dalle-flow VS stable-diffusion-grpcserver

Jina AI is really into generative AI. It started out with DALL·E Flow, swiftly followed by DiscoArt. And then…🦗🦗*🦗🦗. At least for a while…

you can host your own https://github.com/jina-ai/dalle-flow

For example for all the multimodal stuff like clipseg and upscalers, I'm using isolated executors through jina flow: https://github.com/jina-ai/dalle-flow/tree/main/executors

clipseg is an image segmentation method used to find a mask for an image from a prompt. I implemented it as an executor for dalle-flow and added it to my bot yasd-discord-bot.

Merged into [dalle-flow](https://github.com/jina-ai/dalle-flow/pull/112) this morning and works on my Discord bot [yasd-discord-bot](https://github.com/AmericanPresidentJimmyCarter/yasd-discord-bot).

https://github.com/jina-ai/dalle-flow with ports of some code from https://github.com/lstein/stable-diffusion plus some stuff specific to my uses (mostly more exposed settings and meta data on the outputs).

dalle flow - a more advanced version of dall-e mini, running dall-e mega and a diffusion model (free colab), free

Another option is https://github.com/jina-ai/dalle-flow combines DALL-E Mini with some other image processing models, and they have a pre-built Docker image that you could run locally. However, because it loads additional image processing models, you'll need about 21 GB of GPU RAM which is more than a 2080 TI has. You could always try to edit their Dockerfile and re-build it to remove the other models.

For the second half of this article, we’ll use meadowdata/meadowrun-dallemini-demo which contains a notebook for running multiple models as sequential batch jobs to generate images using Meadowrun. The combination of models is inspired by jina-ai/dalle-flow.

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.