Tencent-Hunyuan/HunyuanVideo

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

12476 stars · 1319 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

HunyuanVideo is Tencent's open-source framework for large-scale video generation, providing PyTorch model definitions, pre-trained weights, and inference/sampling code for a diffusion-transformer based text-to-video model. It includes variants for image-to-video, audio-driven avatar animation, and customized video generation.

Use cases

• generate videos from text prompts
• convert a still image into a video
• create audio-driven talking avatar animations
• run a state-of-the-art open video generation model locally
• fine-tune or build custom video generation pipelines
• research diffusion transformer architectures for video

When to choose

• you need high-quality open-weights text-to-video or image-to-video generation
• you have GPU hardware and want to run video generation in PyTorch
• you want a research foundation for video diffusion models
• you need audio-driven human animation or customized video generation

When to avoid

• you lack a capable GPU or large VRAM
• you need a simple hosted API without managing model weights
• your project requires a permissive license (license is custom/restricted)
• you only need lightweight video editing rather than generative synthesis

Facets

library · maturity active

video-processing machine-learning deep-learning llm-inference artificial-intelligence deep-learning media python video-generation diffusion-models diffusion-transformer text-to-video image-to-video pytorch generative-ai video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Tencent-Hunyuan/HunyuanVideo")