prompt
stringlengths 4
8.37k
| conversations
listlengths 2
2
| images
sequencelengths 16
16
|
|---|---|---|
cinematic, detailed statue of a muscular bearded man, full body, fighting in a stoicism ancient greek style. | [
{
"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: [cinematic, detailed statue of a muscular bearded man, full body, fighting in a stoicism ancient greek style.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007632/0.png",
"winvideos/007632/1.png",
"winvideos/007632/2.png",
"winvideos/007632/3.png",
"winvideos/007632/4.png",
"winvideos/007632/5.png",
"winvideos/007632/6.png",
"winvideos/007632/7.png",
"losevideos/007632/0.png",
"losevideos/007632/1.png",
"losevideos/007632/2.png",
"losevideos/007632/3.png",
"losevideos/007632/4.png",
"losevideos/007632/5.png",
"losevideos/007632/6.png",
"losevideos/007632/7.png"
] |
inside the snowstorm. | [
{
"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: [inside the snowstorm.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003839/0.png",
"losevideos/003839/1.png",
"losevideos/003839/2.png",
"losevideos/003839/3.png",
"losevideos/003839/4.png",
"losevideos/003839/5.png",
"losevideos/003839/6.png",
"losevideos/003839/7.png",
"winvideos/003839/0.png",
"winvideos/003839/1.png",
"winvideos/003839/2.png",
"winvideos/003839/3.png",
"winvideos/003839/4.png",
"winvideos/003839/5.png",
"winvideos/003839/6.png",
"winvideos/003839/7.png"
] |
with Water splashing -w 2 - camera rotate cw -motion 4 -size 60 Message: lorena (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: [with Water splashing -w 2 - camera rotate cw -motion 4 -size 60 Message: lorena (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002052/0.png",
"winvideos/002052/1.png",
"winvideos/002052/2.png",
"winvideos/002052/3.png",
"winvideos/002052/4.png",
"winvideos/002052/5.png",
"winvideos/002052/6.png",
"winvideos/002052/7.png",
"losevideos/002052/0.png",
"losevideos/002052/1.png",
"losevideos/002052/2.png",
"losevideos/002052/3.png",
"losevideos/002052/4.png",
"losevideos/002052/5.png",
"losevideos/002052/6.png",
"losevideos/002052/7.png"
] |
a car chasing another car in night, it should be fast. cinematic, 4k, realistic. | [
{
"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 car chasing another car in night, it should be fast. cinematic, 4k, realistic.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007728/0.png",
"losevideos/007728/1.png",
"losevideos/007728/2.png",
"losevideos/007728/3.png",
"losevideos/007728/4.png",
"losevideos/007728/5.png",
"losevideos/007728/6.png",
"losevideos/007728/7.png",
"winvideos/007728/0.png",
"winvideos/007728/1.png",
"winvideos/007728/2.png",
"winvideos/007728/3.png",
"winvideos/007728/4.png",
"winvideos/007728/5.png",
"winvideos/007728/6.png",
"winvideos/007728/7.png"
] |
cute robot fighting with banana by disney -ar 16:9. | [
{
"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: [cute robot fighting with banana by disney -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000881/0.png",
"winvideos/000881/1.png",
"winvideos/000881/2.png",
"winvideos/000881/3.png",
"winvideos/000881/4.png",
"winvideos/000881/5.png",
"winvideos/000881/6.png",
"winvideos/000881/7.png",
"losevideos/000881/0.png",
"losevideos/000881/1.png",
"losevideos/000881/2.png",
"losevideos/000881/3.png",
"losevideos/000881/4.png",
"losevideos/000881/5.png",
"losevideos/000881/6.png",
"losevideos/000881/7.png"
] |
<a href="https://media.discordapp.net/attachments/1123665843365093487/1211160093446381568/1930s_home_video_of_a_realistic_person_whose_face_is_melting_and_dripping_walking_down_the_stairs_in_seed7214178601351078430.mp4?ex=65ed2fbc&is=65dababc&hm=dc3e9b39c691920dac2c9a5baee795e503d0910e7449eb2adff05fbc151fccb7&">https://media.discordapp.net/attachments/1123665843365093487/1211160093446381568/1930s_home_video_of_a_realistic_person_whose_face_is_melting_and_dripping_walking_down_the_stairs_in_seed7214178601351078430.mp4?ex=65ed2fbc&is=65dababc&hm=dc3e9b39c691920dac2c9a5baee795e503d0910e7449eb2adff05fbc151fccb7&</a> 1930s home video of a human with a melting head walking down the stairs inside a house, highly detailed melting grotesque face, colorful, silent film style, art house horror style, grainy film, -ar 16:9. | [
{
"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 href=\"https://media.discordapp.net/attachments/1123665843365093487/1211160093446381568/1930s_home_video_of_a_realistic_person_whose_face_is_melting_and_dripping_walking_down_the_stairs_in_seed7214178601351078430.mp4?ex=65ed2fbc&is=65dababc&hm=dc3e9b39c691920dac2c9a5baee795e503d0910e7449eb2adff05fbc151fccb7&\">https://media.discordapp.net/attachments/1123665843365093487/1211160093446381568/1930s_home_video_of_a_realistic_person_whose_face_is_melting_and_dripping_walking_down_the_stairs_in_seed7214178601351078430.mp4?ex=65ed2fbc&is=65dababc&hm=dc3e9b39c691920dac2c9a5baee795e503d0910e7449eb2adff05fbc151fccb7&</a> 1930s home video of a human with a melting head walking down the stairs inside a house, highly detailed melting grotesque face, colorful, silent film style, art house horror style, grainy film, -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002548/0.png",
"winvideos/002548/1.png",
"winvideos/002548/2.png",
"winvideos/002548/3.png",
"winvideos/002548/4.png",
"winvideos/002548/5.png",
"winvideos/002548/6.png",
"winvideos/002548/7.png",
"losevideos/002548/0.png",
"losevideos/002548/1.png",
"losevideos/002548/2.png",
"losevideos/002548/3.png",
"losevideos/002548/4.png",
"losevideos/002548/5.png",
"losevideos/002548/6.png",
"losevideos/002548/7.png"
] |
realistic alien ship moving between the trees of a forest. | [
{
"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: [realistic alien ship moving between the trees of a forest.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002926/0.png",
"losevideos/002926/1.png",
"losevideos/002926/2.png",
"losevideos/002926/3.png",
"losevideos/002926/4.png",
"losevideos/002926/5.png",
"losevideos/002926/6.png",
"losevideos/002926/7.png",
"winvideos/002926/0.png",
"winvideos/002926/1.png",
"winvideos/002926/2.png",
"winvideos/002926/3.png",
"winvideos/002926/4.png",
"winvideos/002926/5.png",
"winvideos/002926/6.png",
"winvideos/002926/7.png"
] |
Girl Blowing Bubblegum. | [
{
"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: [Girl Blowing Bubblegum.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001982/0.png",
"losevideos/001982/1.png",
"losevideos/001982/2.png",
"losevideos/001982/3.png",
"losevideos/001982/4.png",
"losevideos/001982/5.png",
"losevideos/001982/6.png",
"losevideos/001982/7.png",
"winvideos/001982/0.png",
"winvideos/001982/1.png",
"winvideos/001982/2.png",
"winvideos/001982/3.png",
"winvideos/001982/4.png",
"winvideos/001982/5.png",
"winvideos/001982/6.png",
"winvideos/001982/7.png"
] |
Transport yourself back in time to the grandeur of the Roman Empire, a civilization that shaped the course of history. Immerse yourself in the splendor of ancient Rome, where marble statues line the streets and majestic arches adorn the skyline. Experience the bustling city life, with merchants selling their wares in vibrant marketplaces and citizens going about their daily routines. Journey to the heart of the empire, where the Colosseum stands as a testament to the Romans' architectural prowess and unrivaled entertainment. Witness the triumphs of Roman military campaigns, as legions march in unison and conquer new territories. The movie style is an epic historical drama, capturing the opulence and power of the Roman Empire. Utilize sweeping aerial shots and wide angles to showcase the vastness of ancient Rome's architectural marvels. Experiment with warm and vibrant color palettes to bring the city to life. The resolution should be set to 4K to capture the intricate details of the Roman Empire's grandeur. --gs 18 --neg --ar 16:9 --seed 1357. | [
{
"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: [Transport yourself back in time to the grandeur of the Roman Empire, a civilization that shaped the course of history. Immerse yourself in the splendor of ancient Rome, where marble statues line the streets and majestic arches adorn the skyline. Experience the bustling city life, with merchants selling their wares in vibrant marketplaces and citizens going about their daily routines. Journey to the heart of the empire, where the Colosseum stands as a testament to the Romans' architectural prowess and unrivaled entertainment. Witness the triumphs of Roman military campaigns, as legions march in unison and conquer new territories. The movie style is an epic historical drama, capturing the opulence and power of the Roman Empire. Utilize sweeping aerial shots and wide angles to showcase the vastness of ancient Rome's architectural marvels. Experiment with warm and vibrant color palettes to bring the city to life. The resolution should be set to 4K to capture the intricate details of the Roman Empire's grandeur. --gs 18 --neg --ar 16:9 --seed 1357.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005483/0.png",
"winvideos/005483/1.png",
"winvideos/005483/2.png",
"winvideos/005483/3.png",
"winvideos/005483/4.png",
"winvideos/005483/5.png",
"winvideos/005483/6.png",
"winvideos/005483/7.png",
"losevideos/005483/0.png",
"losevideos/005483/1.png",
"losevideos/005483/2.png",
"losevideos/005483/3.png",
"losevideos/005483/4.png",
"losevideos/005483/5.png",
"losevideos/005483/6.png",
"losevideos/005483/7.png"
] |
floatin islands in the sky in a world of night shadows. | [
{
"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: [floatin islands in the sky in a world of night shadows.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004236/0.png",
