JeremyCJM/DiffSHEG
[CVPR'24] DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
This tool helps create realistic 3D animated characters that express themselves naturally while speaking. You provide an audio file, and it generates corresponding 3D facial expressions and body gestures in real-time. This is ideal for animators, content creators, or game developers looking to automate character animation based on dialogue.
196 stars. No commits in the last 6 months.
Use this if you need to quickly generate lifelike 3D character animations, including both facial expressions and body movements, from spoken audio.
Not ideal if you require highly specific, manually controlled, or stylized animations that do not rely on speech input.
Stars
196
Forks
16
Language
Python
License
BSD-3-Clause
Category
Last pushed
Apr 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JeremyCJM/DiffSHEG"
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