A Canny control LoRA trained for Anima (<a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima">link</a>). Currently requires <a target="_blank" rel="ugc" href="https://github.com/levzzz5154/ComfyUI/tree/ref-latents-support">my fork of ComfyUI.</a>See the version notes for training details.The example workflow is in the image(s).I may either make a custom node or try to get this merged upstream... <a target="_blank" rel="ugc" href="https://github.com/levzzz5154/diffusion-pipe">Training code, fork of diffusion-pipe</a>

Files with SHA256: 37bb7d8a96908ef88dfc501cb002b2e63b07b1f30c1487ddb1ac164d129867de