THUDM
/

CogVideoX1.5-5B-I2V

CogVideoXImageToVideoPipeline

video-generation

Model card Files Files and versions Community

The sample script needs to be updated to fix the OOM (Out of Memory) issue and long inference time caused by not explicitly specifying the height and width.

#14

by llmx - opened 5 days ago

llmx

5 days ago

Ref: T2V inference getting bad results · Issue #520 · THUDM/CogVideo、CogVideoX1.5-5B t2v takes 6 hours to generate a video · Issue #530 · THUDM/CogVideo、CogVideo/inference/cli_demo.py at main · THUDM/CogVideo
Specify the height and width in the pipe.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment