omerbt / MultiDiffusion

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
https://multidiffusion.github.io/
979 stars 57 forks source link

Add Replicate demo and API #2

Closed chenxwh closed 1 year ago

chenxwh commented 1 year ago

Hey @omerbt! 👋

This pull request makes it possible to run your model inside a Docker environment, which makes it easier for other people to run it. We're using an open source tool called Cog to make this process easier.

This also means we can make a web page where other people can run your model! View it here: https://replicate.com/cjwbw/multidiffusion

Replicate also have an API, so people can easily run your model from their code:

import replicate
model = replicate.models.get("cjwbw/multidiffusion")
model.predict(prompt="")

The implementation for adding your model to Replicate can be found here.

We'd like to transfer the Replicate page ownership to your account (simply register with your github usrname) so you can modify and push update to it, let me know!

In case you're wondering who I am, I'm from Replicate, where we're trying to make machine learning reproducible. We got frustrated that we couldn't run all the really interesting ML work being done. So, we're going around implementing models we like. 😊

omerbt commented 1 year ago

Hey @chenxwh :) Thanks, the Replicate page looks great!!! I registered using my GitHub username (https://replicate.com/omerbt)

chenxwh commented 1 year ago

Perfect thanks! The page is here now https://replicate.com/omerbt/multidiffusion :)