diffusion-ui VS diffusers-interpret

You can use diffusion-ui on top of automatic1111 for easy outpainting. Run automatic1111 with --cors-allow-origins=http://127.0.0.1:5173,https://diffusionui.com Then select the automatic1111 backend, upload an image then use the mouse scroll to zoom out.

I see you've got my https://github.com/leszekhanusz/diffusion-ui gui but it seems to be linked to a completely unrelated face-swapping interface?

Yes, checkout diffusion-ui

I modified my GUI Stable Diffusion frontend to be able to use the automatic1111 fork as a backend.

It's not really well known at the moment but you also have my DiffusionUI interface which is based on diffusers with a backend where you can disable the nsfw filter.

GitHub: https://github.com/leszekhanusz/diffusion-ui

One way to do it is to use diffusionui, a web interface I made in vue. Here is a crappy video demo showing the process.

If you want to do inpainting, you can try my diffusionui interface I'll add a feature soon to save the generated images in local storage in the browser. Here is a small demo

It's still a work in progress but you can already play with it. Check it on GitHub

Check the project at https://github.com/JoaoLages/diffusers-interpret

For those who want to explore what the denoising process looks like, check out the [diffusers-interpret package](https://github.com/JoaoLages/diffusers-interpret)! You can generate a GIF like [this one](https://github.com/TomPham97/diffuser/blob/main/diffusion-process.gif?raw=true).

If you have lots of RAM the diffusers-interpreter is an explainability tool that can show exactly how much each token is beings weighted and which part of the image it is influencing.

github.com/JoaoLages/diffusers-interpret