How long before we can get to this level

[gibsonhu123]

https://www.microsoft.com/en-us/research/project/vasa-1/

[MisterT96]

Just wait until they release new weights and then compare again.

[gessyoo]

https://www.microsoft.com/en-us/research/project/vasa-1/

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.

[MisterT96]

https://www.microsoft.com/en-us/research/project/vasa-1/

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.

[gessyoo]

https://www.microsoft.com/en-us/research/project/vasa-1/

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.

[gibsonhu123]

https://www.microsoft.com/en-us/research/project/vasa-1/

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/reel/C6CdHDTOtFW/), 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

[MisterT96]

https://www.microsoft.com/en-us/research/project/vasa-1/

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/reel/C6CdHDTOtFW/), 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.

This is quite impressive, thank you very much!

[gessyoo]

https://www.microsoft.com/en-us/research/project/vasa-1/

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/C5UbGIuPh7G), 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.

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