#HunyuanVideo
wake up babe, new open AI video generation model just dropped

HunyuanVideo
December 3, 2024 at 5:05 AM
February 22, 2025 at 6:22 PM
'tis the season of open-source video models 🎄📹⚡️

Tencent just dropped the weights for ✨HunyuanVideo✨
- 13B parameters
- competitive with closed source
- code & weights released
- demo coming soon 🔥
December 3, 2024 at 8:15 AM
ComfyUI now natively supports HunyuanVideo. With its scale of 1.3 billion parameters, HunyuanVideo represents the most comprehensive and highest-performing text-to-video model in the current open-source domain.
blog.comfy.org/p/hunyuanvid...
HunyuanVideo Native Support in ComfyUI
We’re excited to announce that HunyuanVideo, a groundbreaking 13-billion-parameter open-source video foundation model, is now natively supported in ComfyUI!
blog.comfy.org
December 21, 2024 at 5:59 AM
HunyuanvideoをComfyUIでお試し中
生成出来たのはaha体験
January 8, 2025 at 10:59 AM
This kind of re-prompting layer is used in some other video generation models, such as HunyuanVideo, to improve the quality and diversity of outputs. We don’t know for sure whether this is happening in Sora, but it wouldn’t be surprising.
October 3, 2025 at 6:00 PM
HunyuanVideoGP: Large Video Generation for the GPU Poor

It generates

- a 10.5s duration video at 1280x720 (+ loras) with 24 GB of VRAM
or
- a 14s duration video at 848x480 (+ loras) video with 16 GB of VRAM, no quantization.

github.com/deepbeepmeep...
GitHub - deepbeepmeep/HunyuanVideoGP: HunyuanVideo GP: Large Video Generation Model - GPU Poor version
HunyuanVideo GP: Large Video Generation Model - GPU Poor version - deepbeepmeep/HunyuanVideoGP
github.com
February 26, 2025 at 7:19 AM