Fantasy-AMAP/fantasy-talking2
[AAAI 2026] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation
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.
Stars
66
Forks
3
Language
—
License
—
Category
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.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators