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.

State the quality levels plainly in the README News (#68)

Bowen Xue57e429fbd71f
diff --git a/README.md b/README.md
index e757489..3b597bf 100644
--- a/README.md
+++ b/README.md
@@ -21,7 +21,7 @@ https://github.com/user-attachments/assets/ecda7d0d-7fbe-4e0c-8c29-8f3315bafc15
- **2026-10-06** · **[Gallery](https://freevideo-community.pages.dev/#gallery) is live.** Watch 20-second clips made with FreeVideo, and the four quality levels side by side.
- **2026-10-06** · **[v0.2.2](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.2.2): videos carry their workflow.** Drop a FreeVideo video onto the ComfyUI canvas to restore its prompt, seed and settings.
-- **2026-10-05** · **[v0.2.0](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.2.0): four quality levels.** Light for speed, Max for detail, and one-click sharing cards for your results.
+- **2026-10-05** · **[v0.2.0](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.2.0): four quality levels.** Choose Light, Medium, High or Max for each video; higher levels use more sampling steps and take longer. Results can be exported as sharing images or videos with the generation time and GPU.
- **2026-10-05** · **[v0.1.2](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.1.2): FreeVideo on Mac.** Apple silicon Macs generate MiniMax H3 videos locally (preview).
- **2026-10-03** · **Community LoRAs.** Use MiniMax H3 LoRAs right in your workflow. See [examples](docs/LoRA.md).
- **2026-10-02** · **FreeVideo is open source.** MiniMax H3 on consumer GPUs with as little as 8 GB of VRAM.
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 559a91e..3fb0f52 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -21,7 +21,7 @@ https://github.com/user-attachments/assets/ecda7d0d-7fbe-4e0c-8c29-8f3315bafc15
- **2026-10-06** · **[作品展示](https://freevideo-community.pages.dev/#gallery)上线。** 观看 FreeVideo 生成的 20 秒视频,以及四档质量的并排对比。
- **2026-10-06** · **[v0.2.2](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.2.2):视频自带工作流。** 把 FreeVideo 生成的视频拖到 ComfyUI 画布上,即可还原提示词、种子和全部参数。
-- **2026-10-05** · **[v0.2.0](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.2.0):四档质量。** 轻量求快,极致求精,生成结果可一键导出分享卡片。
+- **2026-10-05** · **[v0.2.0](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.2.0):四档质量。** 每次生成可选择轻量、标准、精细或极致,档位越高,采样步数越多,耗时越长;生成结果可导出为带生成耗时和显卡信息的分享图片或视频。
- **2026-10-05** · **[v0.1.2](https://github.com/FlashML-org/FreeVideo/releases/tag/v0.1.2):支持 Mac。** Apple 芯片 Mac 也能本地生成 MiniMax H3 视频(预览版)。
- **2026-10-03** · **支持社区 LoRA。** 在工作流中直接使用 MiniMax H3 LoRA,参见[示例](docs/LoRA.zh-CN.md)。
- **2026-10-02** · **FreeVideo 开源。** 最低 8GB 显存,即可在消费级显卡上运行 MiniMax H3。