New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How long before we can get to this level #126
Comments
Just wait until they release new weights and then compare again. |
I've made some videos that look better than those VASA-1 examples, but I'm also looking forward to the release of the pre-trained audio model, especially since M$ won't release vasa-1 for some time, if ever. |
How and proof video would be nice. We are really interested in your progress. |
I will post a few examples on social media, (https://www.instagram.com/p/C6Krt38ydtG/), and you are welcome to include them here as examples, as long as you attribute the source. The "how," at least until the audio model is released, is a matter of choosing an appropriate video and photo. The illusion breaks down if the head movement is too rapid or the angle is too extreme. |
Could you provide a better video the instagram reel is partially cutoff |
This is quite impressive, thank you very much! |
Here's another, feel free to use it as an example if you want: https://www.youtube.com/shorts/lgnfAuh5wBY |
https://www.microsoft.com/en-us/research/project/vasa-1/
The text was updated successfully, but these errors were encountered: