Fantastic work. I had real fun playing around with your model.
This pull request makes it possible to run it inside a Docker environment, which makes it easier for other people to run. We're using an open source tool called Cog that handles all the complex stuff like Dockerfile, configuring CUDA, etc.
You can run commands inside the Docker environment:
If you claim your page by signing in with GitHub, then we'll feature it on our site.
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 round implementing models we like. :)
Hey @neuralchen! 👋
Fantastic work. I had real fun playing around with your model.
This pull request makes it possible to run it inside a Docker environment, which makes it easier for other people to run. We're using an open source tool called [Cog](https://github.com/replicate/cog) that handles all the complex stuff like `Dockerfile`, configuring CUDA, etc.
You can run commands inside the Docker environment:
cog run python test_one_image.py ...
Or, a prediction:
cog predict -i source=@source.jpg -i target=@target.jpg
This also means we can make a web page where other people can try out your model! View it here: https://replicate.ai/neuralchen/simswap-image
If you claim your page by signing in with GitHub, then we'll feature it on our site.
In case you're wondering who I am, I'm from [Replicate](https://replicate.ai/home), 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 round implementing models we like. :)
You can sign in with GitHub here to claim the page so you can add more examples, a description, etc. We'll also feature it on our home page and tweet about it. :)
I'm so glad to hear it's helpful. 😄
[You can sign in with GitHub here](https://replicate.ai/login/github/?next=/neuralchen/simswap-image?published=1) to claim the page so you can add more examples, a description, etc. We'll also feature it on our home page and tweet about it. :)
What's better than Robert Downey Jr? Three Robert Downey Jrs!
@neuralchen we'd love to feature this model on replicate.ai and tweet about it. If you're okay with that, you can claim your model here.
What's better than Robert Downey Jr? **Three** Robert Downey Jrs!

@neuralchen we'd love to feature this model on replicate.ai and tweet about it. If you're okay with that, you can [claim your model](https://replicate.ai/login/github/?next=/neuralchen/simswap-image?published=1) here.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Hey @neuralchen! 👋
Fantastic work. I had real fun playing around with your model.
This pull request makes it possible to run it inside a Docker environment, which makes it easier for other people to run. We're using an open source tool called Cog that handles all the complex stuff like
Dockerfile, configuring CUDA, etc.You can run commands inside the Docker environment:
Or, a prediction:
This also means we can make a web page where other people can try out your model! View it here: https://replicate.ai/neuralchen/simswap-image
If you claim your page by signing in with GitHub, then we'll feature it on our site.
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 round implementing models we like. :)
Thanks for your excellent work.
We believe that this effort can significantly improve our respository.
I'm so glad to hear it's helpful. 😄
You can sign in with GitHub here to claim the page so you can add more examples, a description, etc. We'll also feature it on our home page and tweet about it. :)
What's better than Robert Downey Jr? Three Robert Downey Jrs!
@neuralchen we'd love to feature this model on replicate.ai and tweet about it. If you're okay with that, you can claim your model here.