theEricMa/OTAvatar
[CVPR2023] OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering.
This project helps create realistic talking head videos from a single image of a person. You provide one image of a person's face and an audio input (like a speech recording), and it generates a video of that person speaking the audio, complete with synchronized lip movements and facial expressions. This is ideal for content creators, marketers, or educators who need to generate custom video content quickly.
327 stars. No commits in the last 6 months.
Use this if you need to quickly produce a video of a specific person speaking custom audio, using only one photo of their face.
Not ideal if you require highly nuanced emotional expressions or body language beyond basic head movements and lip sync.
Stars
327
Forks
41
Language
Python
License
—
Category
Last pushed
Mar 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/theEricMa/OTAvatar"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrikhuber/eos
A lightweight 3D Morphable Face Model library in modern C++
Uason-Chen/CTR-GCN
[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for...
PeterL1n/BackgroundMattingV2
Real-Time High-Resolution Background Matting
PeterL1n/RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Zielon/MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]