`pip install auto1111sdk`

https://github.com/saketh12/Auto1111SDK

Why we built this, what you can do with it right now, and where we plan to go below:

Why we built this:

As a developer using stable diffusion, you’ve probably used HuggingFace’s diffusers library. However, it just doesn’t make sense to use diffusers when the “gold standard” tool for stable diffusion is Automatic1111’s Stable Diffusion Web UI.

We detail some limitations of diffusers here: https://flush-ai.gitbook.io/automatic-1111-sdk/auto-1111-sdk...

What you can do with it right now:

- Text-to-Image, Image-to-Image, Inpainting, and Outpainting pipelines. - Upscaling pipelines for ESRGAN and Real-ESRGAN - Download & run safetensor model files from Civitai

Where we plan to go:

We’re an open source project, and we intend to remain this way. Our next step is to add support for Stable Diffusion XL, Lora’s, and Dreambooth finetuning. We welcome all contributors!

In the meantime, check out our docs and join our discord.