Lightricks/LTX-Video-ICLoRA-canny-13b-0.9.7

LTX Video ICLoRA Canny 13B 0.9.7

This is a canny control model on top of LTXV_13B_097_DEV trained on custom data.

What is In-Context LoRA (IC LoRA)?

IC LoRA is a method that enables adding video context into the video generation process. This approach allows for video-to-video control on top of the text-to-video model, providing more precise control over the generated content by conditioning the model on reference video frames during inference.

comfy compatible model: ltxv-097-ic-lora-canny-control-comfyui.safetensors

diffusers compatible model:ltxv-097-ic-lora-canny-control-diffusers.safetensors

License

For licensing information, please refer to the LTXV Open Weights License.

Model Details

• Base Model: LTXV_13B_097_DEV
• Training Type: IC LoRA training
• Learning Rate: 0.0002

Sample Outputs

Usage

This model is designed to be used with the LTXV (Lightricks Text-to-Video) pipeline.

🔌 Using Trained LoRAs in ComfyUI

In order to use the trained lora in comfy:

1. Copy the comfyui trained LoRA weights to the models/loras folder in your ComfyUI installation.
2. Use ic_lora/ic-lora.json from official LTXV ComfyUI repository

Dataset

https://huggingface.co/datasets/Lightricks/Canny-Control-Dataset/

Acknowledgments

• Base model by Lightricks
• Training infrastructure: LTX-Video-Trainer