T. Xu

> See my comment here https://github.com/huggingface/diffusers/pull/6730/files#r1468858192 In openai/guideddiffusion, both normal attention and legacy attention are implemented in separate class: * normal: https://github.com/openai/guided-diffusion/blob/main/guided_diffusion/unet.py#L361 * legacy: https://github.com/openai/guided-diffusion/blob/main/guided_diffusion/unet.py#L328 Those two attentions have exactly...

Hi @sayakpaul, any further comments?

Hi, I have found a way to avoid breaking the possible backward deps in class UNetMidBlock2D and updated the PR. The change is still minimal but it does not break...

> @tongdaxu can we move this to the research folder? I am fine with that, what should I do to move this to research folder?

> Hi @tongdaxu, thank you for your great work! > > I am having trouble generating nice images with your PR. I hope you can help :) > > I...

> Hi @tongdaxu, thank you for your great work! > > I am having trouble generating nice images with your PR. I hope you can help :) > > I...

> Thank you for your quick response. Sadly, your instructions did not work either. > > I tried all versions of your repository and different pretrained models, but I still...

> Thank you for your quick response. Sadly, your instructions did not work either. > > I tried all versions of your repository and different pretrained models, but I still...

> 4\. pip install git+https://github.com/huggingface/diffusers.git@refs/pull/6730/head Thank you @kschwethelm, that is very strange. I also find that it fails with torch 1.9 and works with torch 2.1. I do not have...

> Hi, thank you very much for your help! The problem was actually the PyTorch version. I now tried with torch-2.2.0 and it works fine. > >  I can't...