Awesome LTX-2

A curated list of models, text encoders, and tools for the LTX-2 video generation suite.

Intro

• LTX official Blog
• ComfyUI official blogpost
• Prompting Guide for LTX-2
• LTX-2 in ComfyUI Chattable KB

▓ Apps & Tools

LTX2.3-Multifunctional

LTX2.3-Multifunctional is a desktop-optimized version of LTX that lowers GPU requirements and simplifies usage. It integrates all features including image-to-video, text-to-video, start/end frames, lip-sync, video enhancement, and image generation into a single application.

Key Features: - Lower GPU Requirements: Only needs 24GB VRAM (vs 32GB for standard desktop version) - All-in-One Interface: No complex ComfyUI workflows or error-prone nodes - Features: T2V, I2V, start/end frames, lip-sync, video enhancement, image generation, LoRA support - Multi-Frame Insertion: Two modes for generating long videos - Easy Setup: No third-party software required, just install LTX desktop

Downloads & Resources: - HuggingFace | GitHub | ComfyUI Node | Tutorial

▓ Models

LTX-2 models are available in various formats including full weights, transformers-only, and GGUF quantizations for efficient inference.

▣ Checkpoints

• Lightricks/LTX-2 - Official repository.
• Lightricks/LTX-2.3 - Official repository (latest version).
• Drbaph - Quantization

Ver	Name	Precision	Size	Download
2.5	dev		42.02 GB
2.5	dev		21.50 GB
2.5	distilled		42.02 GB
2.5	distilled		21.50 GB
2.5	distilled		18.72 GB
2.5	pt (pre-trained)		43.0 GB
2.5	distilled		20.6 GB
2.5	dev		12.52 GB
2.5	distilled		12.52 GB
2.5	distilled		19.6 GB
2.5	distilled		17.4 GB
2.5	dev		14.4 GB
2.5	distilled		14.4 GB
2.5	distilled		21.9 GB
2.5	dev		21.64 GB
2.5	dev		13.57 GB
2.5	distilled		21.64 GB
2.5	distilled		13.57 GB
2.3	dev		46.1 GB
2.3	dev		29.1 GB
2.3	dev		29.9 GB
2.3	dev		29.1 GB
2.3	dev		21.7 GB
2.3	dev		29.1 GB
2.3	distilled		46.1 GB
2.3	distilled		29.5 GB
2.3	distilled		29.9 GB
2.3	distilled		29.1 GB
2.3	distilled		17.6 GB
2.3	distilled		29.7 GB
2.3	distilled 1.1		46.1 GB
2.3	ltx23_srx fp8_e4m3 experimental		23.1 GB
2	ltx-2-19b dev		43.3 GB
2	ltx-2-19b dev		27.1 GB
2	ltx-2-19b dev		20 GB
2	ltx-2-19b distilled		43.3 GB
2	ltx-2-19b distilled		27.1 GB
2	ltx-2-19b distilled		20 GB

Quantized to fp8_e5m2 to support older Triton with older Pytorch on 30 series GPUs. For WangGP in Pinokio

Ver	Name	Precision	Size	Download
2	ltx-2-19b dev		27.1 GB

· · · · · · · · · · · · · ·

❖ silveroxides Quantizations (mxfp8)

Note: The mxfp8mixed quantization requires a custom fork of ComfyUI-Kitchen with mxfp8 support. Standard ComfyUI installations may not support this quantization format.

Model	Quant	Size	Download
ltx-2.3-22b-dev		29.2 GB
ltx-2.3-22b-distilled		29.1 GB
ltx-2.3-22b-distilled		29.2 GB
ltx-2.3-22b-distilled		29.7 GB

· · · · · · · · · · · · · ·

❖ Distilled LoRA

Ver	Rank	Precision	Size	Download
2.5	450		5.06 GB
2.5	450		4.53 GB
2.5	450		2.66 GB
2.5	450		8.90 GB
2.5	384		7.61 GB
2.5	256		5.10 GB
2.5	256		5.10 GB
2.5	128		2.58 GB
2.5	64		1.32 GB
2.5	128		2.31 GB
2.5	72		1.38 GB
2.3	384		7.61 GB	┊
2.3	208		4.97 GB
2.3	159		3.83 GB
2.3	111		2.74 GB	┊
2.3	105		2.59 GB
2	384		7.67 GB
2	242		4.88 GB
2	175		3.58 GB
2	175		1.79 GB

· · · · · · · · · · · · · ·

❖ TenStrip Distilled LoRA Experiments

Experimental distilled LoRAs optimized for finetunes and I2V workflows. These LoRAs avoid the issues of the massive rank 384 official LoRA which can be counterproductive with conditioned inputs and finetunes.

Name	Rank	Mode	Size	Download
distilled v1.1	36	—	739 MB
distilled v1.1	72	condsafe	662 MB
distilled	72	—	1.4 GB
distilled v1.1	32	condsafe	363 MB
distilled v1.1	52	condsafe	464 MB
distilled v1.1	72	energy	1.6 GB
distilled v1.1	96	energy	2.2 GB

Notes: - Lower rank LoRAs (72 and below) can be used at 1.0 strength safely for I2V first pass, with upscale pass at 0.4-0.5 strength - _ceil suffix indicates the dynamic ceiling during reranking - _condsafe suffix indicates cross-attention and other conditioning layers have been zeroed for better I2V compatibility - The official rank 384 LoRA can actively dampen conditioning signals in I2V workflows; cond_safe versions work much better

Download All LoRAs

· · · · · · · · · · · · · ·

❖ Spatial Upscaler

Required for current two-stage pipeline implementations in this repository. Download to COMFYUI_ROOT_FOLDER/models/latent_upscale_models folder.

Ver	Name	Size	Download
2.5	spatial-upscaler x2 1.0	0.93 GB	┊
2.3	spatial-upscaler x2 1.0	996 MB
2.3	spatial-upscaler x1.5 1.0	1.09 GB
2	spatial-upscaler x2 1.0	1.05 GB

· · · · · · · · · · · · · ·

❖ Temporal Upscaler

Required for current two-stage pipeline implementations in this repository. Download to COMFYUI_ROOT_FOLDER/models/latent_upscale_models folder.

Ver	Name	Size	Download
2.5	temporal-upscaler x2 1.0	0.24 GB	┊
2.3	temporal-upscaler x2 1.0	262 MB
2	temporal-upscaler x2 1.0	262 MB

══════════════════════════════════

▣ Merges

Custom merged models combining multiple control signals or specialized configurations.

Ver	Name	Description	Download
2.3	ltx-2.3-22b-distilled-1.1-fused-union-control	Merged model combining Canny, Depth, and Pose control signals for unified control

══════════════════════════════════

▣ Finetunes

Community finetuned models based on LTX-2.3 with specialized improvements and optimizations. Each finetune family may include a backbone checkpoint, low-VRAM component splits, GGUF quants, and merged or extracted LoRAs. Variant cell links go directly to the resolve/main safetensors/gguf file when a single canonical asset covers the row.

❖ DaSiWa

High-performance LoRA-integrated checkpoint family based on LTX 2.3. Includes distilled (4-step) and non-distilled (20-30 step) variants. Recommended sampler: Euler + Simple/Normal/Linear_Quadratic.

