Ben
Ben
if you want to run it without xformers, just comment out the line : `!wget -O attention.py https://raw.githubusercontent.com/TheLastBen/fast-stable-diffusion/main/precompiled/attention.py ` in the requirements cell
@AIShank I have updated the notebook, try loading the latest colab from the main page and try if the hypernetwork works
I don't think commenting that line will fix the problem with hypernetwork, I'm still looking in the AUTOMATIC1111 repo for answers, until then, add --deepdanbooru in the three last lines...
We're gonna have to wait for more feedback
That would require tapping into the trainer script to download the model from the VRAM at a chosen time, you can request that in the main repo of the dreambooth...
The colab has been updated to perform in-session inference
image generation
you will need the diffusers script to get the model working locally : https://huggingface.co/blog/stable_diffusion
You can run it under windows using docker, preferably under nvidia docker image
I don't think so, just install docker and pull this image : nvcr.io/nvidia/pytorch:22.08-py3