Try the lstein fork: https://github.com/lstein/stable-diffusion/tree/fix-cuda-res...

You'll still need to play with modifying some of the code to get it to run, but `dream.py` works for me. Funny enough, I got only img2img effectively working with the lstein branch; it broke txt2img for me.

Yesterday I thought I broke it too. In my case, the solution was just to make sure that the input image (from the editor or otherwise) was the same size as the output image. Hope it helps.

Apparently, this release should include a Dockerfile for easier replicability.