Datasets:

CodeGoat24
/

VideoDPO

Dataset card Data Studio Files Files and versions Community

Split (1)

train · 10k rows

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.

prompt stringlengths 4 8.37k	conversations listlengths 2 2	images sequencelengths 16 16
driving a car in a peopled street.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [driving a car in a peopled street.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004022/0.png", "losevideos/004022/1.png", "losevideos/004022/2.png", "losevideos/004022/3.png", "losevideos/004022/4.png", "losevideos/004022/5.png", "losevideos/004022/6.png", "losevideos/004022/7.png", "winvideos/004022/0.png", "winvideos/004022/1.png", "winvideos/004022/2.png", "winvideos/004022/3.png", "winvideos/004022/4.png", "winvideos/004022/5.png", "winvideos/004022/6.png", "winvideos/004022/7.png" ]
Rabbit dreamdy pic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Rabbit dreamdy pic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008046/0.png", "losevideos/008046/1.png", "losevideos/008046/2.png", "losevideos/008046/3.png", "losevideos/008046/4.png", "losevideos/008046/5.png", "losevideos/008046/6.png", "losevideos/008046/7.png", "winvideos/008046/0.png", "winvideos/008046/1.png", "winvideos/008046/2.png", "winvideos/008046/3.png", "winvideos/008046/4.png", "winvideos/008046/5.png", "winvideos/008046/6.png", "winvideos/008046/7.png" ]
men is moving by cycling.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [men is moving by cycling.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008665/0.png", "winvideos/008665/1.png", "winvideos/008665/2.png", "winvideos/008665/3.png", "winvideos/008665/4.png", "winvideos/008665/5.png", "winvideos/008665/6.png", "winvideos/008665/7.png", "losevideos/008665/0.png", "losevideos/008665/1.png", "losevideos/008665/2.png", "losevideos/008665/3.png", "losevideos/008665/4.png", "losevideos/008665/5.png", "losevideos/008665/6.png", "losevideos/008665/7.png" ]
extreme closeup of Phythagoras, the ancient Greek philosopher, engaged in deep contemplation within the hallowed halls of the Athens Academy, in an abstract, timeless setting.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [extreme closeup of Phythagoras, the ancient Greek philosopher, engaged in deep contemplation within the hallowed halls of the Athens Academy, in an abstract, timeless setting.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007840/0.png", "winvideos/007840/1.png", "winvideos/007840/2.png", "winvideos/007840/3.png", "winvideos/007840/4.png", "winvideos/007840/5.png", "winvideos/007840/6.png", "winvideos/007840/7.png", "losevideos/007840/0.png", "losevideos/007840/1.png", "losevideos/007840/2.png", "losevideos/007840/3.png", "losevideos/007840/4.png", "losevideos/007840/5.png", "losevideos/007840/6.png", "losevideos/007840/7.png" ]
teddy bear.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [teddy bear.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001757/0.png", "winvideos/001757/1.png", "winvideos/001757/2.png", "winvideos/001757/3.png", "winvideos/001757/4.png", "winvideos/001757/5.png", "winvideos/001757/6.png", "winvideos/001757/7.png", "losevideos/001757/0.png", "losevideos/001757/1.png", "losevideos/001757/2.png", "losevideos/001757/3.png", "losevideos/001757/4.png", "losevideos/001757/5.png", "losevideos/001757/6.png", "losevideos/001757/7.png" ]
a wolf walking in the jungle.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a wolf walking in the jungle.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000617/0.png", "winvideos/000617/1.png", "winvideos/000617/2.png", "winvideos/000617/3.png", "winvideos/000617/4.png", "winvideos/000617/5.png", "winvideos/000617/6.png", "winvideos/000617/7.png", "losevideos/000617/0.png", "losevideos/000617/1.png", "losevideos/000617/2.png", "losevideos/000617/3.png", "losevideos/000617/4.png", "losevideos/000617/5.png", "losevideos/000617/6.png", "losevideos/000617/7.png" ]
a cat walk on the wall.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a cat walk on the wall.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001749/0.png", "winvideos/001749/1.png", "winvideos/001749/2.png", "winvideos/001749/3.png", "winvideos/001749/4.png", "winvideos/001749/5.png", "winvideos/001749/6.png", "winvideos/001749/7.png", "losevideos/001749/0.png", "losevideos/001749/1.png", "losevideos/001749/2.png", "losevideos/001749/3.png", "losevideos/001749/4.png", "losevideos/001749/5.png", "losevideos/001749/6.png", "losevideos/001749/7.png" ]
