Fantasy-AMAP/fantasy-talking

[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

55
/ 100
Established

This project helps create realistic talking videos from a still image and an audio file. You provide a photo of a person and an audio recording of what you want them to say, and it generates a video where the person in the photo speaks the words from the audio with natural lip movements and facial expressions. This is ideal for content creators, marketers, or educators looking to animate static images for presentations or social media.

1,622 stars.

Use this if you need to quickly generate a video of a person speaking from just an image and an audio file, with the option to guide their non-verbal communication.

Not ideal if you need to generate full-body animated characters or require highly complex, custom animation beyond talking head videos.

video-production content-creation digital-avatars marketing-material e-learning
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,622

Forks

126

Language

Python

License

Apache-2.0

Last pushed

Jan 26, 2026

Commits (30d)

0

Get this data via API

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

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