Skip to content

wildminder/awesome-ltx2

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

59 Commits
LTX2-prompt-guide.md
LTX2-prompt-guide.md
 
 
README.md
README.md
 
 
ltx2-basics.md
ltx2-basics.md
 
 

Repository files navigation

Awesome LTX-2

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

ltx-logo

Intro

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:

Models

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

Checkpoints

Ver Name Precision Size Download
2.3 ltx-2.3-22b dev bf16 46.1 GB
2.3 ltx-2.3-22b dev fp8 29.1 GB
2.3 ltx-2.3-22b dev fp8 29.9 GB
2.3 ltx-2.3-22b dev int8 29.1 GB
2.3 ltx-2.3-22b dev nvfp4 21.7 GB
2.3 ltx-2.3-22b dev fp8 29.1 GB
2.3 ltx-2.3-22b distilled bf16 46.1 GB
2.3 ltx-2.3-22b distilled fp8 29.5 GB
2.3 ltx-2.3-22b distilled fp8 29.9 GB
2.3 ltx-2.3-22b distilled int8tensormixed 29.1 GB
2.3 ltx-2.3-22b distilled nvfp4 17.6 GB
2.3 ltx-2.3-22b distilled mxfp8mixed 29.7 GB
2 ltx-2-19b dev bf16 43.3 GB
2 ltx-2-19b dev fp8 27.1 GB
2 ltx-2-19b dev fp4 20 GB
2 ltx-2-19b distilled bf16 43.3 GB
2 ltx-2-19b distilled fp8 27.1 GB
2 ltx-2-19b distilled nvfp4 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 fp8_e5m2 27.1 GB

Distilled LoRA

Ver Rank Precision Size Download
2.3 384 bf16 7.61 GB
2.3 208 bf16 4.97 GB
2.3 159 bf16 3.83 GB
2.3 105 bf16 2.59 GB
2 384 bf16 7.67 GB
2 242 bf16 4.88 GB
2 175 bf16 3.58 GB
2 175 fp8 1.79 GB

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
2.3 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
2.3 temporal-upscaler x2 1.0 262 MB
2 temporal-upscaler x2 1.0 262 MB

══════════════════════════════════

GGUF Quantized Models

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

QuantStack

QuantStack LTX-2.3

Model Quant Size Download
ltx-2.3-22b Q2_K 12.4 GB dev ┊ distilled
ltx-2.3-22b Q3_K_M 14.7 GB dev ┊ distilled
ltx-2.3-22b Q3_K_S 14 GB dev ┊ distilled
ltx-2.3-22b Q4_K_M 17.8 GB dev ┊ distilled
ltx-2.3-22b Q4_K_S 16.7 GB dev ┊ distilled
ltx-2.3-22b Q5_K_M 19.4 GB dev ┊ distilled
ltx-2.3-22b Q5_K_S 18.5 GB dev ┊ distilled
ltx-2.3-22b Q6_K 21 GB dev ┊ distilled
ltx-2.3-22b Q8_0 25.5 GB dev ┊ distilled

QuantStack LTX-2

Model Quant Size Download
LTX-2-dev Q2_K 8.03 GB
LTX-2-dev Q3_K_M 10.3 GB
LTX-2-dev Q3_K_S 9.57 GB
LTX-2-dev Q4_K_M 13.4 GB
LTX-2-dev Q4_K_S 12.3 GB
LTX-2-dev Q5_K_M 15 GB
LTX-2-dev Q5_K_S 14.2 GB
LTX-2-dev Q6_K 16.6 GB
LTX-2-dev Q8_0 21.1 GB
Unsloth

Unsloth LTX-2.3 GGUF

Model Quant Size Download
ltx-2.3-22b BF16 42 GB dev ┊ distilled
ltx-2.3-22b F16 42 GB dev ┊ distilled
ltx-2.3-22b Q2_K 8.28 GB dev ┊ distilled
ltx-2.3-22b Q3_K_M 10.8 GB dev ┊ distilled
ltx-2.3-22b Q3_K_S 9.95 GB dev ┊ distilled
ltx-2.3-22b Q4_0 12.7 GB dev ┊ distilled
ltx-2.3-22b Q4_1 13.8 GB dev ┊ distilled
ltx-2.3-22b Q4_K_M 14.3 GB dev ┊ distilled
ltx-2.3-22b Q4_K_S 13.1 GB dev ┊ distilled
ltx-2.3-22b Q5_0 15.3 GB dev ┊ distilled
ltx-2.3-22b Q5_1 16.3 GB dev ┊ distilled
ltx-2.3-22b Q5_K_M 16.1 GB dev ┊ distilled
ltx-2.3-22b Q5_K_S 15.2 GB dev ┊ distilled
ltx-2.3-22b Q6_K 17.8 GB dev ┊ distilled
ltx-2.3-22b Q8_0 22.8 GB dev ┊ distilled
ltx-2.3-22b UD-Q2_K 8.98 GB dev ┊ distilled
ltx-2.3-22b UD-Q3_K_M 11.8 GB dev ┊ distilled
ltx-2.3-22b UD-Q3_K_S 10.5 GB dev ┊ distilled
ltx-2.3-22b UD-Q4_K_M 15.1 GB dev ┊ distilled
ltx-2.3-22b UD-Q4_K_S 13.7 GB dev ┊ distilled
ltx-2.3-22b UD-Q5_K_M 17.1 GB dev ┊ distilled
ltx-2.3-22b UD-Q5_K_S 15.8 GB dev ┊ distilled