angelfish swimming the the sea.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [angelfish swimming the the sea.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003860/0.png", "winvideos/003860/1.png", "winvideos/003860/2.png", "winvideos/003860/3.png", "winvideos/003860/4.png", "winvideos/003860/5.png", "winvideos/003860/6.png", "winvideos/003860/7.png", "losevideos/003860/0.png", "losevideos/003860/1.png", "losevideos/003860/2.png", "losevideos/003860/3.png", "losevideos/003860/4.png", "losevideos/003860/5.png", "losevideos/003860/6.png", "losevideos/003860/7.png" ]
surreealism face of david bowie.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [surreealism face of david bowie.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004634/0.png", "losevideos/004634/1.png", "losevideos/004634/2.png", "losevideos/004634/3.png", "losevideos/004634/4.png", "losevideos/004634/5.png", "losevideos/004634/6.png", "losevideos/004634/7.png", "winvideos/004634/0.png", "winvideos/004634/1.png", "winvideos/004634/2.png", "winvideos/004634/3.png", "winvideos/004634/4.png", "winvideos/004634/5.png", "winvideos/004634/6.png", "winvideos/004634/7.png" ]
old rabbit sick in bed and his family is next to him , his lips are moving , sad ,cartoonish, colorful,.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [old rabbit sick in bed and his family is next to him , his lips are moving , sad ,cartoonish, colorful,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009594/0.png", "winvideos/009594/1.png", "winvideos/009594/2.png", "winvideos/009594/3.png", "winvideos/009594/4.png", "winvideos/009594/5.png", "winvideos/009594/6.png", "winvideos/009594/7.png", "losevideos/009594/0.png", "losevideos/009594/1.png", "losevideos/009594/2.png", "losevideos/009594/3.png", "losevideos/009594/4.png", "losevideos/009594/5.png", "losevideos/009594/6.png", "losevideos/009594/7.png" ]
Nile River in the time of the Pharaohs with the two copper statues of.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Nile River in the time of the Pharaohs with the two copper statues of.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006703/0.png", "losevideos/006703/1.png", "losevideos/006703/2.png", "losevideos/006703/3.png", "losevideos/006703/4.png", "losevideos/006703/5.png", "losevideos/006703/6.png", "losevideos/006703/7.png", "winvideos/006703/0.png", "winvideos/006703/1.png", "winvideos/006703/2.png", "winvideos/006703/3.png", "winvideos/006703/4.png", "winvideos/006703/5.png", "winvideos/006703/6.png", "winvideos/006703/7.png" ]
beenjamming.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [beenjamming.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000645/0.png", "winvideos/000645/1.png", "winvideos/000645/2.png", "winvideos/000645/3.png", "winvideos/000645/4.png", "winvideos/000645/5.png", "winvideos/000645/6.png", "winvideos/000645/7.png", "losevideos/000645/0.png", "losevideos/000645/1.png", "losevideos/000645/2.png", "losevideos/000645/3.png", "losevideos/000645/4.png", "losevideos/000645/5.png", "losevideos/000645/6.png", "losevideos/000645/7.png" ]
male roblox character dancing, white shirt, blue pants, 8k, high definition, -gs 10 -ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [male roblox character dancing, white shirt, blue pants, 8k, high definition, -gs 10 -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002923/0.png", "winvideos/002923/1.png", "winvideos/002923/2.png", "winvideos/002923/3.png", "winvideos/002923/4.png", "winvideos/002923/5.png", "winvideos/002923/6.png", "winvideos/002923/7.png", "losevideos/002923/0.png", "losevideos/002923/1.png", "losevideos/002923/2.png", "losevideos/002923/3.png", "losevideos/002923/4.png", "losevideos/002923/5.png", "losevideos/002923/6.png", "losevideos/002923/7.png" ]
