JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2025-06-17 13:59:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix bug of i2v; video is already 0-255

Browse Source 
video is already 0-255 and should not be multiplied 255 any more
This commit is contained in:
Zheng Guang Cong 2025-01-11 17:29:27 +08:00 committed by GitHub
parent cd861bbe1e
commit 09a49d3546
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
finetune/trainer.py
View File

@ -526,7 +526,7 @@ class Trainer:
video, self.state.train_frames, self.state.train_height, self.state.train_width
)
# Convert video tensor (F, C, H, W) to list of PIL images
video = (video * 255).round().clamp(0, 255).to(torch.uint8)
video = video.round().clamp(0, 255).to(torch.uint8)
video = [Image.fromarray(frame.permute(1, 2, 0).cpu().numpy()) for frame in video]
logger.debug(