prompt
stringlengths 4
8.37k
| conversations
listlengths 2
2
| images
sequencelengths 16
16
|
|---|---|---|
black cat 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: [black cat flying.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001197/0.png",
"losevideos/001197/1.png",
"losevideos/001197/2.png",
"losevideos/001197/3.png",
"losevideos/001197/4.png",
"losevideos/001197/5.png",
"losevideos/001197/6.png",
"losevideos/001197/7.png",
"winvideos/001197/0.png",
"winvideos/001197/1.png",
"winvideos/001197/2.png",
"winvideos/001197/3.png",
"winvideos/001197/4.png",
"winvideos/001197/5.png",
"winvideos/001197/6.png",
"winvideos/001197/7.png"
] |
3D animation, Shih Tzu puppy. | [
{
"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, Shih Tzu puppy.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000776/0.png",
"winvideos/000776/1.png",
"winvideos/000776/2.png",
"winvideos/000776/3.png",
"winvideos/000776/4.png",
"winvideos/000776/5.png",
"winvideos/000776/6.png",
"winvideos/000776/7.png",
"losevideos/000776/0.png",
"losevideos/000776/1.png",
"losevideos/000776/2.png",
"losevideos/000776/3.png",
"losevideos/000776/4.png",
"losevideos/000776/5.png",
"losevideos/000776/6.png",
"losevideos/000776/7.png"
] |
cup pouring water into another cup. | [
{
"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: [cup pouring water into another cup.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002694/0.png",
"losevideos/002694/1.png",
"losevideos/002694/2.png",
"losevideos/002694/3.png",
"losevideos/002694/4.png",
"losevideos/002694/5.png",
"losevideos/002694/6.png",
"losevideos/002694/7.png",
"winvideos/002694/0.png",
"winvideos/002694/1.png",
"winvideos/002694/2.png",
"winvideos/002694/3.png",
"winvideos/002694/4.png",
"winvideos/002694/5.png",
"winvideos/002694/6.png",
"winvideos/002694/7.png"
] |
Yesterday reappears. | [
{
"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: [Yesterday reappears.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002856/0.png",
"losevideos/002856/1.png",
"losevideos/002856/2.png",
"losevideos/002856/3.png",
"losevideos/002856/4.png",
"losevideos/002856/5.png",
"losevideos/002856/6.png",
"losevideos/002856/7.png",
"winvideos/002856/0.png",
"winvideos/002856/1.png",
"winvideos/002856/2.png",
"winvideos/002856/3.png",
"winvideos/002856/4.png",
"winvideos/002856/5.png",
"winvideos/002856/6.png",
"winvideos/002856/7.png"
] |
sfinks cat with bat wings fighting bird in 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: [sfinks cat with bat wings fighting bird in a forest.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009516/0.png",
"losevideos/009516/1.png",
"losevideos/009516/2.png",
"losevideos/009516/3.png",
"losevideos/009516/4.png",
"losevideos/009516/5.png",
"losevideos/009516/6.png",
"losevideos/009516/7.png",
"winvideos/009516/0.png",
"winvideos/009516/1.png",
"winvideos/009516/2.png",
"winvideos/009516/3.png",
"winvideos/009516/4.png",
"winvideos/009516/5.png",
"winvideos/009516/6.png",
"winvideos/009516/7.png"
] |
a girl 20 years old playing virtual reality glasses with the planet earth in the background, slightly zooming out, 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 girl 20 years old playing virtual reality glasses with the planet earth in the background, slightly zooming out, 4K.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000965/0.png",
"winvideos/000965/1.png",
"winvideos/000965/2.png",
"winvideos/000965/3.png",
"winvideos/000965/4.png",
"winvideos/000965/5.png",
"winvideos/000965/6.png",
"winvideos/000965/7.png",
"losevideos/000965/0.png",
"losevideos/000965/1.png",
"losevideos/000965/2.png",
"losevideos/000965/3.png",
"losevideos/000965/4.png",
"losevideos/000965/5.png",
"losevideos/000965/6.png",
"losevideos/000965/7.png"
] |
giant size amazigh female warrior, light skinned, futuristic, standing next to giant lion, looking down on Marrakesh, golden hour, wide angle shot -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: [giant size amazigh female warrior, light skinned, futuristic, standing next to giant lion, looking down on Marrakesh, golden hour, wide angle shot -camera zoom out.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000518/0.png",
"losevideos/000518/1.png",
"losevideos/000518/2.png",
"losevideos/000518/3.png",
"losevideos/000518/4.png",
"losevideos/000518/5.png",
"losevideos/000518/6.png",
"losevideos/000518/7.png",
"winvideos/000518/0.png",
"winvideos/000518/1.png",
"winvideos/000518/2.png",
"winvideos/000518/3.png",
"winvideos/000518/4.png",
"winvideos/000518/5.png",
"winvideos/000518/6.png",
"winvideos/000518/7.png"
] |
