium shot, the finished latte is lifted and placed by the window, camera slowly pulls back to conclude, (music concludes).
Constraints: The latte art pattern is coherent from pouring to completion; the window's natural light and tabletop are locked; milk foam texture is clear without breaks.
General constraints: Keep no subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be statue-like.

No. 3: Dessert Cut Open Revealing Lava (Molten Chocolate)

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, rich and tempting realistic style, featuring a molten chocolate lava cake. Generate a 30-second dessert lava flow short video.

Prompt

Vertical 9:16, rich and tempting realistic style, featuring a molten chocolate lava cake. Generate a 30-second dessert lava flow short video.
Shot 1: Medium close-up, the lava cake sits on a white porcelain plate dusted with powdered sugar, camera slowly pushes in, warm spotlight, (gentle romantic music starts).
Shot 2: Close-up, a fork gently presses the cake surface creating a crack, camera fixed in a close position, <sound of crust lightly cracking>.
Shot 3: Macro close-up, the moment a knife and fork cut open the cake, chocolate lava slowly oozes out, camera looks down for the climax moment, <thick sauce flowing sound>.
Shot 4: Close-up, a fork lifts a piece with a string of lava, camera slowly moves up and down following the string.
Shot 5: Medium shot, the lava cake and ice cream share the frame, camera slowly pulls back to conclude, (music concludes).
Constraints: The cake's outer shell and lava color/texture remain consistent throughout; the white porcelain plate and warm spotlight are locked; the lava oozing out is the core money shot and must be clearly highlighted.
General constraints: Keep no subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be statue-like.

No. 4: Grilling on Charcoal

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Horizontal 16:9, rustic and smoky realistic style, featuring meat skewers grilled over charcoal fire. Generate a 30-second grilling short video.

Prompt

Horizontal 16:9, rustic and smoky realistic style, featuring meat skewers grilled over charcoal fire. Generate a 30-second grilling short video.
Shot 1: Close-up, meat skewers on a charcoal grill net, fat drips causing small flames, camera slowly pushes in, warm red charcoal fire light, (dynamic grilling atmosphere music starts) <sizzling charcoal sound>.
Shot 2: Macro close-up, camera smoothly pans horizontally across the caramelized crispy crust of the skewers and sprinkled cumin and chili powder.
Shot 3: Medium shot, a hand flips the skewers, creating rising smoke and flames, camera follows the hand movement, <sound of flipping and crackling>.
Shot 4: Close-up, a basting brush sweeps sauce over the skewers as it seeps in, camera fixed in a close position.
Shot 5: Medium close-up, the grilled skewers are arranged on a plate and lifted, camera slowly pulls back to conclude, (music concludes).
Constraints: The type of meat skewers and degree of browning are coherent from start to finish; the charcoal fire and warm red light are locked; smoke and small flames persist to create a smoky atmosphere.
General constraints: Keep no subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be statue-like.

No. 5: Japanese Cuisine Plating

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, minimalist Zen realistic style, the main subject is a sashimi platter, generate a 30-second Japanese cuisine plating short video.

Prompt

Vertical 9:16, minimalist Zen realistic style, the main subject is a sashimi platter, generate a 30-second Japanese cuisine plating short video.
Shot 1: Medium shot, a black stone long plate is placed on a wooden tabletop, the camera slowly pushes in, cool top lighting, (clear and cold guzheng music starts).
Shot 2: Close-up, hands use tweezers to precisely place tuna sashimi and shiso leaves, the camera shoots from a top-down angle for composition, <sound of ingredients being gently placed>.
Shot 3: Macro close-up, the camera smoothly pans horizontally across the fat marbling of salmon and the sheen of ice grains.
Shot 4: Medium close-up, drizzling soy sauce and garnishing with wasabi and petals, the camera slowly orbits around the finished dish.
Shot 5: Full shot, the complete sashimi platter is centered and held still, the camera slowly pulls back to conclude, (music concludes).
Constraints: The types of sashimi, slice thickness, and plating positions remain consistent throughout; the black stone plate and cool top lighting are locked; the composition maintains minimalist negative space.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural, slight movements, not be like statues.

No. 6: Bubble Tea Making

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, fresh and vibrant realistic style, the main subject is a handcrafted pearl milk tea, generate a 30-second bubble tea making short video.

Prompt

Vertical 9:16, fresh and vibrant realistic style, the main subject is a handcrafted pearl milk tea, generate a 30-second bubble tea making short video.
Shot 1: Close-up, cooked brown sugar pearls are poured into the bottom of the cup, coating the sides, the camera slowly pushes in, bright bar lighting, (upbeat pop music starts) <sound of pearls falling into the cup>.
Shot 2: Medium close-up, a hand-held milk pitcher pours freshly brewed tea and fresh milk, the camera is fixed at eye level showing the layering, <sound of pouring>.
Shot 3: Macro close-up, the camera shoots from a top-down angle as ice cubes are dropped in, stirring the tea and milk, <sound of ice cubes clinking>.
Shot 4: Close-up, a sealing machine presses the cup film and a straw is inserted, the camera follows the straw insertion action, <sound of piercing the film>.
Shot 5: Medium shot, a hand holds up the finished milk tea and gently shakes it to show the pearls churning, the camera slowly pulls back to conclude, (music concludes).
Constraints: The layering of the milk tea and the color of the pearls remain consistent throughout; the bright bar lighting and background are locked; the production steps are sequential and do not jump.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural, slight movements, not be like statues.

No. 7: Hand-Pulled Noodles

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Horizontal 16:9, artisanal handcrafted realistic style, the main subject is handmade noodle pulling, generate a 30-second pulled noodles short video.

Prompt

Horizontal 16:9, artisanal handcrafted realistic style, the main subject is handmade noodle pulling, generate a 30-second pulled noodles short video.
Shot 1: Medium shot, the kneaded dough rests on the noodle board, hands press and fold it back, the camera slowly pushes in, warm kitchen lighting, (lively folk music starts) <sound of kneading dough>.
Shot 2: Close-up, hands stretch and pull the dough, repeatedly folding and slapping it against the board, the camera follows the arc of the hands, <sound of slapping dough on the board>.
Shot 3: Medium close-up, the noodles are pulled thinner and thinner into strands and dropped into a boiling pot, the camera shoots from a top-down angle showing the steam billowing, <sound of noodles entering boiling water>.
Shot 4: Close-up, the noodles are scooped up and placed into a large bowl, then broth is poured over, the camera smoothly pans horizontally to show the soup.
Shot 5: Medium shot, green onions are sprinkled and beef slices are arranged to complete the dish, the camera slowly pulls back to conclude, (music concludes).
Constraints: The thickness of the noodles and the final toppings are consistent from start to finish; the warm kitchen lighting and noodle board are locked; the pulling action is continuous, reflecting the handmade feel.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural, slight movements, not be like statues.

No. 8: Breakfast Scene (One-Take)

• Category: Food & Dining
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, warm and healing lifestyle realistic style, the main subject is a Chinese breakfast, generate a 30-second breakfast scene one-take short video.

Prompt

Vertical 9:16, warm and healing lifestyle realistic style, the main subject is a Chinese breakfast, generate a 30-second breakfast scene one-take short video.
Shot 1: One-take following shot, morning light streams through the curtains onto the dining table, the camera slowly pushes in on steaming soup dumplings, (gentle morning piano music starts) <sound of steamer lid being lifted>.
Shot 2: The same long shot smoothly pans horizontally, gliding over golden fried eggs, youtiao (fried dough sticks), and soy milk, with steam and light spots flowing.
Shot 3: The same long shot smoothly tilts up and down, a hand picks up a soup dumpling, dips it in vinegar, and lifts it, <sound of broth dripping>.
Shot 4: The same long shot smoothly orbits a small half-circle, passing by an open book and a steaming coffee cup beside the table.
Shot 5: The same long shot smoothly pulls back, framing a cozy full view of the breakfast, (music concludes).
Constraints: Maintain a single, uninterrupted long take camera movement with no cuts throughout; the food arrangement and morning light tone remain consistent; the camera movement is smooth and connected, reflecting the one-take quality.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural, slight movements, not be like statues.

Beauty & Fashion (6)

No. 1: Lipstick Swatch

• Category: Beauty & Fashion
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the lipstick in Image 1 (the bullet color and tube logo should match Image 1) as the main subject, vertical 9:16, high-saturation makeup aesthetic, generate a 30-second swatch short video.

Prompt

Using the lipstick in Image 1 (the bullet color and tube logo should match Image 1) as the main subject, vertical 9:16, high-saturation makeup aesthetic, generate a 30-second swatch short video.
Shot 1: Extreme close-up, the lipstick @Image 1 bullet slowly twists out, with velvet-like reflections flowing, the camera slowly pushes in, (crisp electronic music starts) <light sound of twisting the cap>.
Shot 2: Close-up, the camera smoothly pans horizontally across the lips, the bullet glides across leaving a full, rich color.
Shot 3: Medium close-up, low-angle shot of the model puckering her lips and smiling, the lip color shows under soft lighting, 【Today's Shade · True Red】.
Shot 4: Close-up, the camera orbits the model's profile, the lip gloss highlight flows as she turns her head.
Shot 5: Medium shot, the model holds the lipstick @Image 1 and poses towards the camera, the camera slowly pulls back, (music concludes).
Constraints: The bullet color and tube logo must match Image 1 and not be changed; the lip color must match the bullet color.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural, slight movements, not be like statues.

No. 2: Foundation Application

• Category: Beauty & Fashion
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the foundation bottle in Image 1 (the bottle and dropper should match Image 1) as the main subject, vertical 9:16, clean and translucent skincare-makeup finish, generate a 30-second application short video.

Prompt

Using the foundation bottle in Image 1 (the bottle and dropper should match Image 1) as the main subject, vertical 9:16, clean and translucent skincare-makeup finish, generate a 30-second application short video.
Shot 1: Extreme close-up, a drop of foundation @Image 1 hangs from the dropper and falls onto the back of the hand, the texture spreads, the camera slowly pushes in, <sound of liquid drop falling>.
Shot 2: Close-up, the camera smoothly pans horizontally, a makeup sponge presses and blends on the cheek, the skin texture gradually becomes even.
Shot 3: Medium close-up, following shot of the model turning her head, the cheek shows a flawless glow under natural light.
Shot 4: Close-up, low-angle shot of the model with eyes closed during application, eyelashes cast soft shadows, (gentle piano music).
Shot 5: Medium shot, the model holds the foundation bottle @Image 1 and smiles, posing, the camera slowly pulls back, 【Nude Flawless】.
Constraints: The bottle and dropper must match Image 1; the makeup finish should look realistic without excessive airbrushing or plastic-like texture.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural, slight movements, not be like statues.

No. 3: Perfume Ambiance

• Category: Beauty & Fashion
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the perfume bottle from Image 1 (bottle shape and engraving as per Image 1) as the main subject, horizontal 16:9, French retro ambiance lighting, generate a 30-second ambiance short film.

Prompt

Using the perfume bottle from Image 1 (bottle shape and engraving as per Image 1) as the main subject, horizontal 16:9, French retro ambiance lighting, generate a 30-second ambiance short film.
Shot 1: Close-up, perfume bottle @Image 1 stands on a stone windowsill, morning light passes through the bottle refracting light spots, camera slowly pushes in, (string ambiance music starts).
Shot 2: Medium shot, camera slowly orbits around the bottle body, glass facets reflect flowing warm light.
Shot 3: Close-up, low-angle shot of the spray moment, mist droplets suspend like golden dust in backlight, <spray light sound>.
Shot 4: Medium close-up, follow the mist drifting towards a sheer curtain, curtain shadows sway gently with the wind.
Shot 5: Medium shot, perfume bottle @Image 1 returns to the stone sill and freezes, camera slowly pulls out, (string music fades).
Constraints: Bottle shape and body engraving must match Image 1; ambiance locked to warm-toned French retro, no cool colors.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural slight movement, not statues.

No. 4: Skincare Essence Dropping

• Category: Beauty & Fashion
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the essence bottle from Image 1 (bottle body and dropper scale as per Image 1) as the main subject, vertical 9:16, crystal clear high-moisture texture, generate a 30-second texture short film.

Prompt

Using the essence bottle from Image 1 (bottle body and dropper scale as per Image 1) as the main subject, vertical 9:16, crystal clear high-moisture texture, generate a 30-second texture short film.
Shot 1: Extreme close-up, dropper suspended in mid-air, a drop of essence @Image 1 is about to fall, camera fixed position, <subtle bubble sound>.
Shot 2: Extreme close-up, essence drop falls and hits the water surface, slow ripples spread, camera slowly pushes in, (water droplet musical accent).
Shot 3: Close-up, camera smoothly pans horizontally, essence forms a crystal clear thread stretching from fingertips.
Shot 4: Medium close-up, overhead shot of essence being applied to the back of the hand, gloss spreads like a mirror.
Shot 5: Medium shot, essence bottle @Image 1 stands frozen against a water-light background, camera slowly rises, 【24-hour hydration lock】.
Constraints: Bottle body and dropper scale must match Image 1; texture must be translucent and stringy, not cloudy.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural slight movement, not statues.

No. 5: Fashion Street Snap

• Category: Beauty & Fashion
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the model's styling from Image 1 (clothing and accessories as per Image 1) as the main subject, vertical 9:16, film grain urban street feel, generate a 30-second street snap short film.

Prompt

Using the model's styling from Image 1 (clothing and accessories as per Image 1) as the main subject, vertical 9:16, film grain urban street feel, generate a 30-second street snap short film.
Shot 1: Medium shot, model @Image 1 pushes open a glass door and steps onto the street, wind lifts the hem of the clothes, camera follows, (retro disco rhythm starts).
Shot 2: Full shot, camera smoothly pans horizontally following the model walking past neon shop windows, reflections flow.
Shot 3: Medium close-up, low-angle shot of the model looking back and taking off sunglasses, backlight outlines golden edges of hair.
Shot 4: Close-up, camera slowly pushes in on accessory details, metal reflections flicker.
Shot 5: Full shot, model @Image 1 stands still in the center of the street, arms outstretched and freezes, camera slowly pulls out and rises, 【CITY WALK】(music concludes).
Constraints: Clothing and accessories must match Image 1, do not alter styles; film grain and urban neon color tone locked throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural slight movement, not statues.

No. 6: Hairstyle Showcase

• Category: Beauty & Fashion
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the model's hairstyle from Image 1 (hair color and style as per Image 1) as the main subject, vertical 9:16, salon-advertisement-level soft light texture, generate a 30-second hairstyle short film.

Prompt

Using the model's hairstyle from Image 1 (hair color and style as per Image 1) as the main subject, vertical 9:16, salon-advertisement-level soft light texture, generate a 30-second hairstyle short film.
Shot 1: Close-up, model @Image 1 lowers head in anticipation, hair strands fall covering the face, camera fixed position, (rhythmic music intro).
Shot 2: Medium close-up, model suddenly tosses head, hair strands arc up in slow motion, camera slowly pulls out, <hair toss wind sound>.
Shot 3: Close-up, camera orbits around the head, light and shadow sweep across the smooth highlights of the hair.
Shot 4: Medium shot, follow the model's fingers running through the hair, hair layers fall distinctly.
Shot 5: Medium close-up, model @Image 1 turns and looks back frozen, hairstyle full and set, camera slowly pushes in, 【Mirror-like shine】.
Constraints: Hair color and style silhouette must match Image 1; hair toss must be natural and smooth, no clipping or breakage.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural slight movement, not statues.

Digital Tech & Gadgets (6)

No. 1: Smartphone Product Rotation

• Category: Digital Tech & Gadgets
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the smartphone from Image 1 (body and logo as per Image 1) as the main subject, horizontal 16:9, tech high-end cool tone, generate a 30-second product showcase film.

Prompt

Using the smartphone from Image 1 (body and logo as per Image 1) as the main subject, horizontal 16:9, tech high-end cool tone, generate a 30-second product showcase film.
Shot 1: Extreme close-up, smartphone @Image 1 on a dark surface lights up, cool light outlines its edges, camera slowly pushes in, (low-frequency electronic sound starts).
Shot 2: Medium shot, camera smoothly orbits to showcase the smartphone @Image 1 backplate metal texture and camera module.
Shot 3: Close-up, camera slowly pans horizontally across side button and port details.
Shot 4: Medium close-up, low-angle shot of the smartphone @Image 1 slowly standing up and levitating, cool light spreads up from the bottom.
Shot 5: Medium shot, smartphone @Image 1 levitates and rotates frozen, camera slowly pulls out, (music concludes).
Constraints: Body and logo must match Image 1, do not alter design; do not fabricate interface content; cool-toned industrial lighting locked throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural slight movement, not statues.

No. 2: Earbuds Ejecting from Charging Case

• Category: Digital Tech & Gadgets
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the earbud charging case from Image 1 (shape and logo as per Image 1) as the main subject, horizontal 16:9, minimalist pure white studio shoot texture, generate a 30-second unboxing short film.

Prompt

Using the earbud charging case from Image 1 (shape and logo as per Image 1) as the main subject, horizontal 16:9, minimalist pure white studio shoot texture, generate a 30-second unboxing short film.
Shot 1: Extreme close-up, charging case @Image 1 rests on a pure white surface, fingertip approaches the lid, camera fixed position, (crisp prompt sound).
Shot 2: Close-up, lid slowly opens, indicator light turns on, camera slowly pushes in, <opening/closing latch sound>.
Shot 3: Medium close-up, earbuds slowly rise and levitate from the case, camera slowly lifts and follows.
Shot 4: Close-up, camera orbits a single earbud, showcasing the in-ear angle and microphone openings.
Shot 5: Medium shot, earbuds and charging case @Image 1 placed together frozen, camera slowly pulls out, 【Seamless portability】.
Constraints: Shape and logo must match Image 1, do not alter structure; pure white seamless background locked, no added clutter.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural slight movement, not statues.

No. 3: Notebook Opening and Closing

• Category: Digital Tech & Gadgets
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the laptop from Image 1 (case and logo as per Image 1) as the main subject, landscape 16:9, premium metallic cold-light texture, generate a 30-second showcase video.

Prompt

Using the laptop from Image 1 (case and logo as per Image 1) as the main subject, landscape 16:9, premium metallic cold-light texture, generate a 30-second showcase video.
Shot 1: Extreme close-up, the notebook @Image 1 lies on its side with the lid closed, cold light sweeps over the aluminum alloy hinge, the camera slowly pans horizontally, (low-frequency ambient sound starts).
Shot 2: Medium close-up, the screen hinge slowly opens and closes until upright, the screen gradually brightens, the camera slowly pushes in, <hinge damping sound>.
Shot 3: Close-up, overhead shot of the keyboard backlight lighting up key by key, a wave of light flows through.
Shot 4: Medium shot, the camera smoothly orbits to showcase the ultra-thin side profile and ports of the body.
Shot 5: Medium shot, the notebook @Image 1 is suspended in a half-open pose, frozen in place, the camera slowly pulls out, (music concludes).
Constraints: Case thickness and logo as per Image 1; do not fabricate specific screen UI content; metallic cold light locked throughout.
General Constraints: Keep without subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural, subtle movement, not like statues.

No. 4: Smart Watch Interface

• Category: Digital Tech & Gadgets
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the smart watch from Image 1 (case and strap as per Image 1) as the main subject, portrait 9:16, bright and lively tech feel, generate a 30-second feature video.

Prompt

Using the smart watch from Image 1 (case and strap as per Image 1) as the main subject, portrait 9:16, bright and lively tech feel, generate a 30-second feature video.
Shot 1: Extreme close-up, the watch @Image 1 raises wrist to wake screen, animation expands, the camera slowly pushes in, (bright electronic music starts).
Shot 2: Close-up, the camera slowly pans horizontally, the crown rotates to switch watch face cards.
Shot 3: Medium close-up, follow shot of wrist swinging, activity data rings jump with the movement.
Shot 4: Close-up, orbiting shot showcasing the texture of the case side and strap clasp.
Shot 5: Medium shot, the watch @Image 1 is worn on the wrist, frozen in place as it lifts, the camera slowly pulls out, 【All-day protection】.
Constraints: Case and strap as per Image 1; interface animations should be simple, do not fabricate specific numerical details.
General Constraints: Keep without subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural, subtle movement, not like statues.

No. 5: Drone Flight

• Category: Digital Tech & Gadgets
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the drone from Image 1 (body and propellers as per Image 1) as the main subject, landscape 16:9, expansive aerial documentary feel, generate a 30-second flight video.

Prompt

Using the drone from Image 1 (body and propellers as per Image 1) as the main subject, landscape 16:9, expansive aerial documentary feel, generate a 30-second flight video.
Shot 1: Medium close-up, the drone @Image 1 slowly lifts off from grass, propellers blurred at high speed, the camera slowly lifts and follows, <propeller hum> (ambient music starts).
Shot 2: Close-up, the camera orbits the hovering body, the gimbal slightly adjusts the lens direction.
Shot 3: Wide shot, follow shot of the drone skimming over a lake surface, its reflection gliding along.
Shot 4: Extreme long shot, overhead shot of the drone flying over a mountain ridge, the land spreading out below.
Shot 5: Medium shot, the drone @Image 1 returns smoothly and hovers, frozen in place, the camera slowly pulls out, (music concludes).
Constraints: Body and propeller structure as per Image 1; flight posture must be stable, conforming to real aerodynamics, no drifting or shaking.
General Constraints: Keep without subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural, subtle movement, not like statues.

No. 6: Chip Macro (Tech Documentary)

• Category: Digital Tech & Gadgets
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the chip from Image 1 (package and silkscreen as per Image 1) as the main subject, landscape 16:9, cold, tech documentary macro texture, generate a 30-second macro video.

Prompt

Using the chip from Image 1 (package and silkscreen as per Image 1) as the main subject, landscape 16:9, cold, tech documentary macro texture, generate a 30-second macro video.
Shot 1: Extreme macro close-up, the chip @Image 1 rests on a circuit board, gold pins gleam with cold light, the camera slowly pushes in, (low-frequency industrial sound starts).
Shot 2: Macro close-up, the camera smoothly pans across the package surface silkscreen and cutting edges.
Shot 3: Macro close-up, overhead shot of solder joints and traces, shallow depth of field with only a line in focus.
Shot 4: Medium close-up, the camera slowly pulls out to reveal the entire circuit board array, indicator lights flicker.
Shot 5: Close-up, the chip @Image 1 is frozen in cold light, the camera slowly orbits to conclude, (music fades out).
Constraints: Package model and silkscreen as per Image 1, do not alter; macro depth of field must be realistic, do not fabricate non-existent circuit structures.
General Constraints: Keep without subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural, subtle movement, not like statues.

Automotive (4)

No. 1: Night Scene Follow Shot

• Category: Automotive
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the car from Image 1 (model and paint as per Image 1) as the main subject, landscape 16:9, cyberpunk night scene cinematic texture, generate a 30-second follow-shot video.

Prompt

Using the car from Image 1 (model and paint as per Image 1) as the main subject, landscape 16:9, cyberpunk night scene cinematic texture, generate a 30-second follow-shot video.
Shot 1: Medium close-up, the car @Image 1 stops at a neon-lit street intersection, headlights illuminate, rain-slicked surface reflects light colors, the camera slowly pushes in, (deep electronic beat starts) <engine gentle roar>.
Shot 2: Medium shot, side follow shot of the vehicle driving down a long neon street, light bands flow over the car paint.
Shot 3: Close-up, the camera smoothly pans across the front fascia headlights and grille cold light.
Shot 4: Wide shot, low-angle shot of the vehicle passing through a tunnel, overhead strip lights quickly sweep by.
Shot 5: Medium shot, the car @Image 1 exits the tunnel, slows down and freezes, the camera slowly pulls out and rises, (rhythm concludes).
Constraints: Car model and paint color as per Image 1, do not alter; night scene neon and wet surface reflective atmosphere locked throughout.
General Constraints: Keep without subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural, subtle movement, not like statues.