"losevideos/004236/1.png",
"losevideos/004236/2.png",
"losevideos/004236/3.png",
"losevideos/004236/4.png",
"losevideos/004236/5.png",
"losevideos/004236/6.png",
"losevideos/004236/7.png",
"winvideos/004236/0.png",
"winvideos/004236/1.png",
"winvideos/004236/2.png",
"winvideos/004236/3.png",
"winvideos/004236/4.png",
"winvideos/004236/5.png",
"winvideos/004236/6.png",
"winvideos/004236/7.png"
] |
moving camera. unreal engine. ancient German wood village century BC near forest. | [
{
"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: [moving camera. unreal engine. ancient German wood village century BC near forest.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005509/0.png",
"winvideos/005509/1.png",
"winvideos/005509/2.png",
"winvideos/005509/3.png",
"winvideos/005509/4.png",
"winvideos/005509/5.png",
"winvideos/005509/6.png",
"winvideos/005509/7.png",
"losevideos/005509/0.png",
"losevideos/005509/1.png",
"losevideos/005509/2.png",
"losevideos/005509/3.png",
"losevideos/005509/4.png",
"losevideos/005509/5.png",
"losevideos/005509/6.png",
"losevideos/005509/7.png"
] |
yastamtieun bialhayawanat fi alhadiqih. | [
{
"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: [yastamtieun bialhayawanat fi alhadiqih.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000189/0.png",
"winvideos/000189/1.png",
"winvideos/000189/2.png",
"winvideos/000189/3.png",
"winvideos/000189/4.png",
"winvideos/000189/5.png",
"winvideos/000189/6.png",
"winvideos/000189/7.png",
"losevideos/000189/0.png",
"losevideos/000189/1.png",
"losevideos/000189/2.png",
"losevideos/000189/3.png",
"losevideos/000189/4.png",
"losevideos/000189/5.png",
"losevideos/000189/6.png",
"losevideos/000189/7.png"
] |
The girl's eyes sparkle with joy and determination as she engages with those around her. She twirls and spins, inviting onlookers to join in her celebration of life. Market-goers pause from their daily tasks to watch in awe as she becomes one with the music and rhythm. | [
{
"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: [The girl's eyes sparkle with joy and determination as she engages with those around her. She twirls and spins, inviting onlookers to join in her celebration of life. Market-goers pause from their daily tasks to watch in awe as she becomes one with the music and rhythm.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003949/0.png",
"winvideos/003949/1.png",
"winvideos/003949/2.png",
"winvideos/003949/3.png",
"winvideos/003949/4.png",
"winvideos/003949/5.png",
"winvideos/003949/6.png",
"winvideos/003949/7.png",
"losevideos/003949/0.png",
"losevideos/003949/1.png",
"losevideos/003949/2.png",
"losevideos/003949/3.png",
"losevideos/003949/4.png",
"losevideos/003949/5.png",
"losevideos/003949/6.png",
"losevideos/003949/7.png"
] |
man smile while lying under big bowl of soup. | [
{
"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: [man smile while lying under big bowl of soup.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002313/0.png",
"losevideos/002313/1.png",
"losevideos/002313/2.png",
"losevideos/002313/3.png",
"losevideos/002313/4.png",
"losevideos/002313/5.png",
"losevideos/002313/6.png",
"losevideos/002313/7.png",
"winvideos/002313/0.png",
"winvideos/002313/1.png",
"winvideos/002313/2.png",
"winvideos/002313/3.png",
"winvideos/002313/4.png",
"winvideos/002313/5.png",
"winvideos/002313/6.png",
"winvideos/002313/7.png"
] |
beautiful witch with tarot of vampires in the city. | [
{
"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: [beautiful witch with tarot of vampires in the city.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003605/0.png",
"losevideos/003605/1.png",
"losevideos/003605/2.png",
"losevideos/003605/3.png",
"losevideos/003605/4.png",
"losevideos/003605/5.png",
"losevideos/003605/6.png",
"losevideos/003605/7.png",
"winvideos/003605/0.png",
"winvideos/003605/1.png",
"winvideos/003605/2.png",
"winvideos/003605/3.png",
"winvideos/003605/4.png",
"winvideos/003605/5.png",
"winvideos/003605/6.png",
"winvideos/003605/7.png"
] |
house inside it with tigers and two indigenous boys inside it. | [
{
"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: [house inside it with tigers and two indigenous boys inside it.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001571/0.png",
"losevideos/001571/1.png",
"losevideos/001571/2.png",
"losevideos/001571/3.png",
"losevideos/001571/4.png",
"losevideos/001571/5.png",
"losevideos/001571/6.png",
"losevideos/001571/7.png",
"winvideos/001571/0.png",
"winvideos/001571/1.png",
"winvideos/001571/2.png",
"winvideos/001571/3.png",
"winvideos/001571/4.png",
"winvideos/001571/5.png",
"winvideos/001571/6.png",
"winvideos/001571/7.png"
] |
Elon Musk, the CEO of Tesla, challenges his employees to a race: he will race them on his bicycle, and they will race him in their Teslas. Who will win?. | [
{
"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: [Elon Musk, the CEO of Tesla, challenges his employees to a race: he will race them on his bicycle, and they will race him in their Teslas. Who will win?.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009292/0.png",
"losevideos/009292/1.png",
"losevideos/009292/2.png",
"losevideos/009292/3.png",
"losevideos/009292/4.png",
"losevideos/009292/5.png",
"losevideos/009292/6.png",
"losevideos/009292/7.png",
"winvideos/009292/0.png",
"winvideos/009292/1.png",
"winvideos/009292/2.png",
"winvideos/009292/3.png",
"winvideos/009292/4.png",
"winvideos/009292/5.png",
"winvideos/009292/6.png",
"winvideos/009292/7.png"
] |
Imagine a dynamic scene where a celestial nebula is undergoing a continuous transformation, to a diverse array of energies, The nebula serves as a canvas for this cosmic metamorphosis, Visualize a vast expanse of space, with a colorful nebula as the central focus.,The nebula's swirling gases and particles hint at its active nature, Depict the nebula as a concentrated source of 'special energy.' ,Show vibrant, ethereal hues emanating from its core, symbolizing its unique nature,As the transformation begins, illustrate the nebula's gradual change, Use progressive images to showcase the transition. Nebulous formations evolve, merge, and disperse, symbolizing the conversion of the 'special energy' into different energies, In subsequent images, represent the newly formed energies, Use distinct visual cues to depict these energies - vibrant bursts of light, swirling patterns, and radiant beams that vary in color and intensity, Convey a sense of harmony and interconnectedness, Show how the different energies interact and influence one another, creating a cosmic symphony of forces, Illustrate the culmination of the transformation, The nebula's appearance has changed significantly, and it now radiates an array of energies, each contributing to the cosmic balance. -- ar 16:9 --gs7 --neg "blurry" --motion1. | [
{
"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: [Imagine a dynamic scene where a celestial nebula is undergoing a continuous transformation, to a diverse array of energies, The nebula serves as a canvas for this cosmic metamorphosis, Visualize a vast expanse of space, with a colorful nebula as the central focus.,The nebula's swirling gases and particles hint at its active nature, Depict the nebula as a concentrated source of 'special energy.' ,Show vibrant, ethereal hues emanating from its core, symbolizing its unique nature,As the transformation begins, illustrate the nebula's gradual change, Use progressive images to showcase the transition. Nebulous formations evolve, merge, and disperse, symbolizing the conversion of the 'special energy' into different energies, In subsequent images, represent the newly formed energies, Use distinct visual cues to depict these energies - vibrant bursts of light, swirling patterns, and radiant beams that vary in color and intensity, Convey a sense of harmony and interconnectedness, Show how the different energies interact and influence one another, creating a cosmic symphony of forces, Illustrate the culmination of the transformation, The nebula's appearance has changed significantly, and it now radiates an array of energies, each contributing to the cosmic balance. -- ar 16:9 --gs7 --neg "blurry" --motion1.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000859/0.png",
"winvideos/000859/1.png",
"winvideos/000859/2.png",
"winvideos/000859/3.png",
"winvideos/000859/4.png",
"winvideos/000859/5.png",
"winvideos/000859/6.png",
"winvideos/000859/7.png",
"losevideos/000859/0.png",
"losevideos/000859/1.png",
"losevideos/000859/2.png",
"losevideos/000859/3.png",
"losevideos/000859/4.png",
"losevideos/000859/5.png",
"losevideos/000859/6.png",
"losevideos/000859/7.png"
] |
4k, car, city, race. | [
{
"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: [4k, car, city, race.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000727/0.png",
"winvideos/000727/1.png",
"winvideos/000727/2.png",
"winvideos/000727/3.png",
"winvideos/000727/4.png",
"winvideos/000727/5.png",
"winvideos/000727/6.png",
"winvideos/000727/7.png",
"losevideos/000727/0.png",
"losevideos/000727/1.png",
"losevideos/000727/2.png",
"losevideos/000727/3.png",
"losevideos/000727/4.png",
"losevideos/000727/5.png",
"losevideos/000727/6.png",
"losevideos/000727/7.png"
] |
The background is a door. A Chinese dragon cartoon image flies in and hovers from outside the screen. Tap your finger in front of the door to activate the door and open it. | [
{
"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: [The background is a door. A Chinese dragon cartoon image flies in and hovers from outside the screen. Tap your finger in front of the door to activate the door and open it.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007177/0.png",
