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.
README: link the community results again and keep the intro short (#154)
Bowen Xue7f2398f7dfef
diff --git a/README.md b/README.mdindex d03cd91..bfdc6f6 100644--- a/README.md+++ b/README.md@@ -32,14 +32,14 @@ https://github.com/user-attachments/assets/ecda7d0d-7fbe-4e0c-8c29-8f3315bafc15FreeVideo is a local inference engine for MiniMax H3 on consumer GPUs, built on [OpenVDN](https://github.com/OpenVDN)'s 8-step [VDN-H3](https://huggingface.co/OpenVDN/vdn-minimax-h3) model with [Video DeltaNet](https://openvdn.github.io/)'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 and a server mode for remote GPUs. Its core features include:+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:- **Hardware-adaptive execution**: Chooses the weight format for each GPU, int8 on GeForce and RTX 30-series cards and FP8 on workstation and datacenter cards, 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](docs/LoRA.md).- **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, Mac and Linux launchers set up ComfyUI, the runtime environment and the models, reuse existing models, and support offline installation. On Linux, `./setup.sh` does the same from a terminal.+- **One-click deployment**: The Windows, Mac and Linux launchers set up ComfyUI, the runtime environment and the models, reuse existing models, and support offline installation.## Getting Started@@ -92,6 +92,7 @@ Setup installs FreeVideo, ComfyUI and the models, then opens FreeVideo in the br### More details- [FreeVideo Adaptive Execution Planner](docs/execution-planning.md)+- [Community results](docs/community-results.md)### Supportdiff --git a/README.zh-CN.md b/README.zh-CN.mdindex fd15e27..6c547eb 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -32,14 +32,14 @@ https://github.com/user-attachments/assets/ecda7d0d-7fbe-4e0c-8c29-8f3315bafc15FreeVideo 是面向消费级显卡的 MiniMax H3 本地推理引擎,基于 [OpenVDN](https://github.com/OpenVDN) 的 8 步模型 [VDN-H3](https://huggingface.co/OpenVDN/vdn-minimax-h3) 和 [Video DeltaNet](https://openvdn.github.io/) 的混合注意力。-它统一调度显存、内存与磁盘,并根据硬件条件调整权重放置、计算精度和注意力内核。FreeVideo 以 ComfyUI 插件形式提供,配备 Windows、macOS 和 Linux 启动器,并支持在远程 GPU 服务器上以服务器模式运行。主要特性包括:+它统一调度显存、内存与磁盘,并根据硬件条件调整权重放置、计算精度和注意力内核。FreeVideo 以 ComfyUI 插件形式提供,配备 Windows、macOS 和 Linux 启动器。主要特性包括:- **硬件自适应**:针对不同显卡选择权重格式(GeForce 和 RTX 30 系用 int8,专业卡和数据中心卡用 FP8),并自动探测可用的注意力内核,无需手动配置。- **低显存推理**:通过权重流式加载、异步预取与分块计算降低峰值显存,最低只需 8GB 显存和 16GB 内存。- **多模态输入**:支持文本、首帧、尾帧,以及图像、视频、音频参考输入。- **社区 LoRA**:支持在工作流中使用 MiniMax H3 社区 LoRA。[查看效果对比](docs/LoRA.zh-CN.md)。- **ComfyUI 集成**:在 ComfyUI 中提供专门的创作面板,支持二次采样和批量生成,并可浏览历史作品;需要更精细的控制时,可切换到节点视图,接入 LoRA 或自定义工作流。-- **一键部署**:Windows、Mac 和 Linux 启动器自动完成 ComfyUI、运行环境与模型的部署,可复用已有模型,并支持离线安装。Linux 上也可以在终端运行 `./setup.sh` 一次装好。+- **一键部署**:Windows、Mac 和 Linux 启动器自动完成 ComfyUI、运行环境与模型的部署,可复用已有模型,并支持离线安装。## 开始使用@@ -92,6 +92,7 @@ git clone https://github.com/FlashML-org/FreeVideo.git && cd FreeVideo### 更多文档- [FreeVideo Adaptive Execution Planner](docs/zh-CN/execution-planning.md)+- [社区实测](docs/zh-CN/community-results.md)### 问题反馈