Ver	Build	Name	Precision	Size	Download
2.3	Distilled	Treasurechest V1		19.58 GB
2.3	Distilled	Solsticecoin V2		28.06 GB
2.3	Distilled	Dragonleap V4		17.10 GB
2.3	Distilled	Dragonleap V4		25.73 GB
2.3	Non-Distilled	GoldenLace V3		27.16 GB
2.3	Non-Distilled	GoldenLace V3		20.24 GB
2.3	Non-Distilled GGUF	GoldenLace V3		7.92 GB
2.3	Non-Distilled GGUF	GoldenLace V3		9.87 GB
2.3	Non-Distilled GGUF	GoldenLace V3		12.41 GB
2.3	Non-Distilled GGUF	GoldenLace V3		14.81 GB
2.3	Non-Distilled GGUF	GoldenLace V3		17.35 GB
2.3	Non-Distilled GGUF	GoldenLace V3		21.99 GB

DaSiWa extracted LoRA:

Build	Name	LoRA Rank	Size	Download
DMD v2 audio	LTX2.3_DMD_v2_avgrank86_audio160_L80-D20	86 (audio 160)	2.16 GB

· · · · · · · · · · · · · ·

❖ 10Eros

I2V-optimised merge using layer scaled merges at different steps. Not a straight weight merge — behaves much nicer than standard LoRA loading and respects prompts.

Ver	Build	Name	Precision	Size	Download
2.3	Full	10Eros v1		44.0 GB
2.3	Full	10Eros v1		27.8 GB
2.3	transformer-only	10Eros v1		28.2 GB
2.3	Full	10Eros v1.2		44.0 GB
2.3	Full	10Eros v1.2		32.7 GB
2.3	Full	10Eros v1.3		44.0 GB
2.3	Full	10Eros v1.3		27.8 GB
2.3	Full	10Eros v1.4		44.0 GB
2.3	Full	10Eros v1.4		27.8 GB
2.3	Full	10Eros v1.4		27.8 GB
2.3	Full	10Eros v1 INT8 ConvRot		23.51 GB

◦ 10Eros GGUF — vantagewithai low-VRAM quants

◦ 10Eros Splits

◦ 10Eros Splits — AX1Y2JP transformer-only fork (alternative split for ComfyUI)

Variant	Download
v1.4 transformer_only bf16
v1.4 transformer_only fp8mixed_learned
v1.4 video VAE bf16

◦ 10Eros Extracted LoRA — maximsobolev275 trained LoRAs

· · · · · · · · · · · · · ·

❖ Sulphur-2-base

Repo: SulphurAI/Sulphur-2-base — uncensored video generation model based on LTX 2.3 with built-in prompt enhancer. Merge base for 10Eros. T2V + I2V native.

◦ Main video model

Ver	Build	Precision	Size	Download
2.3	dev		44.0 GB
2.3	dev		27.8 GB
2.3	distil		44.0 GB
2.3	distil		27.8 GB
2.3	distil		18.6 GB

◦ vantagewithai component split — vantagewithai/Sulphur-2-Base-Split

Component	Precision	Size	Download
model (sulphur_dev_bf16_model)		40.06 GB
model (sulphur_dev_model_fp8mixed)		23.87 GB
model (sulphur_distil_bf16_model)		40.06 GB
vae	—	1.38 GB
audio_vae	—	348.0 MB

◦ Sulphur LoRAs

Ver	Build	Size	Download
2.3	sulphur_lora_rank_768	9.79 GB
2.3 (experimental)	sulphur_experimental_lora_v1	13.87 GB

◦ Prompt Enhancer

Variant	Precision	Size	Download
Censored		879.01 MB
Censored		9.09 GB
Uncensored		879.01 MB
Uncensored		9.33 GB

· · · · · · · · · · · · · ·

❖ JoyAI-Echo Surgical

Surgical finetune based on jdopensource/JoyAI-Echo by joeygambino. Combined "echoVid + ltxAud" surgical variant — jointly fine-tuned for both video generation and audio on top of LTX-2.3. A LoRA extracted from JoyAI-Echo (TenStrip's LTX2.3_JoyAI_Lora_Extracted) is listed separately under ### ▣ Special.

Ver	Build	Name	Precision	Size	Download
2.3	unsplit (full DiT)	echoVid-ltxAud surgical		42.97 GB
2.3	unsplit (full DiT)	echoVid-ltxAud surgical		23.41 GB
2.3	unsplit (full DiT)	echoVid-ltxAud surgical		27.15 GB
2.3	transformer-only	echoVid-ltxAud surgical		26.07 GB

◦ JoyAI-Echo Surgical — GGUF (low-VRAM quants)

· · · · · · · · · · · · · ·

❖ PinkCherry NSFW

Repo: SexGod1979/PinkCherry_NSFW_LTX23 — uncensored NSFW LTX-2.3 finetune family (NSFW content only — do not use for clean content). Pairs with the official LTX-2.3 distilled LoRA 384.

Variant	Precision	Size	Download
v1.3 dev		46.14 GB
v1.3 dev		27.62 GB
v1.5 dev		46.14 GB
v1.5 dev		27.64 GB
v1.6 dev		46.14 GB
v1.6 dev		27.62 GB
v1.6 dev		27.64 GB
v1.7-alpha dev		46.14 GB
v1.7-alpha dev		27.62 GB
v1.7-alpha dev		27.64 GB
v1.8 dev		46.14 GB
v1.8 dev		27.62 GB
v1.8 dev		27.64 GB

◦ PinkCherry GGUF — low-VRAM quants by SexGod1979

❖ Elastic

Elastic is a TensorRT-engine distribution of a LoRA-integrated distilled FP8 T2V variant of LTX-2.3, packaged by TheStageAI as .qlip shard files for H100 GPUs.

Build	Name	Precision	Size	Download
distil + LoRA T2V	Elastic — H100	fp8	~19 GB (49 .qlip shards)

· · · · · · · · · · · · · ·

❖ SpatialAV2AV (BingoG)

Publicly-released audio→audio-video training checkpoints from BingoG/LTX-2-SpatialAV2AV-Checkpoints for spatial-audio conditioned video generation. Two curriculum layouts (E4 Core Dual + Dynamic; E6 reserved for Full) at 480p cap, 113 frames at 25 fps.

Curriculum	Step	Size	Download
E4 Core (Dual + Dynamic)	400	36.22 GB
E4 Core (Dual + Dynamic)	1000	36.22 GB
E6 Full	1000	36.22 GB

Note: these are intermediate training checkpoints, not inference-ready models — useful for fine-tuning experiments and reproducibility only.

══════════════════════════════════

▣ GGUF Quantized Models

These models are optimized for lower memory usage. Note that in ComfyUI, these are typically loaded as transformer-only models.

Special Quantization: PolarQuant Q5

LTX-2.3 (22B) — PolarQuant Q5 is a bit-packed quantization method using Hadamard-Rotated Lloyd-Max Quantization. It achieves optimal Gaussian weight quantization via Hadamard rotation, delivering near-lossless quality with significant size reduction.

Model	Size	Download
LTX-2.3-22B-PolarQuant-Q5	15 GB

Installation: pip install safetensors huggingface_hub scipy ArXiv Reference: 2603.29078

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ Text Encoders

LTX-2/2.3 require Gemma-3-12b variants with text projection layers. LTX-2.5 ships with a Gemma-4-12B text encoder — see the ▣ Gemma-4-12b section below.

▣ Comfy-Org Optimized Encoders

Official and optimized versions for ComfyUI.