"winvideos/007177/1.png",
"winvideos/007177/2.png",
"winvideos/007177/3.png",
"winvideos/007177/4.png",
"winvideos/007177/5.png",
"winvideos/007177/6.png",
"winvideos/007177/7.png",
"losevideos/007177/0.png",
"losevideos/007177/1.png",
"losevideos/007177/2.png",
"losevideos/007177/3.png",
"losevideos/007177/4.png",
"losevideos/007177/5.png",
"losevideos/007177/6.png",
"losevideos/007177/7.png"
] |
A very realistic creeper from Minecraft. | [
{
"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 very realistic creeper from Minecraft.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001793/0.png",
"winvideos/001793/1.png",
"winvideos/001793/2.png",
"winvideos/001793/3.png",
"winvideos/001793/4.png",
"winvideos/001793/5.png",
"winvideos/001793/6.png",
"winvideos/001793/7.png",
"losevideos/001793/0.png",
"losevideos/001793/1.png",
"losevideos/001793/2.png",
"losevideos/001793/3.png",
"losevideos/001793/4.png",
"losevideos/001793/5.png",
"losevideos/001793/6.png",
"losevideos/001793/7.png"
] |
Goku and Satoru Gojo fused 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: [Goku and Satoru Gojo fused together.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008600/0.png",
"losevideos/008600/1.png",
"losevideos/008600/2.png",
"losevideos/008600/3.png",
"losevideos/008600/4.png",
"losevideos/008600/5.png",
"losevideos/008600/6.png",
"losevideos/008600/7.png",
"winvideos/008600/0.png",
"winvideos/008600/1.png",
"winvideos/008600/2.png",
"winvideos/008600/3.png",
"winvideos/008600/4.png",
"winvideos/008600/5.png",
"winvideos/008600/6.png",
"winvideos/008600/7.png"
] |
a panda floating in the sky -ar 16:9 -motion 2. | [
{
"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 panda floating in the sky -ar 16:9 -motion 2.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000137/0.png",
"losevideos/000137/1.png",
"losevideos/000137/2.png",
"losevideos/000137/3.png",
"losevideos/000137/4.png",
"losevideos/000137/5.png",
"losevideos/000137/6.png",
"losevideos/000137/7.png",
"winvideos/000137/0.png",
"winvideos/000137/1.png",
"winvideos/000137/2.png",
"winvideos/000137/3.png",
"winvideos/000137/4.png",
"winvideos/000137/5.png",
"winvideos/000137/6.png",
"winvideos/000137/7.png"
] |
Nu metal, electric guitar, Minecraft, miss teacher, stars, blood Message: kassandra (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: [Nu metal, electric guitar, Minecraft, miss teacher, stars, blood Message: kassandra (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009131/0.png",
"losevideos/009131/1.png",
"losevideos/009131/2.png",
"losevideos/009131/3.png",
"losevideos/009131/4.png",
"losevideos/009131/5.png",
"losevideos/009131/6.png",
"losevideos/009131/7.png",
"winvideos/009131/0.png",
"winvideos/009131/1.png",
"winvideos/009131/2.png",
"winvideos/009131/3.png",
"winvideos/009131/4.png",
"winvideos/009131/5.png",
"winvideos/009131/6.png",
"winvideos/009131/7.png"
] |
A breathtaking panoramic view of the unique planet Veridian Prime, its vibrant violet and emerald-colored sky stretching as far as the eye can see, setting the stage for the planet's extraordinary life, Photography, use a wide-angle lens to capture the vastness of the landscape. | [
{
"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 breathtaking panoramic view of the unique planet Veridian Prime, its vibrant violet and emerald-colored sky stretching as far as the eye can see, setting the stage for the planet's extraordinary life, Photography, use a wide-angle lens to capture the vastness of the landscape.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000224/0.png",
"losevideos/000224/1.png",
"losevideos/000224/2.png",
"losevideos/000224/3.png",
"losevideos/000224/4.png",
"losevideos/000224/5.png",
"losevideos/000224/6.png",
"losevideos/000224/7.png",
"winvideos/000224/0.png",
"winvideos/000224/1.png",
"winvideos/000224/2.png",
"winvideos/000224/3.png",
"winvideos/000224/4.png",
"winvideos/000224/5.png",
"winvideos/000224/6.png",
"winvideos/000224/7.png"
] |
movie trailer advertisement style, young handsome man looking to camera, sudden long hair beard and mustache growth. | [
{
"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: [movie trailer advertisement style, young handsome man looking to camera, sudden long hair beard and mustache growth.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007897/0.png",
"losevideos/007897/1.png",
"losevideos/007897/2.png",
"losevideos/007897/3.png",
"losevideos/007897/4.png",
"losevideos/007897/5.png",
"losevideos/007897/6.png",
"losevideos/007897/7.png",
"winvideos/007897/0.png",
"winvideos/007897/1.png",
"winvideos/007897/2.png",
"winvideos/007897/3.png",
"winvideos/007897/4.png",
"winvideos/007897/5.png",
"winvideos/007897/6.png",
"winvideos/007897/7.png"
] |
Introduce the protagonist, a young Ghanaian artist struggling to find her place in the world of art. Uncover her inner conflicts and aspirations that drive her passion -moving -zoom camera in -zoom camera out - realistic. | [
{
"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: [Introduce the protagonist, a young Ghanaian artist struggling to find her place in the world of art. Uncover her inner conflicts and aspirations that drive her passion -moving -zoom camera in -zoom camera out - realistic.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007169/0.png",
"winvideos/007169/1.png",
"winvideos/007169/2.png",
"winvideos/007169/3.png",
"winvideos/007169/4.png",
"winvideos/007169/5.png",
"winvideos/007169/6.png",
"winvideos/007169/7.png",
"losevideos/007169/0.png",
"losevideos/007169/1.png",
"losevideos/007169/2.png",
"losevideos/007169/3.png",
"losevideos/007169/4.png",
"losevideos/007169/5.png",
"losevideos/007169/6.png",
"losevideos/007169/7.png"
] |
A stop motion android Pierrette performing esoteric magic rituals with a Merkaba by Quay brothers and Tim Burton and Jim Henson, featured on artstation, holographic -seed 24785103046596993 -gs 15. | [
{
"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 stop motion android Pierrette performing esoteric magic rituals with a Merkaba by Quay brothers and Tim Burton and Jim Henson, featured on artstation, holographic -seed 24785103046596993 -gs 15.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009637/0.png",
"winvideos/009637/1.png",
"winvideos/009637/2.png",
"winvideos/009637/3.png",
"winvideos/009637/4.png",
"winvideos/009637/5.png",
"winvideos/009637/6.png",
"winvideos/009637/7.png",
"losevideos/009637/0.png",
"losevideos/009637/1.png",
"losevideos/009637/2.png",
"losevideos/009637/3.png",
"losevideos/009637/4.png",
"losevideos/009637/5.png",
"losevideos/009637/6.png",
"losevideos/009637/7.png"
] |
Make the sky darker, 4K -seed 444 -ar 16:9 -motion 0. | [
{
"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: [Make the sky darker, 4K -seed 444 -ar 16:9 -motion 0.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005289/0.png",
"losevideos/005289/1.png",
"losevideos/005289/2.png",
"losevideos/005289/3.png",
"losevideos/005289/4.png",
"losevideos/005289/5.png",
"losevideos/005289/6.png",
"losevideos/005289/7.png",
"winvideos/005289/0.png",
"winvideos/005289/1.png",
"winvideos/005289/2.png",
"winvideos/005289/3.png",
"winvideos/005289/4.png",
"winvideos/005289/5.png",
"winvideos/005289/6.png",
"winvideos/005289/7.png"
] |
Create an image of Sugarloaf Mountain, Rio de Janeiro, highlighting the incredible views of the city, beaches and Guanabara Bay. | [
{
"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: [Create an image of Sugarloaf Mountain, Rio de Janeiro, highlighting the incredible views of the city, beaches and Guanabara Bay.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007837/0.png",
"losevideos/007837/1.png",
"losevideos/007837/2.png",
"losevideos/007837/3.png",
"losevideos/007837/4.png",
"losevideos/007837/5.png",
"losevideos/007837/6.png",
"losevideos/007837/7.png",
"winvideos/007837/0.png",
"winvideos/007837/1.png",
"winvideos/007837/2.png",
"winvideos/007837/3.png",
"winvideos/007837/4.png",
"winvideos/007837/5.png",
"winvideos/007837/6.png",
"winvideos/007837/7.png"
] |
Tranquil, sunlit oasis, ten-year-old boy, tousled blonde hair, bright blue eyes, graceful dance, imposing gateway, intricate patterns, ethereal golden radiance, lush green surroundings, swaying trees, regal attire, crown, unbridled joy, curiosity, enchantment, innocence, shimmering aura, otherworldly hum, sense of wonder, magic, regally attired hand, captivating, eager, mysteries beyond, innocence, fascination, discovery, world of wonder, magic, royal presence, mesmerizing gateway, enchanting adventure, secrets, treasures. | [
{
"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: [Tranquil, sunlit oasis, ten-year-old boy, tousled blonde hair, bright blue eyes, graceful dance, imposing gateway, intricate patterns, ethereal golden radiance, lush green surroundings, swaying trees, regal attire, crown, unbridled joy, curiosity, enchantment, innocence, shimmering aura, otherworldly hum, sense of wonder, magic, regally attired hand, captivating, eager, mysteries beyond, innocence, fascination, discovery, world of wonder, magic, royal presence, mesmerizing gateway, enchanting adventure, secrets, treasures.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004521/0.png",
"losevideos/004521/1.png",
"losevideos/004521/2.png",
"losevideos/004521/3.png",
"losevideos/004521/4.png",
"losevideos/004521/5.png",
"losevideos/004521/6.png",
"losevideos/004521/7.png",
"winvideos/004521/0.png",
"winvideos/004521/1.png",
"winvideos/004521/2.png",
"winvideos/004521/3.png",
"winvideos/004521/4.png",
"winvideos/004521/5.png",
"winvideos/004521/6.png",