Raju lived in a small village.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Raju lived in a small village.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008486/0.png", "losevideos/008486/1.png", "losevideos/008486/2.png", "losevideos/008486/3.png", "losevideos/008486/4.png", "losevideos/008486/5.png", "losevideos/008486/6.png", "losevideos/008486/7.png", "winvideos/008486/0.png", "winvideos/008486/1.png", "winvideos/008486/2.png", "winvideos/008486/3.png", "winvideos/008486/4.png", "winvideos/008486/5.png", "winvideos/008486/6.png", "winvideos/008486/7.png" ]
Mickey Mouse in overalls.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Mickey Mouse in overalls.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002486/0.png", "losevideos/002486/1.png", "losevideos/002486/2.png", "losevideos/002486/3.png", "losevideos/002486/4.png", "losevideos/002486/5.png", "losevideos/002486/6.png", "losevideos/002486/7.png", "winvideos/002486/0.png", "winvideos/002486/1.png", "winvideos/002486/2.png", "winvideos/002486/3.png", "winvideos/002486/4.png", "winvideos/002486/5.png", "winvideos/002486/6.png", "winvideos/002486/7.png" ]
a blue chihuahua skydiving.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a blue chihuahua skydiving.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008208/0.png", "winvideos/008208/1.png", "winvideos/008208/2.png", "winvideos/008208/3.png", "winvideos/008208/4.png", "winvideos/008208/5.png", "winvideos/008208/6.png", "winvideos/008208/7.png", "losevideos/008208/0.png", "losevideos/008208/1.png", "losevideos/008208/2.png", "losevideos/008208/3.png", "losevideos/008208/4.png", "losevideos/008208/5.png", "losevideos/008208/6.png", "losevideos/008208/7.png" ]
baby dancing fast.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [baby dancing fast.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006633/0.png", "winvideos/006633/1.png", "winvideos/006633/2.png", "winvideos/006633/3.png", "winvideos/006633/4.png", "winvideos/006633/5.png", "winvideos/006633/6.png", "winvideos/006633/7.png", "losevideos/006633/0.png", "losevideos/006633/1.png", "losevideos/006633/2.png", "losevideos/006633/3.png", "losevideos/006633/4.png", "losevideos/006633/5.png", "losevideos/006633/6.png", "losevideos/006633/7.png" ]
Video of Munch's Scream with Wine Labels as Background.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Video of Munch's Scream with Wine Labels as Background.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005093/0.png", "losevideos/005093/1.png", "losevideos/005093/2.png", "losevideos/005093/3.png", "losevideos/005093/4.png", "losevideos/005093/5.png", "losevideos/005093/6.png", "losevideos/005093/7.png", "winvideos/005093/0.png", "winvideos/005093/1.png", "winvideos/005093/2.png", "winvideos/005093/3.png", "winvideos/005093/4.png", "winvideos/005093/5.png", "winvideos/005093/6.png", "winvideos/005093/7.png" ]
full color animation wave,zoom out,moving -ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [full color animation wave,zoom out,moving -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004387/0.png", "winvideos/004387/1.png", "winvideos/004387/2.png", "winvideos/004387/3.png", "winvideos/004387/4.png", "winvideos/004387/5.png", "winvideos/004387/6.png", "winvideos/004387/7.png", "losevideos/004387/0.png", "losevideos/004387/1.png", "losevideos/004387/2.png", "losevideos/004387/3.png", "losevideos/004387/4.png", "losevideos/004387/5.png", "losevideos/004387/6.png", "losevideos/004387/7.png" ]
Describe a peaceful day in a serene forest. Write about the sights, sounds, and sensations experienced while exploring the woods. Use AI to create a simple video with tranquil images of the forest, accompanied by calming background sounds like rustling leaves and birdsong.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Describe a peaceful day in a serene forest. Write about the sights, sounds, and sensations experienced while exploring the woods. Use AI to create a simple video with tranquil images of the forest, accompanied by calming background sounds like rustling leaves and birdsong.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007039/0.png", "losevideos/007039/1.png", "losevideos/007039/2.png", "losevideos/007039/3.png", "losevideos/007039/4.png", "losevideos/007039/5.png", "losevideos/007039/6.png", "losevideos/007039/7.png", "winvideos/007039/0.png", "winvideos/007039/1.png", "winvideos/007039/2.png", "winvideos/007039/3.png", "winvideos/007039/4.png", "winvideos/007039/5.png", "winvideos/007039/6.png", "winvideos/007039/7.png" ]
