stable-diffusion-grpcserver VS stability-sdk

I recently discovered a FlagOnlySafetyChecker for stable diffusion but I'm unable to use it in the program. https://github.com/hafriedlander/stable-diffusion-grpcserver/blob/main/sdgrpcserver/pipeline/safety_checkers.py

- https://github.com/hafriedlander/stable-diffusion-grpcserver I am running it on vast.ai and local installation. A good NVidia card is required.

Stable Cabal’s gRPC Server - An implementation of Stability.AI’s API

This is also already implemented in the GRPC server project here, which now has a nice webui itself: https://github.com/hafriedlander/stable-diffusion-grpcserver

if you want to run such a server locally instead of paying for DreamStudio API credits, you could try https://github.com/hafriedlander/stable-diffusion-grpcserver . You'd still have to manage both a Python server and your Kotlin application, but you could have them in different environments, and you wouldn't have to worry about the complications of how to run a conda environment from inside a Kotlin process.

I use stable diffusion via stability.ai.

SDXL 0.9 is now available on the Clipdrop by Stability AI platform. Stability AI API and DreamStudio customers will be able to access the model this Monday, 26th June as well as other leading image generating tools like NightCafe.

And for your imaging purposes, you might explore things such as the new StableStudio that Stability AI has. Here's an article about StableStudio. Here are imaging things you can do in StableStudio via its API.

I know there are tons are programs out there but I've made some really cool stuff with this free one https://beta.dreamstudio.ai then rotoscoped it onto a green screen then animated it

Currently Midjourney is the best one, but you need to pay. For low to no cost you could use https://app.leonardo.ai/ or https://beta.dreamstudio.ai/

https://beta.dreamstudio.ai/ (belaj bildoj)

> Of course new SD models are also on the horizon…

SDXL is available at https://beta.dreamstudio.ai/ though they say they're going to release more variants.

I think ControlNet is a lot more interesting than just "better tuned models"; it means there's no line between creating something yourself and asking an AI to do it anymore.

(this is actually generated using the new sdxl beta model in https://beta.dreamstudio.ai )