"winvideos/004521/7.png"
] |
one piece nami playing basketball while a car crashes in the background 16:9 cw. | [
{
"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: [one piece nami playing basketball while a car crashes in the background 16:9 cw.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009738/0.png",
"losevideos/009738/1.png",
"losevideos/009738/2.png",
"losevideos/009738/3.png",
"losevideos/009738/4.png",
"losevideos/009738/5.png",
"losevideos/009738/6.png",
"losevideos/009738/7.png",
"winvideos/009738/0.png",
"winvideos/009738/1.png",
"winvideos/009738/2.png",
"winvideos/009738/3.png",
"winvideos/009738/4.png",
"winvideos/009738/5.png",
"winvideos/009738/6.png",
"winvideos/009738/7.png"
] |
a footballer who scores a goal. | [
{
"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 footballer who scores a goal.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008718/0.png",
"winvideos/008718/1.png",
"winvideos/008718/2.png",
"winvideos/008718/3.png",
"winvideos/008718/4.png",
"winvideos/008718/5.png",
"winvideos/008718/6.png",
"winvideos/008718/7.png",
"losevideos/008718/0.png",
"losevideos/008718/1.png",
"losevideos/008718/2.png",
"losevideos/008718/3.png",
"losevideos/008718/4.png",
"losevideos/008718/5.png",
"losevideos/008718/6.png",
"losevideos/008718/7.png"
] |
male superhereos kiss, embrace, romatic, kiss, joy, romcom, shiny black latex rubber, 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: [male superhereos kiss, embrace, romatic, kiss, joy, romcom, shiny black latex rubber, cinematic.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004799/0.png",
"losevideos/004799/1.png",
"losevideos/004799/2.png",
"losevideos/004799/3.png",
"losevideos/004799/4.png",
"losevideos/004799/5.png",
"losevideos/004799/6.png",
"losevideos/004799/7.png",
"winvideos/004799/0.png",
"winvideos/004799/1.png",
"winvideos/004799/2.png",
"winvideos/004799/3.png",
"winvideos/004799/4.png",
"winvideos/004799/5.png",
"winvideos/004799/6.png",
"winvideos/004799/7.png"
] |
slow motion jumping downward. | [
{
"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: [slow motion jumping downward.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008197/0.png",
"losevideos/008197/1.png",
"losevideos/008197/2.png",
"losevideos/008197/3.png",
"losevideos/008197/4.png",
"losevideos/008197/5.png",
"losevideos/008197/6.png",
"losevideos/008197/7.png",
"winvideos/008197/0.png",
"winvideos/008197/1.png",
"winvideos/008197/2.png",
"winvideos/008197/3.png",
"winvideos/008197/4.png",
"winvideos/008197/5.png",
"winvideos/008197/6.png",
"winvideos/008197/7.png"
] |
Superman gliding. | [
{
"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 gliding.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000203/0.png",
"losevideos/000203/1.png",
"losevideos/000203/2.png",
"losevideos/000203/3.png",
"losevideos/000203/4.png",
"losevideos/000203/5.png",
"losevideos/000203/6.png",
"losevideos/000203/7.png",
"winvideos/000203/0.png",
"winvideos/000203/1.png",
"winvideos/000203/2.png",
"winvideos/000203/3.png",
"winvideos/000203/4.png",
"winvideos/000203/5.png",
"winvideos/000203/6.png",
"winvideos/000203/7.png"
] |
High Speed Camera realistic image Maa Lakshmi camera zoom in. | [
{
"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: [High Speed Camera realistic image Maa Lakshmi camera zoom in.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002259/0.png",
"losevideos/002259/1.png",
"losevideos/002259/2.png",
"losevideos/002259/3.png",
"losevideos/002259/4.png",
"losevideos/002259/5.png",
"losevideos/002259/6.png",
"losevideos/002259/7.png",
"winvideos/002259/0.png",
"winvideos/002259/1.png",
"winvideos/002259/2.png",
"winvideos/002259/3.png",
"winvideos/002259/4.png",
"winvideos/002259/5.png",
"winvideos/002259/6.png",
"winvideos/002259/7.png"
] |
a dragon flapping his wings, HR Giger art style. | [
{
"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 dragon flapping his wings, HR Giger art style.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003835/0.png",
"losevideos/003835/1.png",
"losevideos/003835/2.png",
"losevideos/003835/3.png",
"losevideos/003835/4.png",
"losevideos/003835/5.png",
"losevideos/003835/6.png",
"losevideos/003835/7.png",
"winvideos/003835/0.png",
"winvideos/003835/1.png",
"winvideos/003835/2.png",
"winvideos/003835/3.png",
"winvideos/003835/4.png",
"winvideos/003835/5.png",
"winvideos/003835/6.png",
"winvideos/003835/7.png"
] |
dragon flying breathing fire, -camera zoom in. | [
{
"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: [dragon flying breathing fire, -camera zoom in.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003619/0.png",
"losevideos/003619/1.png",
"losevideos/003619/2.png",
"losevideos/003619/3.png",
"losevideos/003619/4.png",
"losevideos/003619/5.png",
"losevideos/003619/6.png",
"losevideos/003619/7.png",
"winvideos/003619/0.png",
"winvideos/003619/1.png",
"winvideos/003619/2.png",
"winvideos/003619/3.png",
"winvideos/003619/4.png",
"winvideos/003619/5.png",
"winvideos/003619/6.png",
"winvideos/003619/7.png"
] |
a prawn character sailing a sailing boat on a lake ar-- 16:9. | [
{
"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 prawn character sailing a sailing boat on a lake ar-- 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000683/0.png",
"losevideos/000683/1.png",
"losevideos/000683/2.png",
"losevideos/000683/3.png",
"losevideos/000683/4.png",
"losevideos/000683/5.png",
"losevideos/000683/6.png",
"losevideos/000683/7.png",
"winvideos/000683/0.png",
"winvideos/000683/1.png",
"winvideos/000683/2.png",
"winvideos/000683/3.png",
"winvideos/000683/4.png",
"winvideos/000683/5.png",
"winvideos/000683/6.png",
"winvideos/000683/7.png"
] |
Cinematic film, a beautiful female robot face on the right side, with a futuristic scene in the background, ultra realistic, -ar 16:9. | [
{
"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: [Cinematic film, a beautiful female robot face on the right side, with a futuristic scene in the background, ultra realistic, -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002416/0.png",
"losevideos/002416/1.png",
"losevideos/002416/2.png",
"losevideos/002416/3.png",
"losevideos/002416/4.png",
"losevideos/002416/5.png",
"losevideos/002416/6.png",
"losevideos/002416/7.png",
"winvideos/002416/0.png",
"winvideos/002416/1.png",
"winvideos/002416/2.png",
"winvideos/002416/3.png",
"winvideos/002416/4.png",
"winvideos/002416/5.png",
"winvideos/002416/6.png",
"winvideos/002416/7.png"
] |
beethoven playing computer keyboards at a laser light rock concert on planet jupiter. | [
{
"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: [beethoven playing computer keyboards at a laser light rock concert on planet jupiter.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004611/0.png",
"winvideos/004611/1.png",
"winvideos/004611/2.png",
"winvideos/004611/3.png",
"winvideos/004611/4.png",
"winvideos/004611/5.png",
"winvideos/004611/6.png",
"winvideos/004611/7.png",
"losevideos/004611/0.png",
"losevideos/004611/1.png",
"losevideos/004611/2.png",
"losevideos/004611/3.png",
"losevideos/004611/4.png",
"losevideos/004611/5.png",
"losevideos/004611/6.png",
"losevideos/004611/7.png"
] |
Timelapse of animal decomposing. | [
{
"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: [Timelapse of animal decomposing.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008694/0.png",
"losevideos/008694/1.png",
"losevideos/008694/2.png",
"losevideos/008694/3.png",
"losevideos/008694/4.png",
"losevideos/008694/5.png",
"losevideos/008694/6.png",
"losevideos/008694/7.png",
"winvideos/008694/0.png",
"winvideos/008694/1.png",
"winvideos/008694/2.png",
"winvideos/008694/3.png",
"winvideos/008694/4.png",
"winvideos/008694/5.png",
"winvideos/008694/6.png",
"winvideos/008694/7.png"
] |
The evil red hawk suddenly appears and flies over the city infamous at night. | [
{
"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: [The evil red hawk suddenly appears and flies over the city infamous at night.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005042/0.png",
"losevideos/005042/1.png",
"losevideos/005042/2.png",
"losevideos/005042/3.png",
"losevideos/005042/4.png",
"losevideos/005042/5.png",
"losevideos/005042/6.png",
"losevideos/005042/7.png",
"winvideos/005042/0.png",
"winvideos/005042/1.png",
"winvideos/005042/2.png",
"winvideos/005042/3.png",
"winvideos/005042/4.png",
"winvideos/005042/5.png",
"winvideos/005042/6.png",
"winvideos/005042/7.png"
] |
Filipino citizen studying in foreign school. | [
{
"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: [Filipino citizen studying in foreign school.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003051/0.png",
"losevideos/003051/1.png",
"losevideos/003051/2.png",
"losevideos/003051/3.png",
"losevideos/003051/4.png",
"losevideos/003051/5.png",
"losevideos/003051/6.png",
"losevideos/003051/7.png",
"winvideos/003051/0.png",
"winvideos/003051/1.png",
"winvideos/003051/2.png",
"winvideos/003051/3.png",
"winvideos/003051/4.png",
"winvideos/003051/5.png",
"winvideos/003051/6.png",
"winvideos/003051/7.png"
] |
long dachshund, wiggling, desert. | [
{
"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: [long dachshund, wiggling, desert.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009030/0.png",
"winvideos/009030/1.png",
"winvideos/009030/2.png",
"winvideos/009030/3.png",
"winvideos/009030/4.png",
"winvideos/009030/5.png",
"winvideos/009030/6.png",
"winvideos/009030/7.png",
"losevideos/009030/0.png",
"losevideos/009030/1.png",
"losevideos/009030/2.png",
"losevideos/009030/3.png",
"losevideos/009030/4.png",
"losevideos/009030/5.png",
"losevideos/009030/6.png",
