This is an example of creating a RunPod serverless worker for Stable Diffusion v2 using cog-stable-diffusion as the base.

This is an implementation of the Diffusers Stable Diffusion v2.1 as a Cog model. Cog packages machine learning models as standard containers.

First, download the pre-trained weights:

cog run script/download-weights

Then, you can run predictions:

cog predict -i prompt="monkey scuba diving"

These are the changes made to the base repo.

• cog.yaml - Add runpod as a dependency
• Add runpod_infer.py file - This defines how the worker interacts with your model, the file name is arbitrary.