No. 2: Detail Close-up Quick Cuts

• Category: Automotive
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the car from Image 1 (model and paint as per Image 1) as the main subject, landscape 16:9, bold high-contrast industrial texture, generate a 30-second detail video.

Prompt

Using the car from Image 1 (model and paint as per Image 1) as the main subject, landscape 16:9, bold high-contrast industrial texture, generate a 30-second detail video.
Shot 1: Extreme close-up, the car @Image 1 headlights illuminate the light strip, cold light outlines the edges, the camera slowly pushes in, (urgent drumbeat starts).
Shot 2: Close-up, cut to the wheel rim, slowly rotating, reflecting light spots.
Shot 3: Close-up, cut to the emblem and grille, metallic highlights sweep across.
Shot 4: Close-up, cut to the exhaust and spoiler lines, the camera smoothly pans.
Shot 5: Medium shot, the car @Image 1 entire vehicle frozen in a beam of light, the camera slowly pulls out, (drumbeat concludes) 【Every detail is sharp】.
Constraints: Car model and paint as per Image 1; quick cuts, each shot focuses on a single component without repetition; high-contrast hard light locked throughout.
General Constraints: Keep without subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural, subtle movement, not like statues.

No. 3: Off-Road Scene

• Category: Automotive
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the off-road vehicle from Image 1 (model and paint color as per Image 1) as the main subject, landscape 16:9, rough wilderness documentary feel, generate a 30-second off-road short film.

Prompt

Using the off-road vehicle from Image 1 (model and paint color as per Image 1) as the main subject, landscape 16:9, rough wilderness documentary feel, generate a 30-second off-road short film.
Shot 1: Medium shot, the off-road vehicle @Image 1 charges up a sand dune kicking up a dust wave, camera follows, <sound of tires grinding sand> (rousing drum music begins).
Shot 2: Close-up, low-angle shot of wheels crushing over gravel, mud and sand splattering onto the lens.
Shot 3: Wide shot, smooth lateral tracking shot following the vehicle fording a shallow stream, water splashing.
Shot 4: Extreme wide shot, overhead shot of the off-road vehicle traversing tracks on the wasteland, a long trail of dust.
Shot 5: Medium shot, the off-road vehicle @Image 1 reaches the ridge top and stops for a final frame, camera slowly rises and pulls back, (drum music concludes).
Constraints: Vehicle model and paint color must match Image 1; off-road dynamics must conform to realistic terrain physics, no floating, slipping, or distortion.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not stone statues.

No. 4: Interior Showcase

• Category: Automotive
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the car interior from Image 1 (materials and color scheme as per Image 1) as the main subject, landscape 16:9, warm and premium cabin lighting feel, generate a 30-second interior short film.

Prompt

Using the car interior from Image 1 (materials and color scheme as per Image 1) as the main subject, landscape 16:9, warm and premium cabin lighting feel, generate a 30-second interior short film.
Shot 1: Extreme close-up, the leather seat stitching @Image 1 undulates under warm light, camera slowly pans, (soothing ambient music begins).
Shot 2: Medium close-up, camera slowly pushes in towards the central control screen, ambient lighting gradually illuminates.
Shot 3: Close-up, orbiting around the steering wheel and paddle shifters, metallic trim reflections flow.
Shot 4: Medium shot, overhead shot of the full cabin, skylight light pours down from above.
Shot 5: Medium close-up, camera slowly rises ending on a final frame of the cabin, warm light suffuses, (music fades) 【Serene Cabin】.
Constraints: Materials and color scheme must match Image 1, no changes; do not fabricate specific UI content for the central control screen; warm cabin lighting tone locked throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not stone statues.

Real Estate & Home (4)

No. 1: Living Room Space Walkthrough

• Category: Real Estate & Home
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, real estate quality promotional film, bright, airy, warm white tone, generate a 30-second living room space walkthrough short film.

Prompt

Vertical 9:16, real estate quality promotional film, bright, airy, warm white tone, generate a 30-second living room space walkthrough short film.
Shot 1: Fixed camera position, morning light slants into the empty living room from floor-to-ceiling windows, dust motes float in the light beams, (gentle piano begins).
Shot 2: Smooth pan, camera glides close to the ground over wooden flooring and a beige fabric sofa, pillow textures clear, <soft footsteps>.
Shot 3: Slow push-in, focus on a steaming cup of coffee and an open book on the coffee table, warm light falls, (strings layer in).
Shot 4: Crane up, camera position slowly lifts from the ground, revealing the open layout connecting the living room and open-plan kitchen/dining area, 【Floor Area 98㎡ North-South Through Ventilation】.
Shot 5: Slow pull-back, retreats to the entrance hall looking back at the depth of the entire living room, warm white final frame, (music concludes).
Constraints: No characters appear throughout; furniture and decor style unified as modern minimalist wood style; lighting maintains consistent morning warm white.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not stone statues.

No. 2: Kitchen Details

• Category: Real Estate & Home
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, high-end appliance texture advertisement, cool metallic gray paired with warm wood tones, generate a 30-second kitchen details short film.

Prompt

Vertical 9:16, high-end appliance texture advertisement, cool metallic gray paired with warm wood tones, generate a 30-second kitchen details short film.
Shot 1: Close-up, water pours from the faucet into the stainless steel sink, water droplets splash in slow motion, <sound of flowing water>.
Shot 2: Smooth pan, camera slides along the quartz countertop past knives, a cutting board, and fresh vegetables, cold light highlights, (lively rhythm begins).
Shot 3: Slow push-in, a drawer automatically slides out showcasing compartmentalized storage and matte handles, warm wood tones, <sound of smooth drawer gliding>.
Shot 4: Overhead shot, gas stove blue flame ignites, oil sizzles in the pan, steam rises, <click of ignition><sizzle of oil>.
Shot 5: Low-angle shot, camera position looks up from the stove towards the range hood and recessed light strips, metallic reflections, 【Integrated Built-in Kitchen Appliances】, (music concludes).
Constraints: No characters appear throughout; countertops remain tidy and clutter-free; metal and wood material textures consistent throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not stone statues.

No. 3: Floor Plan Overhead (Schematic)

• Category: Real Estate & Home
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Landscape 16:9, architectural visualization schematic style, clean white model with soft skylight, generate a 30-second floor plan overhead schematic short film.

Prompt

Landscape 16:9, architectural visualization schematic style, clean white model with soft skylight, generate a 30-second floor plan overhead schematic short film.
Shot 1: Overhead shot, directly vertical top-down view of the complete floor plan white model, partition lines clear, (minimal electronic sound begins).
Shot 2: Slow push-in, camera descends through the "vanished ceiling" into the living room schematic area, furniture presented semi-transparently, <space transition sound effect>.
Shot 3: Orbit, rotates once around the master bedroom schematic area, showcasing bay window and walk-in closet circulation, soft light gradually brightens, (rhythm intensifies).
Shot 4: Smooth pan, slides along the corridor schematic circulation towards the secondary bedroom and bathroom, annotations appear, 【Three Bedrooms Two Living Rooms Dynamic and Static Zoning】.
Shot 5: Crane up, camera position rises back to the global overhead view with area data superimposed, skylight final frame, (music concludes).
Constraints: Entirely schematic white model, not real scene, must include the annotation "Schematic for reference only"; floor plan proportion and structure consistent throughout; no real people or furniture.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not stone statues.

No. 4: Bedroom Ambiance

• Category: Real Estate & Home
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, slow living ambiance advertisement, warm orange night light soft tone, generate a 30-second bedroom ambiance short film.

Prompt

Vertical 9:16, slow living ambiance advertisement, warm orange night light soft tone, generate a 30-second bedroom ambiance short film.
Shot 1: Fixed camera position, bedside warm light turns on instantly illuminating plain bedding and half-drawn curtains, (ambient music begins).
Shot 2: Slow push-in, camera moves close to the pillow, gliding over soft quilt folds and an open book, light and shadow gradually warm, <sound of light rain outside>.
Shot 3: Smooth pan, slides along the foot of the bed past plants and a diffuser on the bay window, warm orange light halo flows, (gentle piano notes).
Shot 4: Crane up, camera position slowly lifts for an overhead view of the entire bed and pendant light soft glow, creating a sense of sleeping envelopment, 【Bedroom with Excellent Natural Light and Ventilation】.
Shot 5: Slow pull-back, retreats to the doorway looking back at the bedroom panorama under the warm light, soft tone final frame, (music concludes).
Constraints: No characters appear throughout; lighting maintains consistent warm orange night tone; bedding and decor maintain unified elegant style.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not stone statues.

Talking Head & Digital Humans (6)

No. 1: Knowledge Monologue

• Category: Talking Head & Digital Humans
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The host is bound to @Image 1 (facial makeup and styling should correspond to the image), vertical screen 9:16, clean studio style for a knowledge blogger with bright soft light, generate a 30-second knowledge monologue short video.

Prompt

The host is bound to @Image 1 (facial makeup and styling should correspond to the image), vertical screen 9:16, clean studio style for a knowledge blogger with bright soft light, generate a 30-second knowledge monologue short video.
Shot 1: Medium close-up, host @Image 1 leans forward looking directly at the camera to pose a question, shallow depth of field bookshelf background, fixed camera position, {Did you know 90% of people use it wrong?}.
Shot 2: Slow push-in, host @Image 1 speaks while raising a finger for emphasis, determined gaze, warm light brightening, (upbeat background music starts).
Shot 3: Cut to, key point graphics appear on the right side of the screen, host @Image 1 turns sideways and points, smooth pan, 【Key Point One Two Three】.
Shot 4: Medium close-up, host @Image 1 turns back to face front, smiling for the summary, tone slows down, fixed camera position, {Remember these three points and that's enough}.
Shot 5: Slow pull-out, host @Image 1 nods to conclude and waves, soft light freeze frame, (music concludes).
Constraints: The host's face must remain consistent with Image 1 throughout; lip-sync must strictly match the dialogue; the studio background remains fixed and unchanged.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural slight movements, not be like statues.

No. 2: News Broadcast

• Category: Talking Head & Digital Humans
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The anchor is bound to @Image 1 (facial makeup and styling should correspond to the image), horizontal screen 16:9, authoritative news studio, cool blue professional tone, generate a 30-second news broadcast short video.

Prompt

The anchor is bound to @Image 1 (facial makeup and styling should correspond to the image), horizontal screen 16:9, authoritative news studio, cool blue professional tone, generate a 30-second news broadcast short video.
Shot 1: Medium shot, anchor @Image 1 sits upright, looking directly at the camera to open, blue news screen behind, fixed camera position, {Good evening viewers, welcome to this broadcast}.
Shot 2: Slow push-in, anchor @Image 1 delivers the lead with a serious expression, steady pace, cool blue light, 【Today's Headlines】.
Shot 3: Cut to, a news footage window appears to the right and behind anchor @Image 1, smooth pan, <studio cue sound>.
Shot 4: Medium close-up, anchor @Image 1 turns to another camera to continue the broadcast, natural eye contact switch, fixed camera position, (low background music).
Shot 5: Slow pull-out, anchor @Image 1 concludes with hands folded in a gesture of thanks, cool blue freeze frame, {Thank you for watching, see you next time}.
Constraints: The anchor's face must remain consistent with Image 1 throughout; lip-sync must strictly match the dialogue; posture is upright and professional, studio background is fixed.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural slight movements, not be like statues.

No. 3: Livestream Sales Monologue

• Category: Talking Head & Digital Humans
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The host is bound to @Image 2 (facial makeup and styling should correspond to the image), vertical screen 9:16, lively livestream sales style, bright high-saturation warm tone, generate a 30-second sales monologue short video.

Prompt

The host is bound to @Image 2 (facial makeup and styling should correspond to the image), vertical screen 9:16, lively livestream sales style, bright high-saturation warm tone, generate a 30-second sales monologue short video.
Shot 1: Medium close-up, host @Image 2 holds up the product close to the camera, enthusiastically calling out, fixed camera position, {Family, look over here, today's product is absolutely amazing!}.
Shot 2: Slow push-in, host @Image 2 points out the product's selling points, exaggerated excited expression, high-saturation warm light, <ding, link-up sound effect>.
Shot 3: Cut to, a price explosion sticker appears at the bottom left of the screen, host @Image 2 claps for emphasis, smooth pan, 【Limited Time Direct Discount Only 99】.
Shot 4: Medium shot, host @Image 2 holds up the product, showing details left and right, speaking pace quickens, fixed camera position, (energetic promotional music).
Shot 5: Slow push-in, host @Image 2 gives a thumbs up to urge orders for the conclusion, warm tone freeze frame, {Don't miss out, hurry up and place your order!}.
Constraints: The host's face must remain consistent with Image 2 throughout; lip-sync must strictly match the dialogue; the product's appearance remains consistent; the background shelf display is fixed.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural slight movements, not be like statues.

No. 4: Late-Night Emotional Radio

• Category: Talking Head & Digital Humans
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The host is bound to @Image 3 (facial makeup and styling should correspond to the image), vertical screen 9:16, late-night radio atmosphere, warm orange low-contrast glow, generate a 30-second emotional radio short video.

Prompt

The host is bound to @Image 3 (facial makeup and styling should correspond to the image), vertical screen 9:16, late-night radio atmosphere, warm orange low-contrast glow, generate a 30-second emotional radio short video.
Shot 1: Medium close-up, host @Image 3 turns slightly towards the microphone, eyes closed, speaking softly, warm orange desk lamp side lighting, fixed camera position, (gentle piano starts) {It's late, how are you who haven't slept yet?}.
Shot 2: Slow push-in, host @Image 3 opens eyes looking into the distance with a gentle expression, eyes glistening, warm light suffusion, <sound of light night rain outside the window>.
Shot 3: Smooth pan, the camera glides past headphones and a warm teacup on the desk, host @Image 3 enters frame whispering, (piano intensifies).
Shot 4: Close-up, host @Image 3 smiles slightly, offering soft comfort, eyelashes flutter slightly, warm orange glow, {May you be treated gently by this world}.
Shot 5: Slow pull-out, host @Image 3 takes off headphones, lowers head with a smile to conclude, soft glow freeze frame, (music concludes).
Constraints: The host's face must remain consistent with Image 3 throughout; lip-sync must strictly match the dialogue; emotions are externalized through eyelash flutters and glistening eyes, avoid straightforward narration-style performance; the warm orange night tone remains consistent throughout.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural slight movements, not be like statues.

No. 5: Teaching Instructor

• Category: Talking Head & Digital Humans
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The instructor is bound to @Image 1 (facial makeup and styling should correspond to the image), horizontal screen 16:9, bright professional online classroom, clean whiteboard tone, generate a 30-second teaching instructor short video.

Prompt

The instructor is bound to @Image 1 (facial makeup and styling should correspond to the image), horizontal screen 16:9, bright professional online classroom, clean whiteboard tone, generate a 30-second teaching instructor short video.
Shot 1: Medium shot, instructor @Image 1 stands in front of a whiteboard, turns to face the camera to begin the lecture, holding a marker, fixed camera position, {In this lesson, we'll only cover one core formula}.
Shot 2: Smooth pan, instructor @Image 1 walks while writing keywords on the whiteboard, camera follows the movement, bright white light, <sound of marker writing>.
Shot 3: Cut to, the whiteboard writing area zooms in, the formula appears highlighted, instructor @Image 1 turns sideways to point, slow push-in, 【Core Formula】.
Shot 4: Medium close-up, instructor @Image 1 turns back to the camera to explain with an example, lively expression, fixed camera position, (lighthearted learning background music).
Shot 5: Slow pull-out, instructor @Image 1 spreads hands with a smile to conclude and nods, white light freeze frame, {Understood? See you next lesson}.
Constraints: The instructor's face must remain consistent with Image 1 throughout; lip-sync must strictly match the dialogue; the whiteboard content is coherent from start to finish; the classroom background is fixed.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural slight movements, not be like statues.

No. 6: Multilingual Clone (Including Editing Task Concept)

• Category: Talking Head & Digital Humans
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The digital human is bound to @Image 1 (facial makeup and styling should correspond to the image), vertical screen 9:16, unified studio style for a multinational brand, simple tech blue tone, generate a 30-second multilingual clone short video.

Prompt

The digital human is bound to @Image 1 (facial makeup and styling should correspond to the image), vertical screen 9:16, unified studio style for a multinational brand, simple tech blue tone, generate a 30-second multilingual clone short video.
Shot 1: Medium close-up, digital human @Image 1 looks directly at the camera, opening with a greeting in Chinese, tech blue background screen, fixed camera position, {Hello everyone, welcome to learn about our product}【Chinese】.
Shot 2: Cut to, the same digital human @Image 1 seamlessly switches to English monologue, lip-sync aligned to English, slow push-in, {Hello everyone, welcome}【English】.
Shot 3: Cut to, digital human @Image 1 switches to Japanese greeting, consistent demeanor, smooth pan, {Mina-san konnichiwa}【Japanese】.
Shot 4: Medium shot, digital human @Image 1 opens arms in a welcoming gesture, multilingual subtitle stream appears in the background, fixed camera position, (tech-sounding background music).
Shot 5: Slow pull-out, digital human @Image 1 smiles and nods to conclude, blue tone freeze frame, (music concludes).
Constraints: Editing task concept — First generate the Chinese master shots, then use the editing instruction "keep the character and camera movements unchanged, only replace the dialogue and lip-sync with the target language" to derive the English/Japanese clones, ensuring the face @Image 1, camera positions, background, and attire remain completely consistent throughout; lip-sync for each language must strictly match its corresponding dialogue; prevent facial drift in the clones.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural slight movements, not be like statues.

Short Dramas & Emotional Stories (8)

No. 1: Convenience Store Reunion (Emotional Reversal)

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the female lead in Image 1 and the male lead in Image 3 (their facial makeup and styling should match the corresponding images), vertical 9:16, cinematic realism, cold blue transitioning to warm orange, generate a 30-second emotional short drama.

Prompt

Refer to the female lead in Image 1 and the male lead in Image 3 (their facial makeup and styling should match the corresponding images), vertical 9:16, cinematic realism, cold blue transitioning to warm orange, generate a 30-second emotional short drama.
Shot 1: Wide shot, the female lead @Image 1 leans against the window alone, head bowed, stirring her coffee, cold blue night tone, the camera slowly pushes in, (light piano begins).
Shot 2: Medium close-up, the male lead @Image 3 pushes the door open and enters the frame, the female lead @Image 1 looks up and freezes, fixed camera with a slight breathing feel, <doorbell dings>.
Shot 3: Close-up, the shot cuts back and forth between the two, the color tone gradually warms, the male lead @Image 3 says softly {I'm here to pick you up}, (piano intensifies).
Shot 4: Close-up, the female lead @Image 1's eyes well up with tears and the corners of her mouth lift into a smile, the camera slowly pulls out, warm orange freeze frame, (music resolves).
Constraints: The faces of the male and female leads must remain consistent with the corresponding images throughout; the convenience store setting is fixed; the emotional reversal is externalized through teary eyes and trembling lips; do not generate clones/twins.
General constraints: Keep it without subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be like statues.

No. 2: Rainy Night Monologue

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The protagonist is bound to @Image 2 (facial makeup and styling should match the corresponding image), vertical 9:16, cool-toned artistic realism, bluish-grey rainy night with low saturation, generate a 30-second emotional monologue short film.

Prompt

The protagonist is bound to @Image 2 (facial makeup and styling should match the corresponding image), vertical 9:16, cool-toned artistic realism, bluish-grey rainy night with low saturation, generate a 30-second emotional monologue short film.
Shot 1: Close-up, rainwater trickles down the glass window, the protagonist's @Image 2 blurred reflection appears behind the glass, fixed camera, <sound of light rain> (low cello begins).
Shot 2: Slow push-in, the protagonist @Image 2 presses against the window gazing at the streetlights in the rainy night, fingertips touching the cold glass, bluish-grey cold light, {Some words can only be told to the rain}.
Shot 3: Smooth pan, the camera glides past a phone with its screen off and a half-cold cup of tea on the table, the protagonist's @Image 2 profile enters the frame, (cello intensifies).
Shot 4: Medium close-up, the protagonist @Image 2 takes a deep breath and closes their eyes, a single tear traces down their cheek, overlapping with a raindrop on the window, slow push-in, <rain intensifies>.
Shot 5: Slow pull-out, the protagonist @Image 2 opens their eyes, pulls a relieved faint smile, and turns away from the window, bluish-grey freeze frame, (music resolves).
Constraints: The protagonist's face must remain consistent with Image 2 throughout; emotions are externalized through fingertips against the glass and tear tracks, avoid direct dialogue like "I'm very sad"; the bluish-grey rainy night tone and setting remain consistent throughout.
General constraints: Keep it without subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be like statues.

No. 3: Family Dining Table

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the mother in Image 1, the father in Image 2, and the child in Image 4 (their facial makeup and styling should match the corresponding images), horizontal 16:9, warm life realism, warm yellow home tone, generate a 30-second family emotional short film.

Prompt

Refer to the mother in Image 1, the father in Image 2, and the child in Image 4 (their facial makeup and styling should match the corresponding images), horizontal 16:9, warm life realism, warm yellow home tone, generate a 30-second family emotional short film.
Shot 1: Wide shot, the family of three sits around the dining table, steam rises from hot dishes, the mother @Image 1 is serving food to the child @Image 4, warm yellow lighting, fixed camera, (warm folk music begins) <clinking of bowls and chopsticks>.
Shot 2: Medium close-up, the father @Image 2 smiles as he serves soup to the mother @Image 1, they exchange a smile, slow push-in, <clinking of soup ladle>.
Shot 3: Close-up, the child @Image 4 puffs their cheeks while eating heartily, looks up and grins, warm light falls on their face, cut to this shot.
Shot 4: Medium shot, the mother @Image 1 reaches out to wipe a corner of the father's @Image 2 mouth, the father is momentarily surprised then holds her hand, smooth pan, (folk music becomes warmer).
Shot 5: Slow crane up, the camera rises to look down on the table full of food and the family leaning close together, warm yellow freeze frame, (music resolves).
Constraints: The faces of the three characters must strictly match the corresponding images, the mother/father/child should have distinct body types and ages, do not generate clones/twins or facial confusion; the dishes on the table and the warm yellow home setting remain consistent throughout.
General constraints: Keep it without subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be like statues.

No. 4: Farewell at the Station

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the female lead in Image 1 and the male lead in Image 3 (their facial makeup and styling should match the corresponding images), horizontal 16:9, cinematic realism, cool-toned platform with slightly warm backlight, generate a 30-second farewell emotional short film.

Prompt

Refer to the female lead in Image 1 and the male lead in Image 3 (their facial makeup and styling should match the corresponding images), horizontal 16:9, cinematic realism, cool-toned platform with slightly warm backlight, generate a 30-second farewell emotional short film.
Shot 1: Wide shot, the platform is crowded with people, the female lead @Image 1 and the male lead @Image 3 stand facing each other, holding hands tightly, a train is beside them, cool tone with backlight, slow push-in, (low strings begin) <train arrival announcement>.
Shot 2: Close-up, their tightly clasped fingers slowly tighten then reluctantly loosen, warm backlight outlines them, fixed camera.
Shot 3: Medium close-up, the male lead @Image 3 reaches up to tuck a strand of wind-blown hair behind the female lead's @Image 1 ear, hesitates to speak, slow push-in, {When you arrive... remember to let me know you're safe}.
Shot 4: Medium shot, the male lead @Image 3 turns and boards the train, the female lead @Image 1 stands still, her shoulders trembling slightly as she holds back tears, smooth pan, (strings rise) <door closing warning sound>.
Shot 5: Slow pull-out, the train departs, the female lead @Image 1 stands alone on the empty platform as a backlit silhouette, cool tone freeze frame, (music resolves).
Constraints: The faces of the male and female leads must remain consistent with the corresponding images throughout; the farewell emotion is externalized through tightening fingers and trembling shoulders, avoid direct crying and shouting; the station platform setting and the interplay of cool/warm backlight remain consistent throughout; do not generate clones/twins.
General constraints: Keep it without subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be like statues.

