HunyuanVideo

Tencent’s 13B video generation model — top-tier motion, heavy VRAM needs.

Install Repository Compare

Fit.

Catalog snapshot

Platforms: Linux, Macos, Windows
Operating systems: Linux, macOS, Windows
Ram floor: 32 GB
Gpu: Required · 45 GB VRAM
Docker: No
Setup: Advanced
Deploy as: Local
Commercial use: Check the license

Tencent Hunyuan Community License — read the MAU clause before product use.

Project.

Fetched Sep 12, 2026¹

License: Other
Stars: 12.5k¹
Forks: 1.3k¹
Open issues: 169¹
Language: Python¹
Last commit: Jun 29, 2026¹
Latest release: Jun 15, 2025
Tags: videodiffusion13b

About.

HunyuanVideo is Tencent’s 13B text- and image-to-video model with the best open motion realism of its class. Full precision wants 45 GB+ VRAM; community quantizations bring it to 24 GB cards. Community license, under-100M-MAU terms.

13B video model · image-to-video · integrated VAE · LoRA support

Alternatives.

Nearby.

All Video AI

WWan2.1Alibaba’s open text-to-video and image-to-video stack.Compare
OOpen-SoraApache-2.0 research stack for training and running video diffusion on 24 GB cards.Compare
CCogVideoXTHUDM open video diffusion with strong prompt following.Compare
FFramePackLong local image-to-video with a low VRAM floor.Compare
LLTX-VideoLightricks open video model aimed at faster local clips.Compare