This is an implementation of the Diffusers Stable Diffusion 1.5 as a Cog model. Cog packages machine learning models as standard containers. This cog also includes Real-ESRGAN to upscale images.

The Docker image built using this repo can be found at: yekta/sc

First, download the pre-trained weights with your Hugging Face auth token:

cog run models/download <your-hugging-face-auth-token>

Then, you can run predictions:

cog predict -i prompt="monkey scuba diving"

Or, build a Docker image:

cog build

Or, push it to Replicate:

cog push r8.im/...