Sexy Temari Dancing.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Sexy Temari Dancing.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006603/0.png", "losevideos/006603/1.png", "losevideos/006603/2.png", "losevideos/006603/3.png", "losevideos/006603/4.png", "losevideos/006603/5.png", "losevideos/006603/6.png", "losevideos/006603/7.png", "winvideos/006603/0.png", "winvideos/006603/1.png", "winvideos/006603/2.png", "winvideos/006603/3.png", "winvideos/006603/4.png", "winvideos/006603/5.png", "winvideos/006603/6.png", "winvideos/006603/7.png" ]
Anime style, female astronaut walking slowly across a purple landscape, columeteric light, stars in the sky, -r 5:2 -camera zoom in -motion 4.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Anime style, female astronaut walking slowly across a purple landscape, columeteric light, stars in the sky, -r 5:2 -camera zoom in -motion 4.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002179/0.png", "winvideos/002179/1.png", "winvideos/002179/2.png", "winvideos/002179/3.png", "winvideos/002179/4.png", "winvideos/002179/5.png", "winvideos/002179/6.png", "winvideos/002179/7.png", "losevideos/002179/0.png", "losevideos/002179/1.png", "losevideos/002179/2.png", "losevideos/002179/3.png", "losevideos/002179/4.png", "losevideos/002179/5.png", "losevideos/002179/6.png", "losevideos/002179/7.png" ]
Old Ufo footage in forest--realistic -- cinematic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Old Ufo footage in forest--realistic -- cinematic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000455/0.png", "losevideos/000455/1.png", "losevideos/000455/2.png", "losevideos/000455/3.png", "losevideos/000455/4.png", "losevideos/000455/5.png", "losevideos/000455/6.png", "losevideos/000455/7.png", "winvideos/000455/0.png", "winvideos/000455/1.png", "winvideos/000455/2.png", "winvideos/000455/3.png", "winvideos/000455/4.png", "winvideos/000455/5.png", "winvideos/000455/6.png", "winvideos/000455/7.png" ]
-haunted Depict the dimly lit interior of the cabin -10 motion -24 fps.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [-haunted Depict the dimly lit interior of the cabin -10 motion -24 fps.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000051/0.png", "losevideos/000051/1.png", "losevideos/000051/2.png", "losevideos/000051/3.png", "losevideos/000051/4.png", "losevideos/000051/5.png", "losevideos/000051/6.png", "losevideos/000051/7.png", "winvideos/000051/0.png", "winvideos/000051/1.png", "winvideos/000051/2.png", "winvideos/000051/3.png", "winvideos/000051/4.png", "winvideos/000051/5.png", "winvideos/000051/6.png", "winvideos/000051/7.png" ]
Iran glorious Message: shah (Font: MODERN).	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Iran glorious Message: shah (Font: MODERN).]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000614/0.png", "losevideos/000614/1.png", "losevideos/000614/2.png", "losevideos/000614/3.png", "losevideos/000614/4.png", "losevideos/000614/5.png", "losevideos/000614/6.png", "losevideos/000614/7.png", "winvideos/000614/0.png", "winvideos/000614/1.png", "winvideos/000614/2.png", "winvideos/000614/3.png", "winvideos/000614/4.png", "winvideos/000614/5.png", "winvideos/000614/6.png", "winvideos/000614/7.png" ]
3D ANIMATION FILM, A FROG SINGING AND DANCING IN FRONT A group of dolfins.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [3D ANIMATION FILM, A FROG SINGING AND DANCING IN FRONT A group of dolfins.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004132/0.png", "losevideos/004132/1.png", "losevideos/004132/2.png", "losevideos/004132/3.png", "losevideos/004132/4.png", "losevideos/004132/5.png", "losevideos/004132/6.png", "losevideos/004132/7.png", "winvideos/004132/0.png", "winvideos/004132/1.png", "winvideos/004132/2.png", "winvideos/004132/3.png", "winvideos/004132/4.png", "winvideos/004132/5.png", "winvideos/004132/6.png", "winvideos/004132/7.png" ]
-gs 24 -motion 4 highly detailed, ילדה רוקדת.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [-gs 24 -motion 4 highly detailed, ילדה רוקדת.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000115/0.png", "winvideos/000115/1.png", "winvideos/000115/2.png", "winvideos/000115/3.png", "winvideos/000115/4.png", "winvideos/000115/5.png", "winvideos/000115/6.png", "winvideos/000115/7.png", "losevideos/000115/0.png", "losevideos/000115/1.png", "losevideos/000115/2.png", "losevideos/000115/3.png", "losevideos/000115/4.png", "losevideos/000115/5.png", "losevideos/000115/6.png", "losevideos/000115/7.png" ]
