Awesome LTX-2

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

Intro

• LTX-2: A New Chapter in Generative AI

• ComfyUI official blogpost

• Prompting Guide for LTX-2

• »» LTX-2 in ComfyUI Chattable KB

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.

Name	Precision	Size	Download
ltx-2-19b dev	bf16	43.3 GB	Lightricks
ltx-2-19b dev	fp8	27.1 GB	Lightricks
ltx-2-19b dev	fp4	20 GB	Lightricks
ltx-2-19b distilled	bf16	43.3 GB	Lightricks
ltx-2-19b distilled	fp8	27.1 GB	Lightricks
ltx-2-19b distilled	nvfp4	20 GB	szwagros

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

Name	Precision	Size	Download
ltx-2-19b dev	fp8_e5m2	27.1 GB	Lightricks

Distilled LoRA

Rank	Precision	Size	Download
384	bf16	7.67 GB	Lightricks
242	bf16	4.88 GB	Lightricks
175	bf16	3.58 GB	Lightricks
175	fp8	1.79 GB	Lightricks

Spatial Upscaler

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

• ltx-2-spatial-upscaler-x2-1.0.safetensors

Temporal Upscaler

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

• ltx-2-temporal-upscaler-x2-1.0.safetensors

══════════════════════════════════

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

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

Unsloth

Unsloth GGUFs

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

Vantage

Vantage AI GGUFs

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

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

Text Encoders

LTX-2 requires Gemma-3-12b variants.

Comfy-Org Optimized Encoders

Official and optimized versions for ComfyUI.

Model Name	Size	Download
gemma_3_12B_it.safetensors	24.4 GB	ComfyUI
gemma_3_12B_it_fpmixed.safetensors	13.7 GB	ComfyUI
gemma_3_12B_it_fp8_scaled.safetensors	13.2 GB	ComfyUI
gemma_3_12B_it_fp4_mixed.safetensors	9.5 GB	ComfyUI

• 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	FusionCow
Gemma ablit fixed	fp8	13.8 GB	FusionCow

Gemma 3 12B IT Heretic

Models by DreamFast

Safetensors

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

GGUF

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

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

Separated Components

Separated LTX2 checkpoint by Kijai. For alternative way to load the models in Comfy

Diffusion Models (Transformer Only)

Name	Precision	Size	Download
ltx-2-19b dev	bf16	37.8 GB	Kijai
ltx-2-19b dev	fp8	21.6 GB	Kijai
ltx-2-19b dev	fp4	14.5 GB	Kijai
ltx-2-19b distilled	bf16	37.8 GB	Kijai
ltx-2-19b distilled	fp8	21.6 GB	Kijai

VAE (Video & Audio)

Component	Precision	Size	Download Link
Video VAE	BF16	2.45 GB	Kijai
Video VAE old	BF16	2.49 GB	Kijai
Audio VAE	BF16	218 MB	Kijai

Embedding Connectors

Name	Precision	Size	Download
Connector dev	bf16	2.86 GB	Kijai
Connector distilled	bf16	2.86 GB	Kijai

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

LoRA

Enchancer, special

• JUST-DUB-IT
• Best-Face-Swap-Video
• Image-to-Video Adapter LoRA
• Lightricks
  • Canny Control
  • Depth Control
  • Detailer
  • Pose Control

Styles

• LTX-2-19b-LoRA-SPROUT
• Hydraulic press
• Cakeify
• Big Anime Breasts
• Clay Stop Motion
• Eat
• Outfit Switch
• Handheld run
• Atomic Explosion
• Squish
• IC luminance map
• Yoshiaki Kawajiri Retro Anime
• DonaldTrump
• WHATUSEE
• Squish – One Hand Only
• HERO CAM
• Animatediff V1
• PUSH TO GLASS
• Object POV
• Group Photo
• EarthZoomOut
• 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

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

Workflow & Technical Notes

Lightricks official WF:

• Text to video full model
• Text to video distilled model (Fast)
• Image to video full model
• Image to video distilled model (Fast)
• Video to video detailer
• IC-LoRA distilled model (depth + human pose + edges)

ComfyUI official WF:

• 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

RuneXX:

Good collection by RuneXX

• 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)