Live data from Hacker News

Show HN: Infinity – Realistic AI characters that can speak

news.ycombinator.com

61–70 of 320 posts

Re: Show HN: Infinity – Realistic AI characters that can speak

#61
post #43

I tried with the drake and drake saying some stuff and while its cool, its still lacking, like his teeth are disappearing partially :S

Thanks for the feedback. The current model was trained at ~320x320 resolution. We believe going higher will result in better videos with finer detail, which we plan to do soon.

Re: Show HN: Infinity – Realistic AI characters that can speak

#64

It's incredibly good - bravo. Only thing missing for this to be immediately useful for content creation, is more variety in voices, or ideally somehow specifying a template sound clip to imitate.

Thanks for the feedback! We used to have more voices, but didn't love the experience, since users had no way of knowing what each voice sounded like without creating a clip themselves. Probably having pre-generated samples for each one would solve that. Let us know if you have any other ideas.

We're also very excited about the template idea! Would love to add that soon.

Re: Show HN: Infinity – Realistic AI characters that can speak

#68
post #4

I look forward to movies that are dubbed moving the face+lips to the dubbed text. Also using the original actors voice.

I thought the larger public was starting to accept subtitles so I was hoping we’d rather see the end of dubbed movies !

Re: Show HN: Infinity – Realistic AI characters that can speak

#69
post #56

Have to say, whilst this tech has some creepy aspects, just playing about with this my family have had a whole sequence of laughs out loud moments - thank you!

I'm so glad! We're trying to increase the laugh out loud moments in the world :)

Re: Show HN: Infinity – Realistic AI characters that can speak

#70

I tried making this short clip [0] of Baron Vladimir Harkonnen announcing the beginning of the clone war, and it's almost fine, but the last frame somehow completely breaks. [0]: https://6ammc3n5zzf5ljnz.public.blob.vercel-storage.com/inf2...

This is a bug in the model we're aware of but haven't been able to fix yet. It happens at the end of some videos but not all.

Our hypothesis is that the "breakdown" happens when there's a sudden change in audio levels (from audio to silence at the end). We extend the end of the audio clip and then cut it out the video to try to handle this, but it's not working well enough.

Post reply on HN