8000 Cannot reproduce VBench-I2V results on CogVideoX-5b-I2V · Issue #131 · Vchitect/VBench · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Cannot reproduce VBench-I2V results on CogVideoX-5b-I2V #131

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHu 8000 b? Sign in to your account

Jump to bottom
Open
Cuogeihong opened this issue Apr 27, 2025 · 4 comments
Open

Cannot reproduce VBench-I2V results on CogVideoX-5b-I2V #131

Cuogeihong opened this issue Apr 27, 2025 · 4 comments
Assignees
@Jacky-hate

Comments

@Cuogeihong
Copy link

We highly appreciate your continuous contribution in t2v, i2v benchmark

Following the guidance, we install the specified environment (cuda 12.1, transformers 4.33.2, torch 2.5.1). We download cogvideox-5b-i2v results from google drive. However, the reproduced results are different from vbench leaderboard. e.g. i2v subject 0.9738 v.s. 0.9719, and we cannot find the explanation. (setting: resolution 3-2, imaging_quality_preprocessing_mode longer)

here is the result json:

results_2025-04-27-19_36_33_eval_results.json
@Jacky-hate
Copy link
Collaborator

Could you provide a list of your conda environments？ @Cuogeihong

@Cuogeihong
Copy link
Author

We downgraded pytorch to 2.0.1 and solve most inconsistency, but we cannot reproduce camera motion's score: 67.86% v.s. 67.68%

pip environment: pip_list.txt

our camera motion evaluate result: results_2025-04-28-19_45_08_eval_results.json

@Jacky-hate
Copy link
Collaborator

We used the pip list you provided and still got the same results as shown on the leaderboard. Could you please share the exact command you used, as well as your conda list (which includes more detailed dependencies)

@Cuogeihong
Copy link
Author

We change pytorch to 2.1.1 and camera motion score: 67.65 v.s. 67.68%, still having a small gap

exec command: python evaluate_i2v.py --videos_path $VIDEO_PATH --dimension camera_motion --ratio 3-2 --output_path ./evaluations/$OUTPUT_NAME --full_json_dir ./vbench2_beta_i2v/vbench2_i2v_full_info.json

conda list: conda_list.txt

new camera motion result: results_2025-05-06-18_26_32_eval_results.json

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Jacky-hate Jacky-hate

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Cuogeihong @Jacky-hate
0