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

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

Distilled LoRA

Spatial Upscaler

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

Temporal Upscaler

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

══════════════════════════════════

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

QuantStack LTX-2

Unsloth

Unsloth LTX-2.3 GGUF

Unsloth LTX-2 GGUF

Vantage

Vantage AI GGUFs

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

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.

• 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

Gemma 3 12B IT Heretic

Models by DreamFast

Safetensors

GGUF

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

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)

[!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)

Embedding Connectors & Text Projection

◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆

LoRA

Enchancer, special

• JUST-DUB-IT
• Best-Face-Swap-Video
• Image-to-Video Adapter LoRA
• Lightricks LTX-2.3
  • Union Control (654 MB)
  • Motion Track Control (327 MB)
  • Motion Track Control
• Lightricks LTX-2
  • 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
• Black Venom
• 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 LTX-2.3 Workflows:

RuneXX LTX-2 Workflows old pre_feb2026