No. 5: Workplace Highlight

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The protagonist is bound to @Image 2 (facial makeup and styling should match the corresponding image), horizontal 16:9, business-inspiring realism, cold blue steel/glass texture transitioning to golden light, generate a 30-second workplace motivational short film.

Prompt

The protagonist is bound to @Image 2 (facial makeup and styling should match the corresponding image), horizontal 16:9, business-inspiring realism, cold blue steel/glass texture transitioning to golden light, generate a 30-second workplace motivational short film.
Shot 1: Medium close-up, the protagonist @Image 2 sits alone in a late-night office, frowning at a screen full of data, cold blue screen light illuminates their face, fixed camera, (low drumbeat begins) <intense keyboard typing>.
Shot 2: Slow push-in, the protagonist @Image 2 suddenly looks up, eyes lighting up, grabs a pen and circles a key point, the screen light brightens sharply, <inspiration strike sound effect>.
Shot 3: Follow shot, the protagonist @Image 2 stands up and strides through the hallway, pushing open the conference room door, the camera follows closely behind their back, (drumbeat intensifies).
Shot 4: Low-angle shot, the protagonist @Image 2 stands before a floor-to-ceiling window, confidently presenting to a group, city skyline in the background, backlit with golden light, {This is our answer}.
Shot 5: Slow orbit, the entire room stands up applauding, the protagonist @Image 2 lets out a sigh of relief and smiles, golden light freeze frame, (music climax resolves) <thunderous applause>.
Constraints: The protagonist's face must remain consistent with Image 2 throughout; the emotional arc is externalized from frowning to relaxation, the transition from cold blue to golden light corresponds to low point to highlight; the office setting is coherent and consistent.
General constraints: Keep it without subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be like statues.

No. 6: Campus Youth

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the girl in Image 4 and the boy in Image 5 (their facial makeup and styling should match the corresponding images), vertical 9:16, youthful fresh realism, bright warm sunlight with high translucency, generate a 30-second campus youth short film.

Prompt

Refer to the girl in Image 4 and the boy in Image 5 (their facial makeup and styling should match the corresponding images), vertical 9:16, youthful fresh realism, bright warm sunlight with high translucency, generate a 30-second campus youth short film.
Shot 1: Wide shot, warm afternoon sunlight slants across the sports field, the girl @Image 4 walks quickly across the track holding books, the wind lifts her skirt, slow push-in, (fresh guitar begins) <light cicada chirping>.
Shot 2: Medium close-up, the boy @Image 5 rides past on a bicycle, brakes suddenly and looks back, their gazes meet and they both freeze for a moment, fixed camera, <bicycle brake sound>.
Shot 3: Close-up, the girl's @Image 4 cheeks flush pink, she lowers her head and smiles with pursed lips, the scattered books are picked up by the boy @Image 5 as he bends down, cut to this shot in warm sunlight.
Shot 4: Medium shot, the two walk side by side along a tree-lined path talking and laughing, light spots dance on their faces, follow shot accompanying them, (guitar becomes more cheerful).
Shot 5: Slow crane up, the camera rises to look down on their receding backs and the campus bathed in golden light, warm sunlight freeze frame, (music resolves).
Constraints: The faces of the girl and boy must remain consistent with the corresponding images throughout, their male/female body types should be distinct, do not generate clones/twins or confusion; the campus setting with bright warm sunlight and high translucency remains consistent throughout; youthful emotions are externalized through flushed cheeks and pursed-lip smiles.
General constraints: Keep it without subtitles; do not generate a Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural, subtle movements, not be like statues.

No. 7: Suspenseful Corridor

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

The protagonist is bound to @Image 2 (facial makeup and styling should correspond to the reference image), vertical screen 9:16, thriller suspense realistic style, dim cold green with high-contrast shadows, generate a 30-second suspense short film.

Prompt

The protagonist is bound to @Image 2 (facial makeup and styling should correspond to the reference image), vertical screen 9:16, thriller suspense realistic style, dim cold green with high-contrast shadows, generate a 30-second suspense short film.
Shot 1: Close-up, a corridor light flickers on and off, the protagonist @Image 2's flashlight beam pierces the darkness, dim cold green, fixed camera, <buzzing current sound from the light tube> (low-frequency hum begins).
Shot 2: Following shot, the camera closely follows behind the protagonist @Image 2 as they slowly walk deeper into the long corridor, hesitant footsteps, elongated shadows, <echoing footsteps>.
Shot 3: Slow push-in, the protagonist @Image 2 suddenly stops, holds their breath, and looks back, pupils contract, sweat beads form, cold green light illuminates their face, <strange clicking sound from behind>.
Shot 4: Cut to, a door at the end of the corridor slowly opens with a sliver of light seeping out, the protagonist @Image 2 raises their light and steps back cautiously, (sharp strings rise sharply).
Shot 5: Slow pull-out, the protagonist @Image 2 stands alone in the center of the long, dark corridor, shadows closing in from all sides, cold green freeze-frame, <sudden silence> (music cuts off abruptly).
Constraints: The protagonist's face must remain consistent with Image 2 throughout; tense emotions are externalized through holding breath, looking back, and sweating with contracted pupils; dim cold green high-contrast lighting and corridor setting remain consistent throughout; use silence at the end to create a suspenseful open ending.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movements, not be like statues.

No. 8: Reconciliation (Using Editing Task for Contrastive Derivation)

• Category: Short Dramas & Emotional Stories
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the female lead from Image 1 and the male lead from Image 3 (their respective facial makeup and styling should correspond to the reference images), vertical screen 9:16, cinematic realism, transitioning from cold gray rainy to warm golden sunny light, generate a 30-second emotional short film about reconciliation.

Prompt

Refer to the female lead from Image 1 and the male lead from Image 3 (their respective facial makeup and styling should correspond to the reference images), vertical screen 9:16, cinematic realism, transitioning from cold gray rainy to warm golden sunny light, generate a 30-second emotional short film about reconciliation.
Shot 1: Medium close-up, the female lead @Image 1 and the male lead @Image 3 stand back-to-back in the cold gray rain, heads bowed, distance between them, fixed camera, (oppressive piano begins) <cold, desolate sound of rain>.
Shot 2: Close-up, an old photo lies spread out in a puddle, getting wet from the rain, in the mirror-like reflection the two grow further apart, slow push-in.
Shot 3: Cut to, the sky clears, warm golden light falls, the male lead @Image 3 turns and reaches out a hand, the female lead @Image 1 slowly looks back with tears in her eyes, smooth lateral movement, (piano transitions to warm and intensifies).
Shot 4: Medium shot, the two embrace, the female lead @Image 1 buries her head in the male lead @Image 3's shoulder, the male lead gently strokes her hair, warm golden backlight outlines them, slow circling, {I'm sorry, I'm back}.
Shot 5: Slow pull-out, the two figures leaning on each other merge into one under the warm golden sunlight, freeze-frame, (music concludes satisfactorily).
Constraints: Editing task approach—first generate shots 1 to 2 as the "cold gray rainy estrangement version" master, then use the editing instruction "keep the faces of @Image 1/@Image 3 and the camera composition unchanged, only change the weather to warm golden sunlight, and the posture from back-to-back to embracing" to derive the contrasting version shots 3 to 5, achieving a warm/cold reversal in the same scene; the faces of the male and female leads must remain consistent throughout, no doppelgangers/twins; reconciliation emotions are externalized through looking back with tears and embracing/burying head.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movements, not be like statues.

Brand Commercials & Ads (6)

No. 1: Fragrance Brand One-Take

• Category: Brand Commercials & Ads
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the perfume bottle from Image 1 as the main subject, wide aspect ratio 2.35:1, high-end cinematic feel, twilight golden tone, generate a 30-second brand atmosphere film, one continuous shot.

Prompt

Refer to the perfume bottle from Image 1 as the main subject, wide aspect ratio 2.35:1, high-end cinematic feel, twilight golden tone, generate a 30-second brand atmosphere film, one continuous shot.
Shot 1: Extreme macro shot starting from a water droplet condensing on the surface of the bottle @Image 1, the camera slowly pulls back, the droplet slides down refracting warm light, (low ambient strings gradually rise).
Shot 2: The camera continues to rise and pan, the perfume bottle @Image 1 stands slowly on a wet marble surface, side backlight outlines the bottle's contour, <sound of a water droplet lightly falling>.
Shot 3: The camera smoothly circles halfway around the bottle, showing the refraction of twilight light through the faceted glass, light spots moving across the surface.
Shot 4: The camera顺势 rises to a bird's-eye view of the entire setup, silk and petals scattered on the surface, twilight golden light fills the frame, 【Scent like light, lingering in this moment】.
Shot 5: The camera slowly pulls back to the macro water droplet, the image blurs and freezes on the brand's twilight golden tone, (strings conclude with a long note).
Constraints: Entire sequence is one continuous shot without cuts; the bottle must match Image 1; the twilight golden tone and wet texture run throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movements, not be like statues.

No. 2: Sportswear Brand Energetic

• Category: Brand Commercials & Ads
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the athlete from Image 2 as the main subject, vertical screen 9:16, high-contrast, hard-edged cool tone, grainy street style, generate a 30-second energetic sportswear brand advertisement.

Prompt

Refer to the athlete from Image 2 as the main subject, vertical screen 9:16, high-contrast, hard-edged cool tone, grainy street style, generate a 30-second energetic sportswear brand advertisement.
Shot 1: Extreme close-up of the athlete @Image 2's eyes suddenly opening in the shadows, low-angle shot, <rapid breathing sound>, (low-frequency drumbeat hits).
Shot 2: The camera quickly follows the athlete @Image 2 as they sprint out of a dark alley, water splashing underfoot, cold blue streetlights create light trails, <sound of shoe soles scraping>.
Shot 3: Low-angle shot looking up as they leap over an obstacle, backlit silhouette fills the frame, (drumbeat intensifies and accelerates).
Shot 4: The camera smoothly pans laterally following their sprinting profile, sweat droplets burst under hard light, muscles tense, <heartbeat thundering>.
Shot 5: The camera slowly pushes in on their roaring face before the finish line, cool tone high-contrast freeze-frame, 【Beyond, there is no finish line】, (drumbeat cuts off abruptly).
Constraints: Cool blue hard light high-contrast throughout; the athlete must match Image 2; rhythm progresses from slow tension to explosive release.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movements, not be like statues.

No. 3: Public Welfare Warmth

• Category: Brand Commercials & Ads
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical screen 9:16, soft natural light, documentary warm tone, shallow depth of field, generate a 30-second public welfare warmth short film, emotion transitioning from loneliness to acceptance.

Prompt

Vertical screen 9:16, soft natural light, documentary warm tone, shallow depth of field, generate a 30-second public welfare warmth short film, emotion transitioning from loneliness to acceptance.
Shot 1: Fixed camera close-up of a pair of small hands tightly clutching a faded cloth doll, morning light slants in, dust motes float, (single piano note softly begins).
Shot 2: The camera slowly pulls back, a solitary girl sits alone in the corner of a rural classroom, soft backlight from the window, <sound of children playing in the distance>.
Shot 3: The camera smoothly pans laterally, a large hand offers a pencil, the girl hesitantly looks up, warm light spreads across her face.
Shot 4: The camera follows the girl as she is led by the hand towards the center of the classroom, classmates gather around, shallow depth of field blurs the background, (warm strings spread out).
Shot 5: The camera slowly rises for a bird's-eye view of the whole class sitting together reading, warm sunlight fills the floor, 【Every child deserves to be seen】, (piano and strings conclude).
Constraints: Soft natural warm light throughout; emotional arc from loneliness to acceptance; shallow depth of field highlights characters.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movements, not be like statues.

No. 4: Fintech Futuristic

• Category: Brand Commercials & Ads
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Refer to the credit card from Image 3 as the main subject, horizontal screen 16:9, calm deep blue tech tone, minimalist high-end texture, generate a 30-second fintech brand film.

Prompt

Refer to the credit card from Image 3 as the main subject, horizontal screen 16:9, calm deep blue tech tone, minimalist high-end texture, generate a 30-second fintech brand film.
Shot 1: Extreme macro shot close to the metal chip texture of the credit card @Image 3, blue data light streams flow across its surface, (low-frequency synthesizer pulses begin).
Shot 2: The camera slowly pulls back, the credit card @Image 3 floats in pure black space, semi-transparent data rings appear around it, <electronic scanning sound>.
Shot 3: The camera smoothly circles the card once, blue light grids flow with the perspective, light and shadow play along the metal edges.
Shot 4: Bird's-eye shot, a city data skyline grows beneath the card, cold blue light points connect into a network, (pulse rhythm advances).
Shot 5: The camera slowly pushes in on the card, freezing on the brand logo, deep blue fades to dark, 【Security, seen in every act of trust】, (synthesizer concludes with a long note).
Constraints: Calm deep blue tech tone throughout; the card must match Image 3; data light stream texture runs throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movements, not be like statues.

No. 5: Refreshing Beverage

• Category: Brand Commercials & Ads
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the beverage can from Image 4 as the main subject, vertical 9:16, high-saturation bright summer tone, transparent watery feel, generate a 30-second refreshing beverage ad.

Prompt

Using the beverage can from Image 4 as the main subject, vertical 9:16, high-saturation bright summer tone, transparent watery feel, generate a 30-second refreshing beverage ad.
Shot 1: Ultra-high-speed macro close-up, a water droplet hits the surface of the chilled beverage can @Image 4 and explodes, low-angle shot, <crisp bursting water sound>, (upbeat electronic beat starts).
Shot 2: The camera slowly circles around the can body @Image 4 covered with condensation droplets, water droplets roll down crystal clear under backlight, sunlight refracts colorful light through them.
Shot 3: The camera quickly pulls back, beverage pours into a glass full of ice, bubbles surge upward, <fizzing bubble sound>.
Shot 4: Low-angle shot looking up at a hand raising the drink towards the blazing sun, lemon and mint scattering in the air, (beat rises).
Shot 5: The camera slowly pushes in to a close-up of bubbles at the cup's rim, high-saturation summer blue and yellow fill the screen, 【One sip awakens the whole summer】, (beat crisply concludes).
Constraints: Maintain high-saturation bright summer tone throughout; the beverage can must match Image 4; emphasize the transparent texture of water droplets and bubbles.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movement, not be statues.

No. 6: Maternal and Infant Brand

• Category: Brand Commercials & Ads
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Vertical 9:16, extremely soft creamy lighting, hazy dreamy shallow depth of field, generate a 30-second gentle maternal and infant brand film.

Prompt

Vertical 9:16, extremely soft creamy lighting, hazy dreamy shallow depth of field, generate a 30-second gentle maternal and infant brand film.
Shot 1: Fixed camera macro close-up of a baby's curled little toes, morning soft light envelops like a veil, (music box clear notes gently start).
Shot 2: The camera slowly pulls back, a mother gently rocks a sleeping baby in her arms, window gauze lets in hazy diffused light, <baby's subtle breathing sound>.
Shot 3: The camera smoothly pans sideways, the mother lowers her head to kiss the baby's forehead, creamy warm light washes over their silhouettes.
Shot 4: The camera slowly rises for a top-down shot of mother and child nestled by a cradle, soft cotton fabrics fill the frame, (gentle strings join in).
Shot 5: The camera slowly pushes in on the baby's blossoming smile, soft light overexposes and blooms, 【Gentleness is the first protection】, (music box and strings conclude).
Constraints: Maintain creamy, extremely soft lighting throughout; hazy shallow depth of field dreamy texture; mood consistently calm and gentle.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movement, not be statues.

Travel & Cultural Tourism (6)

No. 1: Ancient Town Aerial One-Take

• Category: Travel & Cultural Tourism
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Horizontal 16:9, ink-wash blue-grey tone, morning mist poetic cinematic feel, generate a 30-second ancient town cultural tourism aerial film, one continuous shot.

Prompt

Horizontal 16:9, ink-wash blue-grey tone, morning mist poetic cinematic feel, generate a 30-second ancient town cultural tourism aerial film, one continuous shot.
Shot 1: Aerial shot skims extremely low over the bluestone water lane, a black awning boat parts the water through the morning mist, (a pluck of guzheng clear note starts).
Shot 2: The camera顺势 slowly rises, pink walls, black tiles, and horse-head walls unfold in layers, cooking smoke rises from the lanes, <sound of oar paddling water>.
Shot 3: The camera smoothly pans sideways across an arch bridge, faint figures washing clothes under the bridge, reflections ripple on the water surface.
Shot 4: The camera continues ascending, circling around the ancient town's panoramic view, river channels meander like veins, morning mist drifts over blue-grey rooftops, (distant flute joins in).
Shot 5: The camera slowly pulls high for a bird's-eye view定格 of the ancient town nestled among surrounding mountains, ink-wash blue-grey blends into the skyline, 【A thousand-year dream, dwelling by the water】, (guzheng and flute conclude).
Constraints: Entirely one continuous aerial shot without cuts; ink-wash blue-grey morning mist tone throughout; Eastern poetic composition with negative space.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movement, not be statues.

No. 2: Island Vacation

• Category: Travel & Cultural Tourism
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Horizontal 16:9, transparent high-saturation tropical tone, bright sunny texture, generate a 30-second island vacation travel film.

Prompt

Horizontal 16:9, transparent high-saturation tropical tone, bright sunny texture, generate a 30-second island vacation travel film.
Shot 1: Underwater macro close-up of sunlight penetrating the azure seawater creating beams of light, fish dart past, (melodious ukulele starts).
Shot 2: The camera slowly rises above the water surface, revealing white sandy beach, coconut palms, and a clear lagoon, drone smoothly pulls back, <sound of waves lapping the shore>.
Shot 3: Low-altitude tracking shot following a person diving into the transparent shallow sea, water splashes and ripples spread, sunlight fills the water surface.
Shot 4: The camera slowly rises and circles for an aerial俯瞰 of a crescent-shaped bay, a sailboat glides across the emerald green water, (rhythm light and bright).
Shot 5: The camera pushes in on silhouettes toasting against the sunset on the beach, warm golden glow fills the screen, 【Leave your worries on the other side of the shore】, (ukulele concludes).
Constraints: Maintain transparent high-saturation tropical tone throughout; emphasize the azure and clear texture of seawater; mood light and bright.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movement, not be statues.

No. 3: Sacred Snow Mountain

• Category: Travel & Cultural Tourism
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Horizontal 16:9, cold high-contrast snow-white blue tone, extremely clear and grand sense, generate a 30-second snow mountain cultural tourism epic film.

Prompt

Horizontal 16:9, cold high-contrast snow-white blue tone, extremely clear and grand sense, generate a 30-second snow mountain cultural tourism epic film.
Shot 1: Extreme close-up macro shot of the sharp facets of an ice crystal in a snowstorm, cold blue backlight glitters, <howling wind sound>, (low choral vocals start).
Shot 2: The camera slowly pulls back, a solitary snow-capped peak pierces the sea of clouds and stands against the sky, dawn paints the summit with a golden edge, the frame is vast.
Shot 3: Aerial shot smoothly pans sideways skimming over the绵延 snow ridges, wind whips up snow mist like ribbons dancing, cold blue shadows distinct in light and dark.
Shot 4: The camera slowly ascends for a top-down shot of a glacial crevasse winding down, blue ice deep and translucent, (chorus layers and swells grandly).
Shot 5: Low-angle shot定格 at the summit bathed in golden sunlight, holy light pours down at the junction of cold white and warm gold, 【Upward, just to touch purity】, (vocal long note concludes).
Constraints: Maintain cold snow-white blue tone with high contrast throughout; grand and vast composition; highlight ice crystal texture and the golden summit.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movement, not be statues.

No. 4: City Nightscape

• Category: Travel & Cultural Tourism
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Horizontal 16:9, cyberpunk neon high-saturation tone, wet reflective urban feel, generate a 30-second city nightscape travel film.

Prompt

Horizontal 16:9, cyberpunk neon high-saturation tone, wet reflective urban feel, generate a 30-second city nightscape travel film.
Shot 1: Extreme macro close-up of a raindrop sliding down glass, neon light spots blur into迷离 light clusters behind it, (electronic synthesizer pulse starts).
Shot 2: The camera slowly pulls back through the window, drone俯瞰 the繁华 street woven by car light trails after rain, <sound of traffic flow>.
Shot 3: Aerial shot smoothly rises and circles around skyscraper clusters, glass curtain walls reflect neon lights,光影 layer and flicker.
Shot 4: Low-altitude tracking shot following pedestrians with umbrellas in neon-lit streets, wet ground reflects colorful lights, (rhythm律动推进).
Shot 5: The camera slowly pulls high for a俯瞰定格 of the entire sleepless city's sea of lights, neon pulses like breathing, 【Under the lights, all are stories】, (synthesizer concludes).
Constraints: Maintain cyberpunk neon high-saturation throughout; wet reflective texture贯穿; rich layers of light trails and neon.
General Constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters should have natural subtle movement, not be statues.

No. 5: Desert Caravan

• Category: Travel & Cultural Tourism
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Landscape 16:9, warm golden-orange desert tone, high-contrast backlight epic feel, generate a 30-second desert cultural tourism video.

Prompt

Landscape 16:9, warm golden-orange desert tone, high-contrast backlight epic feel, generate a 30-second desert cultural tourism video.
Shot 1: Extreme close-up macro shot of fine sand trickling through fingers, each grain glinting gold in the backlight, (distant string music and hand drum begin).
Shot 2: The camera slowly pulls back, a camel caravan moves slowly in silhouette across undulating sand dunes, the huge sun hangs low on the horizon, <clinking camel bells>.
Shot 3: Aerial shot looking down at the long, slanted shadows cast by the caravan on a sand ridge, the curves of the dunes undulating like silk.
Shot 4: Low-angle shot looking up at the backlit silhouette of the lead camel driver advancing against the wind, wind whipping up sand and dust, (hand drum rhythm intensifies).
Shot 5: The camera slowly rises to an aerial view overlooking the caravan disappearing into the boundless golden sea of sand, warm golden-orange fills the sky and earth, 【穿越荒芜 只为看见辽阔】, (string music and hand drum conclude).
Constraints: Maintain warm golden-orange high-contrast backlight throughout; sand dune curves and caravan silhouettes are the core of composition; epic, vast emotion.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural, slight movement, not be statues.

No. 6: Street Food Tour (One Shot)

• Category: Travel & Cultural Tourism
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Portrait 9:16, warm orange, smoky, high-saturation tone, lively street market texture, generate a 30-second street food tour video, one continuous shot.

Prompt

Portrait 9:16, warm orange, smoky, high-saturation tone, lively street market texture, generate a 30-second street food tour video, one continuous shot.
Shot 1: Extreme macro shot starting from sizzling, oil-splattering ingredients on a griddle, the camera slowly pulls back, steam billowing, <sound of oil crackling>, (lively street percussion music begins).
Shot 2: The camera smoothly pans horizontally through the bustling night market, flames leaping as vendors stir-fry under warm yellow string lights, <bustling sounds of crowds and vendors calling out>.
Shot 3: The camera continues tracking, moving into an alley, passing by steaming baskets being opened with white mist pouring out, skewers glowing red on charcoal, smoky atmosphere permeates.
Shot 4: The camera slowly circles around a table of diners eating heartily, clinking glasses and laughing, warm orange light illuminates their smiling faces, (percussion music rhythm becomes lively).
Shot 5: The camera smoothly rises to a high-angle shot looking down at the entire brightly lit food street, crowds flowing, 【人间烟火 最抚凡心】, (percussion music concludes).
Constraints: Entire video is one continuous shot with no cuts; warm orange, smoky, high-saturation tone; steam, flames, and smoky atmosphere throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural, slight movement, not be statues.