"losevideos/009030/7.png"
] |
3D_Animation_Style_Protagonist_2_female_middleaged_is_in_the_b_2. | [
{
"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_Style_Protagonist_2_female_middleaged_is_in_the_b_2.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003830/0.png",
"winvideos/003830/1.png",
"winvideos/003830/2.png",
"winvideos/003830/3.png",
"winvideos/003830/4.png",
"winvideos/003830/5.png",
"winvideos/003830/6.png",
"winvideos/003830/7.png",
"losevideos/003830/0.png",
"losevideos/003830/1.png",
"losevideos/003830/2.png",
"losevideos/003830/3.png",
"losevideos/003830/4.png",
"losevideos/003830/5.png",
"losevideos/003830/6.png",
"losevideos/003830/7.png"
] |
Spider-Gwen. | [
{
"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: [Spider-Gwen.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009151/0.png",
"losevideos/009151/1.png",
"losevideos/009151/2.png",
"losevideos/009151/3.png",
"losevideos/009151/4.png",
"losevideos/009151/5.png",
"losevideos/009151/6.png",
"losevideos/009151/7.png",
"winvideos/009151/0.png",
"winvideos/009151/1.png",
"winvideos/009151/2.png",
"winvideos/009151/3.png",
"winvideos/009151/4.png",
"winvideos/009151/5.png",
"winvideos/009151/6.png",
"winvideos/009151/7.png"
] |
Make the light and shadow move on this picture Message: 1 Attachment. | [
{
"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: [Make the light and shadow move on this picture Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007796/0.png",
"losevideos/007796/1.png",
"losevideos/007796/2.png",
"losevideos/007796/3.png",
"losevideos/007796/4.png",
"losevideos/007796/5.png",
"losevideos/007796/6.png",
"losevideos/007796/7.png",
"winvideos/007796/0.png",
"winvideos/007796/1.png",
"winvideos/007796/2.png",
"winvideos/007796/3.png",
"winvideos/007796/4.png",
"winvideos/007796/5.png",
"winvideos/007796/6.png",
"winvideos/007796/7.png"
] |
scary old woman face, facing you telling story. | [
{
"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: [scary old woman face, facing you telling story.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008841/0.png",
"losevideos/008841/1.png",
"losevideos/008841/2.png",
"losevideos/008841/3.png",
"losevideos/008841/4.png",
"losevideos/008841/5.png",
"losevideos/008841/6.png",
"losevideos/008841/7.png",
"winvideos/008841/0.png",
"winvideos/008841/1.png",
"winvideos/008841/2.png",
"winvideos/008841/3.png",
"winvideos/008841/4.png",
"winvideos/008841/5.png",
"winvideos/008841/6.png",
"winvideos/008841/7.png"
] |
birdview of a nuclear shockwave spreading on the forest ground. | [
{
"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: [birdview of a nuclear shockwave spreading on the forest ground.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006884/0.png",
"winvideos/006884/1.png",
"winvideos/006884/2.png",
"winvideos/006884/3.png",
"winvideos/006884/4.png",
"winvideos/006884/5.png",
"winvideos/006884/6.png",
"winvideos/006884/7.png",
"losevideos/006884/0.png",
"losevideos/006884/1.png",
"losevideos/006884/2.png",
"losevideos/006884/3.png",
"losevideos/006884/4.png",
"losevideos/006884/5.png",
"losevideos/006884/6.png",
"losevideos/006884/7.png"
] |
beautiful pink view with ocean hyper-realistic, cinematic view, -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, pixelated, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting, error, still -ar 19:9 -motion 3 -camera pan right. | [
{
"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: [beautiful pink view with ocean hyper-realistic, cinematic view, -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, pixelated, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting, error, still -ar 19:9 -motion 3 -camera pan right.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009654/0.png",
"losevideos/009654/1.png",
"losevideos/009654/2.png",
"losevideos/009654/3.png",
"losevideos/009654/4.png",
"losevideos/009654/5.png",
"losevideos/009654/6.png",
"losevideos/009654/7.png",
"winvideos/009654/0.png",
"winvideos/009654/1.png",
"winvideos/009654/2.png",
"winvideos/009654/3.png",
"winvideos/009654/4.png",
"winvideos/009654/5.png",
"winvideos/009654/6.png",
"winvideos/009654/7.png"
] |
a dark shadow figure moving in a bedroom.4k. | [
{
"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 dark shadow figure moving in a bedroom.4k.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006526/0.png",
"losevideos/006526/1.png",
"losevideos/006526/2.png",
"losevideos/006526/3.png",
"losevideos/006526/4.png",
"losevideos/006526/5.png",
"losevideos/006526/6.png",
"losevideos/006526/7.png",
"winvideos/006526/0.png",
"winvideos/006526/1.png",
"winvideos/006526/2.png",
"winvideos/006526/3.png",
"winvideos/006526/4.png",
"winvideos/006526/5.png",
"winvideos/006526/6.png",
"winvideos/006526/7.png"
] |
rain rain -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: [rain rain -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003865/0.png",
"losevideos/003865/1.png",
"losevideos/003865/2.png",
"losevideos/003865/3.png",
"losevideos/003865/4.png",
"losevideos/003865/5.png",
"losevideos/003865/6.png",
"losevideos/003865/7.png",
"winvideos/003865/0.png",
"winvideos/003865/1.png",
"winvideos/003865/2.png",
"winvideos/003865/3.png",
"winvideos/003865/4.png",
"winvideos/003865/5.png",
"winvideos/003865/6.png",
"winvideos/003865/7.png"
] |
An army in a military base. | [
{
"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: [An army in a military base.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004453/0.png",
"winvideos/004453/1.png",
"winvideos/004453/2.png",
"winvideos/004453/3.png",
"winvideos/004453/4.png",
"winvideos/004453/5.png",
"winvideos/004453/6.png",
"winvideos/004453/7.png",
"losevideos/004453/0.png",
"losevideos/004453/1.png",
"losevideos/004453/2.png",
"losevideos/004453/3.png",
"losevideos/004453/4.png",
"losevideos/004453/5.png",
"losevideos/004453/6.png",
"losevideos/004453/7.png"
] |
background filled with code script moving. | [
{
"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: [background filled with code script moving.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004664/0.png",
"losevideos/004664/1.png",
"losevideos/004664/2.png",
"losevideos/004664/3.png",
"losevideos/004664/4.png",
"losevideos/004664/5.png",
"losevideos/004664/6.png",
"losevideos/004664/7.png",
"winvideos/004664/0.png",
"winvideos/004664/1.png",
"winvideos/004664/2.png",
"winvideos/004664/3.png",
"winvideos/004664/4.png",
"winvideos/004664/5.png",
"winvideos/004664/6.png",
"winvideos/004664/7.png"
] |
people moving through the 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: [people moving through the street.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000919/0.png",
"winvideos/000919/1.png",
"winvideos/000919/2.png",
"winvideos/000919/3.png",
"winvideos/000919/4.png",
"winvideos/000919/5.png",
"winvideos/000919/6.png",
"winvideos/000919/7.png",
"losevideos/000919/0.png",
"losevideos/000919/1.png",
"losevideos/000919/2.png",
"losevideos/000919/3.png",
"losevideos/000919/4.png",
"losevideos/000919/5.png",
"losevideos/000919/6.png",
"losevideos/000919/7.png"
] |
cholo simeone cazando venado. | [
{
"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: [cholo simeone cazando venado.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006380/0.png",
"winvideos/006380/1.png",
"winvideos/006380/2.png",
"winvideos/006380/3.png",
"winvideos/006380/4.png",
"winvideos/006380/5.png",
"winvideos/006380/6.png",
"winvideos/006380/7.png",
"losevideos/006380/0.png",
"losevideos/006380/1.png",
"losevideos/006380/2.png",
"losevideos/006380/3.png",
"losevideos/006380/4.png",
"losevideos/006380/5.png",
"losevideos/006380/6.png",
"losevideos/006380/7.png"
] |
holding a tiny baby in hands cartoon blue tint. | [
{
"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: [holding a tiny baby in hands cartoon blue tint.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007180/0.png",
"winvideos/007180/1.png",
"winvideos/007180/2.png",
"winvideos/007180/3.png",
"winvideos/007180/4.png",
"winvideos/007180/5.png",
"winvideos/007180/6.png",
"winvideos/007180/7.png",
"losevideos/007180/0.png",
"losevideos/007180/1.png",
"losevideos/007180/2.png",
"losevideos/007180/3.png",
"losevideos/007180/4.png",
"losevideos/007180/5.png",
"losevideos/007180/6.png",
"losevideos/007180/7.png"
] |
mangrove with sunset. | [
{
"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: [mangrove with sunset.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003171/0.png",
"winvideos/003171/1.png",
"winvideos/003171/2.png",
"winvideos/003171/3.png",
"winvideos/003171/4.png",
"winvideos/003171/5.png",
"winvideos/003171/6.png",
"winvideos/003171/7.png",
"losevideos/003171/0.png",
"losevideos/003171/1.png",
"losevideos/003171/2.png",
"losevideos/003171/3.png",
"losevideos/003171/4.png",
"losevideos/003171/5.png",
"losevideos/003171/6.png",
"losevideos/003171/7.png"
] |
logo written in the grass of an irish field, lush greens -camera pan up left Message: 1 Attachment. | [
{
"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: [logo written in the grass of an irish field, lush greens -camera pan up left Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000610/0.png",
"winvideos/000610/1.png",
"winvideos/000610/2.png",
"winvideos/000610/3.png",
"winvideos/000610/4.png",
"winvideos/000610/5.png",
"winvideos/000610/6.png",
"winvideos/000610/7.png",
"losevideos/000610/0.png",
"losevideos/000610/1.png",
"losevideos/000610/2.png",
"losevideos/000610/3.png",
"losevideos/000610/4.png",
"losevideos/000610/5.png",
"losevideos/000610/6.png",
"losevideos/000610/7.png"
] |
