I'm personally working on a UI as well, that is using InvokeAI :) It has a bit of a different focus, namely organization of generated images and facilitating generating a lot of images quickly via randomization. Here is the current page for it: https://patreon.com/auto_sd_workflow

Currently expanding it a lot with some fun features:

- multi-gpu support (first UI that would support that I think)

- no-click installer (installs everything when you start it up) that works on Windows, Linux and macOS

- A cloud version where you can "rent" access to the UI + very powerful GPU instances without having to run anything locally yourself.

Been waiting to submitting it all to HN as a Show HN but have to wait a bit for everything to get into place first :)

since its paid, i'd classify you as a distro :) https://github.com/sw-yx/prompt-eng/blob/main/README.md#sd-d...

Yes, that makes sense :)

Here's another one for you: https://github.com/brycedrennan/imaginAIry

Imaginairy is great.

Maybe I missed it but didn’t see https://github.com/divamgupta/diffusionbee-stable-diffusion-...

i have diffusionbee.com

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?

And in communities, you can probably add https://stablehorde.net

uhhh... copy paste brainfart sorry. thanks for correction

Since everyone's jumping on the plug wagon, allow me to throw on my project, www.stablecabal.org.

We've got a GRPC server that's backwards compatible with the official grpc.stability.ai but adds advanced features, a Flutter based infinite canvas web client in heavy development, a Discord server and a Krita & Photoshop plugin (all except the last are open source under various licenses).

The outpainting the server supports is (IMHO) the best I've seen, and recently got some a tiny glimpse of attention when combined with the Photoshop plugin - https://twitter.com/NicolayMausz/status/1577767106384433156

great submission, thank you. god its so hard to keep on top of who is doing what.

am reworking my readme now with all the updates

Shameless plug: I was frustrated with the poor UI of notebook-based frontends so I wrote a desktop version here: https://github.com/ahrm/UnstableFusion .

Here is a video of some of its features: https://www.youtube.com/watch?v=XLOhizAnSfQ&t=1s

Here's a cross-platform desktop GUI[0] for img2img/txt2img that takes a unique angle by remaining independent of specific models/scripts, though it was originally designed to work with Stable Diffusion.

[0] https://github.com/westoncb/generation-q

https://github.com/cmdr2/stable-diffusion-ui is pretty popular, and is a 1-click installer for Win and Linux (Mac coming soon). Quite a lot of features, and well-liked by users for its easy-to-install and user-friendly GUI.

ah thanks, i've seen you around but somehow forgot to add. I've put you in as a distro since you bundle SD: https://github.com/sw-yx/prompt-eng/blob/main/README.md#sd-d...

Thanks! :)

Is "dreambooth" a fork? Or another feature that has been created by composing Stable Diffusion w/something else?

yeah you're right, more the latter. i should split it out.

OG dreambooth is proprietary Google code. what everyone's using is a third party replication of it using SD

I wasn't intending to challenge anything of yours. I just saw a lot of "dreambooth" activity on /r/stablediffusion. I haven't kept up on activity in the last week or two and figured you'd know what it was.

Another feature. You can "teach" SD a new concept, e.g., a new person, with a limited number of training images.