foivospar/NED
PyTorch implementation for NED (CVPR 2022). It can be used to manipulate the facial emotions of actors in videos based on emotion labels or reference styles.
This project helps video creators, such as filmmakers or animators, modify the emotional expressions on actors' faces in existing video footage. You input a video of a person speaking or expressing themselves, along with desired emotion labels like "happy" or "angry," or a reference video showing the desired style. The system then outputs a new video where the actor's face conveys the new emotions, all while preserving the original speech and mouth movements.
160 stars. No commits in the last 6 months.
Use this if you need to alter the emotional performance of an actor in a video without re-shooting or losing the original dialogue, for applications like movie post-production, video games, or creating realistic avatars.
Not ideal if you need to generate entirely new facial movements or gestures beyond emotion, or if you require real-time manipulation for live applications.
Stars
160
Forks
26
Language
Python
License
MIT
Category
Last pushed
Oct 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/foivospar/NED"
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