stable-diffusion VS stable-diffusion

I used my own SD repo, but it should easily be portable to others, and the captioning step and be automated. There is current an issue open on the automatic1111 repo, if you found it neat.

fwiw I have my own implementation of the pipeline that is running over an n-many scalable gRPC implementation through jina flow, and I personally think that making the gRPC API first class with an implementation of CompVis stable-diffusion is a mistake.

My stable-diffusion fork

Thanks for the mention! The branch you're probably looking for is here. The code is pretty simple if you want to play with it:

What are the differences between the stable diffusion projects by Stability-AI and RunwayML? In addition, a similar project Diffusers by HuggingFace also exists, is that different as well?

Ok. I refreshed my memory (here). RunwayML did the training. Stability AI donated the compute. At least. 1 member of the german research team has gone to work for RML and basically continued his work there. I'm not clear at all on the relationship between SAI and RML.

Pretty sure. There's an in painting model that is available! I heard it's pretty good! https://github.com/runwayml/stable-diffusion

so use it with the fork it was designed to work on: https://github.com/runwayml/stable-diffusion

source: https://github.com/runwayml/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md

If this gets taken down because of the cucks at Stability, you can also download the model weights at https://github.com/runwayml/stable-diffusion