Pets & Animals (5)

No. 1: Cute Cat Close-up

• Category: Pets & Animals
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the cat @Image 1 as the main subject, portrait 9:16, soft-focus lifestyle flow, warm sunlight beige tone + shallow depth of field, generate a 30-second healing pet short video.

Prompt

Using the cat @Image 1 as the main subject, portrait 9:16, soft-focus lifestyle flow, warm sunlight beige tone + shallow depth of field, generate a 30-second healing pet short video.
Shot 1: Close-up, the cat @Image 1 suddenly opens its eyes wide, pupils staring directly at the camera, fixed camera position, (clear glockenspiel single note) <cat's soft "meow">.
Shot 2: Macro shot, the cat @Image 1's pink nose twitches slightly, whiskers tremble, the camera slowly pushes in, <subtle breathing sound>.
Shot 3: Medium shot, the cat @Image 1 lifts a paw to press down on a floating feather, the camera pans smoothly, (glockenspiel rhythm becomes light and cheerful).
Shot 4: Close-up, the cat @Image 1 yawns, revealing its little tongue, the camera slowly pulls back, <contented purring sound>.
Shot 5: Full shot, the cat @Image 1 curls up into a ball and falls asleep, the camera slowly rises for a high-angle shot, freeze frame, (music fades) 【今天也要好好休息】.
Constraints: The cat's fur color and pattern must match Image 1 consistently throughout; pupils and nose must remain pink; changing breed or color is prohibited.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural, slight movement, not be statues.

No. 2: Dog Running

• Category: Pets & Animals
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the dog @Image 1 as the main subject, landscape 16:9, motion tracking focus, golden backlit grassland + high shutter speed graininess, generate a 30-second热血 running video.

Prompt

Using the dog @Image 1 as the main subject, landscape 16:9, motion tracking focus, golden backlit grassland + high shutter speed graininess, generate a 30-second热血 running video.
Shot 1: Low-angle close-up, the dog @Image 1's hind legs push off the ground, launching into a run, kicking up grass clippings, fixed camera position, (drumbeat suddenly starts) <muffled sound of paws hitting the ground>.
Shot 2: Full shot, the dog @Image 1 stretches its limbs running across the grassland, the camera pans smoothly, tracking focus, <sound of wind rushing past ears>.
Shot 3: Tracking medium shot, the dog @Image 1's ears swept back, tongue hanging out, the camera tracks at a low angle, (rhythm accelerates).
Shot 4: Close-up, the dog @Image 1 leaps over a small stream, water splashing, the camera slowly pushes in, slow motion, <sound of water splashing>.
Shot 5: Full shot, the dog @Image 1 runs towards the camera, stops abruptly, sits down, panting with a grin, the camera slowly pulls back, freeze frame, (music concludes) <happy panting>.
Constraints: The dog's breed and fur color must match Image 1 consistently throughout; running gait must conform to realistic quadrupedal mechanics; floating or sliding steps are prohibited.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural, slight movement, not be statues.

No. 3: Underwater Fish School

• Category: Pets & Animals
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the coral reef tropical fish school @Image 1 as the main subject, landscape 16:9, documentary-level underwater photography, Tyndall light beams + cyan-blue transparent water color, generate a 30-second海底 exploration video.

Prompt

Using the coral reef tropical fish school @Image 1 as the main subject, landscape 16:9, documentary-level underwater photography, Tyndall light beams + cyan-blue transparent water color, generate a 30-second海底 exploration video.
Shot 1: Close-up, a clownfish @Image 1 peeks out from among anemone tentacles, fixed camera position, (ethereal water droplet music begins) <bubbles gurgling>.
Shot 2: Full shot, a school of tropical fish @Image 1 gathers into a silver vortex, the camera slowly circles around, <sound of water flowing>.
Shot 3: Medium shot, the fish school @Image 1 collectively turns and swims through a light beam, the camera moves smoothly horizontally, passing through, (string music expands).
Shot 4: Low-angle shot looking up, full shot, the fish school @Image 1 swims towards the surface silhouette, the camera slowly rises, low-angle shot, <deep-sea low-frequency hum>.
Shot 5: Close-up, the clownfish @Image 1 swims back alone to the anemone and settles, the camera slowly pulls back, freeze frame, (music fades out).
Constraints: The clownfish's orange-white stripes and reef color scheme must match Image 1; fish school movement must maintain natural staggering without overlapping or clipping;整齐 cloned formations are prohibited.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural, slight movement, not be statues.

No. 4: Bird Macro

• Category: Pets & Animals
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the hummingbird @Image 1 as the main subject, portrait 9:16, super macro high-speed photography, morning dew flower cluster + blurred creamy background, generate a 30-second ecological micro video.

Prompt

Using the hummingbird @Image 1 as the main subject, portrait 9:16, super macro high-speed photography, morning dew flower cluster + blurred creamy background, generate a 30-second ecological micro video.
Shot 1: Macro close-up, the hummingbird @Image 1 hovers, wings beating, turning into a transparent arc of motion blur, fixed camera position, (harp harmonics begin) <high-frequency wing buzzing sound>.
Shot 2: Close-up, the hummingbird @Image 1's slender beak probes into a flower stamen to suck nectar, the camera slowly pushes in, <petals trembling lightly>.
Shot 3: Macro shot, the hummingbird @Image 1's iridescent throat feathers change color with angle, the camera slowly circles around, (harp glissando).
Shot 4: Medium shot, the hummingbird @Image 1 shakes morning dew droplets off its body, the camera pans smoothly, slow motion, <water droplets falling>.
Shot 5: Full shot, the hummingbird @Image 1 suddenly darts away and flies out of frame, the camera slowly pulls back, freeze frame on an empty branch, (music concludes).
Constraints: The hummingbird's iridescent feather colors and beak shape must match Image 1; wingbeats must show realistic high-speed motion blur;定格 stiff wings are prohibited.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural, slight movement, not be statues.

No. 5: Anthropomorphic Pet

• Category: Pets & Animals
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Featuring the Shiba Inu with chef's hat @Image 1 as the main subject, vertical 9:16, Pixar-style 3D cartoon, warm kitchen lighting + saturated highlights, generate a 30-second funny anthropomorphic short film. Lock 3D cartoon rendering, prohibit drift into realism.

Prompt

Featuring the Shiba Inu with chef's hat @Image 1 as the main subject, vertical 9:16, Pixar-style 3D cartoon, warm kitchen lighting + saturated highlights, generate a 30-second funny anthropomorphic short film. Lock 3D cartoon rendering, prohibit drift into realism.
Shot 1: Close-up, Shiba Inu @Image 1 wearing a crooked chef's hat stares seriously at the frying pan, fixed camera, (comical bassoon starts) {"Today, toss the wok!"}.
Shot 2: Medium shot, Shiba Inu @Image 1 holds the pan with both paws and tosses vigorously, ingredients fly into the air, camera slowly pushes in, <sizzling oil>.
Shot 3: Full shot, Shiba Inu @Image 1 looks up and opens its mouth to catch them but they all land on its face, fixed camera, (sound effect "ding") <splat, covering the face>.
Shot 4: Close-up, Shiba Inu @Image 1's face covered in batter, dazed and blinking, camera slowly pushes in, {"...Not bad."}.
Shot 5: Medium shot, Shiba Inu @Image 1 calmly presents burnt dish as a treasure, camera slowly pulls out and freezes, (cheerful ending) 【Kitchen Disaster God · Shiba】.
Constraints: Shiba Inu's fur color and chef's hat must remain consistent with Image 1 throughout, lock 3D cartoon style, anthropomorphic facial expressions exaggerated but proportions unified, prohibit shifting to realism mid-way.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters need natural slight movement, not statues.

Kids, Education & Science (5)

No. 1: Mars Exploration Science

• Category: Kids, Education & Science
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Featuring the Mars rover @Image 1 as the main subject, horizontal 16:9, documentary science CG, rusty red surface + cool-toned starry sky, generate a 30-second aerospace science film.

Prompt

Featuring the Mars rover @Image 1 as the main subject, horizontal 16:9, documentary science CG, rusty red surface + cool-toned starry sky, generate a 30-second aerospace science film.
Shot 1: Full shot, rover @Image 1 stands still on the horizon of the red wasteland, camera slowly rises, (grand synthesizer starts) <low howl of Martian wind>.
Shot 2: Close-up, rover @Image 1's six wheels slowly roll over gravel, low-angle camera follows, <mechanical creaking>.
Shot 3: Medium shot, rover @Image 1's robotic arm extends to collect rock sample, camera slowly pushes in, (strings gradually intensify) 【Drilling sample · Analyzing composition】.
Shot 4: Low-angle shot, rover @Image 1 raises its camera mast to look at the sky, camera slowly orbits, <data beeping sound>.
Shot 5: Full shot, rover @Image 1 drives towards a distant crater, camera slowly pulls out and tilts down to freeze, (music swells) 【Next stop: The unknown】.
Constraints: Rover structure and color scheme must remain consistent with Image 1 throughout, Martian surface conforms to realistic low-gravity dust clouds, prohibit Earth vegetation or blue sky.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters need natural slight movement, not statues.

No. 2: Human Organ Illustration

• Category: Kids, Education & Science
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Featuring the 3D heart model @Image 1 as the main subject, horizontal 16:9, medical visualization, semi-transparent texture + dark background with crimson vein lighting, generate a 30-second human body science film. Lock semi-transparent medical 3D style, prohibit drift into realism or gore.

Prompt

Featuring the 3D heart model @Image 1 as the main subject, horizontal 16:9, medical visualization, semi-transparent texture + dark background with crimson vein lighting, generate a 30-second human body science film. Lock semi-transparent medical 3D style, prohibit drift into realism or gore.
Shot 1: Full shot, heart @Image 1 floats in dark space, pulsating slowly, camera slowly orbits, (low-frequency pulse music starts) <heartbeat thumping>.
Shot 2: Close-up, coronary arteries on the surface of heart @Image 1 highlight and appear, camera slowly pushes in, 【Coronary arteries · Blood supply】.
Shot 3: Cross-section medium shot, heart @Image 1 becomes semi-transparent revealing blood flow in four chambers, camera steadily pans, <blood flow surging>.
Shot 4: Close-up, mitral valve of heart @Image 1 opens and closes with the rhythm, fixed camera, (beat synchronized with heartbeat).
Shot 5: Full shot, heart @Image 1 returns to complete form, continues pulsating, camera slowly pulls out and freezes, (music steady) 【Approximately 100,000 beats per day】.
Constraints: Heart anatomical structure and chamber positions must be scientifically accurate based on Image 1, maintain semi-transparent illustrative style, prohibit realistic gore or structural misplacement.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters need natural slight movement, not statues.

No. 3: Children's Picture Book Animation

• Category: Kids, Education & Science
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Featuring the little bear @Image 1 as the main subject, vertical 9:16, 2D hand-drawn picture book style, watercolor paper texture + warm-toned crayon outlines, generate a 30-second bedtime story animation. Lock 2D hand-drawn watercolor style, prohibit drift into realism or 3D.

Prompt

Featuring the little bear @Image 1 as the main subject, vertical 9:16, 2D hand-drawn picture book style, watercolor paper texture + warm-toned crayon outlines, generate a 30-second bedtime story animation. Lock 2D hand-drawn watercolor style, prohibit drift into realism or 3D.
Shot 1: Medium shot, little bear @Image 1 pushes open the wooden door and looks at the starry sky, fixed camera, (music box melody starts) {"The stars are so bright tonight."}.
Shot 2: Full shot, little bear @Image 1 walks along a flower-lined path holding a small lantern, camera steadily pans, <rustling grass>.
Shot 3: Close-up, little bear @Image 1 looks up as a shooting star streaks across, camera slowly pushes in, (ding-dong sound) 【Make a wish】.
Shot 4: Medium shot, little bear @Image 1 closes eyes and puts hands together to make a wish, camera slowly orbits, <gentle night breeze>.
Shot 5: Full shot, little bear @Image 1 lies down in the grass, covers itself with a leaf blanket and falls asleep, camera slowly rises and tilts down to freeze, (music box fades) {"Goodnight, little stars."}.
Constraints: Little bear's design and color scheme must remain consistent with Image 1 throughout, lock 2D hand-drawn watercolor brushstrokes, retain paper texture and outlines, prohibit shifting to 3D or realism.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters need natural slight movement, not statues.

No. 4: Physics Experiment Demonstration

• Category: Kids, Education & Science
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Featuring the Newton's cradle metal balls @Image 1 as the main subject, horizontal 16:9, science demonstration realism, pure laboratory white + side/back hard lighting, generate a 30-second physics science film.

Prompt

Featuring the Newton's cradle metal balls @Image 1 as the main subject, horizontal 16:9, science demonstration realism, pure laboratory white + side/back hard lighting, generate a 30-second physics science film.
Shot 1: Close-up, one end ball of Newton's cradle @Image 1 is lifted and suspended, fixed camera, (suspenseful ticking music starts) <light sound of finger releasing>.
Shot 2: Medium shot, ball @Image 1 swings down, moment of impact and energy transfer, camera slowly pushes in with slow motion, <crisp metal collision>.
Shot 3: Close-up, the other end ball @Image 1 is knocked up into the air, camera steadily follows its ascent, (sound effect "ding") 【Conservation of momentum】.
Shot 4: Full shot, Newton's cradle @Image 1 swings alternately at both ends, camera slowly orbits, <rhythmic collision beats>.
Shot 5: Medium shot, ball @Image 1's swing amplitude gradually decreases towards stillness, camera slowly pulls out and freezes, (music concludes) 【Energy transfers through collisions】.
Constraints: Number of metal balls and frame structure must be based on Image 1, swinging follows real conservation of momentum physics, prohibit floating or amplification that violates mechanics.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters need natural slight movement, not statues.

No. 5: Historical Scene Recreation

• Category: Kids, Education & Science
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Featuring the ancient Roman Colosseum @Image 1 as the main subject, horizontal 16:9, epic historical recreation, golden dusk dust light + aged film grain, generate a 30-second historical documentary.

Prompt

Featuring the ancient Roman Colosseum @Image 1 as the main subject, horizontal 16:9, epic historical recreation, golden dusk dust light + aged film grain, generate a 30-second historical documentary.
Shot 1: Full shot, Colosseum @Image 1 bathed in the setting sun stands majestically, camera slowly rises in aerial shot, (epic vocal chant starts) <ancient wind sound>.
Shot 2: Medium shot, Colosseum @Image 1's stands gradually "grow" and restore from ruins to full seating, camera slowly pushes in, <surge of crowd noise>.
Shot 3: Close-up, details of stone arch carvings on Colosseum @Image 1, camera steadily pans, (drums gradually intensify) 【80 AD · Completion】.
Shot 4: Low-angle full shot, dust rises from the sand of the central arena in Colosseum @Image 1, camera slowly orbits, <long horn blast>.
Shot 5: Full shot, Colosseum @Image 1's restored image "dissipates" back to today's ruins, camera slowly pulls out and tilts down to freeze, (music ends bleakly) 【A millennium later, still standing】.
Constraints: Colosseum architectural structure and ruin locations must be based on Image 1, restored and ruined forms correspond consistently, prohibit fabricating modern elements not historically accurate.
General constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters need natural slight movement, not statues.

Gaming, CG & Fantasy (5)

No. 1: Dragon Dive

• Category: Gaming, CG & Fantasy
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the black dragon and knight from Image 1 as the main subjects, widescreen 2.35:1, cinematic CG, warm rim light + deep blue shadows, generate a 30-second fantasy flight video.

Prompt

Using the black dragon and knight from Image 1 as the main subjects, widescreen 2.35:1, cinematic CG, warm rim light + deep blue shadows, generate a 30-second fantasy flight video.
Shot 1: Wide shot, the black dragon @Image 1 takes off from the canyon with wings spread, the camera slowly rises and follows, (grand orchestral music begins).
Shot 2: Medium shot, the knight @Image 1 lowers his body, the black dragon @Image 1 makes a sharp right turn and dives, the camera follows smoothly (slightly low angle), <howling wind>.
Shot 3: Close-up, the black dragon @Image 1 folds one wing and passes through waterfall mist, the camera slowly pushes in.
Shot 4: Wide shot, the black dragon @Image 1 bursts out of the mist and glides into a forest clearing, the camera slowly pulls back and holds, (music concludes).
Constraints: The appearance of the black dragon and knight must remain consistent with Image 1 throughout, no doppelgangers or twins.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural subtle movement, not be statues.

No. 2: Spellcasting

• Category: Gaming, CG & Fantasy
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the female mage @Image 1 as the main subject, widescreen 2.35:1, cinematic fantasy CG, ghostly blue rune light + particle glow, generate a 30-second spell incantation video.

Prompt

Using the female mage @Image 1 as the main subject, widescreen 2.35:1, cinematic fantasy CG, ghostly blue rune light + particle glow, generate a 30-second spell incantation video.
Shot 1: Close-up, the female mage @Image 1 opens her eyes, runes light up within them, fixed camera, (low chanting suddenly begins) {"In the name of Aether——"}.
Shot 2: Medium shot, the female mage @Image 1 raises her hand, a rotating magic circle gathers in her palm, the camera slowly orbits around, <energy hum intensifies>.
Shot 3: Close-up, particles gather at the female mage @Image 1's fingertips forming a light sphere, the camera slowly pushes in, (music holds its breath for a beat).
Shot 4: Wide shot, the female mage @Image 1 pushes her hands forward, a giant frost explosion erupts and blasts forward, the camera smoothly follows the shockwave, <sudden explosive crash>.
Shot 5: Medium shot, the female mage @Image 1 recovers her stance, panting, the residual light of the magic circle fades, the camera slowly pulls back and holds, (chanting resonance concludes).
Constraints: The female mage's attire and rune color scheme must remain consistent with Image 1 throughout. Magic circles and particles must always be in ghostly blue hues, no mid-video color changes or character distortion.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural subtle movement, not be statues.

No. 3: Mech Reveal

• Category: Gaming, CG & Fantasy
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the giant mech @Image 1 as the main subject, widescreen 2.35:1, hardcore industrial CG, cold steel metal + hangar spotlights and steam, generate a 30-second mech deployment video.

Prompt

Using the giant mech @Image 1 as the main subject, widescreen 2.35:1, hardcore industrial CG, cold steel metal + hangar spotlights and steam, generate a 30-second mech deployment video.
Shot 1: Close-up, the mech @Image 1's main camera/eye suddenly lights up with red light, fixed camera, (industrial bass rumble begins) <system startup hum>.
Shot 2: Low-angle wide shot, the mech @Image 1 slowly raises its head and stands up in the hangar, the camera slowly rises for a low-angle shot, <hydraulic hiss>.
Shot 3: Medium shot, the mech @Image 1 takes a step, causing ground tremors, steam vents, the camera follows with a low angle, (drumbeat hits) <heavy metallic footstep>.
Shot 4: Close-up, the mech @Image 1's shoulder missile pods deploy and lock on, the camera slowly pushes in, (sound effect "Lock-on" beep) 【Armed and Ready】.
Shot 5: Wide shot, the mech @Image 1 charges out of the hangar and leaps into the battlefield, the camera smoothly follows and then pulls back to hold, (music erupts and concludes) <thruster roar>.
Constraints: The mech's body structure and paint scheme must remain consistent with Image 1 throughout. Mechanical joint movement must convey weight and hydraulic logic, no part clipping or unrealistic lightness.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural subtle movement, not be statues.

No. 4: Open World Vista

• Category: Gaming, CG & Fantasy
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the fantasy continent panorama @Image 1 as the main subject, widescreen 2.35:1, open-world game CG, volumetric cloud morning mist + extreme distance depth of field, generate a 30-second world view showcase video.

Prompt

Using the fantasy continent panorama @Image 1 as the main subject, widescreen 2.35:1, open-world game CG, volumetric cloud morning mist + extreme distance depth of field, generate a 30-second world view showcase video.
Shot 1: Wide shot, morning mist drifts over the continent @Image 1's valleys and distant floating islands, the camera slowly rises for an aerial shot, (vast strings music begins) <morning breeze and bird calls>.
Shot 2: Medium shot, a waterfall from the continent @Image 1's giant cliff pours into a sea of clouds, the camera smoothly pans horizontally, <roaring water sound>.
Shot 3: Wide shot, a herd of giant beasts on the continent @Image 1 sweeps across the grassland towards a distant city, the camera slowly follows, (string layers build and advance).
Shot 4: Close-up, an ancient ruin's stone tablet on the continent @Image 1 is covered in carved runes, the camera slowly pushes in, <mysterious low hum>.
Shot 5: Wide shot, the camera pulls up to reveal the entire continent's full view and the twin-sun sky, the camera slowly rises and pulls back to hold, (music majestic conclusion) 【World, awaits your exploration】.
Constraints: The continent's terrain and floating island layout must remain consistent with Image 1 throughout. Extreme depth of field must maintain volumetric fog layers, no terrain misalignment or proportion distortion.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural subtle movement, not be statues.

No. 5: White Model Rendering Demo

• Category: Gaming, CG & Fantasy
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the scene white model @Image 1 as the main subject, materials taken from reference Image 2, landscape 16:9, real-time rendering breakdown demo, starting from a matte gray-white base model, generate a 30-second evolution video from white model to final render.

Prompt

Using the scene white model @Image 1 as the main subject, materials taken from reference Image 2, landscape 16:9, real-time rendering breakdown demo, starting from a matte gray-white base model, generate a 30-second evolution video from white model to final render.
Shot 1: Wide shot, the white model @Image 1, a gray-white untextured scene, slowly rotates to display its volumes, the camera slowly orbits, (techy electronic music begins) 【Blockout·White Model】.
Shot 2: Medium shot, materials @Image 2 are brushed onto the surface of the white model @Image 1, covering stone and wood textures face by face, the camera smoothly pans horizontally, <material loading ticks>.
Shot 3: Close-up, normal and roughness details appear on the scene @Image 1, creating bump texture, the camera slowly pushes in, 【PBR Material·Coloring】.
Shot 4: Wide shot, lights in the scene @Image 1 turn on one by one, casting shadows and reflections, the camera slowly rises, (music layers progress) 【Lighting·Lighting】.
Shot 5: Wide shot, post-processing color grading and volumetric light are added to the scene @Image 1 to become the final frame, the camera slowly pulls back to hold, (music concludes) 【Final Render】.
Constraints: The scene's volumes and structure must remain consistent with Image 1 throughout. Material textures are taken from Image 2 and applied step by step. The transition from white model to final render only changes shading, not geometric layout. No model deformation or visual errors.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural subtle movement, not be statues.

Animation & Cartoons (4)

No. 1: Ghibli Food Episode

• Category: Animation & Cartoons
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using a pair of hands and a late-night kitchen from Image 1 as the main subjects (hands and kitchen as per Image 1), vertical 9:16, Ghibli hand-drawn style, warm yellow night kitchen tone, generate a 30-second healing late-night diner video.

