Joshua Carney

[Dreambooth] Multi-GPU training with accelerate is magnitudes slower than single GPU (non-flax)

1

### Describe the bug I have access to a machine with several NVIDIA A100s. Initially I was using multiple GPUs for Dreambooth training under the idea that it would speed...

[Feature Request]: Support for Apple's Core ML Stable Diffusion

20

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What would your feature do ? https://github.com/apple/ml-stable-diffusion Apple...

Primary Branch Name

1

Why is the primary branch "main" instead of "master"? In case you haven't heard, President Donald Trump recently published an executive order mandating that all branches named "main" be renamed...

[SDXL] Train SDXL refiner for subject generation

9

I've been using the scripts here to fine tune the base SDXL model for subject driven generation to good effect. However, I've found that adding the refiner step usually means...