| Posts | ||
|---|---|---|
| Experimental Reusable Avatar 👁️👄 | Post Reply | |
| Thread Options | ||
|
|
Sep 9 2023 Anchor | |
|
I'm experimenting with an algorithm that allows continuous, real-time reuse of an existing Avatar Animation Sequence). New text can re-use the avatar without generating a new video from the provider. The process begins with any still image (real-person photo, MidJourney, etc) used to AI-Generate an animation video (e.g. D-ID, SadTalker). It works by re-using frame-sequences from the generated video. The original generated video contains all the mouth-shape-sequences that the algo needs. Basically (with some additional magic), the algo takes the sequences that it needs and stitches them together to match the new input-text. Any thoughts on this approach or suggested use-cases? The Avatar Demo Video |
||
Only registered members can share their thoughts. So come on! Join the community today (totally free - or sign in with your social account on the right) and join in the conversation.