https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
291–300 of 320 posts
https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
Oh, this is amazing! I've been having so much fun with it. One small issue I've encountered is that sometimes images remain completely static. Seems to happen when the audio is short - 3 to 5 seconds long.
Can you share an example of this happening? I am curious. We can get static videos if our model doesn't recognize it as a face (e.g. an Apple with a face, or sketches). Here is an example: https://toinfinityai.github.io/v2-launch-page/static/videos/... I would be curious if you are getting this with more normal images.
[1] https://i.pinimg.com/236x/ae/65/d5/ae65d51130d5196187624d52d...
[2] https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
[3] https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
But that image was one which both could find a face and gave a static image once.
https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...
There is prior art here, e.g. Emo from alibaba research ( https://humanaigc.github.io/emote-portrait-alive/ ), but this is impressive and also actually has a demo people can try, so that's awesome and great work!
Yep for sure! EMO is a good one. VASA-1 (Microsoft) and Loopy Avatar (ByteDance) are two others from this year. And thanks!
Earlier quoted context omitted.
just an idea, but what if the appended audio clip was reversed to ensure continuity in the waveform? That is, if > <PILC.
This is exactly what we do today! It seems to work better the more you extend it, but extending it too much introduces other side effects (e.g. the avatar will start to open its mouth, as if it were preparing to talk).
Out of curiosity, where are you training all this ? aka where do you find the money to support such training
Well, I don't know what to think about this, I don't know where we are going. I should read some scifi from back then about conversational agents maybe ? https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2... https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2... https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...