Model Name	Size	Download
gemma_3_12B_it	24.4 GB
gemma_3_12B_it_fpmixed	13.7 GB
gemma_3_12B_it_fp8_scaled	13.2 GB
gemma_3_12B_it_fp4_mixed	9.5 GB
gemma_3_12B_it-int8tensormixed	13.2 GB
gemma_3_12B_it-int8mixedblockwise	13.6 GB
gemma_3_12B_it-int8mixedtensorwise	14.1 GB
gemma_3_12B_it-int8tensormixed	13.2 GB
text_projection_fp8	1.16 GB

• gemma_3_12B_it_fpmixed: Experimental quant. Should be better than the fp8 scaled
• gemma_3_12B_it_fp4_mixed: 90% fp4 layers Note: mxfp8mixed quantization requires a custom fork of ComfyUI-Kitchen with mxfp8 support. Standard ComfyUI setups don't.

· · · · · · · · · · · · · ·

▣ Gemma-3-12b Abliterated

Why Choose Abliterated Encoders?

Standard Gemma models often incorporate safety alignment that "sanitizes" or weakens specific concepts within prompt embeddings. Even when the model doesn't explicitly refuse a request, this internal filtering can dilute creative intent. For LTX-2 video generation, using a standard encoder often results in:

• Reduced Prompt Adherence: Key stylistic or descriptive terms may be ignored or weakened.
• Visual Softening: Visual intensity and fine details are often "muted" to fit generic safety profiles.
• Concept Dilution: Complex or niche creative requests are subtly altered, leading to less faithful representations of your vision.

Abliteration bypasses these restrictive alignment layers, allowing the encoder to translate your prompts into embeddings with maximum fidelity. This ensures LTX-2 receives the most accurate and un-filtered instructions possible.

· · · · · · · · · · · · · ·

▣ Gemma-3-12b IT Heretic

Models by DreamFast. "Heretic" lineage bypasses alignment/restriction layers in the text encoder so LTX-2/2.3 receives the most faithful prompt embeddings. Two upstream versions (v1, v2) plus an AX1Y2JP ultra-uncensored fork and a 3rd-party mradermacher imatrix GGUF re-quant set.

▣ Gemma-4-12b (LTX-2.5 Text Encoders)

LTX-2.5 replaces the Gemma-3-12B text encoder with a Gemma-4-12B encoder. Community "heretic" / uncensored forks bypass alignment layers for maximum prompt fidelity in downstream video generation.

Model	Precision	Size	Download
gemma4-12b-heretic-ltx-2.5		24.46 GB
Gemma-4-12B-it-uncensored-heretic		26.26 GB
Gemma-4-12B-it-uncensored-heretic		13.17 GB
gemma4-12b-ltx2.5-int4int8-mix		7.52 GB
gemma4-12b-with-proj-ltx-2.5		15.50 GB
gemma4-12b-with-proj-ltx-2.5		15.37 GB
gemma4-12b-with-proj-ltx-2.5		11.20 GB

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ Separated Components

Separated LTX2 checkpoint by Kijai and Kijai for LTX-2.3. For alternative way to load the models in Comfy.

▣ Diffusion Models (Transformer Only)

Ver	Name	Precision	Size	Download
2.3	ltx-2.3-22b dev		42 GB
2.3	ltx-2.3-22b dev		23.5 GB
2.3	ltx-2.3-22b dev		24.1 GB
2.3	ltx-2.3-22b dev		25 GB
2.3	ltx-2.3-22b distilled		42 GB
2.3	ltx-2.3-22b distilled		23.5 GB
2.3	ltx-2.3-22b distilled v2		23.2 GB
2.3	ltx-2.3-22b distilled		23.5 GB
2.3	ltx-2.3-22b distilled (experimental)		24.1 GB
2.3	ltx-2.3-22b distilled 1.1		42 GB
2.3	ltx-2.3-22b distilled 1.1		25.2 GB
2.3	ltx-2.3-22b distilled 1.1 (experimental)		24.1 GB
2.3	ltx-2.3-22b dev		20.51 GB
2.3	ltx-2.3-22b distilled 1.1		20.51 GB
2.3	ltx-2.3-22b distilled v3		23.86 GB
2	ltx-2-19b dev		37.8 GB
2	ltx-2-19b dev		21.6 GB
2	ltx-2-19b dev		14.5 GB
2	ltx-2-19b distilled		37.8 GB
2	ltx-2-19b distilled		21.6 GB

[!NOTE]
input_scaled additionally have activation scaling, and are set to run with fp8 matmuls on supported hardware (roughly 40xx and later Nvidia GPUs).

▣ VAE (Video & Audio)

Ver	Component	Precision	Size	Download
2.5	Video VAE		1.37 GB
2.5	Video VAE (conv)		1.35 GB
2.5	Audio VAE		0.34 GB
2.3	Video VAE		1.45 GB	┊
2.3	Cinematic Video VAE		1.38 GB
2.3	Pruna Video VAE		1.27 GB
2.3	TAE (tiny autoencoder)		22 MB
2.3	Audio VAE		365 MB	┊
2	Video VAE		2.45 GB
2	Audio VAE		218 MB

▣ Embedding Connectors & Text Projection

Ver	Name	Precision	Size	Download
2.3	Embeddings Connectors dev		2.31 GB	┊
2.3	Embeddings Connectors distilled		2.31 GB
2	Connector dev		2.86 GB
2	Connector distilled		2.86 GB

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ LoRA

▣ Enchancer, special

• Lightricks LTX-2.3
• LipDub IC-LoRA - Enables lip dubbing on top of LTX-2.3 for video dubbing via joint audio-visual diffusion (based on JustDubIt research)
• OmerHagawa
• Greenscreen Avatar IC-LoRA - Greenscreen avatar IC-LoRA for vertical video
• systms
• SYSTMS FLW IC-LoRA - Seamless shot-to-shot transitions IC-LoRA with trigger word FLW, uses gray frames (RGB 127,127,127) between clips
• LTX-2.3-IC-LoRA-Colorizer by DoctorDiffusion (331 MB) - Colorize black and white videos
• JUST-DUB-IT
• Best-Face-Swap-Video
• Image-to-Video Adapter LoRA
• Original by MachineDelusions
• siraxe variant - Stripped audio layers + rank64 compressed (2.62 GB, 655 MB rank64 bf16)
• Lightricks LTX-2.3
• HDR - Enables 16-bit HDR video generation and converts SDR video to HDR using LogC3 transform for extended dynamic range
• Union Control - Unified IC-LoRA combining Canny + Depth + Pose control signals for multi-signal video generation conditioning
• Motion Track Control - Guides object motion using sparse point trajectories via colored spline overlays on reference videos
• vrgamedevgirl84
• Enhancer1 - Video enhancement LoRA
• Enhancer2 - Second video enhancement LoRA
• oumoumad
• IC luminance map
• LTX-2 IC-LoRA-Ungrade - Removes color grading and contrast from footage, returning neutral ungraded appearance
• LTX-2.3 IC-LoRA-Ungrade - LTX-2.3 version of color grading removal IC-LoRA
• IC-LoRA-Outpaint - Extends video canvas by generating new content in black regions (letterbox areas), filling with temporally consistent content
• IC-LoRA-ReFocus - Removes lens blur and restores focus to out-of-focus footage (lens blur only)
• IC-LoRA-Uncompress - Removes MP4 compression artifacts (blocking, banding, mosquito noise) and restores clean video
• IC-LoRA-MotionDeblur - Removes motion blur from footage
• IC-LoRA-Deinterlace - Removes interlacing artifacts from video
• FXIC LTX2 IC-LoRA - Flux-inspired IC-LoRA for LTX video transformation with multiple optimizer variants (adamw, prodigy, masked) at various training steps
• DeArchive LTX-2.3 - In-Context LoRA for restoring archive video (old B&W footage, low-res web rips, sepia-toned silent-era prints) into colored, high-definition modern cinematography (Rank 128, 5,000 steps)
• Kijai
• Realisdance - IC-LoRA trained on the realisdance dance set (312 MB)
• SAM3D Body v42 - IC-LoRA tied to SAM3D body pose conditioning (624 MB)
• Cseti
• IC-LoRA-Cameraman v1 - Transfers camera movements (zoom, pan, tilt, orbit) from reference video to generated output
• IC-LoRA-EditRefVid v1 - Edit reference video IC-LoRA for editing existing videos using reference guidance
• IC-LoRA-Cameraman v2 - v2 of the Cameraman IC-LoRA with a larger and more diverse dataset; replicates camera motion from a reference video. No trigger word required.
• IC-LoRA-CrossView Prompt v0.9 - Virtual second camera IC-LoRA: give it a reference video + a short camera-angle prompt using the trigger crossview. and re-render the same scene from a new viewpoint. v0.9 proof-of-concept trained on synthetic multi-view data; no starting image needed.
• IC-LoRA-CrossView Warp v0.9 - Depth-warp novel-view IC-LoRA for LTX-Video 2.3 (22B). Given a video + a depth-warp of the same video (from the CrossViewWarp ComfyUI node, Depth Anything V2 input) and an azimuth/elevation/distance offset, renders the scene from that new viewpoint. Sibling of CrossView-Prompt v0.9. (192 MB)

