search

SHI-Labs / Smooth-Diffusion

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024
https://shi-labs.github.io/Smooth-Diffusion/
MIT License
319 stars 8 forks source link

issues when training #21

Open Urheen opened 1 week ago

Urheen commented 1 week ago

Hi when caluclating

grad, = autograd.grad( outputs=(fake_img * noise).sum(), inputs=latents, create_graph=True )

I got this error:

RuntimeError: derivative for aten::_scaled_dot_product_flash_attention_backward is not implemented

Have you faced any errors for this?