Prompt

Using a pair of hands and a late-night kitchen from Image 1 as the main subjects (hands and kitchen as per Image 1), vertical 9:16, Ghibli hand-drawn style, warm yellow night kitchen tone, generate a 30-second healing late-night diner video.
Shot 1: Extreme close-up, a water droplet rolls off a tomato's skin reflecting warm light, fixed slightly overhead camera, <light sound of water droplet falling>, (healing acoustic guitar begins).
Shot 2: Medium shot, a hand holds a knife cutting a tomato, red juice seeps out, the camera slowly pans, <sound of knife cutting through soft/crisp flesh>.
Shot 3: Close-up, tomato pieces slide into a hot oiled pan, white steam rises, the camera slowly pushes in, <sizzle of ingredients hitting the pan>.
Shot 4: Extreme close-up, the hand sprinkles basil leaves and stir-fries, aroma rises, the camera slowly orbits, <rustling sound of spatula stirring>.
Shot 5: Medium shot, hot soup is ladled into a ceramic bowl, hands bring it to the center of the frame, the camera slowly pulls back, <gurgling soup sound>, (acoustic guitar concludes).
Constraints: Lock to Ghibli hand-drawn style, no drift to realism; Only one pair of hands appears throughout, no faces or extra hands; Night kitchen setup must be fixed as per Image 1.
General Constraints: Keep no subtitles; Do not generate Logo; Do not generate watermarks; Use only one camera movement per shot; Characters should have natural subtle movement, not be statues.

No. 2: Chibi Character Interaction

• Category: Animation & Cartoons
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the two big-eyed chibi characters from Image 1 as the main subjects (their design and color scheme must match Image 1 exactly), vertical 9:16, candy-colored cartoon short style, high-saturation soft lighting, generate a 30-second cute interaction clip.

Prompt

Using the two big-eyed chibi characters from Image 1 as the main subjects (their design and color scheme must match Image 1 exactly), vertical 9:16, candy-colored cartoon short style, high-saturation soft lighting, generate a 30-second cute interaction clip.
Shot 1: Extreme close-up, one chibi character widens its eyes, puffs its cheeks trying not to laugh, fixed camera, <cartoon "boing" bouncing sound effect>, (playful marimba starts).
Shot 2: Medium shot, the other character hops closer and offers a heart-shaped candy, camera slowly pans, <footstep bouncing "ding ding" sound>.
Shot 3: Full shot, the two characters hold hands and spin in place, creating a trail of stars, camera slowly orbits, {(characters) "Let's spin together!"}.
Shot 4: Close-up, one character suddenly trips, eyes welling up with tears, camera slowly pushes in, <exaggerated "waa" crying sound effect>.
Shot 5: Medium shot, the other character rushes in for a hug, two hearts pop out of the frame, camera slowly pulls out, 【Friendship Maxed】, (marimba rises and concludes).
Constraints: Lock in chibi candy-colored cartoon style, no drift to realism; the two characters' design and color scheme must strictly follow Image 1; exaggerated expressions and deformations follow cartoon physics.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statues.

No. 3: 3D Pixar Style

• Category: Animation & Cartoons
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the little robot character from Image 1 as the main subject (its design and material must match Image 1 exactly), horizontal 16:9, Pixar-style 3D animation, early morning warm sunlight quality, generate a 30-second healing exploration short.

Prompt

Using the little robot character from Image 1 as the main subject (its design and material must match Image 1 exactly), horizontal 16:9, Pixar-style 3D animation, early morning warm sunlight quality, generate a 30-second healing exploration short.
Shot 1: Extreme close-up, the little robot's round lens eye slowly lights up, focusing on a dandelion, fixed camera, <mechanical focusing "beep" sound>, (orchestral music starts softly).
Shot 2: Medium shot, the little robot tilts its head curiously, extending a mechanical arm to gently touch a petal, camera slowly pushes in, <subtle servo motor whirring sound>.
Shot 3: Full shot, a gust of wind scatters the dandelion seeds, the little robot chases after them running, camera follows, <sound of fluffy seeds floating in the air>.
Shot 4: Low-angle shot, seeds fill the sky, the little robot spreads its arms and looks up, camera slowly tilts up/down, (strings gradually intensify).
Shot 5: Long shot, the little robot stands alone on a hilltop as the sun rises, casting a long shadow, camera slowly pulls out, (orchestral music climaxes and concludes).
Constraints: Lock in Pixar 3D style, no drift to realism or Ghibli hand-drawn; robot design and material must follow Image 1; subsurface scattering warm light throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statues.

No. 4: Watercolor Landscape Animation

• Category: Animation & Cartoons
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the Jiangnan water town from Image 1 as the main subject (composition and color tone must match Image 1 exactly), horizontal 16:9, flowing watercolor hand-drawn animation style, post-rain bluish-gray pastel tone, generate a 30-second poetic four-season transition clip.

Prompt

Using the Jiangnan water town from Image 1 as the main subject (composition and color tone must match Image 1 exactly), horizontal 16:9, flowing watercolor hand-drawn animation style, post-rain bluish-gray pastel tone, generate a 30-second poetic four-season transition clip.
Shot 1: Extreme close-up, a raindrop falls into the water, ripples spread and ink color diffuses, fixed slightly high-angle camera, <clear sound of raindrop hitting water>, (guzheng overtone starts).
Shot 2: Full shot, black tiles and white walls reflected in the water, watercolor brushstrokes gently sway with the waves, camera slowly pans, <sound of light drizzle>.
Shot 3: Long shot, a leaf boat passes under an arched bridge, rippling the water, camera slowly follows, <sound of wooden oar paddling water>.
Shot 4: Medium shot, willow branches by the bridge sprout, petals fall, color tone shifts to spring pink, camera slowly pushes in, <sound of breeze rustling leaves>.
Shot 5: Long shot, dusk falls, lanterns light up one by one, reflecting fully in the river, camera slowly tilts up/down, (guzheng fades away distantly).
Constraints: Lock in flowing watercolor hand-drawn style, no drift to realism or 3D; water town composition must follow Image 1; retain brushstroke bleeding effect and paper texture throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statues.

Sports & Fitness (4)

No. 1: Gym Strength

• Category: Sports & Fitness
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the deadlift athlete from Image 1 as the main subject (person and equipment must match Image 1 exactly), vertical 9:16, hardcore fitness ad style, cool-toned high-contrast steel texture, generate a 30-second power burst clip.

Prompt

Using the deadlift athlete from Image 1 as the main subject (person and equipment must match Image 1 exactly), vertical 9:16, hardcore fitness ad style, cool-toned high-contrast steel texture, generate a 30-second power burst clip.
Shot 1: Extreme close-up, palm slaps chalk heavily onto the barbell, powder splashes, fixed camera, <muffled sound of chalk slap>, (low-frequency drum pulse starts).
Shot 2: Close-up, hands tightly grip the barbell, veins bulging, camera slowly pushes in, <creaking sound of iron bar under stress>.
Shot 3: Full shot, the athlete exerts force to lift the barbell, plates slightly tremble, camera slowly tilts up/down following the lift, <deep exertion grunt>.
Shot 4: Low-angle shot, barbell lifted to the peak, muscle lines outlined by cold light, camera slowly orbits, (drum hits heaviest).
Shot 5: Close-up, barbell slams back to the ground, bounces and vibrates, sweat droplets fly, camera slowly pulls out, <loud crash of iron plates hitting ground>, (drums cut off abruptly).
Constraints: Person and equipment must follow Image 1; cool-toned hard light high contrast throughout; barbell plate tremor and sweat droplets must follow realistic weight physics.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statues.

No. 2: Yoga Stretch

• Category: Sports & Fitness
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the yoga practitioner and the morning-lit studio from Image 1 as the main subjects (person and space must match Image 1 exactly), vertical 9:16, serene zen lifestyle style, morning mist soft light low-saturation tone, generate a 30-second mind-body stretch clip.

Prompt

Using the yoga practitioner and the morning-lit studio from Image 1 as the main subjects (person and space must match Image 1 exactly), vertical 9:16, serene zen lifestyle style, morning mist soft light low-saturation tone, generate a 30-second mind-body stretch clip.
Shot 1: Extreme close-up, practitioner closes eyes for a deep breath, exhaled air stirs fine dust floating in a beam of light, fixed camera, <sound of one long breath>, (singing bowl long tone starts).
Shot 2: Full shot, body slowly folds into a forward bend, morning light spills over the spine, camera slowly tilts up/down, <subtle sound of fabric rubbing>.
Shot 3: Medium shot, arms stretch and flow into warrior pose, breathing steady, camera slowly orbits, (bowl sound and bird song intertwine).
Shot 4: Close-up, fingertips lightly touch the ankle, muscle lines stretch, camera slowly pans, <subtle sound of tendon stretching>.
Shot 5: Full shot, sitting cross-legged with palms together, head bowed, morning mist fills the entire studio, camera slowly pulls out, (singing bowl resonance fades).
Constraints: Person and morning-lit studio must follow Image 1; soft light low-saturation zen tone throughout; movements must be smooth and continuous, no abrupt cuts.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statues.

No. 3: Basketball Dunk

• Category: Sports & Fitness
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the streetball athlete from Image 1 as the main subject (person and court must match Image 1 exactly), horizontal 16:9,热血 street sports ad style,黄昏 warm orange hard light tone, generate a 30-second high-energy dunk clip.

Prompt

Using the streetball athlete from Image 1 as the main subject (person and court must match Image 1 exactly), horizontal 16:9,热血 street sports ad style,黄昏 warm orange hard light tone, generate a 30-second high-energy dunk clip.
Shot 1: Extreme close-up, basketball spins rapidly on a fingertip, texture clear, fixed camera, <friction sound of leather ball spinning>, (electronic drum heavy beat starts).
Shot 2: Full shot, athlete dribbles, breaks through, stops abruptly and changes direction, shoe soles screech on the ground, camera follows, <squealing sound of sneakers braking>.
Shot 3: Medium shot, feet push off the ground, body launches into the air, flying towards the hoop, camera slowly tilts up/down following the jump, <explosive sound of takeoff push>.
Shot 4: Low-angle shot, body suspended in mid-air, hand holding the ball about to slam down, backlit silhouette, camera slowly orbits, (drum beat skips a beat into silence).
Shot 5: Close-up, basketball violently stuffs through the net, hoop shakes intensely, camera slowly pushes in, <loud clang of rim>, (drum beat explodes and concludes).
Constraints: Person and street court must follow Image 1;黄昏 warm orange hard light backlight throughout; hang time and net shake must follow realistic sports physics.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statues.

No. 4: Running Silhouette

• Category: Sports & Fitness
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the morning runner and coastal road from Image 1 as the main subjects (the character silhouette and environment should match Image 1), landscape 16:9, inspirational sports brand film style, sunrise backlight golden-orange tone, generate a 30-second morning running perseverance film.

Prompt

Using the morning runner and coastal road from Image 1 as the main subjects (the character silhouette and environment should match Image 1), landscape 16:9, inspirational sports brand film style, sunrise backlight golden-orange tone, generate a 30-second morning running perseverance film.
Shot 1: Extreme close-up, running shoe steps onto wet asphalt splashing tiny water droplets, fixed slightly overhead camera angle, <sound of shoe sole hitting the ground>, (motivational strings music starts softly).
Shot 2: Medium shot, runner's backlit silhouette strides steadily with sweat dripping along the jawline, camera follows, <steady and powerful breathing rhythm>.
Shot 3: Full shot, coastline extends as the sun leaps from the sea dyeing the sky red, camera slowly lifts and descends, (strings music adds drumbeat progression).
Shot 4: Close-up, swinging arm, watch numbers jump as heart rate climbs, camera slowly pans, <watch ticking prompt sound>.
Shot 5: Long shot, runner's silhouette charges up the hilltop, arms spread open embracing the rising sun, camera slowly pulls back, (strings and drums climax and conclude).
Constraints: Character silhouette and coastal road must match Image 1; sunrise backlight golden-orange tone throughout; running posture and stride frequency must be uniform and连贯 without jerks.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural slight movement, not statues.

Music, Dance & Music Videos (4)

No. 1: Dance Follow Shot

• Category: Music, Dance & Music Videos
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the modern dancer and industrial-style space from Image 1 as the main subjects (the character and scene should match Image 1), portrait 9:16, urban MV follow-shot style, cool blue neon light and shadow tone, generate a 30-second rhythmic dance film.

Prompt

Using the modern dancer and industrial-style space from Image 1 as the main subjects (the character and scene should match Image 1), portrait 9:16, urban MV follow-shot style, cool blue neon light and shadow tone, generate a 30-second rhythmic dance film.
Shot 1: Extreme close-up, dancer's fingertips snap open sharply with the first beat, fixed camera angle, <crisp finger snap>, (rhythmic electronic beat starts).
Shot 2: Full shot, body sways widely, dance steps unfold and swing with the beat, camera follows, <sound of fabric cutting through air>.
Shot 3: Medium shot, spin and jump, skirt draws an arc with neon trailing shadows, camera slowly orbits, (beat intensifies, bass layers in).
Shot 4: Close-up, toes tap the ground rapidly, reflections on the floor shimmer, camera slowly pans, <continuous sound of heels tapping>.
Shot 5: Full shot, final pose, neon lights strobe illuminating the full body轮廓, camera slowly pulls back, (beat concludes on a downbeat).
Constraints: Character and industrial-style space must match Image 1; cool blue neon light and shadow tone throughout; camera movement rhythm must strictly synchronize with the music's downbeats.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural slight movement, not statues.

No. 2: Piano Solo

• Category: Music, Dance & Music Videos
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the pianist and old theater stage from Image 1 as the main subjects (the character and piano should match Image 1), landscape 16:9, classical concert film style, warm golden spotlight dark stage tone, generate a 30-second深情 solo performance film.

Prompt

Using the pianist and old theater stage from Image 1 as the main subjects (the character and piano should match Image 1), landscape 16:9, classical concert film style, warm golden spotlight dark stage tone, generate a 30-second深情 solo performance film.
Shot 1: Extreme close-up, fingertips hover above the keys then gently descend to press the first note, fixed camera angle, (clear, bright single piano note sounds).
Shot 2: Close-up, hands flow across the black and white keys, hammers rise and fall, camera slowly pans, <crisp sound of keys striking strings>.
Shot 3: Medium shot, pianist closes eyes, immersed, body sways slightly with the melody, camera slowly pushes in, (melody gradually builds to高潮).
Shot 4: Full shot, piano isolated under a spotlight on the空旷 stage, dust motes floating in the light, camera slowly lifts and descends, (chords layer and build).
Shot 5: Extreme close-up, final key pressed, finger rests,余音 vibrates, camera slowly pulls back, <sound of string余音 fading>, (melody quietly concludes).
Constraints: Character and piano must match Image 1; warm golden spotlight dark stage tone throughout; hand key-pressing actions must strictly correspond to note starts and stops.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural slight movement, not statues.

No. 3: Street Dance Battle

• Category: Music, Dance & Music Videos
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the two street dancers and underground venue from Image 1 as the main subjects (the characters and location should match Image 1), portrait 9:16, underground street dance documentary style, high-contrast warm-cold mixed lighting tone, generate a 30-second对决 battle film.

Prompt

Using the two street dancers and underground venue from Image 1 as the main subjects (the characters and location should match Image 1), portrait 9:16, underground street dance documentary style, high-contrast warm-cold mixed lighting tone, generate a 30-second对决 battle film.
Shot 1: Extreme close-up, one dancer lowers his cap brim, looks up挑衅, staring directly at the camera, fixed camera angle, <crowd骚动起哄声>, (hip-hop drumbeat drops to start).
Shot 2: Full shot, first dancer rushes into the center,爆发 floor moves,围观 circle parts, camera follows, <solid sound of palms slapping the ground>.
Shot 3: Medium shot, Thomas flare/windmill move, legs划圈, camera slowly orbits, (crowd cheers layer into the beat).
Shot 4: Close-up, opponent接力, hip thrust freeze pose, sweat甩 from cap brim, camera slowly pushes in, <rapid breathing and stomping sounds>.
Shot 5: Full shot, both dancers freeze simultaneously in对峙,围观者 erupt in unison, camera slowly pulls back, {(onlookers) "Oh——!"}, (drumbeat downbeat concludes).
Constraints: Both dancers and underground venue must match Image 1; warm-cold mixed high-contrast lighting throughout; floor moves and spins must follow real physics,连贯 without卡顿.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural slight movement, not statues.

No. 4: Concert Atmosphere

• Category: Music, Dance & Music Videos
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the lead singer and stadium stage from Image 1 as the main subjects (the character and stage should match Image 1), landscape 16:9, large-scale concert live recording style, colored追光 and fluorescent sea tone, generate a 30-second万人合唱 high-energy film.

Prompt

Using the lead singer and stadium stage from Image 1 as the main subjects (the character and stage should match Image 1), landscape 16:9, large-scale concert live recording style, colored追光 and fluorescent sea tone, generate a 30-second万人合唱 high-energy film.
Shot 1: Extreme close-up, lead singer's lips close to the microphone, opens eyes and sings the first line, fixed camera angle, {(lead singer) "This night belongs to you!"}, (rock intro轰鸣 starts).
Shot 2: Full shot,追光 sweeps across the stage, lead singer spreads arms igniting the crowd, camera slowly lifts and descends, <audience's山呼海啸欢呼>.
Shot 3: Long shot, stands, glow sticks connect into an起伏 sea of light swaying to the beat, camera slowly横移, (chorus鼓点齐奏).
Shot 4: Medium shot, lead singer walks to the front of the stage reaching out, audience stretches arms to meet, camera follows, <万人齐声合唱>.
Shot 5: Full shot, fireworks and lasers erupt simultaneously, lead singer raises microphone silhouette, camera slowly pulls back, 【full venue大合唱】, (chorus高潮轰然 concludes).
Constraints: Character and stadium stage must match Image 1; colored追光 and fluorescent sea tone throughout; light strobes and fireworks must synchronize with drum downbeats.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural slight movement, not statues.

Festivals & Solar Terms (5)

No. 1: Spring Festival Reunion

• Category: Festivals & Solar Terms
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the family members from Image 1, Image 2, and Image 3 as the main subjects (each according to their corresponding image), landscape 16:9, festive heartwarming realistic style, warm red lantern tone, generate a 30-second Spring Festival short film.

Prompt

Using the family members from Image 1, Image 2, and Image 3 as the main subjects (each according to their corresponding image), landscape 16:9, festive heartwarming realistic style, warm red lantern tone, generate a 30-second Spring Festival short film.
Shot 1: Slow push in, fireworks绽放 outside the window illuminate the window frame贴 with福字, warm red lanterns sway indoors, (distant Chinese bell sounds and festive music gradually start).
Shot 2: Orbit, family sits around the New Year's Eve dinner table raising glasses, steaming heat and warm light, <light clinking of bowls and chopsticks>.
Shot 3: Fixed camera angle, elderly person @Image 1夹菜 for grandchild with慈爱 smile, close-up of table delicacies with background out of focus.
Shot 4: Smooth follow shot, child @Image 3 holds up red envelope蹦跳 in the courtyard, strings of red lanterns铺展 along the way, <clear, joyful laughter>.
Shot 5: Low angle shot, whole family @Image 2 looks up at漫天 fireworks惊叹, light and shadow洒满 smiling faces.
Shot 6: Slow pull back, whole family raises glasses定格 under big red lanterns at the door, subtitle appears 【Happy New Year Family Reunion】, (festive music concludes).
Constraints: Each character must match their corresponding image;禁止外形一致的分身双胞胎, one person per frame in group shots; red lantern warm tone贯穿全片.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters must have natural slight movement, not statues.

No. 2: Valentine's Day Romance

• Category: Festivals & Solar Terms
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the woman from Image 1 and the man from Image 2 as the main subjects (each according to their respective images), vertical 9:16, French film warm-toned romantic realism, generate a 30-second Valentine's Day short film.

Prompt

Using the woman from Image 1 and the man from Image 2 as the main subjects (each according to their respective images), vertical 9:16, French film warm-toned romantic realism, generate a 30-second Valentine's Day short film.
Shot 1: Slow push-in, at a dusk street corner, woman @Image 1 holding roses looks back with a gentle smile, warm golden backlight outlines her hair, (soft piano single note begins).
Shot 2: Follow shot, man @Image 2 walks quickly through the crowd approaching, neon light spots flow behind him, <heartbeat sound gradually intensifies>.
Shot 3: Orbiting shot, the two embrace and spin in a square scattered with petals, warm light spins into halos, (strings layer and build up).
Shot 4: Fixed camera, close-up of interlocked fingers putting rings on each other, a flash of light reflects off the ring surfaces.
Shot 5: Crane up, camera rises from the two of them, sweeping past tree branches hung with string lights, starry night sky, (music reaches climax).
Shot 6: Slow pull-out, silhouette of the two snuggling on a bench, subtitle appears 【Every Day Loving You】, (piano resonance concludes).
Constraints: The woman must match Image 1, the man must match Image 2; their appearances must be clearly distinct, no twin-like resemblance; warm golden film tone throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statue-like.

No. 3: Mid-Autumn Moon Viewing

• Category: Festivals & Solar Terms
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the person from Image 1 as the main subject (according to Image 1), horizontal 16:9, serene Eastern ink wash impressionism blended with realism, blue-green moonlight tone, generate a 30-second Mid-Autumn Festival short film.

Prompt

Using the person from Image 1 as the main subject (according to Image 1), horizontal 16:9, serene Eastern ink wash impressionism blended with realism, blue-green moonlight tone, generate a 30-second Mid-Autumn Festival short film.
Shot 1: Low-angle shot, a full moon slowly emerges from a sea of clouds, clear moonlight pours down, (ancient zither harmonic sound starts leisurely).
Shot 2: Slow push-in, person @Image 1 stands alone at a stone table in the courtyard looking up at the moon, osmanthus tree shadows sway, <sound of night breeze rustling leaves>.
Shot 3: Fixed camera, close-up of a mooncake being broken open revealing golden flowing filling, tea steam rises gently.
Shot 4: Smooth pan, courtyard lanterns and moon shadows reflect on the rippling water of a pond, <sound of flowing water>.
Shot 5: Orbiting shot, person @Image 1 raises a cup to toast the moon, drinking, sleeves flutter lightly, moonlight flows.
Shot 6: Slow pull-out, silhouette of the person framed with the huge full moon, subtitle appears 【May we all be blessed with longevity】, (ancient zither concludes).
Constraints: The person must match Image 1; unified blue-green moonlight cool tone, avoid warm colors interfering with the moonlit atmosphere.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statue-like.

No. 4: Christmas Atmosphere

• Category: Festivals & Solar Terms
• Source: community
• Author: Atlas Cloud
• Language: en

Description

Using the two family members from Image 1 and Image 2 as the main subjects (each according to their respective images), vertical 9:16, Nordic warm-toned fairy tale realism, fireplace orange light tone, generate a 30-second Christmas short film.

Prompt

Using the two family members from Image 1 and Image 2 as the main subjects (each according to their respective images), vertical 9:16, Nordic warm-toned fairy tale realism, fireplace orange light tone, generate a 30-second Christmas short film.
Shot 1: Slow push-in, snow falls outside the window onto a Christmas tree adorned with lights, fireplace flames flicker inside, (clear bell sounds and Christmas music begin).
Shot 2: Fixed camera, person @Image 1 hangs the last star ornament with a satisfied smile, colored lights reflect on their face.
Shot 3: Follow shot, person @Image 2 runs towards the tree holding a gift box, looking around in surprise, warm orange halos flow, <sound of unwrapping gift paper>.
Shot 4: Overhead shot, gingerbread cookies, hot cocoa, and candles arranged on the table, steam and icing shimmer.
Shot 5: Orbiting shot, the two @Image1 @Image2 snuggle by the fireplace clinking glasses, snowflakes fall outside the window.
Shot 6: Slow pull-out, warm light from inside shines through the window frame on a snowy night, subtitle appears 【Merry Christmas】, (Christmas music concludes).
Constraints: Each person must match their respective image, appearances must be distinct, no twin-like resemblance, one person each in shared frames; fireplace warm orange tone throughout.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statue-like.