• IC-LoRA-CrossView Warp v2 - v2 of the depth-warp novel-view IC-LoRA for LTX-2.3 (22B): given a video + a depth-warp of the same video (CrossViewWarp ComfyUI node, Depth Anything V2 input) and an azimuth/elevation/distance offset, renders the scene from a new viewpoint. Checkpoint at 6000 steps. (330 MB)

• 100percentrobot

• Audio-Reactive LORA - Generates audio-reactive videos with motion synchronized to musical elements (beats, rhythm)
• LiconStudio
• VBVR-lora-I2V - Enhances video generation for complex reasoning tasks including multi-object interactions, physical causality, and spatial relationships
• VBVR-lora-I2V Special
• Licon MSR V2 - Multiple Subject Reference v2: IC-LoRA preserving character identity / clothing / objects across frames in multi-reference video generation. Improves consistency, stability and scene logic vs. v1. Requires the ComfyUI-Licon-MSR plugin.

• Licon MSR V1 (LTX-2.5) - Multiple Subject Reference v1 for LTX-2.5: IC-LoRA preserving character identity / clothing / objects across frames in multi-reference video generation (1.31 GB, LTX-2.5-Licon-MSR-V1.safetensors). Requires the ComfyUI-Licon-MSR plugin.

• TheBurgstall

• LTX-2.3-Skin-Hair - Refines skin texture and hair rendering, reduces plastic skin artifacts, improves specular highlights
• VR-360-Outpaint IC-LoRA - Outpaints standard widescreen footage into a full 360° equirectangular projection for immersive/VR viewing.

• Seamless-Equirectangular LTX-2.3 LoRA - Rank-128 LoRA for equirectangular 360° text-to-video generation with LTX-2.3 (15k steps). Trigger Equirectangular. Pairs with the ComfyUI-Seamless-Equirectangular node pack and EquiRoPE / Geometric CFG / per-step roll / circular VAE / wrapped noise setup.

• Nightfury16

• Staging IC-lora 512 - Staging IC-LoRA for video composition control (512 latent scale)
• siraxe
• MergeGreen IC-lora - Maintains motion at start/end frames, use middle frames with RGB 0,191,0 (75% green fill) in IC-LoRA workflow
• TTM IC-lora - Makes cutouts cartoony and adds cartoony characters to video scenes, based on the TTM approach (use with Img To Video bypass + Add Video IC-LoRA Guide node)
• Lightricks LTX-2
• Canny Control - Edge detection control for structural guidance
• Depth Control - Depth map conditioning for 3D spatial control
• Detailer - Enhances fine details and textures in generated videos
• Pose Control - Human pose estimation control for motion guidance

Upscaler LoRAs: * LTX 2.3 Upscale IC-LoRA by Zlikwid * Generative refinement LoRA for upscaling lower-res or soft videos * Works by bicubic upscaling first, then running through LTX 2.3 with this LoRA * Use prompt: upscale * LTX2.3-ICEdit-Insight by JoyFox Lab * Task-aware video restoration and editing model family * Supports: Video Restoration, HD Enhancement, Watermark Removal, Subtitle Removal * Singularity LTX-2.3 OmniCine by WarmBloodAban * Comprehensive optimizer for LTX2.3 I2V and First/Last Frame workflows * Features: Limb Evolution, Shot Injection, Natural Expression, Physical Integrity, Cross-Style Potential * Uses "Singularity" prompting framework with 7-block bilingual structure * yuvraj108c * LTX-2.3-22b-IC-LoRA-Any-Trajectory-Instruction - IC-LoRA porting Any Trajectory Instruction (ATI) to LTX-2.3; lets users draw motion paths on an input image and have the model generate videos following those trajectories (splines). Trained on 25 video pairs at 768x768x81 bucket size, 3000 steps. * zghhui * OmniNFT RL-LoRA - Modality-wise Omni Diffusion Negative-aware Fine-Tuning RL-LoRA for joint audio-video generation (paper arXiv:2605.12480). Provides both LTX-2 and LTX-2.3 variants. * LTX-2.3-OmniNFT-RL-LoRA (Kijai mirror) - Same OmniNFT RL-LoRA repackaged by Kijai in bf16 (588 MB). * VetoBugger * LTX2.3-CrispLora - Crisp enhancement LoRA for LTX-2.3 (LTX2.3_Crisp_Enhance.safetensors). * SyFeee * LTX-2.3 Dual-Character LoRA - Image-to-video character-consistency LoRA tuned for two-character dialogue scenes and multi-shot cinematic generation. Works for ancient Chinese fantasy, modern urban, and 3D anime styles. Recommended strength 0.7-0.9 standalone, 0.3-0.5 when stacked with style LoRAs. * WarmBloodAban * Singularity LTX-2.3 OmniCine V1 - Updated V1 of the OmniCine integrated optimization framework. Restructures LTX-Video 2.3 generation logic with focus on I2V, First/Last Frame, and Reference-to-Video workflows. Nearly 100,000 training steps. Includes Singularity-LTX-2.3_OmniCine_V1.safetensors (2.57 GB) and Singularity-LTX-2.3_OmniCine_V1nsf.safetensors (2.57 GB, NSF variant).

