Tencent-Hunyuan/HunyuanCustom
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
This project helps content creators, marketers, and video editors generate custom videos featuring specific subjects, maintaining their appearance consistently. You provide a subject's image, text prompts, audio, or an existing video, and it outputs a new video with that subject performing actions or integrated into scenes you define. It's designed for professionals who need to create custom video content efficiently, like for virtual advertisements or singing avatars.
1,211 stars.
Use this if you need to create new videos where specific characters or objects from images or other videos are consistently present and performing actions based on text, audio, or video prompts.
Not ideal if you are looking for a simple video editing tool or if your primary need is basic video trimming and merging without subject customization.
Stars
1,211
Forks
108
Language
Python
License
—
Category
Last pushed
Oct 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Tencent-Hunyuan/HunyuanCustom"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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