No. 5: Start of Spring Solar Term

• Category: Festivals & Solar Terms
• Source: community
• Author: Atlas Cloud
• Language: en

Description

No reference person, horizontal 16:9, Twenty-Four Solar Terms Eastern aesthetics, fresh watercolor impressionism blended with realism, tender green sprout tone, generate a 30-second Start of Spring short film.

Prompt

No reference person, horizontal 16:9, Twenty-Four Solar Terms Eastern aesthetics, fresh watercolor impressionism blended with realism, tender green sprout tone, generate a 30-second Start of Spring short film.
Shot 1: Slow push-in, a tender bud quietly pushes through ice crystals at the tip of a withered branch covered with residual snow, morning light penetrates, (clear and bright bamboo flute single note begins).
Shot 2: Macro fixed camera, an icicle melts and a drop falls onto moist soil, <clear sound of water droplet>.
Shot 3: Smooth pan, residual snow recedes in the field, tender green spreads, the first wildflower peeks out, <sound of spring breeze gently brushing>.
Shot 4: Low-angle shot, swallows skim across the azure sky circling, willow branches sprout new green swaying in the wind, (flute sound gradually rises).
Shot 5: Crane up, camera rises from the tender bud overlooking the awakening earth, streams thaw and rush, (traditional string and wind instruments layer and build up).
Shot 6: Slow pull-out, a tree of new green stands in the field, subtitle appears 【Start of Spring, All Things Begin to Grow】, (traditional instruments conclude).
Constraints: Color transitions from cool gray residual snow to warm tender green, reflecting the seasonal change from winter to spring; no characters appear on screen.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statue-like.

Nature, Astronomy & Documentaries (4)

No. 1: Star Trails Time-Lapse

• Category: Nature, Astronomy & Documentaries
• Source: community
• Author: Atlas Cloud
• Language: en

Description

No reference person, horizontal 16:9, BBC documentary-level starry sky time-lapse photography, deep space dark blue tone, generate a 30-second starry sky time-lapse short film.

Prompt

No reference person, horizontal 16:9, BBC documentary-level starry sky time-lapse photography, deep space dark blue tone, generate a 30-second starry sky time-lapse short film.
Shot 1: Low-angle shot, the Milky Way arch spans the zenith, stars rotate and flow, foreground silhouette of a solitary peak, (low-pitched cosmic ambient electronic music begins).
Shot 2: Fixed camera time-lapse, star trails draw concentric arcs centered on Polaris, <sound of night insects humming>.
Shot 3: Slow pan, the Milky Way slowly sinks behind distant mountains, a meteor streaks across the night sky leaving a long tail.
Shot 4: Crane up, camera rises from the grassland ground, the Milky Way unfolds together with the horizon, (strings lay foundation and gradually enter).
Shot 5: Slow push-in, deep space nebula's purple-red gas clouds churn within the starry sea, stars twinkle.
Shot 6: Slow pull-out, the starry sky recedes to a single tent's faint light, subtitle appears 【The Universe · Eternal As Ever】, (ambient music concludes).
Constraints: Time-lapse texture throughout, celestial motion smooth and continuous; unified deep blue and dark purple cool tones, no character close-ups.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statue-like.

No. 2: Aurora Flow

• Category: Nature, Astronomy & Documentaries
• Source: community
• Author: Atlas Cloud
• Language: en

Description

No reference person, horizontal 16:9, Arctic documentary realism, ice-snow polar night and emerald green aurora tone, generate a 30-second aurora short film.

Prompt

No reference person, horizontal 16:9, Arctic documentary realism, ice-snow polar night and emerald green aurora tone, generate a 30-second aurora short film.
Shot 1: Low-angle shot, emerald green aurora curtains suddenly light up the horizon, rolling like waves, (ethereal synthesizer wall of sound suddenly rises).
Shot 2: Slow pan, aurora reflects on a frozen lake surface, snowfield a silvery white, <howling sound of polar wind>.
Shot 3: Fixed camera time-lapse, aurora transitions from green to purple, dancing and changing rapidly, stars faintly visible within.
Shot 4: Slow push-in, details of the aurora curtains flow down like silk, <low rumbling sound of ice cracking>.
Shot 5: Crane up, camera sweeps past snow-covered pine forest rising towards the sky full of aurora, cold and transparent.
Shot 6: Slow pull-out, aurora envelops the entire ice field, a solitary tree stands, subtitle appears 【Polar Lights】, (wall of sound gradually fades and concludes).
Constraints: Aurora color transitions natural and smooth, avoid harsh flickering; cool tones dominant, no characters appear on screen.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; use only one camera movement per shot; characters need natural subtle movement, not statue-like.

No. 3: Volcanic Lava

• Category: Nature, Astronomy & Documentaries
• Source: community
• Author: Atlas Cloud
• Language: en

Description

No reference characters, landscape 16:9, geological documentary stunning realism, contrasting tones of fiery red lava and black rock with cold smoke, generate a 30-second volcano short film.

Prompt

No reference characters, landscape 16:9, geological documentary stunning realism, contrasting tones of fiery red lava and black rock with cold smoke, generate a 30-second volcano short film.
Shot 1: Slow push-in, fiery red lava boils and splatters sparks inside the volcanic crater, thick smoke billows, (low-frequency rumbling drums start).
Shot 2: Fixed camera position, lava flow slowly spreads over black rock surface, forming golden-red cracks, <gurgling, burning sound of magma>.
Shot 3: Overhead shot, lava river winds like a golden vein cutting through the charred hillside.
Shot 4: Slow pan, lava falls into the sea surface, causing white steam explosions, <sound of water and fire violently interacting>.
Shot 5: Low-angle shot, under the night sky, volcanic eruption launches lava bombs drawing orange-red arcs, smoke column rises to the sky, (drums reach climax).
Shot 6: Slow pull-out, embers flicker like stars on the cooled lava field, subtitle appears 【Earth · Fiery Heart】, (rumbling gradually fades and concludes).
Constraints: Strong contrast between fiery red warm light and black rock cool tones; lava flow texture realistic and viscous, no characters appear.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; each shot uses only one camera movement; characters need natural slight movement, not statues.

No. 4: Forest Morning Mist

• Category: Nature, Astronomy & Documentaries
• Source: community
• Author: Atlas Cloud
• Language: en

Description

No reference characters, landscape 16:9, nature documentary healing realism, morning light Tyndall effect and verdant misty forest tones, generate a 30-second forest morning mist short film.

Prompt

No reference characters, landscape 16:9, nature documentary healing realism, morning light Tyndall effect and verdant misty forest tones, generate a 30-second forest morning mist short film.
Shot 1: Slow push-in, morning light penetrates tall fir forest forming distinct Tyndall beams, thin mist flows, (ethereal flute and bird songs start).
Shot 2: Fixed camera position, dewdrop hangs from the tip of a fern leaf refracting morning light before falling, <crisp bird calls here and there>.
Shot 3: Smooth pan, mist drifts slowly over mossy stones and stream in the forest, <babbling stream>.
Shot 4: Low-angle shot, camera tilts up along the tree trunk to the forest canopy where sunlight pours down, light spots dance.
Shot 5: Follow shot, a deer quietly walks through the misty forest with light steps, glances back, <rustle of fallen leaves>.
Shot 6: Slow pull-out, panoramic view of the forest in morning mist gradually brightens, subtitle appears 【Morning Forest · All Sounds Awaken】, (flute melody fades and concludes).
Constraints: Beams and mist layers are transparent and natural; verdant soft warm tones, animal movements realistic and not stiff, no characters appear.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; each shot uses only one camera movement; characters need natural slight movement, not statues.

Anthropomorphic & Creative Memes (2)

No. 1: AI Model Personified Fighting

• Category: Anthropomorphic & Creative Memes
• Source: community
• Author: Atlas Cloud
• Language: en

Description

No reference characters, using original personified fighting contestants (not alluding to any real company or brand trademarks), vertical 9:16, cyber arena热血 anime style, neon holographic tones, generate a 30-second personified fighting short film.

Prompt

No reference characters, using original personified fighting contestants (not alluding to any real company or brand trademarks), vertical 9:16, cyber arena热血 anime style, neon holographic tones, generate a 30-second personified fighting short film.
Shot 1: Slow push-in, two original mecha personified contestants confront each other, charging up in the center of the holographic arena, their chest energy cores light up, (energetic electronic drumbeat explodes and starts).
Shot 2: Follow shot, the blue data-stream contestant throws a light punch with trailing afterimages, <high-frequency energy hum>.
Shot 3: Orbiting shot, the orange computing-power contestant dodges sideways and blocks with a backhand, sparks fly, neon light trails surround.
Shot 4: Low-angle shot, two fists collide, releasing a shockwave that flips holographic spectator stands particles, subtitle pops up 【Reasoning Speed Duel】.
Shot 5: Fixed camera position slow motion, the blue contestant's core overloads and cracks as they are knocked back, code fragments scatter, <electric current crackling sound>.
Shot 6: Slow pull-out, the orange contestant stands on the ring raising a fist, holographic leaderboard lights up, subtitle appears 【This Round Winner】, (drumbeat concludes).
Constraints: The two contestants' color schemes and designs must be clearly distinct (blue vs orange), no twin-like appearance, one of each in frame; purely original personifications, no real brand logos or names appear.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; each shot uses only one camera movement; characters need natural slight movement, not statues.

No. 2: Programming Languages Personified Bickering

• Category: Anthropomorphic & Creative Memes
• Source: community
• Author: Atlas Cloud
• Language: en

Description

No reference characters, using original personified characters (not alluding to any real company or brand trademarks), landscape 16:9, office sitcom humorous style, bright warm tones, generate a 30-second personified bickering short film.

Prompt

No reference characters, using original personified characters (not alluding to any real company or brand trademarks), landscape 16:9, office sitcom humorous style, bright warm tones, generate a 30-second personified bickering short film.
Shot 1: Slow push-in, two original programmer personified characters look at each other across workstations raising eyebrows, desktop code holographic screens flicker, (playful jazz tune starts).
Shot 2: Fixed camera position, the snake mascot character lazily spreads hands and吐槽台词 {I do it in one line, you write twenty}, <keyboard typing sounds>.
Shot 3: Follow shot, the gear armor character不服 gets up slamming the table retorting {But I run ten times faster than you}, holographic screen pops up a progress bar.
Shot 4: Orbiting shot, the two characters stand back-to-back refusing to yield, code symbols collide above their heads bursting sparks, <clinking collision sound effects>.
Shot 5: Overhead shot, a third coffee cup cute pet character brings two cups of coffee to mediate, the two look at each other awkwardly.
Shot 6: Slow pull-out, the three characters put arms around shoulders clinking cups reconciling and laughing, subtitle appears 【Different Strengths Make the Strongest Stack】, (jazz tune concludes).
Constraints: The three characters' designs and color schemes must be clearly distinct (snake/gear/coffee cup), no twin-like appearance, one of each in frame; purely original personifications, no real programming language trademarks, logos, or registered names appear.
General constraints: Keep no subtitles; do not generate Logo; do not generate watermarks; each shot uses only one camera movement; characters need natural slight movement, not statues.

Film & Storytelling (11)

No. 1: Wordless Narrative

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

From writing a letter indoors to posting it, the shots transition from shallow depth-of-field to a golden valley panorama, maintaining a consistent mood.

Prompt

A 30-second wordless visual story, imbued with the quiet elegance of the French countryside, set on a summer afternoon in Provence. A young woman in a beige linen dress finishes writing a letter by hand at an old wooden table in a stone cottage, then steps outside, walks along a gravel path through a sunflower field, and gently slips the letter into a vintage yellow mailbox at the village edge. The shot begins with a shallow depth-of-field close-up on the indoor table, passes through the doorway—where light gradually gives way to shadow—and finally pulls up and out to reveal a wide panoramic view of the golden valley. Only ambient sounds throughout—cicadas, wind, the rustle of pen on paper, and the soft click of the mailbox closing—like the lingering silence after sending a letter to a distant place.

No. 2: Concept Short Film

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Multiple dreamlike scenes flow seamlessly within a single 30s shot, unified in atmosphere, lighting, and narrative tone.

Prompt

Cinematic brand concept short film. @Image 1 as the first frame, the image slightly shaky, the lens gradually pushes in, arriving at the rapidly receding tree shadows outside the window, the speed of the shadows receding faster and faster, suddenly cuts to @Image 2, the speed suddenly slows, the lens follows the stream slowly forward, birdsong and floral fragrance.
The lens moves down, underwater, sound effects include the sound of bubbles in water, a group of orange jellyfish swim gracefully past the lens @Image 3, the lens slowly pulls back, a school of small fish flashes past the lens and then swims from the water into the room through the window @Image 4, a girl looks left and right, admiring the small fish.
The lens slowly pulls back, the image goes out of focus, then refocuses and becomes clear again, switching with the music rhythm: Chinese garden lattice window @Image 5 light circles, church stained glass window, airplane porthole, dome skylight, bay window, Venetian blinds, European dormer window, door peephole, camera viewfinder, bird's eye, human eye close-up.
The image stays on the human eye close-up, then the eye closes, the screen goes black, then suddenly opens, the word "seedance" with a heavy accent appears in the center of the eye.

No. 3: Multi-Character Ensemble Scene

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Multiple actors and environmental settings are maintained stably throughout the shot.

Prompt

30 seconds, 16:9, one-shot, realistic cinematic texture, European palace ballroom party ensemble shot. Scene references @Image 8, @Image 13, @Image 17, main chandelier details reference @Image 15, champagne glass references @Image 1 and @Image 10, champagne tower references @Image 3 and @Image 6, confetti streamers reference @Image 19. Characters are: Male 1 reference @Image 2, Male 2 reference @Image 11, Male 3 reference @Image 4, Male 4 reference @Image 7, Female 1 reference @Image 9, Female 2 reference @Image 5, Male 5 reference @Image 16, Female 3 reference @Image 18, Male 6 reference @Image 12, Female 4 reference @Image 14, Male 7 reference @Image 20, other background guests maintain the same banquet style to complete the ensemble.

The shot starts with Male 2 holding a tray. Male 2 holds a tray with both hands at chest level, with several champagne glasses on the tray. Male 1 extends his right hand from the left front of the frame, picks up a champagne glass with his right hand, raises it to the front of his right shoulder, and says loudly to the guests ahead: "Everyone, enjoy this party!" (Voice reference @Audio 1) While speaking, he raises the glass with his right hand, opens his left hand, and slightly lifts his head. Immediately after speaking, he opens his mouth and laughs heartily, looking left first, then right. The lens simultaneously pulls back to form a five-person ensemble. Male 1 stands in the center, right hand holding the glass aloft, left hand open. Male 3 stands behind and to the left of Male 1, right hand raising a glass to shoulder height, looking at Male 1. Male 4 stands behind and to the right of Male 1, left hand holding a glass at chest level, right hand punches upward once, looking at Male 1. Female 1 stands to the left of Male 1, clapping twice with hands at chest level. Female 2 stands to the right of Male 1, right hand raising a glass, left hand raised in cheer. Background guests also raise glasses, applaud, and turn to look at Male 1.

After Male 2 finishes serving the drink, he continues holding the tray with both hands, walking from in front of the opening quintet towards the right side of the frame, the tray always kept level. The camera follows Male 2 moving right, foreground passing by gown hems, hands holding glasses, shoulders and profiles of people, background continuously showing the chandelier, curtains, pillars, dance floor, and champagne tower. Male 2 stops in front of the second ensemble group, standing in mid-foreground, holding the tray with both hands.

The second ensemble group remains in the same frame and space. On the left side of the frame is the toasting group. Male 5 stands opposite Female 3, picks up a champagne glass from Male 2's tray with his right hand, raises it to his chest, looks at Female 3 and says: "Cheers to tonight." (Voice reference @Audio 2) Female 3 holds her own champagne glass in her right hand, raises her right hand to lightly clink with Male 5 once, then brings the glass back to her chest. On the right side of the frame is the dance invitation group. Male 6 and Female 4 stand facing each other, both empty-handed, not holding champagne glasses. Male 6 looks at Female 4, extends his right hand forward, palm up, and says: "May I have this dance?" (Voice reference @Audio 3) Female 4 pauses for a moment, then looks up at Male 6, smiles, and places her left hand on Male 6's right hand. This frame simultaneously contains the left-side toasting, right-side dance invitation, waiter holding the tray, and background guest activities.

After Female 4 accepts the invitation, Male 6, holding Female 4's left hand with his right hand, leads her towards the center of the dance floor, both empty-handed throughout. Female 4 lifts her skirt hem with her right hand for easier movement. The camera follows them onto the dance floor. The crowd at the edge of the dance floor begins to respond: some applaud, some raise glasses, some sway gently. After Male 6 reaches the center of the dance floor, he takes Female 4's right hand with his left, places his right hand on Female 4's back, Female 4 places her left hand near Male 6's shoulder, entering a dance posture. Male 7 stands at the edge of the dance floor applauding, other background guests along the outer circle of the dance floor perform applauding, raising glasses, gentle swaying actions.

The camera then orbits Male 6 and Female 4 clockwise. Male 6 leads Female 4 through two dance moves: first, Male 6 leads Female 4 in a half-turn; second, Male 6 raises his hand high, allowing Female 4 to spin a full circle in place, Female 4's red skirt flaring out. The crowd in the background continues to applaud, raise glasses, and sway along the outer circle of the dance floor, Male 1 and the opening quintet are also in the background continuing to raise glasses and cheer. Confetti streamers fall from directly above the dance floor during this segment, concentrated over the center of the dance floor and above the heads of the main couple, few in number, only a small amount of long, thin streamers, falling vertically, not covering the entire hall. The lens finally continues to orbit the two dancers, keeping them centered in the frame, background is the dance floor, crowd, chandelier, curtains, and a small amount of falling confetti, forming the closing shot.
[0-3s] Close-up shot, lens focused on the hand of @Image 1 plucking the strings of the @Image 2 guqin. On the left, a bronze incense burner @Image 3 emits a wisp of smoke. In the background, the blurred figure of a man in white @Image 4 is playing the @Image 5. Sound effect reference @Audio 1, scene set on a small boat @Image 7 on water @Image 6, distant mountains reference @Image 8.
[3-5s] The man in white @Image 4 stands 【on the bow of the boat/rises】... a circular anomaly, the woman from @Image 9 holding @Image 10 attacks, sound effect reference @Audio 2.
[5-10s] The man in white and the woman in red engage in intense aerial combat over the lake, sound effect reference @Audio 3. The woman in red holds a red umbrella, the man holds a fan @Image 11. The water surface below is stirred by powerful qi into huge ring-shaped waves, sound effect reference @Audio 4, like a water storm, special effects reference @Video 1.
[10-20s] The man in white chases the woman in red into a bamboo forest @Image 12, performing qinggong on the water surface …… (Subsequent paragraphs obscured by video cover, not fully visible)

No. 4: 3D White Model Storyboard Preview

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Professional 3D assets and material reference input, faithfully inheriting structure and camera choreography.

Prompt

Maintain the camera movement, duration, composition, shot scale, spatial relationships, object positions, model structure, and motion trajectory from @Video 1 unchanged. Using @Image 1 as a reference for material, lighting, color, and overall atmosphere, replace the white model material in @Video 1 with realistic materials close to @Image 1. Add natural light and shadow, contact shadows, ambient light, reflections, highlights, and spatial depth, presenting an overall realistic, cinematic-grade rendering quality.

No. 5: Gorilla Rock Climbing Motion Transfer

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Using real human climbing video as reference, precisely transferring the same set of climbing motions, force rhythm, and body structure onto a gorilla.

Prompt

Transfer the motion from @Video 1 onto a large gorilla climbing on a cliff, without changing the camera movement rhythm or the actions.

No. 6: Film Lighting Redistribution

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Rewriting the entire clip's lighting layout while preserving original composition, characters, and camera movement.

Prompt

Reference the light in @Video 1, changing it from harsh overhead noon light to side light at sunset.

No. 7: Replace Actor's Expression & Age

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Change only the actor's age and micro-expressions precisely, keeping the shot, framing, and rhythm intact in one continuous take.

Prompt

Retain the composition, camera position, lighting, and performance rhythm of @Video 1, only rewrite the appearance and expression of the female lead in the frame: let her age naturally from her twenties to her sixties, the hidden forbearance in her eyes slowly dissolves, tears slide past the corner of her eye, the corners of her mouth gradually lift, finally breaking into a smile through tears. The entire process is a single continuous shot, no jump cuts, no flickering, facial features gradually change with age without drifting.

No. 8: Adjust Film Style

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Change the overall visual style like live-action realism, illustration, or comics with one click, keeping composition and camera movement unchanged.

Prompt

Maintain the camera movement and rhythm of @Video 1, change the visual style sequentially to: black and white comic style, Japanese anime style, American hardcore style, ink wash animation style.

No. 9: Extend Short Footage Into Film

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

High-fidelity temporal extension naturally extends short clips into longer finished films.

Prompt

Based on @Video 1, extend the video by 5 seconds, telling the story of a bee flying over and landing on a painting, then a macro close-up shows golden pollen particles covering the bee's legs and abdomen, the bee flaps its wings and takes off, the camera follows it flying to another flower of the same species, in slow motion, pollen shakes off from the bee's fuzz, precisely falling into the pistil—the pollination moment is magnified.
Based on @Video 2, extend the video by 5 seconds, with time-lapse photography quality: the original yellow petals slowly wither, the pistil position begins to swell, growing from an unripe small fruit, changing color, becoming plump, eventually becoming a mature pod. The pod surface is covered with morning dew, shimmering with soft highlights in the sunlight.
Based on @Video 3, extend the video by 5 seconds with time-lapse photography, the background flashes through day and night, the mature fruit naturally splits open, a seed slides out and falls, the camera follows it through the air, falling into the moist soil in @Image 1.
Based on @Video 3, extend the video by 5 seconds with time-lapse photography, the background flashes through day and night, the mature fruit naturally splits open, a seed slides out and falls, the camera follows it through the air, falling into the moist soil in @Image 1.

No. 10: Multi-Scene Fast-Cut With Multiple People

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

A generated result featuring a flower passed across global scenes with people saying thanks in local languages.

