seems unable to accurately reproduce the style of the reference image？

[akk-123]

can you support deadiff with diffusers?

[akk-123]

what's more, deadiff seems unable to accurately reproduce the style of the reference image, I test with app.py

Input image:

generate image: (prompt: a man, portrait)

input image:

generate image:

[longmans]

what's more, deadiff seems unable to accurately reproduce the style of the reference image, I test with app.py

Input image: generate image: (prompt: a man, portrait)

input image: generate image:

The same, still can't reproduce the result.

[zhang2002forwin]

Hello, is there a problem in ldm/modules/new_attention.py？In picture, self.atten2 function doesn't have the 'img_weight'. How do you solve this problem? Thanks a lot!!! I have tried to remove the parm 'img_weight', and then there is another problem in CrossAttention's forward function.

[Tianhao-Qi]

Hello, is there a problem in ldm/modules/new_attention.py？In picture, self.atten2 function doesn't have the 'img_weight'. How do you solve this problem? Thanks a lot!!! I have tried to remove the parm 'img_weight', and then there is another problem in CrossAttention's forward function.

This issue may stem from that you've not correctly installed xformers, so the computation of joint text-image cross attention layer will run into trouble. Therefore, please carefully check the package xformers.

[zhang2002forwin]

Thanks!! Your work is so fantastic!