Open mgcyung opened 1 year ago
Hello mgcyung,
Thanks for the interest in our project! Our current implementation doesn't support a skeleton or keypoints, but this sounds like an interesting way to extend DA-Fusion's capabilities! Since our method builds on the HuggingFace stable diffusion model, open source tools like the HuggingFace ControlNet (https://arxiv.org/abs/2302.05543, https://huggingface.co/lllyasviel/ControlNet) could be added.
If you decide to work on this, I'd be delighted to support the endeavor by providing help using DA-Fusion!
Warm regards, Brandon
Can skeleton or keypoints information be used as a reference to generate images in da-fussion?