This is a Canny control IC-LoRA trained on top of LTX-2-19b, enabling structure-preserving video generation from text and reference frames.

IC LoRA enables conditioning video generation on reference video frames at inference time, allowing fine-grained video-to-video control on top of a text-to-video, base model. It allows also the usage of an intial image for image-to-video, and generate audio-visual output.

ltx-2-19b-ic-lora-canny-control.safetensors

See the LTX-2-community-license for full terms.

• Base Model: LTX-2-19b Video
• Training Type: IC LoRA
• Control Type: Canny edge conditioning

1. Copy the LoRA weights into models/loras.
2. Use the official IC-LoRA workflow from the LTX-2 ComfyUI repository.

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

• Base model by Lightricks
• Training infrastructure: LTX-2 Community Trainer