Prompt

Live-action style, fast-paced editing, cinematic feel, 4K, 24fps, warm natural light, real human performance, natural lip-sync, no subtitles. Using the passing of a fresh flower as the core visual thread of the entire video, the flower quickly travels from one country to the next, connecting different regions and people across the globe. In each scene, a person receives the flower, shows a sincere smile, and says "Thank you" in the local language. The overall rhythm is light, fast, and smooth, with dynamic shots emphasizing authentic street/life atmosphere, warm cross-cultural connections, and the transmission of goodwill between people.
Transition method: The previous person hands the flower out of frame, the next shot shows another person catching the flower in a new scene
Or use quick whip pans, motion blur, foreground occlusion for seamless transitions
Maintain the visual continuity of the flower in the frame, creating a "one-shot global pass" feeling
Shot style: Handheld follow shots, slight camera shake, quick push/pull, combination of close-ups and medium shots, authentic ambient sound atmosphere, cinematic street photography quality. Background music is warm, light, with a sense of world travel, ending with a gentle fade-out.
Scene 1 【@Image 1】 Inside a Chinese flower shop, a real-life scene. A girl receives a rose, looks at the camera and smiles, saying naturally: "谢谢!" The shot follows the flower being handed in from the right side of the frame, the girl gently raises the bouquet after receiving it.
Scene 2【@Image 2】 An English street, slightly cool weather, natural street scene. A man receives a carnation, smiles and nods, saying: "Thank you!" Transition via whip pan, the flower is whipped into this scene from the previous one.
Scene 3 【@Image 3】 A Mexican market, rich in color, full of life. An auntie receives a bunch of marigolds, puts her hands together, and says warmly: "¡Gracias!" The camera quickly passes by stalls and crowds, freezing on the moment of receiving the flower.
Scene 4 【@Image 4】 An Indonesian village, natural sunlight. A child receives a frangipani flower, smiles happily, gives a slight bow, saying: "Terima kasih!" The shot has a slight sense of running, the atmosphere is innocent and natural.
Scene 5 【@Image 5】 A Thai street, lively market atmosphere. A vendor receives a string of jasmine garland, puts her hands together, and says kindly: "ขอบคุณค่ะ!" The camera pushes in lightly, the garland sways slightly in the sunlight.
Scene 6 【@Image 6】 An Arabian courtyard, soft light and shadow, elegant environment. A lady receives a desert rose, touches her chest and smiles, saying: "شكراً!" The frame is quiet and warm, the person's expression is sincere.
Scene 7 【@Image 7】 A Brazilian community, vibrant and lively atmosphere. A boy receives a gerbera daisy, very happy, saying: "Obrigado!" The shot is rhythmic, full of vitality.
Scene 8 【@Image 8】 A Japanese street, a salaryman receives a small flower on a bento box, bows politely, saying: "ありがとう！" The shot is short and crisp, retaining an urban sense of rhythm.
Scene 9 【@Image 9】 A Korean street, modern urban feel. A young woman receives an azalea flower, naturally puts her hands together, smiles and says: "감사합니다!" The camera lingers slightly on her smiling moment, then the image fades out softly.

No. 11: Multi-Language Version Simultaneous Release

• Category: Film & Storytelling
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Movie trailer promotion, creating multiple language voiceover versions from a single production.

Prompt

Change any English in the sound, dialogue, narration, and title subtitles to French/Japanese, keep everything else consistent.

Advertising & E-commerce (8)

No. 1: Live-Action TV Commercial

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

A single 30s vertical ad fully carrying brand narrative from product details to scene performance.

Prompt

Produce a 30-second vertical home furnishing advertisement. The main product is a light gray-green modular sectional sofa with rounded curved lines, low thick cushions, paired with a beige blanket and brown pillows.
The first 15 seconds are a pure white seamless studio product showcase: the sofa is displayed completely, the camera slowly pushes in close, pans horizontally, and moves laterally to show the outline and form, finally pulling back to a full shot and freeze. Lighting is even and soft, background is pure white and clean, no sweeping lights, no flash whites.
The last 15 seconds transition into a warm-lit living room at dusk: the hostess, wearing beige knit loungewear, sits on the sofa reading a book, legs on the beige blanket; she gently places a coffee cup, a cat jumps onto the sofa; a child runs in and leans on her shoulder, the hostess looks down and smiles; at night, a floor lamp lights up, the three quietly lean on the sofa, the camera slowly pulls back and freezes, leaving space for the brand logo. The overall style is restrained, gentle, clean, with authentic and natural visuals.

No. 2: 3D Animated Advertisement

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Generates a 3D animated ad with bright colors, refreshing fruit textures, and a humorous commercial style.

Prompt

3D animated advertisement style, bright and translucent colors, the fruit pulp and juice should have a strong sense of refreshment and impact. The overall vibe is like a high-quality commercial animated short film, with a touch of exaggerated humor. The desert horned lizard character is cute, agile, with rich expressions, reference 【Image 1】. The visual texture references the soft natural light, fine fur/skin texture, dreamy macro depth of field, realistic yet slightly whimsical feeling in the reference image.
0-3 seconds: The scene is a desert scorched by the blazing sun. The air is hot and distorted, the sand is burning, and the distance seems to be smoking. A desert horned lizard lies on the hot sand, tongue slightly out, eyes dazed, almost dried out by the sun. It takes a couple of steps and wobbles, the whole lizard looks like it's about to "evaporate".
Sound effect: whooshing heatwave sound, slight exaggerated cracking sound.
3-6 seconds: The desert horned lizard suddenly stops, its nose twitching. It looks down and sees a cool, plump grapefruit with water droplets buried in the sand. The grapefruit glistens brightly in the sunlight, its skin delicate, like a miracle suddenly appearing in the desert.
Performance: The lizard's eyes instantly widen, as if seeing a lifeline.
Sound effect: A "ding" discovery sound effect.
6-8 seconds: The desert horned lizard makes a flying pounce, grabs the grapefruit tightly with both hands, and presses its whole face against the peel. It shows a happy expression of "finally alive again". The frame freezes for 1 second, forming an exaggerated and funny advertising memory point.
Sound effect: A thud sound, then half a second of silence.
8-11 seconds: The desert horned lizard grabs the grapefruit. The grapefruit peel cracks open, revealing the plump, translucent and shiny pulp inside. The next moment, the juice doesn't just flow out, but gushes out like a tsunami.
Sound effect: A "crunch" biting sound, followed by an exaggerated juice explosion sound.
11-16 seconds: Orange-pink, clear and shiny grapefruit juice gushes out wildly, cascading down the sand dunes, quickly submerging the entire desert. The dry yellow sand instantly turns into a cool, sparkling, fruity-scented summer ocean. The desert's cacti, stones, and small sand dunes are swallowed by the juice wave, the scene exaggerated and dreamy.
Performance: The desert horned lizard is excited at first, but the next moment realizes something is wrong, its expression changes from delight to panic.
16-20 seconds: The desert horned lizard is almost submerged by the "grapefruit sea", frantically clinging to half a grapefruit, floating on the sea surface like holding a lifebuoy. It pokes its head out, wet and looking dazed. The sea surface sparkles, its color like juice illuminated by sunlight.
Sound effect: Exaggerated splashing sounds, wave sounds, with a touch of comedy.
20-23 seconds: Suddenly cut to a white screen. The brand name and slogan appear centered on the screen: "Seedance Grapefruit, what you bite into is the pulp, what gushes out is summer."
Voiceover reads the entire sentence: "Seedance Grapefruit, what you bite into is the pulp, what gushes out is summer."
Sound effect: Clean and refreshing brand chime sound.
23-29 seconds: The white screen cuts back. The desert horned lizard is now leisurely sitting on the floating grapefruit, wearing small sunglasses, holding a sippy cup, drifting slowly on the "juice sea" on vacation. Orange pulp, small ice cubes, and cool water droplets float around, the sky turns azure blue, the atmosphere shifts from "survival" to "vacation". Finally, the desert horned lizard leans contentedly against the grapefruit, the camera pulls back, freezing on a refreshing, bright, and fun summer scene.
Sound effect: Relaxing summer music, gentle lapping waves.
Subtitles can just keep the brand name, no need to add too much text.

No. 3: Fashion Brand Short Film

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Feeds multiple clothing, handbag, footwear items with model and scene references for free combination into multi-outfit, multi-scene fashion shots.

Prompt

Please generate a 30-second one-take video. Script: 6 models enter the frame one after another in a relay, the entire shot moves seamlessly through, with music beats switching outfits. @Image 1 wearing @Image 2 in the scene of @Image 3, sound effect reference @Audio 1. @Image 3 wearing @Image 4, wearing the hat from @Image 5, putting on @Image 6 sunglasses, walking out holding coffee, background is @Image 7 displaying @Image 8, sound effect reference @Audio 2. @Image 9 in the scene of @Image 10, wearing @Image 11 and @Image 12 striking a pose. @Image 13 carrying @Image 14, wearing @Image 15 walking in @Image 16, sound effect reference @Audio 3. @Image 17 wearing @Image 18 on head, carrying @Image 19, walking in @Image 20, sound effect reference @Audio 4. @Image 21 wearing @Image 22 walking the runway in @Image 23, sound effect reference @Audio 5.

No. 4: Product Usage Guide Video

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Creates a full-process video for the first-time use of a steam oven combo.

Prompt

The product is @Image 1, the installation and usage instructions are @Image 2. Create a video of the entire first-use process for a steam oven combo.

No. 5: Viral Video Reuse

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Generate an ad short for headphones using the camera work and editing rhythm of a reference video.

Prompt

Reference the camera movement style and editing rhythm of @Video 1 to generate an advertising short for headphones @Image. Adapt to a scene that fits the product's tone, emphasizing modernity, simplicity, and a tech feel. The switching points between product close-ups and scene panoramas should be consistent with the original video, maintaining the same motion speed and transition methods.

No. 6: E-Commerce SKU Batch Reuse

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Batch replace product styles/colors within the same shot, covering an entire SKU line with one shoot.

Prompt

The soda beverage image is @Image 1, and the scene image is @Image 2. Showcase the soda beverage through close-up, near, medium, and long shots, with smooth lens connections and consistent subject.

Replace the soda beverage bottle in @Video 1 with the pink beverage bottle from @Image 3.

Replace the soda beverage bottle in @Video 2 with the purple beverage bottle from @Image 4.

Replace the soda beverage bottle in @Video 3 with the green beverage bottle from @Image 5.

No. 7: Localization For Overseas Ads

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Quickly produce multi-region versions by changing ethnicity, product, or copy while keeping shots and rhythm.

Prompt

@Image 1 is the product image, @Image 2 is the host and scene image. The host waves their hands in sync with the lines while speaking. The expression is genuine and natural.
0-2 seconds: Fixed shot of @Image 2, the host speaks to the camera in Chinese, the line is "The first cup of coffee in the morning, can't wait.".
(2–5s) Press the switch, fixed shot, the line is "Press once, coffee in 3 seconds."
(5–9s) Continue looking at the camera and speaking, the line is "Office, business trips, late-night work—freshly ground coffee always with you."
(9–12s) Look at the camera and speak, the line is "The lifesaver for workers, limited-time price drop."
Replace the person in the video with an American female, and change the copy voiceover to English.
Replace the person in the video with a Spanish male, and change the copy voiceover to Spanish.
Replace the person in the video with an Indonesian female, and change the copy voiceover to Indonesian.
Replace the person in the video with a Malaysian male, and change the copy voiceover to Malaysian.

No. 8: Home Renovation Plan Demo

• Category: Advertising & E-commerce
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

With a simple prompt, the model reinterprets new decor styles on the same space, switching materials, furniture, colors, and lighting while keeping layout and camera work.

Prompt

Use the input video as the exact source and preserve the original camera movement, timing, composition, room layout, lighting, shadows, furniture positions, and all objects.
Only edit two materials in the living room:
1. Replace the light fabric sofa on the right side of the room with a rich brown leather sofa. Keep the exact same sofa shape, size, position, cushion layout, armrests, backrest, and perspective. The new sofa should look like realistic brown leather, with natural leather grain, subtle wrinkles, stitching, soft glossy highlights, and physically believable reflections from the window light.

2. Replace the visible warm wooden floor with polished white marble flooring. Keep the exact same floor plane, perspective, scale, and room geometry. The marble should be white to light gray with natural subtle veins, realistic seams, and controlled polished reflections. The marble reflections should respond to the window light, furniture legs, plants, sofa base, and room shadows.

Everything else must remain unchanged: the window, curtains, walls, wall art, TV, TV console, plants, rug, coffee table, books, radiator, shelves, doorframe, lighting, shadows, camera motion, and overall warm interior atmosphere. The rug and coffee table stay exactly where they are, on top of the new marble floor. The edit should look like a realistic interior renovation, not a new generated room.

Maintain temporal consistency across the full video. The sofa and floor materials must remain stable from frame to frame with no flickering, warping, melting, or object changes. Preserve the original video’s natural daylight, warm tone, soft shadows, lens behavior, and smooth camera movement.
Negative Prompt
Do not change the room layout. Do not move furniture. Do not add or remove objects. Do not change the rug, coffee table, TV, plants, curtains, window, wall art, shelves, radiator, or doorframe. Do not change the camera movement. Do not change the sofa shape or size. Do not make the leather look plastic. Do not make the marble overly reflective like a mirror. Do not create broken or chaotic marble veins. Do not replace the rug with marble. Do not alter the walls or ceiling. No people, no text, no logo, no UI, no selection mask, no fantasy effect, no melting transition, no flickering.

Knowledge & Explainer (6)

No. 1: Astronomy Knowledge Visualization

• Category: Knowledge & Explainer
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Transforming abstract principles into continuous visual videos.

Prompt

Generate a science popularization video explaining how the Moon was born. The visual quality should have a cinematic feel, with strong visual effects and visual tension during the explosion/convergence process. It must conform to facts and follow scientific basis.

0-2s: Distant space view, the Earth's arc and blue atmosphere at the bottom of the frame, a small dark red celestial body suspended in the black universe far above, the camera is mostly still, slowly showing the distance relationship between Earth and the body.
2-3s: Cut to a close-up, a huge celestial body covered with orange-red lava cracks approaches the edge of Earth, Earth's atmosphere forms a blue arc at the bottom right, the camera is still, the celestial body's sense of oppression increases.
Dialogue: 4.5 billion years ago, Earth was struck by a Mars-sized celestial body.
3-5s: The lava celestial body impacts the edge of Earth, intense white-orange burst of light erupts from the contact point, a large amount of hot debris and flames scatter outward along Earth's surface, the camera follows the explosion shockwave continuously pushing forward.
5-8s: The hot material after the impact converges into a glowing orange-red molten sphere in space, surrounded by swirling debris and dust, one side of Earth is visible in the background, the camera slowly pulls back from close to far.
8-10s: A glowing ring of molten material and debris belt appears next to Earth, orange-red material distributes around Earth's orbit, black space background, the camera maintains a distant observation view.
Dialogue: The impact partially melted both, and material was flung into Earth's orbit.
10-12s: Cut to a close-up of the lunar surface, gray cratered terrain covered with orange-red molten cracks, scattered rocks and dust, the scene gradually transitions from hot cracks to a cooled gray surface.
12-14s: The gray lunar surface continues to form, the cratered landscape becomes more stable, the edge and dark side of the Moon appear on the right side of the frame, the camera slowly pulls back, showing the Moon aggregating from the debris.
Dialogue: The debris aggregated into the Moon over tens of millions of years. The moon above your head is the product of this impact.
14-21s: Earth and the Moon are in the same frame, the camera pulls back, the Moon moves away from Earth. A ruler appears between Earth and the Moon, with numbers continuously growing on the ruler.
Dialogue: It is still moving away from Earth at a rate of 3.8 centimeters per year.

No. 2: Children's Science Animation

• Category: Knowledge & Explainer
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

A Chinese-style illustrated scroll unfolds with narration, the visuals continuously expanding with the story.

Prompt

Children's Silk Road culture science animation short, Dunhuang mural and Silk Road scroll style, mineral color flat animation, mineral pigment texture, ochre, silk white, azurite, malachite, dark blue, cinnabar, gold line accents, flat layering, scroll-style flowing composition, no real photography, no 3D realism, no childish cartoons. Focus on the origin and spread of pomegranates, do not emphasize modern consumption methods, keep the modern part under 7 seconds.
00:00-00:04, a Silk Road scroll slowly unfolds, a gently swaying pomegranate appears on a branch. Voiceover: "Did you know? The pomegranate we commonly see today actually came from a place far west of China long, long ago — the Western Regions."
00:04-00:08, a hand gently picks the pomegranate, holding it up, distant mountains, patterns, and roads unfold. Voiceover: "At first, it grew in sun-drenched lands. Later, people took it on journeys, preparing to go to even farther places."
00:08-00:15, a camel caravan carries the pomegranate through desert, oasis, and city gate. Voiceover: "The pomegranate followed the camel caravan slowly moving forward. Along the way, it had to cross deserts, pass through oases, and walk through tall city gates. This very long road is the famous ancient Silk Road."
00:15-00:20, the pomegranate enters more towns and life scenes with merchants and travelers. Voiceover: "What traveled the Silk Road wasn't just silk. Many distant fruits, spices, and seeds also came to new places along this road. This is how the pomegranate gradually became known to more people."
00:20-00:23, the pomegranate is cut open, revealing ruby-like seeds. Voiceover: "Later, people discovered that pomegranates are not only beautiful, but also hide many small seeds like rubies inside."
00:23-00:27, the ancient scenes in the scroll slowly transition to today, the pomegranate appears on a modern table, a group of children sit together eating pomegranates. Voiceover: "Thus, after a very long spread, the pomegranate set out from the Western Regions and finally entered life today."
00:27-00:30, the branch pomegranate, camel caravan, desert, oasis, city gate, and today's table pomegranate converge in the scroll. Voiceover: "So, a small pomegranate also holds a journey across lands and time."

No. 3: Live-Action Knowledge Explanation

• Category: Knowledge & Explainer
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

A real person narrates throughout, naturally demonstrating with physical props, with coherent lip-sync and rhythm.

Prompt

A 6-year-old girl with pigtails sits on a sofa, with small models of porcelain from various dynasties placed in front of her. She holds up the models one by one to introduce them: ① Holds a coarse pottery jar: 'The earliest porcelain evolved from pottery. Primitive porcelain existed as early as the Shang Dynasty.' Background fades in a scene of Shang Dynasty primitive porcelain artifacts. ② Holds a celadon-glazed small bowl: 'The celadon from the Yue Kiln and the white porcelain from the Xing Kiln were most famous in the Tang Dynasty, and there were also colorful Tang Sancai.' Background fades in a scene of Tang Sancai artifacts. ③ Holds a sky-blue small dish: 'Porcelain from the Song Dynasty is the most beautiful. The sky-blue color of Ru Kiln ware could only be fired after the rain cleared and the sky turned blue.' Background fades in a scene of Ru Kiln artifacts. ④ Holds a blue-and-white porcelain small vase: 'During the Ming and Qing dynasties, blue-and-white porcelain and enamel colors were all available, and they were sold all over the world.' Background fades in a scene of blue-and-white porcelain artifacts. Finally, the little girl holds up her own drawing of blue-and-white porcelain and smiles at the camera, accompanied by light and cheerful children's BGM.

No. 4: Structural Deconstruction And Principle Restoration

• Category: Knowledge & Explainer
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Restore the structure and logic behind the reference images by mimicking the camera movement and rhythm of the reference video.

Prompt

Generate a video based on the creativity of @Video 1. The requirement is to restore the entire assembly process of the house from @Image 1, @Image 2, @Image 3, and @Image 4.

No. 5: The Evolution Of Currency

• Category: Knowledge & Explainer
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Using a miniature world on a wooden desktop, narrate the five-thousand-year history of currency in a continuous shot, from barter to mobile payment.

Prompt

A 30-second stop-motion miniature video with English narration. On a warm wooden table, five miniature worlds are arranged from left to right—barter, shells and copper coins, Song Dynasty paper money, modern cash and bank cards, and today's mobile payment. The camera slowly pans horizontally, sweeping across this handcrafted timeline of currency. The scene features clay figurines and a tilt-shift lens effect, accompanied by calm English voiceover. The five-thousand-year history of currency is narrated in a continuous long shot—from the weight held in the palm to the lightness carried in the pocket.

No. 6: Maritime Museum Multilingual Narration

• Category: Knowledge & Explainer
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

One guide moves through different exhibits, naturally switching between English, Singapore-accented Mandarin, Malay, and Japanese.

Prompt

30s multilingual Southeast Asian heritage museum documentary. One guide leads through four connected galleries about trade, migration, craft, and Singapore's regional history. Warm, authentic museum realism, not tourism advertising.
0-7.5s Port Model Gallery, English.Singapore harbor and Malacca Strait model, moving ship lights, blue map wall. Guide: "Singapore has always been a meeting point, not just a destination."
7.5-15s Ceramics & Spice Room, Mandarin.Blue-white porcelain, spice jars, cinnamon, cloves, pepper, wooden crates, warm light. Guide: "These ceramics and spices record a way of life that grew from the sea."
15-22.5s Malacca Trade Gallery, Malay.Teak walls, ship model, batik, pewter, route maps, brass lanterns. Guide: "Di Selat Melaka, kapal, rempah dan bahasa bertemu. Perdagangan menghubungkan banyak budaya."
22.5-30s Travel Objects Gallery, Japanese.Suitcases, letters, textiles, family photos in glass cases, soft paper light. Guide: "旅の品物は、場所を移すたびに、新しい意味を持ちます。"
Camera: 16:9 warm documentary style, slow museum walkthrough, guide moments mixed with object close-ups.

Industrial & Manufacturing (4)

No. 1: First-Person Drone Flight

• Category: Industrial & Manufacturing
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

A first-person FPV drone racing perspective, cinematic single shot, flying through dynamic landscapes.

Prompt

Overall setting: First-person FPV racing drone perspective, cinematic live-action quality, single continuous shot without cuts, total duration 25 seconds. Sunny day, clear blue sky, realistic lighting and atmospheric perspective. The lens always faces the drone's forward direction, high speed with slight body tilt and inertial sway. Spatial relationships strictly follow the red line one-way progression: starting point (lower left hillside) → waterfall top ① → waterfall bottom → village ② → gap between two distant mountains ③ → distant valley vista, always forward, no turning back, no reverse flight, no returning to start.
Motion path (connected sequentially):
The drone starts low from a green hillside at the lower left of the canyon, accelerates climbing close to the slope, flying towards the large waterfall cascading down the left cliff wall; climbs up along the left cliff wall of the waterfall, circles to the top of the waterfall, overlooking the drop point and source stream from above (corresponding to marker ①).
After passing the waterfall top, the drone lowers its nose, dives down along the outer cliff wall of the waterfall, skimming the edge of the splashing water mist (not entering the water curtain), descending to just above the river surface at the waterfall base; then turns right, flying at high speed along the winding river in a smooth wave pattern, skimming over the roofs of a stone house village in the middle of the valley (corresponding to marker ②).
After passing through the village, continue deeper along the river valley to the right, charging at full speed towards the two highest mountains in the distance, passing precisely through the center of the V-shaped gap between the two peaks (corresponding to marker ③), exiting the frame into an open distant valley vista, ending steadily.
Negative constraints: No on-screen text / markers / red line / numbering; do not pass through the water curtain head-on, do not fly into the water mist; do not fly backwards, no unnecessary hovering or stalling; weather and lighting consistent throughout; total duration strictly 25 seconds, no black screens or accelerated jump cuts mid-way.
Generate a 15-second first-person FPV perspective ultra-high-speed drone穿梭 video, cinematic, single continuous shot. The shot starts from a low-altitude point near the Huangpu River surface / the base of the Oriental Pearl TV Tower, first rapidly ascends and smoothly circles around the tower body, lower sphere, upper sphere, and antenna spire of the Oriental Pearl, then according to the spatial relationship of the red line trajectory in the image,高速飞越 the Huangpu River, charges towards the Lujiazui financial district,穿梭 left and right,起伏 up and down between the Shanghai Tower, Shanghai World Financial Center (SWFC), and Jin Mao Tower trio, finally follows the direction of the arrow in the image, (but do not show the red line, it's only for guidance)冲刺 towards the right front of the Pudong skyline, ending in an open distant city vista.
Generate a 15-second first-person FPV perspective ultra-high-speed drone穿梭 video, cinematic, single continuous shot. The shot starts from a low-altitude point near the base of Tokyo Tower, first rapidly ascends and smoothly circles around the red-and-white tower body, main observatory, and spire of Tokyo Tower, then according to the spatial relationship of the red line trajectory in the image,高速掠过 the dense city rooftops of Minato and Shibuya wards, charges towards the Shinjuku skyscraper cluster,穿梭 left and right,起伏 up and down between the Metropolitan Government Building, Mode Gakuen Cocoon Tower, and glass-curtain-wall high-rises, finally follows the direction of the arrow in the image towards the right front of the Shinjuku skyline, ending in a distant Tokyo vista under golden黄昏余晖. (But do not show the red line, it's only for guidance)

No. 2: Robot Action Interaction

• Category: Industrial & Manufacturing
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

A humanoid robot performs the precise steps of cracking and frying an egg in a modern kitchen.

