Carson Katri

All of our pipelines in Dream Textures use generators, and it works well for us with cancellation and step previews: https://github.com/carson-katri/dream-textures/blob/c3f3a3780c2229eb4cce7390f193b59b0569f64a/generator_process/actions/prompt_to_image.py#L509 It would be nice to have this option upstream,...

Similar feature implemented in #229

Dream Textures does not use InvokeAI as of #405

Looks like the dependencies were not downloaded successfully. In the `dream_textures` addon folder, is the `.python_dependencies` folder empty? There should be a folder diffusers and huggingface_hub in there (among others)

DreamStudio does not support depth to image yet.

They currently only provide text to image, image to image, and inpainting.

Hmm, that's unfortunate. Can you please share the full error log so I can see what code is importing distutils?

Please specify what graphics card you have. Stable diffusion requires at least 4GB of VRAM, and more if your card doesn’t support half precision math.

Have you tried restarting and closing other programs to make more RAM/VRAM available to Stable Diffusion? It needs to be able to load the model into memory, which is a...

If monitoring from task manager, you have to switch the GPU stat to show CUDA usage afaik.