open the big door, Flash motion.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [open the big door, Flash motion.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008202/0.png", "winvideos/008202/1.png", "winvideos/008202/2.png", "winvideos/008202/3.png", "winvideos/008202/4.png", "winvideos/008202/5.png", "winvideos/008202/6.png", "winvideos/008202/7.png", "losevideos/008202/0.png", "losevideos/008202/1.png", "losevideos/008202/2.png", "losevideos/008202/3.png", "losevideos/008202/4.png", "losevideos/008202/5.png", "losevideos/008202/6.png", "losevideos/008202/7.png" ]
colourful aliens 1969 pulp art illustration --ar 2:3.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [colourful aliens 1969 pulp art illustration --ar 2:3.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004966/0.png", "losevideos/004966/1.png", "losevideos/004966/2.png", "losevideos/004966/3.png", "losevideos/004966/4.png", "losevideos/004966/5.png", "losevideos/004966/6.png", "losevideos/004966/7.png", "winvideos/004966/0.png", "winvideos/004966/1.png", "winvideos/004966/2.png", "winvideos/004966/3.png", "winvideos/004966/4.png", "winvideos/004966/5.png", "winvideos/004966/6.png", "winvideos/004966/7.png" ]
goldilock in the cottage,three beds are in room,make video animated close up.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [goldilock in the cottage,three beds are in room,make video animated close up.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000217/0.png", "losevideos/000217/1.png", "losevideos/000217/2.png", "losevideos/000217/3.png", "losevideos/000217/4.png", "losevideos/000217/5.png", "losevideos/000217/6.png", "losevideos/000217/7.png", "winvideos/000217/0.png", "winvideos/000217/1.png", "winvideos/000217/2.png", "winvideos/000217/3.png", "winvideos/000217/4.png", "winvideos/000217/5.png", "winvideos/000217/6.png", "winvideos/000217/7.png" ]
baby kangaroo in the fields of the Netherlands, windmills im tej background, style of fauvism.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [baby kangaroo in the fields of the Netherlands, windmills im tej background, style of fauvism.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001268/0.png", "winvideos/001268/1.png", "winvideos/001268/2.png", "winvideos/001268/3.png", "winvideos/001268/4.png", "winvideos/001268/5.png", "winvideos/001268/6.png", "winvideos/001268/7.png", "losevideos/001268/0.png", "losevideos/001268/1.png", "losevideos/001268/2.png", "losevideos/001268/3.png", "losevideos/001268/4.png", "losevideos/001268/5.png", "losevideos/001268/6.png", "losevideos/001268/7.png" ]
homeless sitting in front of shop in the city but beside of the city lamp, midnight, rainy.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [homeless sitting in front of shop in the city but beside of the city lamp, midnight, rainy.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009774/0.png", "losevideos/009774/1.png", "losevideos/009774/2.png", "losevideos/009774/3.png", "losevideos/009774/4.png", "losevideos/009774/5.png", "losevideos/009774/6.png", "losevideos/009774/7.png", "winvideos/009774/0.png", "winvideos/009774/1.png", "winvideos/009774/2.png", "winvideos/009774/3.png", "winvideos/009774/4.png", "winvideos/009774/5.png", "winvideos/009774/6.png", "winvideos/009774/7.png" ]
wall-e and eve together.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [wall-e and eve together.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009809/0.png", "losevideos/009809/1.png", "losevideos/009809/2.png", "losevideos/009809/3.png", "losevideos/009809/4.png", "losevideos/009809/5.png", "losevideos/009809/6.png", "losevideos/009809/7.png", "winvideos/009809/0.png", "winvideos/009809/1.png", "winvideos/009809/2.png", "winvideos/009809/3.png", "winvideos/009809/4.png", "winvideos/009809/5.png", "winvideos/009809/6.png", "winvideos/009809/7.png" ]
