[Andrew]

You can replace

--xformers

with

--opt-sdp-no-mem-attention

[Andrew]

Have you tried deleting the venv folder and restart?

xformers is a bit outdated. You can try the following A1111 parameter in place of xformers

–opt-sdp-no-mem-attention

[Andrew]

Hi, this is the correct link:

https://huggingface.co/Lykon/DreamShaper/resolve/main/DreamShaper_3.32_baked_vae_clip_fix_half.safetensors?download=true

where do you get the link?

[Andrew]

The job seemed to have completed. There’s a warning but no error.

Are you able to find the video in the output directory?

Otherwise, it is likely one of those issues only appear on Mac since most users are on windows. You can report this issue on their github page (the URL that you used to install the extension)

 

[Andrew]

Yes they have the same quality.

[Andrew]

Thanks for reporting! The notebook is fixed.

[Andrew]

Hi! You can start new topics in the appropriate forum.

[Andrew]

Leave a message in the forum. I will get back to you shortly.

[Andrew]

Yes, you can use multiple ControlNet with Image Prompt adapter. Make sure the weights are sum to be around 1.

https://stable-diffusion-art.com/image-prompt/

[Andrew]

Hello Jose! Welcome!

[Andrew]

Hi Jawad! Welcome to my site. Feel free to leave a message if you have any questions!

[Andrew]

They could be doing roop or IP-adapter with inpainting, or both. Perhaps the hardest part is to match the skin color with the face. They must have some kind of global generation like IP-adapter, and followed by swapping the face with roop.

I am curious to try it out in A1111 if you can find a sample dataset of inputs and outputs.

[Andrew]

Responded to you in the post. Do you still see issue?

[Andrew]

Thank you! Best wishes to your journey of diffusion!

[Author]

Posts