▣ Styles

• elismasilva
• Latin Dance - Latin dance motion/style LoRA for LTX-2.3 (rank ~128). (214 MB)
• OmerHagawa
• LTX2 UME PixelArt LoRA - Pixel art style LoRA for LTX-2
• Playtime-AI
• Commission LTX-2.3 MtF Transformation - MtF transformation style LoRA for LTX 2.3
• Andro0s
• Pixar Toon Style LoRA - Pixar-style CGI toon cinematic look with trigger word P1x4r
• Cseti
• Arcane-Jinx v1 - Style LoRA inspired by Arcane's Jinx character design
• ReStyle IC-LoRA - Image-guided style transfer IC-LoRA that re-renders videos in a target style while preserving original content and motion
• lopho
• Gantz O v1.0.0 - Movie-style LoRA (654 MB, 10000 steps)
• bionicman69
• Arnold Style - Arnold Style LoRA for LTX 2.3. Get to the choppa!
• Star Trek TNG Style - Star Trek: The Next Generation style LoRA for LTX 2.3
• joeygambino
• Surfaces Realism - Materials/realism LoRA (rank 32, video branch) that kills the "plastic" look: cracked wet asphalt stays cracked and wet, concrete gets pores and rust streaks, floors scuff, wood grains show. No trigger word — trains as unconditional LoRA behavior. Load at 1.0 and write prompts normally. (336 MB)
• CoachBate
• Abercrom-ME - Vintage A&F Quarterly americana style-transfer IC-LoRA: transforms an input photo (subject + clothing + scene) into moody monochrome / sun-drenched beach / locker-room aesthetics with full styling makeover. Image-conditioned; pairs with the bundled ABERCROM-ME IC-LoRA by coachbate-v3_20steps_3phase_3stage3.json workflow. (384 MB, 2000 steps)
• ssjenforcer191
• Homelander - Character IC-LoRA for The Boys' Homelander. Triggerword HeroHomelander (optionally append wearing red leather gloves / dark blue cape and ornate red-and-gold collar). Rank 64, 1500 steps, no regularization. Note: occasional letterbox black bars from training data. (~1.25 GB)
• oumoumad
• LTX-2-19b-LoRA-SPROUT
• Clay Stop Motion
• kabachuha
• Hydraulic press
• Cakeify
• Big Anime Breasts
• Eat
• Squish – One Hand Only
• POP! Inflatable Animation - Comically inflate and pop cartoon/anime characters into confetti and fabric scraps (I2V focused)
• CRT Animation Terminal by lovis93 - Real late-80s/early-90s CRT monitor look with scanlines, phosphor glow, chromatic aberration, and dithering. Trigger word: crtanim,. Available in 4000 and 10000 training steps variants
• vrgamedevgirl84 Style LoRAs
• ClayMationStyle - Clay animation style LoRA for LTX-2.3
• Wild West Style
• Paper Cut Out Style
• Post Apocalyptic Style
• Pixar Toon Style
• Luxe Sensual Style
• Soft Enhance Style
• Crisp Enhance Style
• Fantasy Puppet Style
• Fantasy Realism Style
• Fantasy Painterly Style
• Fantasy Anime Style
• Cozy Felt Style
• Clay Mation Style
• 90s Animation Style
• Alissonerdx LTX-LoRAs Collection - Comprehensive collection including:
• Anime2Half-Real - Converts anime-style content to half-realistic aesthetic (4500 steps, rank64)
• Edit-Anything Global - Global editing LoRA variants (6000-9000 steps, rank128)
• Inpaint Masked R2V/T2V - Region-based inpainting LoRAs for masked video editing
• Real2Anime/Anime2Real - Style conversion LoRAs (rank64)
• Nebsh
• Outfit Switch
• Handheld run
• Atomic Explosion
• HERO CAM
• Animatediff V1
• PUSH TO GLASS
• Object POV
• Squish
• Yoshiaki Kawajiri Retro Anime - LoRA trained on Yoshiaki Kawajiri's distinctive retro anime art style
• Playtime-AI
• DonaldTrump
• Rick_and_Morty - BETA LoRA for Rick and Morty animated style
• LTX-2.3-Rick_And_Morty_v2 - Updated Rick and Morty v2 LoRA trained on the Smith and Rick Sanchez characters (undertrained; voices/clothing can be off; v3 in training)
• LTX-2.3-Wednesday_Addams
• LTX-2.3-Kermit_the_Frog
• LTX-2.3-Jenna_Coleman
• LTX-2.3-Marge_Simpson - Marge Simpson character LoRA trained on the base LTX-2.3 Dev model. Trigger words: 2d animation, Marge Simpson (use 2d animation to avoid getting 3D animation)
• LTX-2.3-Bender - Bender (Futurama) character LoRA. Trigger words: 2d animation, Bender the bending robot
• LTX-2.3 Sulphur Gyrating Hips - Motion LoRA driven by the trigger She thrusts her hips in a sexual manner
• SOLRICKS
• LTX-2.3-Yesilcam-Turkish-Cinema - Nostalgic Yeşilçam Turkish cinema visual style with warm cinematic tones and classic film atmosphere. Recommended strength 0.7.
• ltx-2-3-ue5-style-lora - Unreal Engine 5 (UE5) cinematic style LoRA. Trigger word: ue5_style.
• Sci-Fi Cinema - a cinematic science-fiction style LoRA for LTXV / LTX-2.3. Trigger word: srx_scifilm.
• LTX-2.3 Product Ad Style - Cinematic product-commercial style for luxury / cosmetics / tech / fashion ads. Trigger srx_commercial, recommended strength 0.85.
• LTX-2.3 The Art of Marbling - Marbling / ebru ink-flow style (paper, pigment, fluid art, Turkish ebru). Trigger srx_ebrumotion, recommended strength 0.85.
• SyFeee
• ltx2.3-chinese-drama-charlora - Character LoRA trained on 78 episodes of Chinese historical drama; specialises base model for live-action, photoreal cinematic generation in Han dynasty / wuxia settings. Trigger words: char_0_person through char_9_person. Recommended strength 0.8–0.9.
• ltx2.3-chinese-drama-iclora-canny - IC-LoRA conditioning on Canny edge/line-art video; controls scene composition and architectural layout from reference outlines. Use with char_0_person for character reference.
• ltx2.3-chinese-drama-iclora-depth - IC-LoRA conditioning on monocular depth video (Depth-Anything-3); transfers 3D geometric structure from reference to generated video. Strong on interior scenes.
• ltx2.3-chinese-drama-iclora-pose - IC-LoRA conditioning on DWPose 133-keypoint skeleton render; transfers pose from reference video while preserving Chinese drama style. Stackable with character LoRA.
• LTX-2.3-SyFe-ID-LoRA - Identity (ID) LoRA for LTX-2.3 that preserves subject likeness / identity across frames. Two checkpoints (id_lora_ours_768, id_lora_ours_704), 1.16 GB each.
• LTX-2.3-SyFe-Plain-AV-LoRA - Plain audio/video LoRA for LTX-2.3. Multiple checkpoints: production v1/v2 and bilingual (704) at ~0.86/0.43 GB, plus a unified v5 at 0.11 GB.
• mxturbo
• Formula1-Cockpit-T-Cam-LTX2.3 - LoRA trained on 1.6L V6 Turbo Hybrid Era F1 T-Cam onboard footage. Generates cockpit/T-cam onboard video. Trigger: 16LV6HybridF1 (car type); follow the "T-cam onboard view..." / "AT-cam onboard view..." prompt style.
• chsengni
• ltx2.3-fpv-motion - Smoother FPV (First Person View) camera movements and improved low-speed flight shots.
• EllaPriest45 — three large LTX-2.3 LoRA collections (NSFW / characters / styles); open each repo for the full file list
• LTX2.3_Actions — Huge collection of NSFW LoRAs for LTX-2.3 (179 .safetensors, ~137 GB): explicit action / motion / pose LoRAs. Pairs with 10Eros / Sulphur-2.
• LTX2.3_Characters — Character LoRAs: massive per-celebrity likeness collection for LTX-2.3 (394 .safetensors, ~130 GB; each Name - LTX2.3.safetensors ~327 MB).
• LTX2.3_Styles — Style LoRAs: large visual-style collection for LTX-2.3 (35 .safetensors, ~20 GB): anime, claymation, cyberpunk, post-apocalyptic, cozy felt, and more.
• Se0ulSeeker LTX-2.3 i2v NSFW LoRAs — A collection / list of NSFW i2v (image-to-video) LoRAs for LTX-2.3 (NSFW content only — do not use for clean content).
• lynaNSFW DR34ML4Y AIO NSFW LTX-2.3 — AIO (all-in-one) NSFW LoRA collection for LTX-2.3 with three versions (V1 / V2 / V3), 1.94 GB each (NSFW content only — do not use for clean content).
• TheBurgstall
• LTX-2.3-Body-Positivity
• LTX-2.3-Googly-Eyes
• TheBurgstall (LTX-2)
• EarthZoomOut
• GroupPhoto
• WHATUSEE
• Black Venom
• Levmar
• ltx2-lora — Image-to-Video LoRA fine-tuned from ltx-2.3-22b-dev.safetensors with the LTX LoRA Trainer (6000 steps, LR 1e-4, batch 1). Two checkpoints: lora_weights_step_02000.safetensors and lora_weights_step_06000.safetensors (~428 MB each). License: other.
• Lightricks
• Camera Control: dolly-in
• Camera Control: dolly-left
• Camera Control: dolly-out
• Camera Control: dolly-right
• Camera Control: jib-down
• Camera Control: jib-up
• Camera Control: static
• Union-Control
• eraRelentless
• LTXreal - Realism stylization for LTX-2.3; trigger realism
• nnndite
• ltx2.3 Foot Model - Foot / lower-limb LoRA for LTX-2.3
• fal
• LTX-2.3 IC-LoRA — 3D Render to Photoreal - IC-LoRA turning rough 3D viewport / Blender blockouts into photoreal cinematic video while preserving composition and camera. Trigger 3DREAL. v2 (3DREAL-strong-v2) is the newest and is also exposed on fal.ai as render-to-real.
• a3xrfgb
• Fable 5 — Vintage Style LoRA - Vintage-style minimal-illustration / stop-motion / typography LoRA for LTX-2.3, used in the Fable 5 intro. Trained on a personal RTX 3090 (~5 hours).

