HunyuanVideo
Tencent’s 13B-parameter open video foundation model.
- Stars
- 12.6K
- Forks
- 1.4K
- Open issues
- 187
- Last commit
- 2026-10-08
Live from the GitHub API · updated 2026-10-15
What is HunyuanVideo?
HunyuanVideo is a large open video generation model from Tencent with strong motion and visual quality. It has image-to-video and avatar variants, FP8 weights and multi-GPU parallel inference, and is supported in ComfyUI and Diffusers.
Key features
- High-quality text-to-video up to 720p
- Image-to-video variant
- FP8 weights and xDiT multi-GPU inference
- ComfyUI and Diffusers integrations
System requirements
- Platforms
- Linux
- GPU
- NVIDIA
- VRAM
- 45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations
How to install HunyuanVideo
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Linux
- 1Clone and install following the README’s conda instructions.
git clone https://github.com/Tencent-Hunyuan/HunyuanVideo cd HunyuanVideo pip install -r requirements.txt - 2Download the weights as described in ckpts/README.md, then sample.
python3 sample_video.py --video-size 720 1280 --video-length 129 --infer-steps 50 --prompt "A cat walks on the grass, realistic style." --flow-reverse --save-path ./results
Strengths
- Excellent motion quality
- Active ecosystem
Limitations
- Very high VRAM needs
- Custom license with regional restrictions
HunyuanVideo alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| HunyuanVideo Tencent’s 13B-parameter open video foundation model. | 12.6K | Tencent Hunyuan Community License | 45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations | |
| Wan 2.2 Alibaba’s open-weight video generation models (text, image and speech to video). | 17.9K | Apache-2.0 | 24 GB for TI2V-5B at 720p; 80 GB-class GPUs (or offloading) for A14B models | |
| LTX-Video Fast, real-time-capable open video generation from Lightricks. | 11.1K | Apache-2.0 | 12 GB+ for smaller variants; more for 13B models | |
| CogVideoX Open text-to-video and image-to-video models from Zhipu AI / Tsinghua. | 13.1K | Apache-2.0 | ~12–24 GB depending on model and optimizations (see the README table) | |
| FramePack Long image-to-video generation on laptop GPUs with as little as 6 GB VRAM. | 17.3K | Apache-2.0 | 6 GB minimum | |
| AnimateDiff Animate your Stable Diffusion checkpoints with plug-in motion modules. | 12.3K | Apache-2.0 | 8–12 GB |
Related models
FAQ
Is HunyuanVideo free?
Yes — HunyuanVideo is open-source software released under the Tencent Hunyuan Community License license. Check the license (and any model weight licenses) before commercial use.
Does HunyuanVideo run on Windows, Mac and Linux?
HunyuanVideo supports: Linux.
What hardware do I need for HunyuanVideo?
NVIDIA. VRAM: 45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations
How do I install HunyuanVideo?
1. Clone and install following the README’s conda instructions. 2. Download the weights as described in ckpts/README.md, then sample.
What are the best HunyuanVideo alternatives?
Popular alternatives include Wan 2.2, LTX-Video, CogVideoX, FramePack. See the comparison table on this page.
Can I use HunyuanVideo online without installing it?
If you don’t have a large GPU, AiLoft runs Veo 3.1 and Kling 2.5 in the cloud — generate and compare clips in the browser.
No 24 GB GPU? Generate AI video online
Run Veo 3.1 and Kling 2.5 in the cloud and compare clips side by side — pay per clip.