Splash with oilcolors Message: Hello (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: [Splash with oilcolors Message: Hello (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002319/0.png",
"losevideos/002319/1.png",
"losevideos/002319/2.png",
"losevideos/002319/3.png",
"losevideos/002319/4.png",
"losevideos/002319/5.png",
"losevideos/002319/6.png",
"losevideos/002319/7.png",
"winvideos/002319/0.png",
"winvideos/002319/1.png",
"winvideos/002319/2.png",
"winvideos/002319/3.png",
"winvideos/002319/4.png",
"winvideos/002319/5.png",
"winvideos/002319/6.png",
"winvideos/002319/7.png"
] |
young forging suit hero movie. | [
{
"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: [young forging suit hero movie.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002059/0.png",
"losevideos/002059/1.png",
"losevideos/002059/2.png",
"losevideos/002059/3.png",
"losevideos/002059/4.png",
"losevideos/002059/5.png",
"losevideos/002059/6.png",
"losevideos/002059/7.png",
"winvideos/002059/0.png",
"winvideos/002059/1.png",
"winvideos/002059/2.png",
"winvideos/002059/3.png",
"winvideos/002059/4.png",
"winvideos/002059/5.png",
"winvideos/002059/6.png",
"winvideos/002059/7.png"
] |
mark Zuckerberg as fighter in boxing ring. | [
{
"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: [mark Zuckerberg as fighter in boxing ring.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002577/0.png",
"winvideos/002577/1.png",
"winvideos/002577/2.png",
"winvideos/002577/3.png",
"winvideos/002577/4.png",
"winvideos/002577/5.png",
"winvideos/002577/6.png",
"winvideos/002577/7.png",
"losevideos/002577/0.png",
"losevideos/002577/1.png",
"losevideos/002577/2.png",
"losevideos/002577/3.png",
"losevideos/002577/4.png",
"losevideos/002577/5.png",
"losevideos/002577/6.png",
"losevideos/002577/7.png"
] |
Create a video in which lawyer Gabriel Antunes defends his client who is being accused by a robot of crashing his Tesla. | [
{
"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: [Create a video in which lawyer Gabriel Antunes defends his client who is being accused by a robot of crashing his Tesla.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008334/0.png",
"losevideos/008334/1.png",
"losevideos/008334/2.png",
"losevideos/008334/3.png",
"losevideos/008334/4.png",
"losevideos/008334/5.png",
"losevideos/008334/6.png",
"losevideos/008334/7.png",
"winvideos/008334/0.png",
"winvideos/008334/1.png",
"winvideos/008334/2.png",
"winvideos/008334/3.png",
"winvideos/008334/4.png",
"winvideos/008334/5.png",
"winvideos/008334/6.png",
"winvideos/008334/7.png"
] |
1955, muted colors composition, dark surrealist impression, steam machinery, robots, peeling paint, glowing chemical bottles, maps, clutter, smoke, grime, dark room. chimps holding glowing bottles, camera depth of field, style of Diane Arbus. | [
{
"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: [1955, muted colors composition, dark surrealist impression, steam machinery, robots, peeling paint, glowing chemical bottles, maps, clutter, smoke, grime, dark room. chimps holding glowing bottles, camera depth of field, style of Diane Arbus.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006894/0.png",
"losevideos/006894/1.png",
"losevideos/006894/2.png",
"losevideos/006894/3.png",
"losevideos/006894/4.png",
"losevideos/006894/5.png",
"losevideos/006894/6.png",
"losevideos/006894/7.png",
"winvideos/006894/0.png",
"winvideos/006894/1.png",
"winvideos/006894/2.png",
"winvideos/006894/3.png",
"winvideos/006894/4.png",
"winvideos/006894/5.png",
"winvideos/006894/6.png",
"winvideos/006894/7.png"
] |
blue skies and oceans. | [
{
"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: [blue skies and oceans.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003633/0.png",
"losevideos/003633/1.png",
"losevideos/003633/2.png",
"losevideos/003633/3.png",
"losevideos/003633/4.png",
"losevideos/003633/5.png",
"losevideos/003633/6.png",
"losevideos/003633/7.png",
"winvideos/003633/0.png",
"winvideos/003633/1.png",
"winvideos/003633/2.png",
"winvideos/003633/3.png",
"winvideos/003633/4.png",
"winvideos/003633/5.png",
"winvideos/003633/6.png",
"winvideos/003633/7.png"
] |
a dark kinky sexy techno rave of futuristic white chrome fantasy sexy female techno goth elfecore sci-fi deities androids cyborgs, techno dj, fire, laser beams, playing on alien modular synthesizers, flashing lights, psychedelic colors, techno raving, techno dancing, alien scenery, alien plants, party lights, cinematic, boiler room party -ar 3:4. | [
{
"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: [a dark kinky sexy techno rave of futuristic white chrome fantasy sexy female techno goth elfecore sci-fi deities androids cyborgs, techno dj, fire, laser beams, playing on alien modular synthesizers, flashing lights, psychedelic colors, techno raving, techno dancing, alien scenery, alien plants, party lights, cinematic, boiler room party -ar 3:4.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006973/0.png",
"winvideos/006973/1.png",
"winvideos/006973/2.png",
"winvideos/006973/3.png",
"winvideos/006973/4.png",
"winvideos/006973/5.png",
"winvideos/006973/6.png",
"winvideos/006973/7.png",
"losevideos/006973/0.png",
"losevideos/006973/1.png",
"losevideos/006973/2.png",
"losevideos/006973/3.png",
"losevideos/006973/4.png",
"losevideos/006973/5.png",
"losevideos/006973/6.png",
"losevideos/006973/7.png"
] |
Generate a stunning and detailed image of a beautiful Indian angel standing gracefully in a lush forest. Emphasize intricate facial features, radiant beauty, and flowing open hair. Ensure the background reflects the enchanting beauty of nature, creating a serene and captivating scene. | [
{
"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: [Generate a stunning and detailed image of a beautiful Indian angel standing gracefully in a lush forest. Emphasize intricate facial features, radiant beauty, and flowing open hair. Ensure the background reflects the enchanting beauty of nature, creating a serene and captivating scene.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009176/0.png",
"losevideos/009176/1.png",
"losevideos/009176/2.png",
"losevideos/009176/3.png",
"losevideos/009176/4.png",
"losevideos/009176/5.png",
"losevideos/009176/6.png",
"losevideos/009176/7.png",
"winvideos/009176/0.png",
"winvideos/009176/1.png",
"winvideos/009176/2.png",
"winvideos/009176/3.png",
"winvideos/009176/4.png",
"winvideos/009176/5.png",
"winvideos/009176/6.png",
"winvideos/009176/7.png"
] |
a woman dressed in a white dress running through a beautiful field at sunset - fps 24. | [
{
"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 woman dressed in a white dress running through a beautiful field at sunset - fps 24.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004674/0.png",
"winvideos/004674/1.png",
"winvideos/004674/2.png",
"winvideos/004674/3.png",
"winvideos/004674/4.png",
"winvideos/004674/5.png",
"winvideos/004674/6.png",
"winvideos/004674/7.png",
"losevideos/004674/0.png",
"losevideos/004674/1.png",
"losevideos/004674/2.png",
"losevideos/004674/3.png",
"losevideos/004674/4.png",
"losevideos/004674/5.png",
"losevideos/004674/6.png",
"losevideos/004674/7.png"
] |
fast timelapse of weaving representation of hope and unity, cinematic dramatic style. | [
{
"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: [fast timelapse of weaving representation of hope and unity, cinematic dramatic style.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003945/0.png",
"winvideos/003945/1.png",
"winvideos/003945/2.png",
"winvideos/003945/3.png",
"winvideos/003945/4.png",
"winvideos/003945/5.png",
"winvideos/003945/6.png",
"winvideos/003945/7.png",
"losevideos/003945/0.png",
"losevideos/003945/1.png",
"losevideos/003945/2.png",
"losevideos/003945/3.png",
"losevideos/003945/4.png",
"losevideos/003945/5.png",
"losevideos/003945/6.png",
"losevideos/003945/7.png"
] |
boy Ghost playing in the empty swimming pool, 1950. | [
{
"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: [boy Ghost playing in the empty swimming pool, 1950.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009494/0.png",
"winvideos/009494/1.png",
"winvideos/009494/2.png",
"winvideos/009494/3.png",
"winvideos/009494/4.png",
"winvideos/009494/5.png",
"winvideos/009494/6.png",
"winvideos/009494/7.png",
"losevideos/009494/0.png",
"losevideos/009494/1.png",
"losevideos/009494/2.png",
"losevideos/009494/3.png",
"losevideos/009494/4.png",
"losevideos/009494/5.png",
"losevideos/009494/6.png",
"losevideos/009494/7.png"
] |
cinematic cgi action scene in high detail, hyper realistic, of an annoying narcissistic obese woman with short hair and cheesy patriot tattoos, in the artistic style of Greg Nicotero, -fps 24 -motion 4 -camera pan up -gs 24. | [
{
"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: [cinematic cgi action scene in high detail, hyper realistic, of an annoying narcissistic obese woman with short hair and cheesy patriot tattoos, in the artistic style of Greg Nicotero, -fps 24 -motion 4 -camera pan up -gs 24.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006601/0.png",
"losevideos/006601/1.png",
"losevideos/006601/2.png",
"losevideos/006601/3.png",
"losevideos/006601/4.png",
"losevideos/006601/5.png",
"losevideos/006601/6.png",
"losevideos/006601/7.png",
"winvideos/006601/0.png",
"winvideos/006601/1.png",
"winvideos/006601/2.png",
"winvideos/006601/3.png",
"winvideos/006601/4.png",
"winvideos/006601/5.png",
"winvideos/006601/6.png",
"winvideos/006601/7.png"
] |
A figurative form, softly colored, with bright hues and ethereal patterns, that shines. | [
{
"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 figurative form, softly colored, with bright hues and ethereal patterns, that shines.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007034/0.png",
