JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2026-05-13 20:17:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(inference): correct output path in VAE encode success message

Browse Source 
The print statement incorrectly used the encoded_output tensor variable
instead of args.output_path when displaying the save location.

Changed: {encoded_output}/encoded.pt → {args.output_path}/encoded.pt
This commit is contained in:
Test User 2026-02-19 02:45:16 +00:00
parent 7a1af71545
commit cf5c58e69c
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
inference/cli_vae_demo.py
View File

@ -143,7 +143,7 @@ if __name__ == "__main__":
encoded_output = encode_video(args.model_path, args.video_path, dtype, device)
torch.save(encoded_output, args.output_path + "/encoded.pt")
print(
f"Finished encoding the video to a tensor, save it to a file at {encoded_output}/encoded.pt"
f"Finished encoding the video to a tensor, saved to {args.output_path}/encoded.pt"
)
elif args.mode == "decode":
assert args.encoded_path, "Encoded tensor path must be provided for decoding."