daanelson / speedy-stable-diffusion-inpainting

Filling in images quickly with Stable Diffusion and AITemplate

  • Public
  • 323 runs
  • License
Run with an API
Playground API Examples README Versions
  1. Author
    @daanelson
    Version
    22.04
    Commit
    61b26560cc068d7a5da91bcd602bc94c389525d8

    c6489923

    Latest

    Release notes

    Inpainting with Stable Diffusion 2.0. Resumed from stable-diffusion-2-base (512-base-ema.ckpt) and trained for another 200k steps. Follows the mask-generation strategy presented in LAMA which, in combination with the latent VAE representations of the masked image, are used as an additional conditioning.