Unsloth LTX-2 GGUF

Model Quant Size Download
ltx-2-19b-dev BF16 37.8 GB
ltx-2-19b-dev F16 37.8 GB
ltx-2-19b-dev UD-Q2_K_L 10.1 GB
ltx-2-19b-dev UD-Q2_K_XL 11.6 GB
ltx-2-19b-dev Q2_K 8.1 GB
ltx-2-19b-dev Q3_K_L 10.7 GB
ltx-2-19b-dev Q3_K_M 10.1 GB
ltx-2-19b-dev Q3_K_S 9.47 GB
ltx-2-19b-dev Q4_0 11.3 GB
ltx-2-19b-dev Q4_1 12.3 GB
ltx-2-19b-dev Q4_K_M 12.8 GB
ltx-2-19b-dev Q4_K_S 11.9 GB
ltx-2-19b-dev Q5_0 13.7 GB
ltx-2-19b-dev Q5_1 14.6 GB
ltx-2-19b-dev Q5_K_M 14.3 GB
ltx-2-19b-dev Q5_K_S 13.6 GB
ltx-2-19b-dev Q6_K 16 GB
ltx-2-19b-dev Q8_0 20.4 GB
Vantage

Vantage AI GGUFs

Model Quant Size Download
ltx-2-19b-dev Q3_K_M 9.96 GB
ltx-2-19b-dev Q3_K_S 9.28 GB
ltx-2-19b-dev Q4_0 11.6 GB
ltx-2-19b-dev Q4_1 12.4 GB
ltx-2-19b-dev Q4_K_M 12.8 GB
ltx-2-19b-dev Q4_K_S 11.8 GB
ltx-2-19b-dev Q5_0 13.6 GB
ltx-2-19b-dev Q5_1 14.5 GB
ltx-2-19b-dev Q5_K_M 14.4 GB
ltx-2-19b-dev Q5_K_S 13.5 GB
ltx-2-19b-dev Q6_K 15.9 GB
ltx-2-19b-dev Q8_0 20.4 GB
ltx-2-19b-distilled Q3_K_M 9.96 GB
ltx-2-19b-distilled Q3_K_S 9.28 GB
ltx-2-19b-distilled Q4_0 11.6 GB
ltx-2-19b-distilled Q4_1 12.4 GB
ltx-2-19b-distilled Q4_K_M 12.8 GB
ltx-2-19b-distilled Q4_K_S 11.8 GB
ltx-2-19b-distilled Q5_0 13.6 GB
ltx-2-19b-distilled Q5_1 14.5 GB
ltx-2-19b-distilled Q5_K_M 14.4 GB
ltx-2-19b-distilled Q5_K_S 13.5 GB
ltx-2-19b-distilled Q6_K 15.9 GB
ltx-2-19b-distilled Q8_0 20.4 GB

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

Text Encoders

LTX-2 requires Gemma-3-12b variants. LTX-2.3 uses text projection layers.

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-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

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-Abliterated

Fixed versions of the abliterated Gemma-3-12b-it model by FusionCow, modified specifically for compatibility with LTX-2. The original model

Model Precision Size Download
Gemma ablit fixed bf16 23.5 GB
Gemma ablit fixed fp8 13.8 GB
Gemma 3 12B IT Heretic

Models by DreamFast

Safetensors

Model Precision Size Download
Gemma_3_12B_it Heretic bf16 23.5 GB
Gemma_3_12B_it Heretic fp8 12.8 GB

GGUF

Quant Size Quality Recommendation Download
F16 22GB Lossless Reference, same as original
Q8_0 12GB Excellent Best quality quantization
Q6_K 9.0GB Very Good High quality, good compression
Q5_K_M 7.9GB Good Balanced quality/size
Q5_K_S 7.7GB Good Slightly smaller Q5
Q4_K_M 6.8GB Good Still useful
Q4_K_S 6.5GB Decent Smaller Q4 variant
Q3_K_M 5.6GB Acceptable For very low VRAM only
Sikaworld1990 Gemma-3-12b Abliterated

NVFP4 quantization variants by Sikaworld1990 optimized for Blackwell GPUs.