"losevideos/007034/1.png",
"losevideos/007034/2.png",
"losevideos/007034/3.png",
"losevideos/007034/4.png",
"losevideos/007034/5.png",
"losevideos/007034/6.png",
"losevideos/007034/7.png",
"winvideos/007034/0.png",
"winvideos/007034/1.png",
"winvideos/007034/2.png",
"winvideos/007034/3.png",
"winvideos/007034/4.png",
"winvideos/007034/5.png",
"winvideos/007034/6.png",
"winvideos/007034/7.png"
] |
phone call now. | [
{
"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: [phone call now.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004965/0.png",
"winvideos/004965/1.png",
"winvideos/004965/2.png",
"winvideos/004965/3.png",
"winvideos/004965/4.png",
"winvideos/004965/5.png",
"winvideos/004965/6.png",
"winvideos/004965/7.png",
"losevideos/004965/0.png",
"losevideos/004965/1.png",
"losevideos/004965/2.png",
"losevideos/004965/3.png",
"losevideos/004965/4.png",
"losevideos/004965/5.png",
"losevideos/004965/6.png",
"losevideos/004965/7.png"
] |
A bearded Santa Claus dressed in red is sitting in the lotus position under a Christmas tree. | [
{
"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 bearded Santa Claus dressed in red is sitting in the lotus position under a Christmas tree.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000511/0.png",
"winvideos/000511/1.png",
"winvideos/000511/2.png",
"winvideos/000511/3.png",
"winvideos/000511/4.png",
"winvideos/000511/5.png",
"winvideos/000511/6.png",
"winvideos/000511/7.png",
"losevideos/000511/0.png",
"losevideos/000511/1.png",
"losevideos/000511/2.png",
"losevideos/000511/3.png",
"losevideos/000511/4.png",
"losevideos/000511/5.png",
"losevideos/000511/6.png",
"losevideos/000511/7.png"
] |
police eating donuts Message: Guaita (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: [police eating donuts Message: Guaita (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001245/0.png",
"losevideos/001245/1.png",
"losevideos/001245/2.png",
"losevideos/001245/3.png",
"losevideos/001245/4.png",
"losevideos/001245/5.png",
"losevideos/001245/6.png",
"losevideos/001245/7.png",
"winvideos/001245/0.png",
"winvideos/001245/1.png",
"winvideos/001245/2.png",
"winvideos/001245/3.png",
"winvideos/001245/4.png",
"winvideos/001245/5.png",
"winvideos/001245/6.png",
"winvideos/001245/7.png"
] |
woman wearing only a hat. | [
{
"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: [woman wearing only a hat.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006279/0.png",
"winvideos/006279/1.png",
"winvideos/006279/2.png",
"winvideos/006279/3.png",
"winvideos/006279/4.png",
"winvideos/006279/5.png",
"winvideos/006279/6.png",
"winvideos/006279/7.png",
"losevideos/006279/0.png",
"losevideos/006279/1.png",
"losevideos/006279/2.png",
"losevideos/006279/3.png",
"losevideos/006279/4.png",
"losevideos/006279/5.png",
"losevideos/006279/6.png",
"losevideos/006279/7.png"
] |
A skyscape 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: [A skyscape of /.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002298/0.png",
"winvideos/002298/1.png",
"winvideos/002298/2.png",
"winvideos/002298/3.png",
"winvideos/002298/4.png",
"winvideos/002298/5.png",
"winvideos/002298/6.png",
"winvideos/002298/7.png",
"losevideos/002298/0.png",
"losevideos/002298/1.png",
"losevideos/002298/2.png",
"losevideos/002298/3.png",
"losevideos/002298/4.png",
"losevideos/002298/5.png",
"losevideos/002298/6.png",
"losevideos/002298/7.png"
] |
strange and cool cartoon clip, burning cross. | [
{
"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: [strange and cool cartoon clip, burning cross.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000167/0.png",
"losevideos/000167/1.png",
"losevideos/000167/2.png",
"losevideos/000167/3.png",
"losevideos/000167/4.png",
"losevideos/000167/5.png",
"losevideos/000167/6.png",
"losevideos/000167/7.png",
"winvideos/000167/0.png",
"winvideos/000167/1.png",
"winvideos/000167/2.png",
"winvideos/000167/3.png",
"winvideos/000167/4.png",
"winvideos/000167/5.png",
"winvideos/000167/6.png",
"winvideos/000167/7.png"
] |
monsters gathered in a group on a foreign planet landscape in a 1970s french cinema animation style. | [
{
"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: [monsters gathered in a group on a foreign planet landscape in a 1970s french cinema animation style.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009028/0.png",
"winvideos/009028/1.png",
"winvideos/009028/2.png",
"winvideos/009028/3.png",
"winvideos/009028/4.png",
"winvideos/009028/5.png",
"winvideos/009028/6.png",
"winvideos/009028/7.png",
"losevideos/009028/0.png",
"losevideos/009028/1.png",
"losevideos/009028/2.png",
"losevideos/009028/3.png",
"losevideos/009028/4.png",
"losevideos/009028/5.png",
"losevideos/009028/6.png",
"losevideos/009028/7.png"
] |
a robot mammoth coming from the background walking, grass and stones, green smoke background, surreal iridescence -neg "deformation, distortion, reflection, rays of light, beam of light, still, strange movement, still, no movement, cars, turn, rotate" -motion 1 -gs 12 -fps 24 -hide. | [
{
"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 robot mammoth coming from the background walking, grass and stones, green smoke background, surreal iridescence -neg "deformation, distortion, reflection, rays of light, beam of light, still, strange movement, still, no movement, cars, turn, rotate" -motion 1 -gs 12 -fps 24 -hide.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006456/0.png",
"winvideos/006456/1.png",
"winvideos/006456/2.png",
"winvideos/006456/3.png",
"winvideos/006456/4.png",
"winvideos/006456/5.png",
"winvideos/006456/6.png",
"winvideos/006456/7.png",
"losevideos/006456/0.png",
"losevideos/006456/1.png",
"losevideos/006456/2.png",
"losevideos/006456/3.png",
"losevideos/006456/4.png",
"losevideos/006456/5.png",
"losevideos/006456/6.png",
"losevideos/006456/7.png"
] |
all galaxy and stars fall, scattering,on earth 8k , 4k. | [
{
"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: [all galaxy and stars fall, scattering,on earth 8k , 4k.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008829/0.png",
"winvideos/008829/1.png",
"winvideos/008829/2.png",
"winvideos/008829/3.png",
"winvideos/008829/4.png",
"winvideos/008829/5.png",
"winvideos/008829/6.png",
"winvideos/008829/7.png",
"losevideos/008829/0.png",
"losevideos/008829/1.png",
"losevideos/008829/2.png",
"losevideos/008829/3.png",
"losevideos/008829/4.png",
"losevideos/008829/5.png",
"losevideos/008829/6.png",
"losevideos/008829/7.png"
] |
dragon ball z fight, flying, energy blast, dark, cinematic, thunder, man, alien, —ar 16:9. | [
{
"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: [dragon ball z fight, flying, energy blast, dark, cinematic, thunder, man, alien, —ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003042/0.png",
"winvideos/003042/1.png",
"winvideos/003042/2.png",
"winvideos/003042/3.png",
"winvideos/003042/4.png",
"winvideos/003042/5.png",
"winvideos/003042/6.png",
"winvideos/003042/7.png",
"losevideos/003042/0.png",
"losevideos/003042/1.png",
"losevideos/003042/2.png",
"losevideos/003042/3.png",
"losevideos/003042/4.png",
"losevideos/003042/5.png",
"losevideos/003042/6.png",
"losevideos/003042/7.png"
] |
1980s weed angel in heaven. | [
{
"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: [1980s weed angel in heaven.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004921/0.png",
"winvideos/004921/1.png",
"winvideos/004921/2.png",
"winvideos/004921/3.png",
"winvideos/004921/4.png",
"winvideos/004921/5.png",
"winvideos/004921/6.png",
"winvideos/004921/7.png",
"losevideos/004921/0.png",
"losevideos/004921/1.png",
"losevideos/004921/2.png",
"losevideos/004921/3.png",
"losevideos/004921/4.png",
"losevideos/004921/5.png",
"losevideos/004921/6.png",
"losevideos/004921/7.png"
] |
richard dean anderson drinking beer. | [
{
"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: [richard dean anderson drinking beer.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009048/0.png",
"losevideos/009048/1.png",
"losevideos/009048/2.png",
"losevideos/009048/3.png",
"losevideos/009048/4.png",
"losevideos/009048/5.png",
"losevideos/009048/6.png",
"losevideos/009048/7.png",
"winvideos/009048/0.png",
"winvideos/009048/1.png",
"winvideos/009048/2.png",
"winvideos/009048/3.png",
"winvideos/009048/4.png",
"winvideos/009048/5.png",
"winvideos/009048/6.png",
"winvideos/009048/7.png"
] |
both are watching TV. | [
{
"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: [both are watching TV.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002754/0.png",
"losevideos/002754/1.png",
"losevideos/002754/2.png",
"losevideos/002754/3.png",
"losevideos/002754/4.png",
"losevideos/002754/5.png",
"losevideos/002754/6.png",
"losevideos/002754/7.png",
"winvideos/002754/0.png",
"winvideos/002754/1.png",
"winvideos/002754/2.png",
"winvideos/002754/3.png",
"winvideos/002754/4.png",
"winvideos/002754/5.png",
"winvideos/002754/6.png",
"winvideos/002754/7.png"
] |
An image of a sunrise, with a young boy get up early in the morning yawning as he gets out of bed,3d animation,4k animation. | [
{
"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: [An image of a sunrise, with a young boy get up early in the morning yawning as he gets out of bed,3d animation,4k animation.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002293/0.png",
"winvideos/002293/1.png",
"winvideos/002293/2.png",
"winvideos/002293/3.png",
"winvideos/002293/4.png",
"winvideos/002293/5.png",
"winvideos/002293/6.png",
"winvideos/002293/7.png",
"losevideos/002293/0.png",
"losevideos/002293/1.png",
"losevideos/002293/2.png",
"losevideos/002293/3.png",
