sd-webui-bayesian-merger VS malten

As context, for a while now I've been looking into improving current automated model merging methods(and some other stuff, gonna present something nice in a few months when I get to finishing it). It's practically a 26 dimensional stochastic black box optimization problem and that was kind of fine so far (shoutout to https://github.com/s1dlx/sd-webui-bayesian-merger and all the work people put there, especially the author).

I’ve implemented a Bayesian optimizer for stable diffusion model merging [0]. This is because I do not have patience and/or time to try all different block combinations by hand. It started as a personal thing but now multiple people are working on it and a small community was born.

[0] https://github.com/s1dlx/sd-webui-bayesian-merger

What kind of community would you like to be a part of?

Do you see yourself as a leader or a follower?

Thank-you for working on Malten:

https://malten.com/

Lots of things. But one I am coming back to is called Malten (https://malten.com). It was essentially a place for me to blackhole my thoughts anonymously rather than putting them on twitter. Recently as I've seen ChatGPT take off it's made me revisit the project and create an integration for it (not yet publicly hosted). Ideally I'd just be able to voice my thoughts to an AI now in a private manner. Let's see.

https://github.com/asim/malten for anyone who wants to run it themselves.

I built something similar but it wasn't intended as a clipboard. Mostly for anonymous chat but I personally ended up using it as a clip board. The difference. We don't persist anything on the server side, it's totally in memory and you can create new streams that have shorter ttls.

Website: https://malten.xyz

Source code: https://github.com/asim/malten