Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
multimodalart 
posted an update 7 days ago
Post
3670
Self-Forcing - a real-time video distilled model from Wan 2.1 by @adobe is out, and they open sourced it 🐐

I've built a live real time demo on Spaces 📹💨

multimodalart/self-forcing
multimodalart
•
edited 7 days ago

The technique is really cool! They distill the model without showing video examples, just by simulating the inference process at training - and they release the training code too!

Read more: https://self-forcing.github.io
And chat with the authors: https://huggingface.co/papers/2506.08009

AIartist68
•
edited 3 days ago

Cool space! Nervously anticipating error message saying that I have exceeded the quota for the day. Hasn't happened yet. Disappointed that I am not able to download and save the videos I create. Could that be a browser error?

image.png

In this post