Model Precision Size Download
Gemma-3-12b QAT Abliterated FP4 NVFP4-HF 12.1 GB
Gemma-3-12b QAT Abliterated FP4 NVFP4-Pure 8.91 GB
Gemma-3-12b HereticX Abliterated bf16 15 GB
Gemma-3-12b High-Fidelity Abliterated bf16 14.1 GB
  • FP4-HF: High-fidelity mixed precision calibration
  • FP4-Pure: Pure FP4 quantization for maximum compression
  • HereticX: Uncensored variant with maximum prompt fidelity
  • High-Fidelity: Optimized for quality with better detail preservation

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

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 bf16 42 GB
2.3 ltx-2.3-22b dev fp8 23.5 GB
2.3 ltx-2.3-22b dev fp8_input_scaled 25 GB
2.3 ltx-2.3-22b distilled bf16 42 GB
2.3 ltx-2.3-22b distilled fp8_input_scaled 23.5 GB
2.3 ltx-2.3-22b distilled v2 fp8_input_scaled v2 23.2 GB
2.3 ltx-2.3-22b distilled fp8 23.5 GB
2.3 ltx-2.3-22b distilled (experimental) mxfp8 24.1 GB
2 ltx-2-19b dev bf16 37.8 GB
2 ltx-2-19b dev fp8 21.6 GB
2 ltx-2-19b dev fp4 14.5 GB
2 ltx-2-19b distilled bf16 37.8 GB
2 ltx-2-19b distilled fp8 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
2.3 Video VAE BF16 1.45 GB ┊
2.3 Audio VAE BF16 365 MB ┊
2 Video VAE BF16 2.45 GB
2 Audio VAE BF16 218 MB

Embedding Connectors & Text Projection

Ver Name Precision Size Download
2.3 Embeddings Connectors dev bf16 2.31 GB ┊
2.3 Embeddings Connectors distilled bf16 2.31 GB
2 Connector dev bf16 2.86 GB
2 Connector distilled bf16 2.86 GB

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

LoRA

Enchancer, special

Styles

Special

  • Wan2.1 VAE Adapter
    • Latent space adapter for converting between LTX-2 and Wan2.1 VAE representations
    • latent_adapter_final.pt (447 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:

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

Workflow & Technical Notes

Lightricks official WF:

LTX-2.3:

LTX-2:

ComfyUI official WF:

RuneXX LTX-2.3 Workflows:

Text-to-Video (T2V):

Workflow
T2V Basic
T2V Single Pass

Image-to-Video / Text-to-Video (I2V/T2V):

Workflow
I2V T2V Basic
I2V T2V Basic Custom Audio
I2V T2V Basic GGUF
I2V T2V Basic ID-Lora Reference Audio
I2V T2V Dev Full-Steps
I2V T2V Single Pass
I2V T2V Talking Avatar (Fish-Audio-Pro)
I2V T2V Talking Avatar (Qwen-TTS)

Long Video:

Workflow
I2V T2V Long Video Custom Audio
I2V T2V Long Video Custom Audio Loop
I2V T2V Long Video Custom Audio Singlepass Loop

First-Last Frame Video (FL2V):

Workflow
FL2V Custom Audio
FL2V First Last Frame Injection

First-Middle-Last Frame Video (FML2V):

Workflow
FML2V First Middle Last Frame Guider
FML2V First Middle Last Frame Injection
FML2V Guider Custom Audio

Video-to-Video (V2V):

Workflow
V2V Extend Any Video
V2V Foley Add Sound To Any Video
V2V Just Talk Add Lipsynced Voice To Any Video
V2V ReTake Recreate Any Section Of Any Video
RuneXX LTX-2 Workflows old pre_feb2026
Workflow
First Last Frame (guide node)
First Last Frame (in-place node)
First Middle Last Frame (guide node)
I2V Basic (GGUF)
I2V Basic
I2V IC-Control (pose)
I2V Simple First Middle Last Frame (1-pass K-Sampler)
I2V Talking Avatar (voice clone Qwen-TTS)
I2V and T2V (beta test sampler previews)
I2V and T2V Basic (Custom Audio)
I2V and T2V IC-Control (All-In-One Pose Canny Depth)
I2V and T2V Simple (1-pass K-Sampler)
I2V and T2V Simple (1-pass)
T2V Basic (GGUF)
T2V Basic (low vram)
T2V Basic
T2V Talking Avatar (voice clone Qwen-TTS)
V2A Foley (add sound to any video)
V2V (extend any video)
V2V Head Swap Experimental (BFS lora)
V2V Just Dub It (experimental)(translate speech auto dubbing)
V2V Just Dub It (with voice clone)(auto dubbing translation)(experimental)

About

All available LTX-2 models, encoders, workflows, LoRAs for ComfyUI

Topics

video ai model lora itv video-ai t2v comfyui ltxv ltx-2

Resources

Readme
Activity

Stars

270 stars

Watchers

12 watching

Forks

21 forks
Report repository

Contributors 1