[FOSS] docker-diffusers-api: multiple pipelines, models & more

This is the base production image powering https://kiri.art/.
Formerly known as “gadicc/banana-sd-base”.

  • Pipelines: txt2img, img2img and inpainting in a single container
  • Models: stable-diffusion, waifu-diffusion, and easy to add others (e.g. jp-sd)
  • All model inputs supported, including setting nsfw filter per request
  • Permute base config to multiple forks based on yaml config with vars
  • Optionally send signed event logs / performance data to a REST endpoint
  • Can automatically download a checkpoint file and convert to diffusers.

The project now has it’s own subforum: