HunyuanVideo v1.0: Open Source Video Generation Model for ComfyUI

Tencent's first open-source video generation model. Transformer-based with 3D VAE, 720p T2V and I2V for ComfyUI.

H

HunyuanVideo v1.0

VideoText-to-VideoImage-to-Video

Tencent'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.

Hugging FaceComfy-Org packGitHubPaperComfyUI examples
DeveloperTencent
Open-source announce2024-12
ArchitectureDiffusion Transformer + 3D VAE
LicenseOpen weights (see HF repo LICENSE)
Typical Comfy output720p T2V / I2V via Comfy-Org bf16 packs

Guides and workflows related to this model series.

HunyuanVideo Image-to-Video GGUF, FP8 and ComfyUI Native Workflow Complete Guide with Examples
HunyuanVideo Image-to-Video GGUF, FP8 and ComfyUI Native Workflow Complete Guide with Examples

A comprehensive tutorial on using Tencent's HunyuanVideo model in ComfyUI for image-to-video generation, including environment setup, model installation, and workflow instructions

Video
I2v
Hunyuanvideo
HunyuanVideo Text-to-Video Workflow Guide and Examples
HunyuanVideo Text-to-Video Workflow Guide and Examples

A comprehensive tutorial on using Tencent's Hunyuan Video model in ComfyUI for text-to-video generation, including environment setup, model installation, and workflow instructions

Video
T2v