Fantasy-AMAP/fantasy-talking

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

55
/ 100
Established

Synthesizes audio-driven talking portraits by conditioning the Wan2.1 diffusion video model with wav2vec2 audio embeddings and optional motion prompts for controllable gesture generation. Achieves efficient inference through persistent parameter optimization, reducing memory requirements from 40GB to 5GB while supporting both Hugging Face and ModelScope ecosystem integrations. Provides a Gradio interface and ComfyUI node wrapper for accessible deployment.

1,622 stars.

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.