▣ Special

• Wan2.1 VAE Adapter
• Latent space adapter for converting between LTX-2 and Wan2.1 VAE representations
• latent_adapter_final.pt (447 MB)
• TenStrip
• LTX2.3 JoyAI LoRA Extracted - LoRA extracted from jdopensource/JoyAI-Echo; boosts prompt response and motion in LTX-2.3 (also used for NSFW/Sulphur/Eros) at strength 0.4–0.7.
• DMD LoRA (r256) - DMD-distillation delta extraction from JoyAI-Echo, reshaped for rank-256 sampling. Use at 1.0 with 8/4-step upscale or experiment with other sigmas; any euler or LTX-compatible sampler. No custom loading needed. (4.86 GB)
• DMD LoRA Hybrid v1 - Hybrid DMD distillation: works inside blocks 0-25 to increase movement strength above the standalone DMD without letting the LTX distilled LoRA redraw or bring negative base-model tendencies. Improves movement smoothness and consistency. (4.86 GB)
• DMD LoRA Hybrid v2 - v2 of the hybrid DMD distillation. (4.86 GB)
• ltx-community
• ltx2-compile-keytest - IC-LoRA fine-tune from ltx-2.3-22b-dev.safetensors (300 training steps, batch size 1, LR 2e-4). Trained with the LTX LoRA Trainer.
• zzmicer
• Sax - Saxophone audio LoRA (video-only, no-audio conditioning) at 4000 steps. (403 MB)
• Violin (8s) - Violin audio LoRA trained on 8-second clips at 3000 steps. (856 MB)
• Guitar - Acoustic guitar audio LoRA at 3000 steps. (1.71 GB)
• DJ - DJ/electronic-music audio LoRA (rank 128, LR 5e-4) at 1800 steps. (1.71 GB)
• Lightricks
• LTX-2.3-22b-LoRA-Foley-V2A - Official Lightricks Foley V2A (video-to-audio) LoRA for LTX-2.3. Generates realistic, visually-synced Foley sound effects from video. Rank ~small (216 MB); pairs with the workflow JSON in the repo (ltx-2.3-foley-v2a.json).
• LTX-2.3-22b-IC-LoRA-Clean-Plate - Official Lightricks Clean-Plate IC-LoRA. Removes people/objects from video frames for steady background plates. Rank 128 (312 MB); pairs with the LTX-2.3_-_V2V_mass_remove_people_Clean-Plate-Lora.json workflow.
• LTX-2.3-22b-IC-LoRA-Relight - Official Lightricks Relight IC-LoRA (single-stage, distilled). Relights a scene using a reference sphere image that defines the target lighting direction and color. Pairs with the bundled LTX-2.3_Relight_ICLoRA_SingleStage_Distilled.json workflow. (312 MB)
• LTX-2.3-22b-IC-LoRA-Cross-Eyed - Official Lightricks Cross-Eyed IC-LoRA v0.9. Converts standard video into side-by-side 3D stereo output (cross-eyed viewing). (327 MB)
• LTX-2.3-22b-IC-LoRA-Colorization - Official Lightricks Colorization IC-LoRA v0.9. Adds realistic color to B&W or desaturated input video. (906 MB)
• LTX-2.3-22b-IC-LoRA-Deblur - Official Lightricks Deblur IC-LoRA v0.9. Removes blur and restores sharp, focused video. (906 MB)
• LTX-2.3-22b-IC-LoRA-Decompression - Official Lightricks Decompression IC-LoRA v0.9. Removes MP4 compression artifacts (banding, mosquito noise) and restores clean video. (906 MB)
• LTX-2.3-22b-IC-LoRA-Water-Simulation - Official Lightricks Water-Simulation IC-LoRA v0.9. Adds physically-plausible fluid/water dynamics to reference video (reflections, ripples, splashes). (906 MB)
• LTX-2.3-22b-IC-LoRA-Instant-Shave - Official Lightricks Instant-Shave IC-LoRA v0.9. Removes facial hair in video-to-video. (654 MB)
• LTX-2.3-22b-IC-LoRA-In-Outpainting - Official Lightricks In-Outpainting IC-LoRA v0.9. Extends canvas in any direction from reference video, filling new regions with consistent scene content. (1.31 GB)
• LTX-2.3-22b-IC-LoRA-Day-To-Night - Official Lightricks Day-To-Night IC-LoRA v0.9. Converts daytime footage to nighttime with matched lighting/shadows. (327 MB)
• LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler - Official Lightricks Pixel-Spatial-Upscaler IC-LoRA for LTX-2.5. Adds x2 pixel-level spatial upscaling to a video pass. (0.30 GB)
• fbjr
• LTX-2.3-22b-IC-LoRA-Audio-Only-Context - Two IC-LoRA checkpoints for audio-only and cross-modal audio-video context conditioning on LTX-2.3. Audio-only checkpoint (156 MB, audio_only_step_01000.safetensors) preserves a reference audio identity through a generation pass; cross-modal checkpoint (276 MB, cross_modal_step_01000.safetensors) extends that to joint audio-video conditioning.
• FuzzPuppy
• LTX-2.3 Foley - Video-to-audio LoRA for LTX-2.3 that adds realistic, visually synchronized Foley / sound effects over a video (multiplier 1.0–3.0; pairs with the LTX Community License).
• Black Magic - Video-to-video IC-LoRA for low-light / shadow reconstruction. Restores underexposed footage to natural, well-exposed video with realistic colors and recovered shadow detail. Pairs with the bundled ltx23-black-magic-lora-workflow.json. (312 MB)
• Hoffm4nz
• LTX-2.3-22b-IC-LoRA-Golden-Hour - IC-LoRA fine-tune that biases generation toward warm "Golden Hour" lighting aesthetics. Root canonical checkpoint ltx-2.3-22b-ic-lora-golden-hour.safetensors (312 MB); four per-step snapshots are also available in the checkpoints/ folder of the repo (step_00250 → step_01000, 312 MB each).
• JanKanta

