YoungSeng/DiffuseStyleGesture
DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models (IJCAI 2023) | The DiffuseStyleGesture+ entry to the GENEA Challenge 2023 (ICMI 2023, Reproducibility Award)
This project helps creators generate realistic and expressive body gestures for virtual characters or avatars simply by providing an audio input. It takes an audio file with speech and a specified gesture style (e.g., happy, neutral) and outputs a motion file (BVH) that animates a character's upper body. This is ideal for animators, virtual content creators, or game developers looking to add natural, synchronized gestures to spoken dialogue.
206 stars.
Use this if you need to automatically generate natural, style-controlled upper-body gestures for an avatar based on spoken audio.
Not ideal if you require full-body gesture generation or need extremely precise, hand-keyed animation control for specific complex movements.
Stars
206
Forks
31
Language
Python
License
MIT
Category
Last pushed
Nov 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/YoungSeng/DiffuseStyleGesture"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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