climate change realistic profesional ligthing.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [climate change realistic profesional ligthing.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004926/0.png", "winvideos/004926/1.png", "winvideos/004926/2.png", "winvideos/004926/3.png", "winvideos/004926/4.png", "winvideos/004926/5.png", "winvideos/004926/6.png", "winvideos/004926/7.png", "losevideos/004926/0.png", "losevideos/004926/1.png", "losevideos/004926/2.png", "losevideos/004926/3.png", "losevideos/004926/4.png", "losevideos/004926/5.png", "losevideos/004926/6.png", "losevideos/004926/7.png" ]
Brutalist Shapes float in desert at dawn Alfred Stieglitz grainy black and white 1900s.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Brutalist Shapes float in desert at dawn Alfred Stieglitz grainy black and white 1900s.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008156/0.png", "losevideos/008156/1.png", "losevideos/008156/2.png", "losevideos/008156/3.png", "losevideos/008156/4.png", "losevideos/008156/5.png", "losevideos/008156/6.png", "losevideos/008156/7.png", "winvideos/008156/0.png", "winvideos/008156/1.png", "winvideos/008156/2.png", "winvideos/008156/3.png", "winvideos/008156/4.png", "winvideos/008156/5.png", "winvideos/008156/6.png", "winvideos/008156/7.png" ]
A snowy walk.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A snowy walk.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009968/0.png", "losevideos/009968/1.png", "losevideos/009968/2.png", "losevideos/009968/3.png", "losevideos/009968/4.png", "losevideos/009968/5.png", "losevideos/009968/6.png", "losevideos/009968/7.png", "winvideos/009968/0.png", "winvideos/009968/1.png", "winvideos/009968/2.png", "winvideos/009968/3.png", "winvideos/009968/4.png", "winvideos/009968/5.png", "winvideos/009968/6.png", "winvideos/009968/7.png" ]
a manga anime fight between two women.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a manga anime fight between two women.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006620/0.png", "losevideos/006620/1.png", "losevideos/006620/2.png", "losevideos/006620/3.png", "losevideos/006620/4.png", "losevideos/006620/5.png", "losevideos/006620/6.png", "losevideos/006620/7.png", "winvideos/006620/0.png", "winvideos/006620/1.png", "winvideos/006620/2.png", "winvideos/006620/3.png", "winvideos/006620/4.png", "winvideos/006620/5.png", "winvideos/006620/6.png", "winvideos/006620/7.png" ]
a line moving across the screen -gs 16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a line moving across the screen -gs 16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005556/0.png", "winvideos/005556/1.png", "winvideos/005556/2.png", "winvideos/005556/3.png", "winvideos/005556/4.png", "winvideos/005556/5.png", "winvideos/005556/6.png", "winvideos/005556/7.png", "losevideos/005556/0.png", "losevideos/005556/1.png", "losevideos/005556/2.png", "losevideos/005556/3.png", "losevideos/005556/4.png", "losevideos/005556/5.png", "losevideos/005556/6.png", "losevideos/005556/7.png" ]
2D, 15th century miniature, Cherry Tree, Monk picks cherries, moving hand, -Motion 2 -neg deformed, misshapen, bad anatomy, deformed body.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [2D, 15th century miniature, Cherry Tree, Monk picks cherries, moving hand, -Motion 2 -neg deformed, misshapen, bad anatomy, deformed body.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005787/0.png", "winvideos/005787/1.png", "winvideos/005787/2.png", "winvideos/005787/3.png", "winvideos/005787/4.png", "winvideos/005787/5.png", "winvideos/005787/6.png", "winvideos/005787/7.png", "losevideos/005787/0.png", "losevideos/005787/1.png", "losevideos/005787/2.png", "losevideos/005787/3.png", "losevideos/005787/4.png", "losevideos/005787/5.png", "losevideos/005787/6.png", "losevideos/005787/7.png" ]
superman saving a man who jump.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [superman saving a man who jump.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003164/0.png", "losevideos/003164/1.png", "losevideos/003164/2.png", "losevideos/003164/3.png", "losevideos/003164/4.png", "losevideos/003164/5.png", "losevideos/003164/6.png", "losevideos/003164/7.png", "winvideos/003164/0.png", "winvideos/003164/1.png", "winvideos/003164/2.png", "winvideos/003164/3.png", "winvideos/003164/4.png", "winvideos/003164/5.png", "winvideos/003164/6.png", "winvideos/003164/7.png" ]