• LensRemover - Video-to-video IC-LoRA that removes lens flares, veiling glare, lens dirt, and other optical artifacts from footage while keeping the underlying scene intact. Dual-encoding: works on both sRGB/Rec.709 and ARRI LogC3 inputs (selected via trigger word). Pairs with the bundled LensRemover_comfyui_workflow.json. (312 MB)

• vpakarinen

• Motion Stabilizer for LTX-2.3 - Motion LoRA stabilises body movement and rotation in LTX-2.3.
• Comfy-Org
• ltx-2.3-22b-ic-lora-ingredients-0.9 - Comfy-Org-distributed ingredients IC-LoRA for LTX-2.3 (the other three siblings in the same folder — id-lora-celebvhq-3k, id-lora-talkvid-3k, distilled_1.1_lora_dynamic_fro09_avg_rank_111_bf16 — are already linked from the Checkpoints / ID-LoRA tables).
• linoyts
• ltx2.3-ic-lora-ingredients-multishot - IC-LoRA fine-tune from ltx-2.3-22b-dev.safetensors (2,500 training steps, LR 1e-4). Trained for multi-shot ingredient-conditioned generation.
• ltx2-ic-lora-ui - LoRA fine-tune from ltx-2.3-22b-dev.safetensors (20 training steps; treats UI-screen aesthetics). Inherits LTX-2.3 base license.
• rzgar
• Motion Enhancer (N54W) - General-purpose N54W motion enhancer LoRA. Enhances fluidity, coherence, and motion when stacked as a companion LoRA alongside other specialized models. Extensively tested with top-rated Civitai LoRAs. (2.17 GB)
• Distilled LoRA 384-1.1 "n4w" — Modified official 384-1.1 distilled LoRA that cooperates with N54W LoRAs (instead of fighting them), improving motion and appearance. Two variants: full rank ~7.08 GB (ltx-2.3-22b-distilled-lora-384-1.1_n4w.safetensors) and low-VRAM rank-128 ~2.40 GB (ltx-2.3-22b-distilled-lora-384-1.1_rank_128_n4w.safetensors). Use at strength 0.5–0.65 stacked with your N54W LoRA. Apache-2.0.
• joeygambino
• American Accent (audio) - Audio-branch LoRA (rank 32) that makes accent wording in prompts actually work. LTX-2.3's voice prior ignores accent requests in certain regions (e.g. young female characters default to Australian); this LoRA turns accent prompts into reliable control. Requires 24 fps — off-24 fps overrides accent wording entirely. (168 MB)

▣ ID-LoRA (Identity-Driven In-Context LoRA)

ID-LoRA is a method that enables identity-preserving audio-video generation in a single model. It jointly generates a subject's appearance and voice, letting a text prompt, a reference image, and a short audio clip govern both modalities together. Built on top of LTX-2.3 (22B), it is the first method to personalize visual appearance and voice within a single generative pass.

Unlike cascaded pipelines that treat audio and video separately, ID-LoRA operates in a unified latent space where a single text prompt can simultaneously dictate the scene's visual content, environmental acoustics, and speaking style—while preserving the subject's vocal identity and visual likeness.

Key Features: - Text prompt controls the scene and content - Reference image preserves the subject's visual likeness - Short audio clip preserves the subject's vocal identity - Single unified generation pass for both appearance and voice

Available LoRAs for LTX-2.3:

LoRA	LoRA Rank	Size	Download
ID-LoRA-TalkVid-3K	128	1.1 GB	┊
ID-LoRA-CelebVHQ-3K	128	1.1 GB	┊

Resources: - Project Page | GitHub | Paper (arXiv: 2603.10256)

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ ComfyUI Nodes

▣ Custom Node Collections

• 10S-Comfy-nodes by TenStrip - Custom ComfyUI nodes for improving motion quality when working with LTX 2.3's combined audio/video latent pipeline. Includes Latent Cross Fade Auto Concat, Audio Latent Stretch, Latent Motion Sharpener, Latent Temporal Upsampler, Latent Motion Retime, and Latent Temporal Inpainter for clean 30fps output from 24fps sampled models.

• Deno Custom Nodes by Deno2026 - Practical ComfyUI custom nodes focused on fast real-world workflow improvements including (Deno) Resize Box, Multi Image Loader, LTX Sequencer, LTX Model Loader, Easy Model Download Helper, LTX Multi LoRA Loader, and LTX Prompt Guide.

• PromptRelay by kijai - Enables consistent multilingual lip-sync while maintaining voice consistency across languages. Distributes video latent frames across segments with smart prompt node supporting inline and block syntax styles.

• WhatDreamsCost ComfyUI by WhatDreamsCost - LTX Director 2.0 plus a variety of custom ComfyUI nodes and workflows for creating AI-generated video content including Multi Image Loader, LTX Sequencer, LTX Keyframer, Speech Length Calculator, Load Video UI, and Load Audio UI. 1.7k+ stars.

• ComfyUI-Sapiens2 by kijai - ComfyUI nodes for Sapiens2 computer vision models from Facebook Research. Supports pose estimation, body-part segmentation, surface normal estimation, and pointmap estimation with model variants from 400M to 5B parameters.

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ LoRA Training

For training LTX LoRAs, the community uses a variety of official scripts, community-developed forks, and cloud-based platforms.

Primary Local Training Tools

• Official LTX-2 Trainer: This is the standard Python-based package for training LoRAs, full fine-tuning, and In-Context (IC) LoRAs. It is designed for Linux and requires CUDA and Triton.
  • Link: Official LTX-2 Trainer Repository
• Musubi-Tuner (AkaneTendo25 Fork): Widely considered the fastest and most efficient local trainer for LTX-2 and 2.3. It features significantly smaller cache sizes (up to 12x smaller than AI Toolkit) and better iteration speeds, reaching up to 2 iterations per second on an RTX 5090.
  • Link: AkaneTendo25 Musubi-Tuner Fork
• AI Toolkit (by Ostris): A popular third-party tool that supports LTX-2 character and image-to-video LoRAs. While beginner-friendly, some users reported issues with audio training on the main branch.
  • Link: Official AI Toolkit Repository
• AI Toolkit: BIG-DADDY-VERSION (ArtDesignAwesome Fork): This specific fork was created to fix broken audio and voice training in the original AI Toolkit. It is optimized for hardware like the RTX 5090.
  • Link: ArtDesignAwesome AI Toolkit Fork
• rs-nodes (richservo): A collection of nodes that includes a full LTX Lora trainer directly within ComfyUI. It is designed to be memory-efficient, allowing training on cards with as little as 11GB-12GB of VRAM by using ComfyUI's native weight loaders.
  • Link: rs-nodes ComfyUI Trainer
• SimpleTuner: A highly optimized trainer for Linux that supports LTX-2 and is noted for its ability to handle larger datasets on limited VRAM via block swapping.
  • Link: SimpleTuner Repository

