Fantasy-AMAP/fantasy-talking2

[AAAI 2026] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

23
/ 100
Experimental

This project helps animators and content creators generate highly realistic talking portraits from audio. It takes an audio input and an image of a person, and outputs a video of that person speaking the audio with natural lip movements, expressions, and overall visual quality. Anyone creating animated characters for media, marketing, or educational content would find this useful.

No commits in the last 6 months.

Use this if you need to animate a static portrait or image to realistically speak an audio track, prioritizing natural motion, accurate lip-sync, and high visual quality.

Not ideal if you're looking to generate full-body animations or modify the background environment of the video.

portrait-animation video-generation content-creation digital-media virtual-assistants
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 7 / 25
Community 6 / 25

How are scores calculated?

Stars

66

Forks

3

Language

License

Last pushed

Aug 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Fantasy-AMAP/fantasy-talking2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.