search

MountaintopLotus / braintrust

A Dockerized platform for running Stable Diffusion, on AWS (for now)
Apache License 2.0
1 stars 2 forks source link

Truss for deploying trained models via Jupyter #87

Open JohnTigue opened 1 year ago

JohnTigue commented 1 year ago

Interesting find: Deploy your Stable Diffusion model from a Jupyter notebook using Truss.

This came up while working on DreamBooth. They seem to be using it by training on Colab and then deploying for inference on, say, AWS.

JohnTigue commented 1 year ago

And Truss is really supposed to be the easiest way for you to take a model that is kind of stuck or confined inside a notebook and turn it into a server via a Truss. And then you can do a lot of things with that. So you can deploy it on AWS, you can deploy it on your own infrastructure. You can deploy it on base ten. But the goal of trust is to act as a packaging layer.