ComfyUI Extension: ComfyUI-LTXVideo
Custom nodes for LTX-Video support in ComfyUI
Custom Nodes (68)
- Add LTX Latent Guide
- 🅛🅣🅧 Add VAE Decoder Noise
- 🅛🅣🅧 APG Guider
- 🅛🅣🅧 Dynamic Conditioning
- 🅛🅣🅧 Guider Parameters
- 🅛🅣🅧 Image to CPU
- 🅛🅣🅧 Linear transition with overlap
- 🅛🅣🅧 Low VRAM Audio VAE Loader
- 🅛🅣🅧 Low VRAM Checkpoint Loader
- Low VRAMLoad Latent Upscale Model
- LTX Attention Bank
- LTX Attn Block Override
- LTX Attention Override
- LTX Feta Enhance
- LTX Flow Edit CFG Guider
- LTX Flow Edit Sampler
- LTX Forward Model Pred
- LTX Apply Perturbed Attention
- LTX Prepare Attn Injection
- 🅛🅣🅧 LTXQ8Patch
- LTX Reverse Model Pred
- LTX Rf-Inv Forward Sampler
- LTX Rf-Inv Reverse Sampler
- 🅛🅣🅧 LTXV Adain Latent
- 🅛🅣🅧 LTXV Add Guide Advanced
- 🅛🅣🅧 LTXV Add Latent Guide
- 🅛🅣🅧 LTXV Add Latents
- 🅛🅣🅧 LTXV Apply STG
- 🅛🅣🅧 LTXV Base Sampler
- 🅛🅣🅧 LTXV CLIP Model Loader
- 🅛🅣🅧 LTXV Dilate Latent
- 🅛🅣🅧 LTXV Extend Sampler
- 🅛🅣🅧 LTXV Film Grain
- 🅛🅣🅧 Gemma 3 Model Loader
- 🅛🅣🅧 Gemma 3 Prompt Enhancer
- 🅛🅣🅧 LTXV Img To Video Advanced
- 🅛🅣🅧 LTXV Img To Video Condition Only
- 🅛🅣🅧 LTXV In Context Sampler
- 🅛🅣🅧 LTXV Latent Upsampler
- 🅛🅣🅧 LTXV Latent Upsampler Model Loader
- 🅛🅣🅧 LTXV Linear Overlap Latent Transition
- 🅛🅣🅧 LTXV Loader
- 🅛🅣🅧 LTXV Looping Sampler
- 🅛🅣🅧 LTXV Model Configurator
- 🅛🅣🅧 LTXV Multi Prompt Provider
- 🅛🅣🅧 LTXV Patcher VAE
- 🅛🅣🅧 LTXV Per Step Adain Patcher
- 🅛🅣🅧 LTXV Per Step Stat Norm Patcher
- 🅛🅣🅧 LTXV Preprocess Masks
- 🅛🅣🅧 LTXV Prompt Enhancer
- 🅛🅣🅧 LTXV Prompt Enhancer Loader
- 🅛🅣🅧 LTXVQ8Lora Model Loader
- 🅛🅣🅧 LTXV Select Latents
- 🅛🅣🅧 LTXV Set Audio Video Mask By Time
- 🅛🅣🅧 LTXV Set Video Latent Noise Masks
- 🅛🅣🅧 LTXV Shift Sigmas
- 🅛🅣🅧 LTXV Spatio Temporal Tiled VAE Decode
- 🅛🅣🅧 LTXV Stat Norm Latent
- 🅛🅣🅧 LTXV Tiled Sampler
- 🅛🅣🅧 LTXV Tiled VAE Decode
- Modify LTX Model
- 🅛🅣🅧 Multimodal Guider
- 🅛🅣🅧 Multi Prompt Provider
- 🅛🅣🅧 Set VAE Decoder Noise
- 🅛🅣🅧 STG Advanced Presets
- 🅛🅣🅧 STG Guider
- 🅛🅣🅧 STG Guider Advanced
- 🅛🅣🅧 STG Guider Node
README
ComfyUI-LTXVideo
A collection of powerful custom nodes that extend ComfyUI's capabilities for the LTX-2 video generation model.
LTX-2 is built into ComfyUI core (see it here), making it readily accessible to all ComfyUI users. This repository hosts additional nodes and workflows to help you get the most out of LTX-2's advanced features.
To learn more about LTX-2 See the main LTX-2 repository for model details and additional resources.
Prerequisites
Before you begin using an LTX-2 workflow in ComfyUI, make sure you have:
- ComfyUI installed (Download here](https://www.comfy.org/download)
- CUDA-compatible GPU with 32GB+ VRAM
- 100GB+ free disk space for models and cache
Quick Start 🚀
We recommend using the LTX-2 workflows available in Comfy Manager.
- Open ComfyUI
- Click the Manager button (or press Ctrl+M)
- Select Install Custom Nodes
- Search for “LTXVideo”
- Click Install
- Wait for installation to complete
- Restart ComfyUI
The nodes will appear in your node menu under the “LTXVideo” category. Required models will be downloaded on first use.
Example Workflows
The ComfyUI-LTXVideo installation includes several example workflows. You can see them all at: ''' ComfyUI/custom_nodes/ComfyUI-LTXVideo/example_workflows/ '''
Text to video full modelText to video distilled model (Fast)Image to video full modelImage to video distilled model (Fast)Video to video detailerIC-LoRA distilled model (depth + human pose + edges)
Required Models
Download the following models:
LTX-2 Model Checkpoint - Choose and download one of the models to COMFYUI_ROOT_FOLDER/models/checkpoints folder.
ltx-2-19b-dev-fp8.safetensorsltx-2-19b-distilled-fp8.safetensorsltx-2-19b-dev.safetensorsltx-2-19b-distilled.safetensors
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.
Distilled LoRA - Required for current two-stage pipeline implementations in this repository (except DistilledPipeline and ICLoraPipeline). Download to COMFYUI_ROOT_FOLDER/models/loras folder.
Gemma Text Encoder Download all files from the repository to COMFYUI_ROOT_FOLDER/models/text_encoders/gemma-3-12b-it-qat-q4_0-unquantized.
LoRAs Choose and download to COMFYUI_ROOT_FOLDER/models/loras folder.
ltx-2-19b-ic-lora-canny-control.safetensorsltx-2-19b-ic-lora-depth-control.safetensorsltx-2-19b-ic-lora-detailer.safetensorsltx-2-19b-ic-lora-pose-control.safetensorsltx-2-19b-lora-camera-control-dolly-in.safetensorsltx-2-19b-lora-camera-control-dolly-left.safetensorsltx-2-19b-lora-camera-control-dolly-out.safetensorsltx-2-19b-lora-camera-control-dolly-right.safetensorsltx-2-19b-lora-camera-control-jib-down.safetensorsltx-2-19b-lora-camera-control-jib-up.safetensorsltx-2-19b-lora-camera-control-static.safetensors
Advanced Techniques
Low VRAM
- For systems with low VRAM you can use the model loader nodes from low_vram_loaders.py. Those nodes ensure the correct order of execution and perform the model offloading such that generation fits in 32 GB VRAM.
- Use --reserve-vram ComfyUI parameter:
python -m main --reserve-vram 5(or other number in GB). - For complete information about using LTX-2 models, workflows, and nodes in ComfyUI, please visit our Open Source documentation.