zai-org/CogVideo
1
0
Fork 0
mirror of https://github.com/zai-org/CogVideo.git synced 2026-10-12 02:27:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #500 from THUDM/main

Browse Source 
Merge
This commit is contained in:
Yuxuan.Zhang
2024-11-13 21:15:49 +08:00
committed by GitHub
parent e7a35ea33b cd5ceca22b
commit 5e3e3aabe0
4 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -189,7 +189,7 @@ models we currently offer, along with their foundational information.
<tr>
<td style="text-align: center;">Video Resolution</td>
<td colspan="1" style="text-align: center;">1360 * 768</td>
<td colspan="1" style="text-align: center;">256 <= W <=1360<br> 256 <= H <=768<br> W,H % 16 == 0</td>
<td colspan="1" style="text-align: center;"> Min(W, H) = 768 <br> 768 ≤ Max(W, H) ≤ 1360 <br> Max(W, H) % 16 = 0 </td>
<td colspan="3" style="text-align: center;">720 * 480</td>
</tr>
<tr>
README_ja.md
+1 -1
View File
@@ -181,7 +181,7 @@ CogVideoXは、[清影](https://chatglm.cn/video?fr=osm_cogvideox) と同源の
<tr>
<td style="text-align: center;">ビデオ解像度</td>
<td colspan="1" style="text-align: center;">1360 * 768</td>
<td colspan="1" style="text-align: center;">256 <= W <=1360<br> 256 <= H <=768<br> W,H % 16 == 0</td>
<td colspan="1" style="text-align: center;"> Min(W, H) = 768 <br> 768 ≤ Max(W, H) ≤ 1360 <br> Max(W, H) % 16 = 0 </td>
<td colspan="3" style="text-align: center;">720 * 480</td>
</tr>
<tr>
README_zh.md
+1 -1
View File
@@ -171,7 +171,7 @@ CogVideoX是 [清影](https://chatglm.cn/video?fr=osm_cogvideox) 同源的开源
<tr>
<td style="text-align: center;">视频分辨率</td>
<td colspan="1" style="text-align: center;">1360 * 768</td>
<td colspan="1" style="text-align: center;">256 <= W <=1360<br> 256 <= H <=768<br> W,H % 16 == 0</td>
<td colspan="1" style="text-align: center;"> Min(W, H) = 768 <br> 768 ≤ Max(W, H) ≤ 1360 <br> Max(W, H) % 16 = 0 </td>
<td colspan="3" style="text-align: center;">720 * 480</td>
</tr>
<tr>
tools/parallel_inference/parallel_inference_xdit.py
+2 -1
View File
@@ -78,8 +78,9 @@ def main():
num_frames=input_config.num_frames,
prompt=input_config.prompt,
num_inference_steps=input_config.num_inference_steps,
generator=torch.Generator(device="cuda").manual_seed(input_config.seed),
generator=torch.Generator().manual_seed(input_config.seed),
guidance_scale=6,
use_dynamic_cfg=True,
).frames[0]
end_time = time.time()