"losevideos/002293/4.png",
"losevideos/002293/5.png",
"losevideos/002293/6.png",
"losevideos/002293/7.png"
] |
<a href="https://media.discordapp.net/attachments/1129390284053164134/1129819313621184642/JayJFalconer_man_hitchhiking_on_lonely_country_road_with_his_th_b58f6d08-82c2-425e-b387-9a4fe26408f5.png">https://media.discordapp.net/attachments/1129390284053164134/1129819313621184642/JayJFalconer_man_hitchhiking_on_lonely_country_road_with_his_th_b58f6d08-82c2-425e-b387-9a4fe26408f5.png</a> man walking in the windw on a country road --ar 16:9. | [
{
"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 href=\"https://media.discordapp.net/attachments/1129390284053164134/1129819313621184642/JayJFalconer_man_hitchhiking_on_lonely_country_road_with_his_th_b58f6d08-82c2-425e-b387-9a4fe26408f5.png\">https://media.discordapp.net/attachments/1129390284053164134/1129819313621184642/JayJFalconer_man_hitchhiking_on_lonely_country_road_with_his_th_b58f6d08-82c2-425e-b387-9a4fe26408f5.png</a> man walking in the windw on a country road --ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000743/0.png",
"losevideos/000743/1.png",
"losevideos/000743/2.png",
"losevideos/000743/3.png",
"losevideos/000743/4.png",
"losevideos/000743/5.png",
"losevideos/000743/6.png",
"losevideos/000743/7.png",
"winvideos/000743/0.png",
"winvideos/000743/1.png",
"winvideos/000743/2.png",
"winvideos/000743/3.png",
"winvideos/000743/4.png",
"winvideos/000743/5.png",
"winvideos/000743/6.png",
"winvideos/000743/7.png"
] |
video of a cow eating ice cream. | [
{
"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 a cow eating ice cream.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008910/0.png",
"losevideos/008910/1.png",
"losevideos/008910/2.png",
"losevideos/008910/3.png",
"losevideos/008910/4.png",
"losevideos/008910/5.png",
"losevideos/008910/6.png",
"losevideos/008910/7.png",
"winvideos/008910/0.png",
"winvideos/008910/1.png",
"winvideos/008910/2.png",
"winvideos/008910/3.png",
"winvideos/008910/4.png",
"winvideos/008910/5.png",
"winvideos/008910/6.png",
"winvideos/008910/7.png"
] |
shot pov rear in motion a fat man walking down the streets of buenos aires city at dawn, documentary shot by won kar wai and william eggleston, 16mm color, film shot. | [
{
"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: [shot pov rear in motion a fat man walking down the streets of buenos aires city at dawn, documentary shot by won kar wai and william eggleston, 16mm color, film shot.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003013/0.png",
"losevideos/003013/1.png",
"losevideos/003013/2.png",
"losevideos/003013/3.png",
"losevideos/003013/4.png",
"losevideos/003013/5.png",
"losevideos/003013/6.png",
"losevideos/003013/7.png",
"winvideos/003013/0.png",
"winvideos/003013/1.png",
"winvideos/003013/2.png",
"winvideos/003013/3.png",
"winvideos/003013/4.png",
"winvideos/003013/5.png",
"winvideos/003013/6.png",
"winvideos/003013/7.png"
] |
a cinema full of fish watching a film the only light is the projector, cinematic, photoreal, atmospheric, detailed, anamorphic -fps24 -motion 4 -ar 16:9 -styleraw -camera zoom out. | [
{
"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 cinema full of fish watching a film the only light is the projector, cinematic, photoreal, atmospheric, detailed, anamorphic -fps24 -motion 4 -ar 16:9 -styleraw -camera zoom out.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003394/0.png",
"winvideos/003394/1.png",
"winvideos/003394/2.png",
"winvideos/003394/3.png",
"winvideos/003394/4.png",
"winvideos/003394/5.png",
"winvideos/003394/6.png",
"winvideos/003394/7.png",
"losevideos/003394/0.png",
"losevideos/003394/1.png",
"losevideos/003394/2.png",
"losevideos/003394/3.png",
"losevideos/003394/4.png",
"losevideos/003394/5.png",
"losevideos/003394/6.png",
"losevideos/003394/7.png"
] |
create a airbus 380-800 with 5 floors and i need it to be in singapore airlines. | [
{
"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: [create a airbus 380-800 with 5 floors and i need it to be in singapore airlines.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003761/0.png",
"winvideos/003761/1.png",
"winvideos/003761/2.png",
"winvideos/003761/3.png",
"winvideos/003761/4.png",
"winvideos/003761/5.png",
"winvideos/003761/6.png",
"winvideos/003761/7.png",
"losevideos/003761/0.png",
"losevideos/003761/1.png",
"losevideos/003761/2.png",
"losevideos/003761/3.png",
"losevideos/003761/4.png",
"losevideos/003761/5.png",
"losevideos/003761/6.png",
"losevideos/003761/7.png"
] |
cinematic BMW E38 driving on the highway. | [
{
"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: [cinematic BMW E38 driving on the highway.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003787/0.png",
"winvideos/003787/1.png",
"winvideos/003787/2.png",
"winvideos/003787/3.png",
"winvideos/003787/4.png",
"winvideos/003787/5.png",
"winvideos/003787/6.png",
"winvideos/003787/7.png",
"losevideos/003787/0.png",
"losevideos/003787/1.png",
"losevideos/003787/2.png",
"losevideos/003787/3.png",
"losevideos/003787/4.png",
"losevideos/003787/5.png",
"losevideos/003787/6.png",
"losevideos/003787/7.png"
] |
A dark-skinned girl in a room sitting in an armchair is reading the Bible to her friends who are around her listening, large, illuminated windows, you can see the trees through the window. | [
{
"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 dark-skinned girl in a room sitting in an armchair is reading the Bible to her friends who are around her listening, large, illuminated windows, you can see the trees through the window.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000915/0.png",
"losevideos/000915/1.png",
"losevideos/000915/2.png",
"losevideos/000915/3.png",
"losevideos/000915/4.png",
"losevideos/000915/5.png",
"losevideos/000915/6.png",
"losevideos/000915/7.png",
"winvideos/000915/0.png",
"winvideos/000915/1.png",
"winvideos/000915/2.png",
"winvideos/000915/3.png",
"winvideos/000915/4.png",
"winvideos/000915/5.png",
"winvideos/000915/6.png",
"winvideos/000915/7.png"
] |
the most realistic video -gs 22 --neg "no serious tone" -- ar 16:9 --seed 1998. | [
{
"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: [the most realistic video -gs 22 --neg "no serious tone" -- ar 16:9 --seed 1998.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001472/0.png",
"losevideos/001472/1.png",
"losevideos/001472/2.png",
"losevideos/001472/3.png",
"losevideos/001472/4.png",
"losevideos/001472/5.png",
"losevideos/001472/6.png",
"losevideos/001472/7.png",
"winvideos/001472/0.png",
"winvideos/001472/1.png",
"winvideos/001472/2.png",
"winvideos/001472/3.png",
"winvideos/001472/4.png",
"winvideos/001472/5.png",
"winvideos/001472/6.png",
"winvideos/001472/7.png"
] |
a kid is flying. | [
{
"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 kid is flying.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001110/0.png",
"winvideos/001110/1.png",
"winvideos/001110/2.png",
"winvideos/001110/3.png",
"winvideos/001110/4.png",
"winvideos/001110/5.png",
"winvideos/001110/6.png",
"winvideos/001110/7.png",
"losevideos/001110/0.png",
"losevideos/001110/1.png",
"losevideos/001110/2.png",
"losevideos/001110/3.png",
"losevideos/001110/4.png",
"losevideos/001110/5.png",
"losevideos/001110/6.png",
"losevideos/001110/7.png"
] |
A japanese schoolgirl is reading by the sea, her hands are turning a page, vista, realism, 16:9. | [
{
"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 japanese schoolgirl is reading by the sea, her hands are turning a page, vista, realism, 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006051/0.png",
"winvideos/006051/1.png",
"winvideos/006051/2.png",
"winvideos/006051/3.png",
"winvideos/006051/4.png",
"winvideos/006051/5.png",
"winvideos/006051/6.png",
"winvideos/006051/7.png",
"losevideos/006051/0.png",
"losevideos/006051/1.png",
"losevideos/006051/2.png",
"losevideos/006051/3.png",
"losevideos/006051/4.png",
"losevideos/006051/5.png",
"losevideos/006051/6.png",
"losevideos/006051/7.png"
] |
1920s scifi movie, retrofuturism, realistic, cube spacecraft landing, muted colors, god rays, dreamcore, dreamscape, lucid dream, astral projection, psychedelic, trippy, abstract, liminal space, found footage, metropolis -motion 4 -ar16:9. | [
{
"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: [1920s scifi movie, retrofuturism, realistic, cube spacecraft landing, muted colors, god rays, dreamcore, dreamscape, lucid dream, astral projection, psychedelic, trippy, abstract, liminal space, found footage, metropolis -motion 4 -ar16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006130/0.png",
"losevideos/006130/1.png",
"losevideos/006130/2.png",
"losevideos/006130/3.png",
"losevideos/006130/4.png",
"losevideos/006130/5.png",
"losevideos/006130/6.png",
"losevideos/006130/7.png",
"winvideos/006130/0.png",
"winvideos/006130/1.png",
"winvideos/006130/2.png",
"winvideos/006130/3.png",
"winvideos/006130/4.png",
"winvideos/006130/5.png",
"winvideos/006130/6.png",
"winvideos/006130/7.png"
] |
Shawn Mendes and Ed Sheeran christmas carols. | [
{
"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: [Shawn Mendes and Ed Sheeran christmas carols.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001799/0.png",
"winvideos/001799/1.png",
"winvideos/001799/2.png",
"winvideos/001799/3.png",
"winvideos/001799/4.png",
"winvideos/001799/5.png",
"winvideos/001799/6.png",
"winvideos/001799/7.png",
"losevideos/001799/0.png",
"losevideos/001799/1.png",
"losevideos/001799/2.png",
"losevideos/001799/3.png",
"losevideos/001799/4.png",
"losevideos/001799/5.png",
"losevideos/001799/6.png",
"losevideos/001799/7.png"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.