FreeVideo 把 MiniMax H3 的视频生成搬到个人电脑:最低 8 GB 显存加 16 GB 内存,程序会依据硬件条件选择加速路径。底层采用 Video DeltaNet(VDN),提供 Windows、macOS、Linux 三个平台版本,并附社区结果画廊以及 Discord、QQ 群、微信群入口;说明文档有中英文两个版本。画廊可将四个质量档位并排对照,便于判断画质与速度的取舍。v0.5.0 加入 H3 Image,本地能生成最高 16 MP 图片,显存门槛仍为 8 GB;v0.4.0 带来 AI agent、分钟级视频和编辑视图,文档提到 Claude Code、Codex 这类 agent 可参与制作。仓库以 Python 编写,当前在 Python 日榜排第 16 位,面向本地部署。想在自有设备上试视频与图像生成、又不想被高显存挡住的用户,可按平台选择版本。Apache-2.0 许可。
| Windows | macOS | Linux | Community Results | Gallery | Discord | QQ Group | WeChat Group |
English · 中文
Make videos on the computer you already own. Powered by Video DeltaNet (VDN), FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, with acceleration adapted to your hardware.
https://github.com/user-attachments/assets/ecda7d0d-7fbe-4e0c-8c29-8f3315bafc15
More clips and the four quality levels side by side in the gallery →
FreeVideo is a local inference engine for MiniMax H3 on consumer GPUs, built on OpenVDN's 8-step VDN-H3 model with Video DeltaNet's hybrid attention.
It coordinates VRAM, system memory and disk, adapting weight placement, compute precision and attention kernels to the available hardware. FreeVideo runs as a ComfyUI plugin, with launchers for Windows, macOS and Linux. Its core features include:
Security software: FreeVideo.exe is code-signed. If security software blocks FreeVideo.exe or quarantines files in the FreeVideo folder, check that the SHA-256 of FreeVideo.exe matches the value on the release page, then restore the files and add the FreeVideo folder to the software's exclusion list.
Offline installation: Download the packages from Quark and drag the ZIP files into the launcher without extracting them. A fully offline installation needs the four model packs (video model, text encoder, video & audio decoder, and sampling caches), plus the environment package for a new ComfyUI installation. After importing only the environment package, you can also choose Automatic download for the models (v0.3.12 or newer). The audio reference cache is optional and is used only when a reference includes audio.
This preview has been tested on an M5 Mac with 24 GB of unified memory. See the Mac guide for generation times and memory.
The Mac preview isn't notarized by Apple yet, so macOS blocks it the first time you open it. Download it only from the Releases page, then check the file and approve it as described in the Mac guide. This approves FreeVideo only; your other security settings stay as they are.
Install FreeVideo as a custom node:
cd ComfyUI/custom_nodes
git clone https://github.com/FlashML-org/FreeVideo.git
Restart ComfyUI, open Workflow → Browse Templates → FreeVideo → FreeVideo-All-in-One, and complete the setup in FreeVideo Settings.
To update, run git pull in custom_nodes/FreeVideo (or update the node in ComfyUI-Manager) and restart ComfyUI.
Desktop: Download FreeVideo-Linux-x86_64.AppImage, make it executable and open it, then follow the same steps as on Windows.
Terminal or server:
git clone https://github.com/FlashML-org/FreeVideo.git && cd FreeVideo
./setup.sh
Setup installs FreeVideo, ComfyUI and the models, then opens FreeVideo in the browser. Afterwards, type freevideo to open it again. On a server, connect from your own computer through SSH, or run freevideo server --listen 0.0.0.0 for an access link on your local network. See the Linux guide.
Report bugs in GitHub Issues, or ask questions on Discord, QQ or WeChat.
FreeVideo is based on VDN-H3. If you use FreeVideo in your research, please cite the Video DeltaNet paper:
@article{xi2026videodeltanet,
title={Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation},
author={Xi, Haocheng and Xie, Yiming and Zhao, Hexu and Zhang, Yiwen and Liu, Michael and Creavin, Thomas and Keutzer, Kurt and Li, Xiuyu and Lv, Zhaoyang and Xu, Chenfeng and Feng, Haiwen},
journal={arXiv preprint arXiv:2609.20744},
year={2026}
}
Bowen Xue · Shuo Yang · Haocheng Xi · Xiaoze Fan · Chenfeng Xu
Special thanks to AIwood爱屋研究室 and T8star-Aix for testing the project and providing valuable feedback.
Listed in chronological order of participation.
We thank OpenVDN for Video DeltaNet / VDN-H3 and its open-source model weights, training code and inference implementation.
We thank Impossible Research for providing computation resources.
We also thank MiniMax H3 for the base model and the following projects: ComfyUI, Diffusers, SageAttention, the MiniMax H3 latent upscaler, the H3 text encoder for ComfyUI and Qt for Python.
The code is released under the Apache License 2.0. The model weights are licensed under the MiniMax H3 Community License, which includes territorial and acceptable-use restrictions.
| 日期 | 榜单 | 排名 | 周期新增 | 总 STAR |
|---|