Prompt

On the stovetop from left to right are: a small white porcelain bowl containing one white egg, a gas stove, a white round porcelain plate. Behind the stovetop stand an open-mouthed stainless steel oil bottle (no cap), a wooden-handled spatula, a black non-stick frying pan. These objects remain in the frame throughout.
A white humanoid dual-arm household robot stands in front of the stovetop. Its right hand grips the pan handle and places the non-stick frying pan on the stove burner. Its left index finger and thumb pinch the gas stove knob and slowly turn it counterclockwise. As the knob turns, a steady blue flame rises from the burner. The right hand picks up the oil bottle and pours a minimal amount of oil into the pan, just enough to thinly coat the bottom with an oil film, no visible liquid oil surface, then places the oil bottle back.
The right hand steadily picks up the egg from the small white bowl and moves it horizontally above the pan rim. The camera slowly pushes in for a close-up of the egg and pan rim. The right hand gently taps the egg's side against the pan rim; clearly showing the eggshell contacting the rim, a横向裂缝 appearing on the shell, and the edge slightly lifting. The left hand comes over, both hands' thumbs and index fingers分别捏住 the two shell halves and pull them apart sideways. The egg contents slide into the pan, the egg white solidifies turning white, the yolk居中. The camera slowly pulls back to the original position. Both hands place the two empty shell halves side by side on a corner to the right of the stovetop.
The robot's left hand holds the pan handle to steady the pan. The right hand picks up the wooden-handled spatula and gently pushes the egg's edge with the铲头 to shape it. At this point, the fried egg's upward-facing side is white egg white covering a凸起的完整黄色蛋黄. After the egg bottom solidifies, the铲头 scoops under the entire egg from the bottom, tosses the fried egg upward to flip it, and the egg falls back into the pan. After flipping, the upward-facing side is an even light golden brown, surface平整, edges slightly crispy, the yolk pressed underneath and not visible. After flipping, the fried egg continues frying for a short while with this side up; the robot does not flip it a second time.
Modern open kitchen, light gray cabinets, morning light enters from the right window, warm tone. Third-person fixed wide-angle medium shot, camera positioned slightly high directly in front of the stovetop; only during the egg cracking and shell splitting does the camera slowly push in for a close-up, then pull back to the original position, one continuous shot. Sound: slight click of knob turning, ignition "pop" sound,清脆响声 of eggshell tapping pan rim, continuous sizzling of frying, metal scraping sound of spatula.

No. 3: 3D Asset Product Demo

• Category: Industrial & Manufacturing
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Professional 3D white model with material reference, generating structural and functional demonstrations.

Prompt

The product is @Image 1, and the product assembly content is @Image 2 @Image 3. Help me generate an industrial installation video. The visuals should be unified, the steps clear, and the assembly logical.

No. 4: Synthetic Robot Training Data

• Category: Industrial & Manufacturing
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Modify video elements and environment to create clean industrial lab training data.

Prompt

Modify @Video 1, replace the left robotic arm and gripper with the silver robotic hand from @Image 1;
Replace the grabbed item with a slice of whole wheat toast; replace the original green wall and blue table with a clean white-gray industrial laboratory environment, with metal equipment racks, gray-white workbenches, and white laboratory lighting in the background.

Creative & Misc (3)

No. 1: Character Multi-Scene Travel

• Category: Creative & Misc
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

A one-shot sequence following a person in a black coat through six distinct, emotionally charged rooms.

Prompt

One continuous shot, the camera smoothly follows a person in a black coat, reference 【Image 1】, moving from left to right through six connected rooms with different color tones and atmospheres. Each room has the same structure: white walls, herringbone light wood floor, French double-hung floor-to-ceiling windows, white gauze curtains, reference 【Image 2】 but the scenery outside the window and the indoor atmosphere are completely different. The protagonist walks at a constant speed throughout, passing through each open door in the wall.
0-5 seconds, first room, theme is American comic book fight, protagonist enters the room and fights with character 【Image 3】, character is defeated;
5-10 seconds, second room, theme is warmth, felt style, window scene is a sunflower field 【Image 4】, indoor lighting is warm orange soft light, a painter is painting sunflowers 【Image 5】. The protagonist also becomes felt style upon entering;
10-15 seconds, third room, theme is sadness, the entire picture is in black and white comic book stop-motion style, raining outside the window, indoor lighting is cold gray and low, a person sits alone on the floor in the center of the empty room, head down hugging knees, a mobile phone beside them lit with an unanswered call interface. The protagonist enters the room, turns off the room's light, immediately turns it on, the room becomes colorful, instantly filled with blooming flowers;
15-20 seconds, fourth room, theme is joy, the entire scene is a room submerged in the sea, reference 【Image 6】, the protagonist swims into the room, surrounded by beautiful coral reefs and schools of fish;
20-25 seconds, fifth room, theme is surprise, window scene is a night sky full of fireworks, reference 【Image 7】, indoor light is colored and flickering, the protagonist is swept into the cheering atmosphere.
25-30 seconds, finally the protagonist arrives at a blank room, stands in the center and snaps their fingers, with the sound effect of a finger snap.
Overall cinematic quality, high-fashion advertisement style, lighting completely determined by the window scenes creating strong emotional contrast, no text in the frame.

No. 2: Personified IP Character Film

• Category: Creative & Misc
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Anthropomorphic characters seamlessly blend with real scenes, maintaining consistent appearance, actions, and accent throughout, bringing imagined roles into realistic plots.

Prompt

In a medium shot, personified sunflowers form a unique botanical band, with plants neatly arranged. Warm sunlight pours down, making the golden petals bright and vivid under the light and shadow. A breeze sweeps through the flower patch, causing the leaves to sway gently, accompanied by faint rustling sounds. The sunflower at the front of the group has a standing microphone set up before it. It uses its right "hand" leaf to press down and adjust the microphone to a suitable height, speaking in a deep, gentle British accent: "Partners, let's spread beauty through song." The other sunflowers each hold different instruments and begin to play: some use their leaves to beat a round drum, some carry guitars, and others play wind instruments, each performing their role in perfect harmony. The lead sunflower straightens its posture, faces the microphone directly, extends a leaf to clap overhead in rhythm, ready to start singing.
American Western film style. A scorching sun, yellow sand, a small town. An orange cat wearing a miniature cowboy hat and a fringed leather vest pushes open a door, the door hinge creaking and stirring up dust. The camera quickly pushes in: the bearded bartender wiping a glass behind the counter sees the cat, his hand jerks, and the glass shatters on the floor; three cowboys in the corner turn their heads simultaneously, their tobacco-chewing mouths freeze, close-up on their widened eyes and twitching mustaches, background with three "whoosh" whip crack sound effects. The camera returns to a medium shot of the cat. It kicks up dust from the wooden floor with its hind paw, lifts its chin, and says in a fierce yet drawn-out tone with an American accent: "Fresh milk, brother. Ain't nobody gonna greet me?" The entire room falls silent for half a second, then the cowboys all take off their hats in unison, letting out a drawn-out "Whoa—" of amazement, harmonica slide sound rising. The camera does a 360°环绕 shot around the cat, showing it walking to the bar, jumping onto a high stool, and its proud, sassy little expression.

No. 3: Dance Motion Transfer

• Category: Creative & Misc
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Using a real dancer's motion video as reference, precisely transfer the movements to a target character, aligning motion paths, rhythm, and limb details while retaining Dunhuang-style attire, hair accessories, and body rhythm.

Prompt

Referencing the character movements in @Video 1, generate a dance video featuring a character wearing Dunhuang-style attire in front of the Mogao Caves.

Capability Showcase (7)

No. 1: Extended Scene: Warm Living Room Life

• Category: Capability Showcase
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Seamlessly extend a warm living room scene with reading, a cat, a child, and evening ambiance.

Prompt

Using @Video 1 as the original footage, keep the sofa, color palette, lighting, and camera movement logic completely consistent. Naturally extend the timeline at its end and seamlessly continue the warm living room life scene: The hostess, wearing beige knit loungewear, sits on the same sofa reading, with a beige blanket on her lap, and gently places a coffee cup on the tea table; a cat lightly jumps onto the cushion; a child runs in and leans on her shoulder, the hostess looks down and smiles; the floor lamp lights up at night, the three quietly lean on the sofa, the camera slowly pulls back and holds, leaving space for the brand logo.

No. 2: Gecko Escape Plan: Audio Reference

• Category: Capability Showcase
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

Two geckos, one cautious and one impulsive, plan their escape from a circus backstage in a 3D animated short.

Prompt

[Two Geckos' Escape Meeting — 3D Animation | Circus Backstage | About 20 Seconds]

[Logline] The opening uses an establishing shot to show 'this is the circus backstage', then two geckos (one chubby, one tiny) discuss escape strategies, have a brief argument, and finally reach an agreement; amplified backstage ambient noise is primary, with background music almost always present, intensifying at key emotional points.

[Character Reference (Appearance 100% consistent, no drift throughout)]
——Chubby: A plump, round-bodied gecko with a rotund belly, short thick limbs, skin with warm brown spotted matte scale texture, a thick short tail storing fat making it look pudgy, wide toe pads, puffy cheeks, large round eyes, a simple expression, and slightly slow movements; personality is cautious, timid, loves to eat, but can muster courage and think of solutions at critical moments.
——Tiny: A petite juvenile gecko, eyes large and bright almost filling its small head, skin with light yellow-green fresh scale color and fine spots, tail thin and flexible, toe tips can adhere for climbing, movements are agile and jumpy; personality is impatient, impulsive, fearless, and the one who proposes the escape.

[Voice Reference (Fixed voice per character)]
Chubby: Low, simple, middle-aged male voice, slightly slow speech, with a timid tremble. Reference [Audio 1].
Tiny: High, fast, youthful voice, sharp and impulsive, voice cracks when emotions run high. Reference [Audio 2].
[Ambient Sound Reference]
——Ambience: A layer of circus backstage ambient noise (distant tent clamor, faint animal sounds, canvas flapping in wind, wooden frame creaking, distant human voices with reverb, etc.) runs throughout as the scene's atmospheric base; ambient sound volume is overall amplified, most prominent in the opening establishing shot, serving as the main sound field of the entire piece; ambient sound reference [Audio 3].

[Background Music Reference]
——Accent: A piece of background music (playfully suspenseful, light with a touch of tension), almost always present as a base, appearing for a long duration, gently fades in from the opening establishing shot, volume intensifies at the proposal, argument climax, and ending freeze-frame; only briefly lowered during dense dialogue to make way for lines, but never completely disappears, does not cover dialogue, does not overpower; music reference [Audio 4].
[Scene Lock (Geometrically constant, no drift throughout)]
Circus Backstage: Inside a dim, cluttered circus backstage tent, ambient noise reference matches ambient sound — left side has a row of animal cages (cold light seeps through gaps), center has several stacked prop boxes and rolled-up colorful tent canvas, right side has a canvas flap exit leading outside (gaps emit night blue light) and a swaying warm yellow hanging lamp, ground is trampled wood shavings and straw. Layout locked: Two geckos surround a large prop box used as a table in the center — Chubby lies on the left side of the box (x~30%), back against the cages; Tiny climbs / hops on top or right side of the box (x~65%), most active, toe tips occasionally adhering to the box surface. Exit is at the far right of the frame.
[3D Animation Style / Visual Texture] High-quality 3D animation, fine rendering of scales and skin (visible detailed texture of each scale, skin micro-gloss and muscle movement, softness of toe pad adhesion), character expressions exaggerated and lively, rich with cartoon performance tension; night circus backstage atmosphere — cold blue ambient light primary, right-side warm yellow hanging lamp secondary, teal-and-amber warm-cool contrast, shallow depth of field, cinematic lighting, 55mm virtual lens.

[Shot Language] Handheld-style agile camera movement with real operational weight; editing rhythm driven by emotion, emotional climax points can sync with accentuated downbeats from [Audio 4]. Opening uses an establishing shot to show the scene, then each segment first uses a positioning wide shot to establish the two geckos' relative positions, then cuts into coverage shots. Moderate use of rhythmic staging: quick whip pans switching between speakers, crash-in close-ups landing on emotional climax points, fast-cut shot/reverse-shot during argument. Facial close-ups must capture eyes, vertical pupil contraction, throat movement, toe tip gripping, and mouth shapes; eye lines look at each other, never at the camera; natural blinking (including gecko-style eye licking) and eye movement. Hard cuts, no dissolves.
[Hard Locks] Only the two named geckos throughout, no third gecko, no extras, no clones/duplicates; their size difference (plump / petite) maintained every frame; dialogue spoken word-for-word (English), only one main speaker at a time (argument climax allows brief overlapping/interrupting); opening establishing shot segment has no dialogue; audio track hierarchy: amplified [Audio 3] ambient noise primary, [Audio 4] accent background music long-duration base and intensifying at key points, not covering dialogue; no subtitles / on-screen text; 3D realistic scale skin, stable, no extra limbs or ghosting.

Shot 1 (0–3 sec) · Establishing Shot (No Dialogue)
Pure environment shot, no character dialogue: camera slowly pans across the circus backstage tent interior — left side animal cages' cold light, center stacked prop boxes and rolled colorful tent canvas, right side canvas flap exit emitting night blue light and swaying warm yellow lamp, trampled wood shavings and straw on ground. This segment ambient noise volume is highest, most prominent (tent clamor, distant animal sounds, canvas flapping in wind, frame creaking), [Audio 4] accent gently fades in here as a base, clearly establishing 'this is the circus backstage'. Hard cut.

Shot 2 (3–7 sec) · Positioning + Proposal
Positioning wide shot reveals two geckos surrounding the central prop box. Hard cut. — Handheld medium shot pushes in on Tiny (voice reference [Audio 2]), it hops onto the box, toe tips audibly adhere to the surface (with crisp adhesion sound effect), speaking low and urgent: "Tonight — we break out of here!" — Reverse shot to Chubby (voice reference [Audio 1]) facial close-up, throat constricts, vertical pupils tremble, trembling voice: "B-break out? It's dangerous…"

Shot 3 (7–13 sec) · Argument Confrontation (Climax)
Fast-cut shot/reverse-shot argument, allows brief overlapping dialogue, — Tiny (voice reference [Audio 2]) jumps, tail flicks, points at Chubby, voice cracking: "You're just a coward!" — Chubby (voice reference [Audio 1]) unusually raises volume to overpower it, near tears: "Stop shouting — the guard'll hear us!" Facial close-ups: each face showing anger and panic, vertical pupils contracting, throat and tail shaking violently; at the argument peak, music and ambient noise briefly lower to highlight the two arguing voices.

Shot 4 (13–18 sec) · Turning Point + Agreement
— Chubby (voice reference [Audio 1]) suddenly musters courage, serious: "I'll block the guard. You slip out and open the door." — Whip pan to Tiny, pauses, vertical pupils relax, grins: "…That actually works!" (Music warms up, volume rises again)

Shot 5 (18–20 sec) · Freeze Frame High-Five
Slow push two-gecko side-by-side shot: both geckos extend small claws (toe pads touch) stacked together (with gentle toe pad contact sound effect), eyes look together towards the right exit, [Audio 4] accent ends with one accentuated downbeat. Tiny (voice reference [Audio 2]) whispers: "Midnight. We move." Night light from the canvas flap gap illuminates their determined faces, frame freezes on their resolute expressions, amplified ambient noise and music together fade out.

[Negative Constraints] No third gecko or any extras/clones; their sizes and appearances must not drift or face-swap; no duplicated props; no character duplicates in mirror reflections; no subtitles, no on-screen text, no text overlays; only hard cuts, no dissolves; opening establishing shot segment must not have character dialogue; maintain the emotional arc of "ambient setup → proposal → argument confrontation → agreement", ending must land on both parties agreeing and determined; audio track hierarchy fixed as amplified ambient noise primary, background music long-duration base and intensifying at key points, not covering dialogue. Characters speak English (All characters speak English).

No. 3: Headphone Ad: Cinematic Motion And Rhythm Transfer

• Category: Capability Showcase
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Create a headphone ad by transferring the camera work and editing rhythm from a reference video.

Prompt

Reference the camera movement techniques and editing rhythm of @Video 1 to generate an advertising short film for the headphones @Image. Adapt to scenes that match the product's tone, emphasizing modernity, simplicity, and a sense of technology. The switching points between product close-ups and scene panoramas are consistent with the original film, maintaining the same motion speed and transition methods.

No. 4: One-Shot Journey Through Time

• Category: Capability Showcase
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

A 26-second one-shot film follows a solitary woman through shifting seasons and day into night.

Prompt

Core Instruction: A full 26-second one-shot (One-Shot) narrative short film, stable follow shot, referencing [Video 1] and smooth orbiting camera movement, referencing [Video 2] interwoven. Smooth sense of progression. Achieve day-night alternation and seasonal flow within the shot. The protagonist is a European woman [Image 1], placed in a bustling crowd full of life, highlighting an extreme sense of loneliness and cinematic photography quality.

Segmented Camera Movement and Scene Description:
0-3 seconds (steady back follow): An old wooden door [Image 2] creaks open, the camera closely follows the European woman's back wearing [Image 3] as she steps out. She pauses slightly at the threshold, the street ahead dappled with light and shadow, the sounds of hawking and crowds washing over her. Her expression is detached as she slowly steps forward to merge into the street.
3-6 seconds (back/side follow): The camera maintains smooth follow, she enters a crowded morning market, atmosphere reference [Video 3]. Both sides are packed with vibrantly colored fruit stalls and spice shops, a troupe of street performers is breathing fire dragons, reference [Image 4], the firelight illuminates the crowd, but she doesn't glance sideways, walking at a steady pace through.
6-9 seconds (side smooth orbit): The camera begins a smooth orbit towards the front side, capturing the protagonist's profile. She passes a noisy butcher shop [Image 5], a young mother carrying a baby [Image 6] brushes past her, the baby stares at her curiously, but she merely lowers her eyes slightly to avoid the gaze, not pausing at all.
9-12 seconds (front reverse follow): The camera continues orbiting to the protagonist's front, performing a reverse follow shot. The crowd ahead suddenly parts naturally like Moses parting the sea, a large elephant draped in ornate red cloth [Image 7] appears from the right side of the frame with steady steps, occupying most of the frame.
12-15 seconds (gap penetration and orbit back): At the moment the woman and the elephant are about to collide, the camera cleverly slides through the narrow gap between the elephant and the woman, orbiting back to her back. The elephant passes by, massive and quiet, mischievous children cheer and chase it. Elephant bells, laughter are deafening, yet she doesn't even slow her pace.
15-18 seconds (environmental light gradient): As she walks, the light within the long shot magically transforms—the piercing summer sunlight instantly softens, a gust of wind swirls up a sky full of golden leaves [Image 8], the season seamlessly transitions to late autumn within the same long shot. Leaves brush past her shoulder.
18-21 seconds (360-degree immersive orbit): Ahead suddenly erupts into a grand street festival [Image 9]. The air sprays confetti and shredded paper, vendors lean out cheering. At this moment, the camera executes a continuous 360-degree orbiting shot, creating an extremely strong visual tear between the quiet, lonely protagonist and the狂热 surroundings.
21-24 seconds (orbit back to side/rear): When the camera completes its orbit and returns to her side/rear, the falling confetti has quietly transformed into a sky full of falling snow—instantly winter [Image 10]. Pedestrians纷纷 put up umbrellas or pull up hoods, the woman shivers slightly, turns up her coat collar, her clothing changes to [Image 11], continuing her solitary walk in the snow.
24-26 seconds (slow push follow): As she walks towards the end of the long street, the sky visibly darkens during her progression, day seamlessly sinks into night. The dim yellow street lamps and stall light bulbs on both sides light up one after another [Image 12], vendors pack up their goods, the喧闹声 seems to be slowly absorbed and distanced by the heavy snow, her steps gradually slow. The night sky suddenly erupts with grand fireworks [Image 13], fireworks sound reference [Audio 1]五彩 light spots flicker and dance on the building walls and in her eyes. The world remains热闹, yet she looks up quietly, the camera slowly pulls back, ending gently here.

No. 5: Martial Scene Swap: Cold Weapon Duel

• Category: Capability Showcase
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

• Inputs:

Description

Replace a bare-handed fight with a cold weapon duel in a classical, atmospheric setting.

Prompt

Replace the bare-handed fight video of two people @Video 1 with the empty-handed probing style before a cold weapon duel.
Replace the scene with a medieval stone castle platform, ancient courtyard flat ground, mountain fortress outer platform, or simple stone brick dueling ground, with a background of ancient castle walls, wind, fog, distant mountain lines, and flat stone ground @Image 1.
Replace the clothing of the man in dark clothes in the video with @Image 2, and replace the man in light clothes with @Image 3. Keep the actions unchanged, do not alter the original rhythm.
AI effects only enhance environment and texture: wind blowing clothes, light fog, a small amount of dust at contact points, cold metallic reflective texture, slight grain, and epic color grading. Overall style is restrained, realistic, classical hardcore duel atmosphere. Background music hits the beat.

No. 6: Complex Emotions In Theater Audience

• Category: Capability Showcase
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

A young girl in a theater audience watches a performance with a mix of pride, heartache, and suppressed tears.

Prompt

Theater audience, a young girl with her hands clasped near her chin, gazing at the performance on stage. Her emotions are complex and mixed; there is pride in her eyes, heartache, and the glimmer of suppressed tears. Her lips are lightly pressed together, her eyelashes tremble, tears well up in her eyes but she forces them not to fall. The core presentation is the authentic, mixed feelings of watching someone dearest to you shine.

No. 7: Acceptance Letter's Quiet Joy

• Category: Capability Showcase
• Source: official
• Author: ByteDance Seedance
• Language: en
• Video: View

Description

A young woman experiences restrained, complex emotions upon receiving her acceptance letter at dusk.

Prompt

A young East Asian woman sits by a study window at dusk, facing a laptop, warm golden side/back light on her face. Her performance is deeply restrained, with emotion conveyed through her eyes, shallow breathing, a choked throat, and trembling fingertips. She moves from disbelief to tearful suspension; as one tear falls, a faint smile appears, ending in quiet relief as she looks outside. Slow, steady camera movement, close-ups for micro-expressions, a slight push-in at the moment the tear gives way to a smile, soft focus on " Acceptance Letter," 35mm film texture, shallow depth of field, low-light grain.

❓ Frequently asked questions

What is Seedance 2.5 Skill?

It is the installable Agent Skill in skills/seedance-2-5-skill/. It improves prompts, prepares required storyboards or references, executes through Atlas Cloud, and reviews the outputs.

Does the Skill require public Seedance 2.5 access?

No. The current executable default is Seedance 2.0. The Skill uses Seedance 2.5 only when the selected provider actually exposes it.

Does every video need a storyboard?

No. The Skill creates or uses a storyboard only when it materially improves multi-shot planning, continuity, or reference control.

Which Atlas route is used?

Atlas Cloud Skill is the default inside an Agent conversation. MCP, CLI, and REST are selected explicitly for their corresponding environments.

Can I use the prompts without installing the Skill?

Yes. Browse and copy any prompt directly. Install the Skill when you want prompt adaptation, storyboard handling, execution, polling, and automated review.

npm ci
npm run generate
npx tsc --noEmit

🔗 Resources

• Atlas Cloud official website
• Seedance 2.5 prompt gallery
• Atlas Cloud Seedance 2.5 page
• Atlas Cloud Skill
• Atlas MCP Server
• Atlas CLI
• Atlas Cloud model catalog
• Discord

📄 License

CC BY 4.0

All prompts are shared for learning, organization, and discovery. Open an issue if anything should be removed.

This README is auto-generated. 2026-08-16.