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.

docs: add a community result row

Bowen Xued018c71ebe29
diff --git a/docs/community-results.md b/docs/community-results.md
index ca1a82f..70fbea6 100644
--- a/docs/community-results.md
+++ b/docs/community-results.md
@@ -78,6 +78,7 @@ Thanks to the community members who sent diagnostic reports. FreeVideo already r
| 3090 | 24 GB | 64 GB | 1344×768 | 6.6 s | Light | 0.3.24 | 461 s | 0.4.0 | 430 s (−31 s) |
| 3060 Laptop | 6 GB | 40 GB | 1344×768 | 5.2 s | Light | 0.4.7 | 510 s | 0.4.7 | Already optimal |
| 5060 Laptop | 8 GB | 32 GB | 1344×768 | 3 s | Medium | 0.4.7 | 541 s | 0.4.7 | Already optimal |
+| 5060 Ti | 16 GB | 34 GB | 1344×768 | 5.2 s | Medium | 0.4.8 | 2521 s | 0.4.8 | Already optimal¹² |
- Time: end to end, from submission until the video is saved.
- After: the estimated time, derived from the report's stage times and from complete planned runs on our test machines (RTX 3090 and RTX 5060 Ti on Windows, RTX PRO 6000 on Linux) under the reporting machine's VRAM and RAM limits, not from reruns on that machine.
@@ -93,3 +94,4 @@ 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.
diff --git a/docs/zh-CN/community-results.md b/docs/zh-CN/community-results.md
index 9a42967..41bc5d3 100644
--- a/docs/zh-CN/community-results.md
+++ b/docs/zh-CN/community-results.md
@@ -78,6 +78,7 @@
| 3090 | 24 GB | 64 GB | 1344×768 | 6.6 s | 轻⁠量 | 0.3.24 | 461 s | 0.4.0 | 430 s⁠(−31 s⁠) |
| 3060 笔⁠记⁠本 | 6 GB | 40 GB | 1344×768 | 5.2 s | 轻⁠量 | 0.4.7 | 510 s | 0.4.7 | 已⁠是⁠最⁠优 |
| 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 |
- 用时:从提交到视频保存完成的端到端用时。
- 优化后:预估用时,根据报告中的分段用时,结合测试机(Windows RTX 3090 和 RTX 5060 Ti、Linux RTX PRO 6000)在报告机器的显存和内存上限下运行完整规划的实测推算,不是在报告机器上重跑。
@@ -93,3 +94,4 @@
- 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。