Cloud Training Platforms

• Fal.ai: Provides a dedicated cloud trainer for custom styles and effects, though it is primarily limited to image-based training datasets.
  • Link: Fal.ai LTX2 Video Trainer
• RunComfy: A cloud service that offers a pre-configured AI Toolkit setup specifically for LTX-2 training.
  • Link: RunComfy LTX-2 Training

Essential Dataset & Captioning Tools

• Taz's Ultimate Captioning Tool: A Hugging Face space frequently used by the community to generate the long, detailed, cinematographic prompts (around 200 words) that LTX-2 requires for high-quality training.
  • Link: LoRA Caption Assistant (Hugging Face)
• AI Video Clipper & LoRA Captioner: A modular pipeline designed to automate local dataset creation using WhisperX and Qwen2-VL, including support for RTX 5090 Blackwell cards.
  • Link: AI Video Clipper & LoRA Captioner

Training Requirements Summary

• Dataset: Videos should typically be cut to 121 frames (exactly 4.84 seconds) to align with the model's architectural "8n+1" rule.
• Hardware: While 16GB VRAM is possible with extreme offloading in tools like rs-nodes, 24GB is the practical minimum for quantized training. For best results and speed, 48GB to 80GB (H100 or RTX 6000) is preferred.
• Precision: It is now officially recommended to train on the full BF16 model for LTX 2.3 rather than FP8 for superior quality.

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

▓ Workflow & Technical Notes

❖ RuneXX

RuneXX LTX-2.3 Workflows:

• I2V T2V Basic
• I2V T2V Basic GGUF
• I2V T2V Dev Full-Steps
• I2V T2V Simple Single Pass
• T2V Basic
• T2V Simple Single Pass

Movie-Maker:

• I2V Short-Story PromptRelay-Timeline multi-image multi-sequence
• I2V Short-Story PromptRelay multi-image multi-sequence
• I2V T2V Short-Story PromptRelay-Timeline multi-sequence
• I2V T2V Short-Story PromptRelay multi-sequence

Multi-ref-character-sheet:

• I2V Multi-subject Reference Licon-MSR V1-lora (older version)
• I2V Multi-subject Reference Licon-MSR V2 LTX-Ingredients OmniNTF Experimental
• I2V Multi-subject Reference Licon-MSR V2-lora
• T2V/R2V Character Sheet Best-Face-ID LoRA
• T2V/R2V Face-ref + audio-ref Best-Face-ID LoRA + ID-LoRA audio
• T2V/R2V Face-ref + custom audio Best-Face-ID LoRA
• T2V/R2V Face-ref image only Best-Face-ID LoRA

Helper-wf:

• Flux-Klein Character Sheet from ref image
• Ideogram Reference Sheet for Ingredients LoRA
• Qwen-Image Character Sheet from ref image ZIT refiner

Talking-Avatar-TTS:

• I2V T2V Talking Avatar (Qwen-TTS)
• I2V T2V Talking Avatar (Fish-Audio-Pro)
• I2V T2V Talking Avatar (OmniVoice-TTS)

Video-2-Video:

Just-Talk — add voice to silent video: * V2V Just Talk Prompt Lip-synced Voice * V2V Just Talk Prompt Lipsynced Voice Sam3 * V2V Just Talk Custom Audio Lip-synced To Any Video * V2V Just Talk Dub Any Silent Video Multilanguage

Extend-Any-Video: * V2V Extend Any Video * V2V Extend Any Video Multi-Extend Long Video * V2V Extend Any Video towards Last-Frame-image

Inpaint: * V2V Inpainting Inpaint-T2V-lora Sam3-Masking * V2V Inpainting Inpaint-T2V-lora Sam2-Point-Masking

Shot-to-Shot-Transition: * V2V Shot-to-Shot Transition Systms-FLW-lora * V2V Shot-to-Shot Transition MergeGreen IC-Lora * V2V Shot-to-Shot Transition Re-Take Inpaint

Other: * V2V Remove Watermark Subtitles ICEdit-Insight-lora * V2V Expand Any Video IC-Lora-Outpaint * V2V Foley Add Sound To Any Video (Foley-Lora) * V2V ReTake recreate any section of any video * V2V Video-Edit remove add replace restyle EditAnything-Lora * V2V High Dynamic Range IC-HDR-lora * V2V Just-Dub-It Multilanguage Dubbing IC-Lora-LipDub * V2V Change Viewpoint Angle CrossView-Lora * V2V Upscale Any Video Pixel-Spatial-Lora * V2V Mass Remove People Clean-Plate-Lora

Music-Video-Creator:Music-Video-Creator: * I2V T2V Music-Video multi-scene full render * I2V T2V Music-Video multi-scene save per segment * I2V T2V Music-Video Prompt-Relay multi-scene save per segment * Helper-Workflows: * AceStep-XL create music from a prompt * Flux-Klein transform firstframe * Qwen-Image transform firstframe next scene or different angle LoRA * Video merge combine with interpolate upscale

Others: * I2V T2V Basic custom audio with Gemma-API example

Custom-Audio:

• I2V T2V Basic ID-Lora Reference Audio
• I2V T2V Dev Custom Audio
• I2V T2V Basic Custom Audio

First-Last-Frame: * First-Last-Frame Workflows * FLF2V First Last Frame * FLF2V First Last Frame Custom Audio * FLF2V First Last Frame Transition LoRA * FML2V First Middle Last Frame Guider * FML2V First Middle Last Frame Injection * FML2V Guider Custom Audio

Long-Video-Experimental:

• I2V T2V Long Video Custom Audio Loop
• I2V T2V Long Video Custom Audio
• I2V T2V Long Video Custom Audio singlepass loop

3-Pass-Experimental:

• I2V T2V Experimental 3-pass 1.5x Upscaler
• I2V T2V DEV Experimental 3-Pass

Control-reference:

• I2V TV2V Transfer Camera Movements IC-Cameraman LoRA
• I2V TV2V Transfer Body Movements IC-Union-Control-lora DWPose
• I2V TV2V Transfer Body Movements IC-Union-Control-lora SDPose
• I2V TV2V Transfer Body Movements IC-RealisDance-lora

Helper-Workflows:

• AceStep-XL Create Music From a Prompt
• Flux-Klein Transform Firstframe
• Qwen-Image Transform Firstframe Next Scene or Different Angle LoRA

Other-examples:

• I2V T2V Basic Custom Audio with Gemma-API

═══●═══●═══●═══●═══●═══●═══●═══●═══

❖ Lightricks

LTX-2.3: * ICLoRA Motion Track Control * Union Control * Single Stage * Two Stage

LTX-2: * Text to Video Full * Text to Video Distilled * Image to Video Full * Image to Video Distilled * ICLoRA * Video to Video * Video to Video Detailer

❖ vrgamedevgirl84

vrgamedevgirl84 LTX 2.3 Music Video Creator:

• Music Video Creator Workflow
• Prompt Creator Workflow - Audio upload, beat detection, scene timing, lyrics analysis, style selection, prompt generation
• Text-to-Video Workflow - LoRA integration, advanced prompt controls, Remake Mode, video stitching
• Image-to-Video Workflow - Uses Z-Image Turbo and LTX 2.3
• Requirements: ComfyUI, LTX 2.3 models, Z-Image Turbo model, FFmpeg, vrgamedevgirl custom nodes

❖ ComfyUI

• Text-to-video
• Text-to-video Distilled (faster, 8 steps)
• Image-to-video
• Image-to-video Distilled (faster, 8 steps)
• Depth control
• Canny control
• Pose control