dfserver is a distributed backend AI pipeline server. The initial purpose of this project was to build a self-hosted distributed GPU cluster to run the stable diffusion model, but it has a potential to expend to general AI models, or large-scale production service.
Task Sequence Diagram
Build the dfserver
$ git clone "https://github.com/huo-ju/dfserver.git" $ cd dfserver $ make linux-amd64 #or make linux-arm64
cp configs/config.toml.sample configs/config.toml
Edit the config.toml, setup the username/password/host address/port of the rabbitmq.
The default configuration was defined ONE task queue for stable diffusion ai worker (name is ai.sd14), ONE discord bot service, ONE process worker for discord(name is discord.server1)
AI Worker Install
pyworker dir to the GPU server, and install all diffusers dependencies(nvidia drivers, CUDA, pytorch, models etc…).
cd pyworker pip install -r requirements.txt git clone https://github.com/huggingface/diffusers.git
AI Worker Configuration
cp configs/config.ini.sample configs/config.ini
Edit the config.ini, setup the username/password/host address/port of the rabbitmq.
Run the ai worker
Add the discord bot to your disord server, and input your prompt.
!dream Cute sticker design of a AI image generator robotic pipeline service, app icon, trending on appstore, trending on pixiv, hyper-detailed, sharp
The ai task will be collected from user input by discord bot, and published to the rabbitmq, then the task will be fetched by ai worker (running on GPU servers).
The result (generated images) will be published back to the rabbitmq, fetched by process worker (discord.server1), and sent back to the user.
Run the dfserver and aiworker on boot, please see the systemd scripts in
-  Response error messages to users
-  More AI workers, eg: upscale worker
-  Multi GPUs worker support
-  Initial image
-  Mask/Inpaint