Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation
This tool helps animators and content creators generate realistic, expressive portrait animations from a single still image. You provide a static portrait photo and a separate video demonstrating the desired motion and facial expressions. The output is a new video where the person from your photo realistically performs the movements and expressions from the driving video, creating consistent and high-quality animations.
336 stars.
Use this if you need to bring a static portrait image to life with dynamic facial expressions and body movements, such as for creating virtual avatars, animated characters, or engaging marketing content.
Not ideal if you're looking for a simple web-based solution for basic image animation, as it requires specific hardware and command-line execution.
Stars
336
Forks
35
Language
Python
License
—
Category
Last pushed
Dec 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Tencent-Hunyuan/HunyuanPortrait"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...
3DTopia/MaterialAnything
[CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion