- Home
- AI video generators
- HunyuanVideo
On the recordRead 11 Oct 202625 facts
HunyuanVideo
HunyuanVideo · Shenzhen, China · founded 1998
On the record
- AI avatars
- Nogithub.com · read 19 Sep 2026
- API access
- Nogithub.com · read 19 Sep 2026
- Architecture
- The model uses a unified image and video generative architecture with a hybrid dual-stream to single-stream Transformer design and full attention.github.com · read 11 Oct 2026
- Commercial use
- Yesgithub.com · read 19 Sep 2026
- Community tools
- The project lists community contributions including native ComfyUI support and a ComfyUI wrapper.github.com · read 11 Oct 2026
- Downloads
- The project provides inference code and pretrained model weights, with FP8 weights also available to reduce GPU memory use by about 10GB.github.com · read 11 Oct 2026
- Generation
- The repository supports text-prompt video generation at 540p and 720p, with 129-frame configurations.github.com · read 11 Oct 2026
- Hardware requirements
- The model requires an NVIDIA GPU with CUDA; the stated peak GPU memory requirements are 60GB for 720p 129-frame generation and 45GB for 544p 129-frame generation.github.com · read 11 Oct 2026
- Image-to-video
- The project links a separate HunyuanVideo image-to-video model with inference code and checkpoints.github.com · read 11 Oct 2026
- Integrations
- The repository says HunyuanVideo is integrated into Diffusers and offers parallel inference code powered by xDiT.github.com · read 11 Oct 2026
- License
- The Tencent Hunyuan Community License grants a royalty-free limited license, excludes the EU, UK, and South Korea, and requires a separate Tencent license for products or services exceeding 100 million monthly active users at release.github.com · read 11 Oct 2026
- Lower-memory option
- FP8 quantized weights save about 10GB of GPU memory, according to the repository.github.com · read 11 Oct 2026
- Maker
- Tencent says it was founded in 1998 and is headquartered in Shenzhen, China.tencent.com · read 11 Oct 2026
- Maximum resolution
- 1080pgithub.com · read 19 Sep 2026
- Model size
- The model has over 13 billion parameters.github.com · read 11 Oct 2026
- Operating system
- Linux is the tested operating system, and the repository provides a Linux installation guide and Docker images.github.com · read 11 Oct 2026
- Product
- HunyuanVideo is an open-source video foundation model; the repository provides PyTorch model definitions, pretrained weights, and inference and sampling code.github.com · read 11 Oct 2026
- Prompt rewriting
- Its prompt rewrite model offers Normal and Master modes; the Master mode adds detail about composition, lighting, and camera movement and may lose some semantic details.github.com · read 11 Oct 2026
