Skip to content
SPECIFICTION
Get listed

HunyuanVideo

github.com

LinuxSelf-hosted
Visit github.com
Spec score 7.6 #13 of 23 in Text-to-Video Generators

Spec sheet

Purpose
HunyuanVideo is an open-source video foundation model with code and pretrained weights for video generation.Read 11 Oct 2026 · github.com
Product
HunyuanVideo is an open-source video foundation model; the repository provides PyTorch model definitions, pretrained weights, and inference and sampling code.Read 11 Oct 2026 · github.com
Integrations
The repository says HunyuanVideo is integrated into Diffusers and offers parallel inference code powered by xDiT.Read 11 Oct 2026 · github.com
Support
Tencent says it is not obligated to support, update, train users on, or develop further versions of the released works.Read 11 Oct 2026 · github.com
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.Read 11 Oct 2026 · github.com
Headquarters
Shenzhen, ChinaRead 28 Sep 2026 · github.com
Founded
1998Read 28 Sep 2026 · github.com
Maker
Tencent says it was founded in 1998 and is headquartered in Shenzhen, China.Read 11 Oct 2026 · tencent.com
AI avatars
NoRead 19 Sep 2026 · github.com
API access
NoRead 19 Sep 2026 · github.com
Architecture
The model uses a unified image and video generative architecture with a hybrid dual-stream to single-stream Transformer design and full attention.Read 11 Oct 2026 · github.com
Commercial use
YesRead 19 Sep 2026 · github.com
Community tools
The project lists community contributions including native ComfyUI support and a ComfyUI wrapper.Read 11 Oct 2026 · github.com
Downloads
The project provides inference code and pretrained model weights, with FP8 weights also available to reduce GPU memory use by about 10GB.Read 11 Oct 2026 · github.com
Generation
The repository supports text-prompt video generation at 540p and 720p, with 129-frame configurations.Read 11 Oct 2026 · github.com
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.Read 11 Oct 2026 · github.com
Image-to-video
The project links a separate HunyuanVideo image-to-video model with inference code and checkpoints.Read 11 Oct 2026 · github.com
Lower-memory option
FP8 quantized weights save about 10GB of GPU memory, according to the repository.Read 11 Oct 2026 · github.com
Maximum resolution
1080pRead 19 Sep 2026 · github.com
Model size
The model has over 13 billion parameters.Read 11 Oct 2026 · github.com
Operating system
Linux is the tested operating system, and the repository provides a Linux installation guide and Docker images.Read 11 Oct 2026 · github.com
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.Read 11 Oct 2026 · github.com
Text encoder
The model uses a decoder-only multimodal large language model as its text encoder.Read 11 Oct 2026 · github.com
Text-to-video
The released model generates videos from text prompts, with supported output settings up to 720p and 129 frames.Read 11 Oct 2026 · github.com
Use and audience
The project releases code and weights to let the community experiment with video-generation ideas and applications.Read 11 Oct 2026 · github.com

Where Specifiction places it

Alternatives to HunyuanVideoAll alternatives →