HunyuanVideo v1.0: Open Source Video Generation by Tencent
Tencent's first open-source video generation model. Transformer-based with 3D VAE, 720p T2V and I2V.
HunyuanVideo v1.0
VideoText-to-VideoImage-to-VideoTencent's first open-source video generation model. Diffusion Transformer with 3D VAE — text-to-video and image-to-video at 720p. Prefer Comfy-Org split files for native ComfyUI; Kijai / city96 packs for wrapper or GGUF workflows.
| Developer | Tencent |
| Open-source announce | 2024-12 |
| Architecture | Diffusion Transformer + 3D VAE |
| License | Tencent-HunyuanVideo |
| Typical Comfy output | 720p T2V / I2V via Comfy-Org bf16 packs |
Guides and workflows related to this model series.
HunyuanVideo I2V in ComfyUI: Image-to-Video Workflow Guide
Generate AI videos from images with HunyuanVideo I2V in ComfyUI. Guide for GGUF, FP8, and native workflows. Covers model setup, parameter tuning, and step-by-step instructions for Tencent HunyuanVideo image-to-video generation.
HunyuanVideo T2V in ComfyUI: Text-to-Video Workflow Guide and Examples
Create AI videos from text prompts with HunyuanVideo T2V in ComfyUI. Guide covering GGUF, FP8, and native workflows for Tencent HunyuanVideo text-to-video generation, including model setup and parameter tuning.
Comments
Sign in with GitHub to join the discussion.