EvalCrafter / constants.py
shadowcun
Initial commit
7d9d01e
raw
history blame
3.56 kB
# this is .py for store constants
MODEL_INFO = ['Models', 'Ver.','Abilities']
TASK_INFO = [ 'Resolution', 'FPS', 'Open Source', 'Length', 'Speed', 'Motion', 'Camera', 'Final Sum Score', 'Motion Quality', 'Text-Video Alignment', 'Visual Quality', 'Temporal Consistency']
TASK_INFO_v2 = ['Final Sum Score', 'Motion Quality', 'Text-Video Alignment', 'Visual Quality', 'Temporal Consistency', 'Resolution', 'FPS', 'Open Source', 'Length', 'Speed', 'Motion', 'Camera']
AVG_INFO = ['Final Sum Score', 'Motion Quality', 'Text-Video Alignment', 'Visual Quality', 'Temporal Consistency']
DATA_TITILE_TYPE = ["markdown", "number", "number", "number", "number", "number", "number", "number", "number", "number", "number", "number", "number", "number", "number"]
CSV_DIR = "./file/result.csv"
# COLUMN_NAMES = MODEL_INFO + TASK_INFO
COLUMN_NAMES = MODEL_INFO + TASK_INFO_v2
DATA_NUM = [3158, 1831, 4649, 978, 2447, 657, 97, 331, 85, 1740, 2077, 1192]
LEADERBORAD_INTRODUCTION = """# EvalCrafter Leaderboard 🏆
Welcome to the cutting-edge leaderboard for text-to-video generation, where we meticulously evaluate state-of-the-art generative models using our comprehensive framework, ensuring high-quality results that align with user opinions. Join us in this exciting journey towards excellence! 🛫
More methods will be evalcrafted soon, stay tunned ❤️ Join our evaluation by sending an email 📧 ([email protected])! You may also read the [EvalCrafter paper](https://arxiv.org/abs/2310.11440) for more detailed information 🤗
"""
TABLE_INTRODUCTION = """In the table below, we summarize each dimension performance of all the models. """
LEADERBORAD_INFO = """
The vision and language generative models have been overgrown in recent years. For video generation,
various open-sourced models and public-available services are released for generating high-visual quality videos.
However, these methods often use a few academic metrics, \eg, FVD or IS, to evaluate the performance. We argue that
it is hard to judge the large conditional generative models from the simple metrics since these models are often trained
on very large datasets with multi-aspect abilities. Thus, we propose a new framework and pipeline to exhaustively evaluate
the performance of the generated videos. To achieve this, we first conduct a new prompt list for text-to-video generation
by analyzing the real-world prompt list with the help of the large language model. Then, we evaluate the state-of-the-art video
generative models on our carefully designed benchmarks, in terms of visual qualities, content qualities, motion qualities, and
text-caption alignment with around 18 objective metrics. To obtain the final leaderboard of the models, we also fit a series of
coefficients to align the objective metrics to the users' opinions. Based on the proposed opinion alignment method, our final score
shows a higher correlation than simply averaging the metrics, showing the effectiveness of the proposed evaluation method.
"""
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""@inproceedings{Liu2023EvalCrafterBA,
title={EvalCrafter: Benchmarking and Evaluating Large Video Generation Models},
author={Yaofang Liu and Xiaodong Cun and Xuebo Liu and Xintao Wang and Yong Zhang and Haoxin Chen and Yang Liu and Tieyong Zeng and Raymond Chan and Ying Shan},
year={2023},
url={https://api.semanticscholar.org/CorpusID:264172222}
}"""