Carson Katri

Exactly, so every object prompt needs to be contained in the main prompt, and it weights the tokens differently for each pixel depending on what object is there.

Seems like DreamStudio does not support prompt batches, I will need to either disable this or manually send the prompts to the backend one by one.

Upscaling is not functioning in 0.0.9. I believe this will be fixed with #410

This can happen when you previously had Dream Textures v0.0.5 or earlier where the dependencies were installed into Blender's site-packages. You can fix this by removing the following folders: 1....

@k-a-s-o-u You need the `stable-diffusion-2-depth` model to use the projection feature.

@p4vv37 that would be great! The main projection code is here: https://github.com/carson-katri/dream-textures/blob/main/operators/project.py And the depth pipeline is here: https://github.com/carson-katri/dream-textures/blob/main/generator_process/actions/depth_to_image.py Anything that uses libraries other than those built-in to Blender will...

That sounds like how the auto bake works: https://github.com/carson-katri/dream-textures/pull/495 Except it just draws it all with Blender’s GPU module from Python, no geometry nodes or anything.

Dream Textures no longer has any submodules. Please see the updated guide for setting up a development environment: https://github.com/carson-katri/dream-textures/blob/main/docs/DEVELOPMENT_ENVIRONMENT.md

@hendersj follow the instructions to install dependencies in that document

I’m going to close this issue as the instructions were updated.