design only!!!!!! 2 0 5 0 s retro future art deco designs borders lines decorations space machine. muted colors. | [
{
"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: [design only!!!!!! 2 0 5 0 s retro future art deco designs borders lines decorations space machine. muted colors.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008848/0.png",
"losevideos/008848/1.png",
"losevideos/008848/2.png",
"losevideos/008848/3.png",
"losevideos/008848/4.png",
"losevideos/008848/5.png",
"losevideos/008848/6.png",
"losevideos/008848/7.png",
"winvideos/008848/0.png",
"winvideos/008848/1.png",
"winvideos/008848/2.png",
"winvideos/008848/3.png",
"winvideos/008848/4.png",
"winvideos/008848/5.png",
"winvideos/008848/6.png",
"winvideos/008848/7.png"
] |
dreaming girl whith her dog. | [
{
"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: [dreaming girl whith her dog.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006301/0.png",
"losevideos/006301/1.png",
"losevideos/006301/2.png",
"losevideos/006301/3.png",
"losevideos/006301/4.png",
"losevideos/006301/5.png",
"losevideos/006301/6.png",
"losevideos/006301/7.png",
"winvideos/006301/0.png",
"winvideos/006301/1.png",
"winvideos/006301/2.png",
"winvideos/006301/3.png",
"winvideos/006301/4.png",
"winvideos/006301/5.png",
"winvideos/006301/6.png",
"winvideos/006301/7.png"
] |
guadeloupe futuristic tomorrowland movie 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: [guadeloupe futuristic tomorrowland movie 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004191/0.png",
"winvideos/004191/1.png",
"winvideos/004191/2.png",
"winvideos/004191/3.png",
"winvideos/004191/4.png",
"winvideos/004191/5.png",
"winvideos/004191/6.png",
"winvideos/004191/7.png",
"losevideos/004191/0.png",
"losevideos/004191/1.png",
"losevideos/004191/2.png",
"losevideos/004191/3.png",
"losevideos/004191/4.png",
"losevideos/004191/5.png",
"losevideos/004191/6.png",
"losevideos/004191/7.png"
] |
andrew tate drives bugatti. | [
{
"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: [andrew tate drives bugatti.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003926/0.png",
"losevideos/003926/1.png",
"losevideos/003926/2.png",
"losevideos/003926/3.png",
"losevideos/003926/4.png",
"losevideos/003926/5.png",
"losevideos/003926/6.png",
"losevideos/003926/7.png",
"winvideos/003926/0.png",
"winvideos/003926/1.png",
"winvideos/003926/2.png",
"winvideos/003926/3.png",
"winvideos/003926/4.png",
"winvideos/003926/5.png",
"winvideos/003926/6.png",
"winvideos/003926/7.png"
] |
A teen getting surprised by a top hat landing on his head, while trying to take a picture. | [
{
"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 teen getting surprised by a top hat landing on his head, while trying to take a picture.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009246/0.png",
"winvideos/009246/1.png",
"winvideos/009246/2.png",
"winvideos/009246/3.png",
"winvideos/009246/4.png",
"winvideos/009246/5.png",
"winvideos/009246/6.png",
"winvideos/009246/7.png",
"losevideos/009246/0.png",
"losevideos/009246/1.png",
"losevideos/009246/2.png",
"losevideos/009246/3.png",
"losevideos/009246/4.png",
"losevideos/009246/5.png",
"losevideos/009246/6.png",
"losevideos/009246/7.png"
] |
She adopted a beautiful form to entice him, but Rama meanwhile kindly rejected her advances, telling her that he was faithful to his wife Sita and thus would never take another wife. Rejected,. | [
{
"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: [She adopted a beautiful form to entice him, but Rama meanwhile kindly rejected her advances, telling her that he was faithful to his wife Sita and thus would never take another wife. Rejected,.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000774/0.png",
"winvideos/000774/1.png",
"winvideos/000774/2.png",
"winvideos/000774/3.png",
"winvideos/000774/4.png",
"winvideos/000774/5.png",
"winvideos/000774/6.png",
"winvideos/000774/7.png",
"losevideos/000774/0.png",
"losevideos/000774/1.png",
"losevideos/000774/2.png",
"losevideos/000774/3.png",
"losevideos/000774/4.png",
"losevideos/000774/5.png",
"losevideos/000774/6.png",
"losevideos/000774/7.png"
] |
Dazzling city lights illuminating the tokyo night sky. | [
{
"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: [Dazzling city lights illuminating the tokyo night sky.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000523/0.png",
"winvideos/000523/1.png",
"winvideos/000523/2.png",
"winvideos/000523/3.png",
"winvideos/000523/4.png",
"winvideos/000523/5.png",
"winvideos/000523/6.png",
"winvideos/000523/7.png",
"losevideos/000523/0.png",
"losevideos/000523/1.png",
"losevideos/000523/2.png",
