Missing guided implementation for DDIM sampling

lucidrains / denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

MIT License

8.02k stars 1k forks source link

Missing guided implementation for DDIM sampling #208

Open houxianxu opened 1 year ago

houxianxu commented 1 year ago

Hi Phil,

It seems that the classifier guidance is missing for DDIM sampling. The cond_fn is not used in the ddim_sample function.

https://github.com/lucidrains/denoising-diffusion-pytorch/blob/0dee2d8eebe251e666ef60c1b48d3333a18f4065/denoising_diffusion_pytorch/guided_diffusion.py#L666

lucidrains commented 1 year ago

@houxianxu ohh yea, i think someone else contributed the guided implementation. i'll look up who it is later and ping him or her

ptoyip commented 1 year ago

@lucidrains May I ask are there any updates of the implementation? I'm currently working on 1D guidance diffusion based on the repo, and I need to use guidance diffusion with ddim process. I'm not confidence about my own implementation so I want to ask are there any of repo that I can refer to (if any)?