Vibe Coding DiscoverHunyuanVideo
View on GitHubHunyuanVideo: A Systematic Framework For Large Video Generation Model
Open-source code and pretrained weights for Tencent's 13B-parameter HunyuanVideo generative model. Includes text-to-video inference, a Gradio demo, prompt rewriting, multi-GPU execution, and FP8 support.
Use Cases
Generate videos from text promptsGenerate images with a unified image-and-video architectureRun video generation inference across multiple GPUsGenerate videos with FP8 weights to reduce GPU memory useRewrite prompts for video generation
Built With
- Language
- Python
- Frameworks
- PyTorch · Hugging Face Diffusers · Hugging Face Transformers · Accelerate · Gradio · xDiT
Tags
video generation · text-to-video · diffusion transformer · generative AI · video foundation model · multimodal · GPU inference · FP8 · multi-GPU