Skip to content

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.

Add a note on security software blocking the Windows launcher

Bowen Xue2d1a7ffd12d5
diff --git a/README.md b/README.md
index 7c841d1..95d443e 100644
--- a/README.md
+++ b/README.md
@@ -54,6 +54,8 @@ It coordinates VRAM, system memory and disk, adapting weight placement, compute
<img alt="FreeVideo creative workspace" src="https://github.com/user-attachments/assets/7647a6f8-4306-403c-b147-45d7a393e18d" width="92%">
</div>
+**Security software:** FreeVideo.exe is code-signed. If security software blocks it or quarantines files in the installation folder, compare the file's SHA-256 with the value shown for the download on the release page, restore the file, and add the FreeVideo folder to the software's exclusion list.
+
**Offline installation:** Download the packages from [Quark](https://pan.quark.cn/s/c51235b84618) 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.
### macOS (Apple silicon preview)
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 5d40f74..7807fcd 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -54,6 +54,8 @@ FreeVideo 是面向消费级显卡的 MiniMax H3 本地推理引擎,基于 [Op
<img alt="FreeVideo 创作面板" src="https://github.com/user-attachments/assets/f4719079-bb48-4836-9c64-2473477cd1a0" width="92%">
</div>
+**安全软件:** FreeVideo.exe 已进行代码签名。如果安全软件拦截该文件,或隔离了安装目录中的文件,请先将文件的 SHA-256 与发布页中该下载文件显示的值核对,一致后恢复文件,并把 FreeVideo 文件夹加入该软件的排除列表。
+
**离线安装:** 从[夸克网盘](https://pan.quark.cn/s/c51235b84618)下载离线包,将 ZIP 文件直接拖入启动器,无需解压。完全离线安装需要「视频模型」「文本编码器」「视频与音频解码器」「采样缓存」四个模型包,全新安装 ComfyUI 时还需要「运行环境」包。也可以只导入「运行环境」包,再在模型来源中选择**自动下载**(v0.3.12 及以上)。「音频参考缓存」为可选包,仅在参考素材带有音频时使用。
### macOS(Apple 芯片预览版)