Fantasy-AMAP/fantasy-portrait
FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
This tool helps animators and content creators bring static portraits to life by animating facial expressions. You provide an input image, optionally with multiple characters, and a 'driver' video showing the desired facial movements. The output is a video of your input portrait(s) dynamically expressing the emotions from the driver video, making character animations more engaging.
502 stars. No commits in the last 6 months.
Use this if you need to create compelling, expressive animations from still images, especially for multiple characters in a single scene or animating based on separate drive videos.
Not ideal if you're looking for a simple, no-code online tool, as this requires setting up a local development environment.
Stars
502
Forks
35
Language
Python
License
Apache-2.0
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-portrait"
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