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.
docs: unify Chinese community table cells and reword the reference footnote
Bowen Xuee7528b8d3e5c
diff --git a/docs/community-results.md b/docs/community-results.mdindex f80ae50..77d839d 100644--- a/docs/community-results.md+++ b/docs/community-results.md@@ -138,5 +138,5 @@ Thanks to the community members who sent diagnostic reports. FreeVideo already r- ⁹ The drive holding the model files reads at about 80 MB/s; reading them took about 570 s of the 1676 s.- ¹⁰ GPU shared: other programs were using about 29% of the graphics card during the run, so FreeVideo's steps ran at a little over 70% of their usual speed. With the card free, the same request takes about 7200 s.- ¹¹ With 16 GB of RAM, the text encoder and part of the video model cannot stay in memory and are read from the drive; text encoding and the first pass, which wait on these reads, took about 460 s of the 887 s.-- ¹² Reference-video task: the reference video and audio roughly double the sequence the model processes, so each step takes about twice as long as a plain request of the same size.+- ¹² Task with a reference: every step also processes the reference video, images or audio, so each step takes longer than a plain request of the same size, up to about twice as long with a long reference.- ¹³ Preview (first pass only).diff --git a/docs/zh-CN/community-results.md b/docs/zh-CN/community-results.mdindex 0d646c7..57c867e 100644--- a/docs/zh-CN/community-results.md+++ b/docs/zh-CN/community-results.md@@ -80,12 +80,12 @@| 5060 笔记本 | 8 GB | 32 GB | 1344×768 | 3 s | 标准 | 0.4.7 | 541 s | 0.4.7 | 已是最优 || 5060 Ti | 16 GB | 34 GB | 1344×768 | 5.2 s | 标准 | 0.4.8 | 2521 s | 0.4.8 | 已是最优¹² || 4060 | 8 GB | 32 GB | 768×1344 | 17 s | 轻量 | 0.4.8 | 1942 s | 0.4.8 | 已是最优 |-| M1 Max | 统一内存 | 64 GB | 960×544 | 2.3 s | 轻量 | 0.4.8 | 1226 s | 0.4.8 | 已是最优 |+| M1 Max | 统一内存 | 64 GB | 960×544 | 2.3 s | 轻量 | 0.4.8 | 1226 s | 0.4.8 | 已是最优 || 3070 | 8 GB | 32 GB | 1344×768 | 5.2 s | 轻量⁵ | 0.4.8 | 285 s | 0.4.8 | 已是最优 || 3060 | 12 GB | 34 GB | 1664×960 | 6.6 s | 标准 | 0.4.8 | 4025 s | 0.4.8 | 已是最优¹² |-| 4070 Laptop | 8 GB | 34 GB | 1344×768 | 15 s | 轻量⁵ | 0.4.8 | 1444 s | 0.4.8 | 已是最优¹² |-| 5060 Ti | 16 GB | 56 GB | 960×544 | 10 s | 轻量 | 0.4.6 | 904 s | 0.4.9 | 805 s (−99 s) |-| 3070 Laptop | 8 GB | 64 GB | 1344×768 | 10 s | 轻量 | 0.4.9 | 1267 s | 0.4.9 | 已是最优 |+| 4070 笔记本 | 8 GB | 34 GB | 1344×768 | 15 s | 轻量⁵ | 0.4.8 | 1444 s | 0.4.8 | 已是最优¹² |+| 5060 Ti | 16 GB | 56 GB | 960×544 | 10 s | 轻量 | 0.4.6 | 904 s | 0.4.9 | 805 s(−99 s) |+| 3070 笔记本 | 8 GB | 64 GB | 1344×768 | 10 s | 轻量 | 0.4.9 | 1267 s | 0.4.9 | 已是最优 || 3060 | 12 GB | 64 GB | 768×1344 | 5 s | 轻量 | 0.4.12 | 639 s | 0.4.12 | 已是最优 || 5080 | 16 GB | 64 GB | 768×1344 | 3 s | 极致 | 0.3.20 | 216 s | 0.3.20 | 已是最优 || 4060 Ti | 8 GB | 32 GB | 960×544 | 5 s | 轻量 | 0.4.12 | 333 s | 0.4.12 | 已是最优 |@@ -138,5 +138,5 @@- ⁹ 模型文件所在的硬盘读取约 80 MB/s,1676 秒里约 570 秒用于读取模型文件。- ¹⁰ 显卡被占用:生成过程中其他程序占用了约 29% 的显卡,FreeVideo 每一步只有独占时七成多一点的速度;显卡空出来时,同样的请求约需 7200 秒。- ¹¹ 16 GB 内存留不下文本编码器和视频模型的一部分,需要从硬盘读取;887 秒里约 460 秒是等待这些读取的文本编码和第一遍。-- ¹² 参考视频任务:参考视频和参考音频使模型处理的序列约增加一倍,每步耗时约为相同尺寸普通请求的两倍。+- ¹² 带参考的任务:每一步还要处理参考视频、参考图片或参考音频,所以每步耗时比相同尺寸的普通请求长;参考较长时约为两倍。- ¹³ 预览(只做第一遍)。