Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

http://polymorf.me/

A Talking Avatar AI generator similar to d-id. Worked on it for 2 months but I have problems adding natural head movement to the speaker. About 100 users so far but 0 revenue. Very low traffic (like 10-20 users/day). Not sure where to go next, at moment trying to focus more on marketing and getting feedback



Have you tried just going image-to-depth map? You could render the image in 3d with shallow depth then just shift the camera a bit

The main issue with moving mouths is the relative stillness, it's enough to introduce coherent motion in the user's field of vision.

If anything it might give you a unique distinction vs d-id, the head movements it doesn't aren't natural at all, but it's enough to not make it feel stiff


Interesting. I guess camera movement on 3d scenes would make the video more dynamic. That will put the focus more the "video aspect" as opposed to "Avatar" aspect of the product. I might explore that feature a little bit.





Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: