vbench 0.1.3

Video generation benchmark

VBench is a comprehensive benchmark suite for video generative models. You can use VBench to evaluate video generation models from 16 different ability aspects.

This project is the PyPI implementation of the following research:

VBench: Comprehensive Benchmark Suite for Video Generative Models
Ziqi Huang^∗, Yinan He^∗, Jiashuo Yu^∗, Fan Zhang^∗, Chenyang Si, Yuming Jiang, Yuanhan Zhang, Tianxing Wu, Qingyang Jin, Nattapol Chanpaisit, Yaohui Wang, Xinyuan Chen, Limin Wang, Dahua Lin⁺, Yu Qiao⁺, Ziwei Liu⁺

Installation

pip install vbench

To evaluate some video generation ability aspects, you need to install detectron2 via:

pip install detectron2@git+https://github.com/facebookresearch/detectron2.git

If there is an error during detectron2 installation, see here.

Usage

Evaluate Your Own Videos

We support evaluating any video. Simply provide the path to the video file, or the path to the folder that contains your videos. There is no requirement on the videos' names.

• Note: We support customized videos / prompts for the following dimensions: 'subject_consistency', 'background_consistency', 'motion_smoothness', 'dynamic_degree', 'aesthetic_quality', 'imaging_quality'

To evaluate videos with customed input prompt, run our script with --mode=custom_input:

python evaluate.py \
    --dimension $DIMENSION \
    --videos_path /path/to/folder_or_video/ \
    --mode=custom_input

alternatively you can use our command:

vbench evaluate \
    --dimension $DIMENSION \
    --videos_path /path/to/folder_or_video/ \
    --mode=custom_input

Evaluation on the Standard Prompt Suite of VBench

command line

    vbench evaluate --videos_path $VIDEO_PATH --dimension $DIMENSION

For example:

    vbench evaluate --videos_path "sampled_videos/lavie/human_action" --dimension "human_action"

python

    from vbench import VBench
    my_VBench = VBench(device, <path/to/VBench_full_info.json>, <path/to/save/dir>)
    my_VBench.evaluate(
        videos_path = <video_path>,
        name = <name>,
        dimension_list = [<dimension>, <dimension>, ...],
    )

For example:

    from vbench import VBench
    my_VBench = VBench(device, "vbench/VBench_full_info.json", "evaluation_results")
    my_VBench.evaluate(
        videos_path = "sampled_videos/lavie/human_action",
        name = "lavie_human_action",
        dimension_list = ["human_action"],
    )

Evaluation on a specific category from VBench

command line

vbench evaluate \
    --videos_path $VIDEO_PATH \
    --dimension $DIMENSION \
    --mode=vbench_category \
    --category=$CATEGORY

or

python evaluate.py \
    --dimension $DIMENSION \
    --videos_path /path/to/folder_or_video/ \
    --mode=vbench_category

Prompt Suite

We provide prompt lists are at prompts/.

Check out details of prompt suites, and instructions for how to sample videos for evaluation.

Citation

If you find this package useful for your reports or publications, please consider citing the VBench paper:

 @article{huang2023vbench,
     title={{VBench}: Comprehensive Benchmark Suite for Video Generative Models},
     author={Huang, Ziqi and He, Yinan and Yu, Jiashuo and Zhang, Fan and Si, Chenyang and Jiang, Yuming and Zhang, Yuanhan and Wu, Tianxing and Jin, Qingyang and Chanpaisit, Nattapol and Wang, Yaohui and Chen, Xinyuan and Wang, Limin and Lin, Dahua and Qiao, Yu and Liu, Ziwei},
     journal={arXiv preprint arXiv:2311.17982},
     year={2023}
 }