| Download | Discord | QQ Group | WeChat Group |
English · 中文
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
https://github.com/user-attachments/assets/ecda7d0d-7fbe-4e0c-8c29-8f3315bafc15
About
FreeVideo is a local inference engine for running MiniMax H3 on consumer GPUs. Built on OpenVDN's 8-step VDN-H3 model, it schedules VRAM, system memory and disk as a single memory hierarchy, and plans weight placement, compute precision and attention kernels according to the GPU architecture and available resources. FreeVideo is delivered as a ComfyUI plugin: the Windows launcher installs and starts ComfyUI, and on Linux FreeVideo can also be used from the command line. Its core features include:
- Hardware-adaptive execution: Chooses the FP8 compute path for each GPU architecture, either native FP8 or FP8 storage with BF16 compute, and automatically probes the available attention kernels.
- Low-memory inference: Weight streaming, asynchronous prefetching and chunked computation keep peak memory low, enabling inference with as little as 8 GB of VRAM and 16 GB of RAM.
- Multimodal inputs: Text prompts, first and last frames, and image, video and audio references.
- Community LoRAs: Use MiniMax H3 LoRAs in your workflow. See examples.
- ComfyUI integration: A dedicated creative workspace inside ComfyUI that supports two-pass sampling and batch generation and keeps a history of past creations. For finer control, switch to the node view to add LoRAs or customize the workflow.
- One-click deployment: The Windows launcher sets up ComfyUI, the runtime environment and the models, reuses existing models, and supports offline installation.
Getting Started
Windows
- Download FreeVideo.exe and run it.
- Select an existing ComfyUI folder or install a new one. Existing model folders can be added for reuse; missing models are downloaded automatically.
- Click Install & launch. ComfyUI opens in the browser with the FreeVideo workspace.
Offline installation: Download the packages from Quark and drag the ZIP files into the launcher without extracting them. The common models and the model pack for your GPU (30/40 series or 50 series) are required; a new ComfyUI installation also requires the environment package.
Existing ComfyUI
Install FreeVideo as a custom node:
cd ComfyUI/custom_nodes
git clone https://github.com/FlashML-org/FreeVideo.gitRestart ComfyUI, open Workflow → Browse Templates → FreeVideo → FreeVideo-All-in-One, and complete the setup in FreeVideo Settings.
Linux
Install:
git clone https://github.com/FlashML-org/FreeVideo.git && cd FreeVideo
./setup.shGenerate a video from a prompt file:
./freevideo generate --prompt-file prompt.txt --out video.mp4More details
Support
Report bugs in GitHub Issues, or ask questions on Discord, QQ or WeChat.
Citation
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}
}Team
Project Team
Bowen Xue · Shuo Yang · Haocheng Xi · Xiaoze Fan · Chenfeng Xu
Special Thanks
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.
Acknowledgment
FreeVideo is built on MiniMax H3 and VDN-H3, and uses the following projects: ComfyUI, Diffusers, SageAttention, the MiniMax H3 latent upscaler, the H3 text encoder for ComfyUI and Qt for Python.
License
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.