"losevideos/000523/3.png",
"losevideos/000523/4.png",
"losevideos/000523/5.png",
"losevideos/000523/6.png",
"losevideos/000523/7.png"
] |
a woman with wind in her hair, 4K -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 woman with wind in her hair, 4K -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004025/0.png",
"losevideos/004025/1.png",
"losevideos/004025/2.png",
"losevideos/004025/3.png",
"losevideos/004025/4.png",
"losevideos/004025/5.png",
"losevideos/004025/6.png",
"losevideos/004025/7.png",
"winvideos/004025/0.png",
"winvideos/004025/1.png",
"winvideos/004025/2.png",
"winvideos/004025/3.png",
"winvideos/004025/4.png",
"winvideos/004025/5.png",
"winvideos/004025/6.png",
"winvideos/004025/7.png"
] |
sunset by Jon Klassen. | [
{
"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: [sunset by Jon Klassen.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003180/0.png",
"losevideos/003180/1.png",
"losevideos/003180/2.png",
"losevideos/003180/3.png",
"losevideos/003180/4.png",
"losevideos/003180/5.png",
"losevideos/003180/6.png",
"losevideos/003180/7.png",
"winvideos/003180/0.png",
"winvideos/003180/1.png",
"winvideos/003180/2.png",
"winvideos/003180/3.png",
"winvideos/003180/4.png",
"winvideos/003180/5.png",
"winvideos/003180/6.png",
"winvideos/003180/7.png"
] |
prompt:A person is playing piano -seed 4774256. | [
{
"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: [prompt:A person is playing piano -seed 4774256.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008989/0.png",
"losevideos/008989/1.png",
"losevideos/008989/2.png",
"losevideos/008989/3.png",
"losevideos/008989/4.png",
"losevideos/008989/5.png",
"losevideos/008989/6.png",
"losevideos/008989/7.png",
"winvideos/008989/0.png",
"winvideos/008989/1.png",
"winvideos/008989/2.png",
"winvideos/008989/3.png",
"winvideos/008989/4.png",
"winvideos/008989/5.png",
"winvideos/008989/6.png",
"winvideos/008989/7.png"
] |
a cloud burst of color splashing all over, motion 1, cinematic, 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: [a cloud burst of color splashing all over, motion 1, cinematic, camera zoom in.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007529/0.png",
"losevideos/007529/1.png",
"losevideos/007529/2.png",
"losevideos/007529/3.png",
"losevideos/007529/4.png",
"losevideos/007529/5.png",
"losevideos/007529/6.png",
"losevideos/007529/7.png",
"winvideos/007529/0.png",
"winvideos/007529/1.png",
"winvideos/007529/2.png",
"winvideos/007529/3.png",
"winvideos/007529/4.png",
"winvideos/007529/5.png",
"winvideos/007529/6.png",
"winvideos/007529/7.png"
] |
Cyrus the Great, also known as Cyrus II of Persia, was the founder of the Persian Empire under the Achaemenid dynasty. | [
{
"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: [Cyrus the Great, also known as Cyrus II of Persia, was the founder of the Persian Empire under the Achaemenid dynasty.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002666/0.png",
"winvideos/002666/1.png",
"winvideos/002666/2.png",
"winvideos/002666/3.png",
"winvideos/002666/4.png",
"winvideos/002666/5.png",
"winvideos/002666/6.png",
"winvideos/002666/7.png",
"losevideos/002666/0.png",
"losevideos/002666/1.png",
"losevideos/002666/2.png",
"losevideos/002666/3.png",
"losevideos/002666/4.png",
"losevideos/002666/5.png",
"losevideos/002666/6.png",
"losevideos/002666/7.png"
] |
animal, beach, black cat, blue sky, cat, caustics, clouds, cloudy sky, sky, dog, footprints, horizon, no humans, ocean, outdoors, planet, sand, shadow, coast, sky, water, waves, running. | [
{
"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: [animal, beach, black cat, blue sky, cat, caustics, clouds, cloudy sky, sky, dog, footprints, horizon, no humans, ocean, outdoors, planet, sand, shadow, coast, sky, water, waves, running.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001947/0.png",
"losevideos/001947/1.png",
"losevideos/001947/2.png",
"losevideos/001947/3.png",
"losevideos/001947/4.png",
"losevideos/001947/5.png",
"losevideos/001947/6.png",
"losevideos/001947/7.png",
"winvideos/001947/0.png",
"winvideos/001947/1.png",
"winvideos/001947/2.png",
"winvideos/001947/3.png",
"winvideos/001947/4.png",
"winvideos/001947/5.png",
"winvideos/001947/6.png",
"winvideos/001947/7.png"
] |
people stuck in Matrix,cinematic look,uhd. | [
{
"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 stuck in Matrix,cinematic look,uhd.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005717/0.png",
"losevideos/005717/1.png",
"losevideos/005717/2.png",
"losevideos/005717/3.png",
"losevideos/005717/4.png",
"losevideos/005717/5.png",
"losevideos/005717/6.png",
"losevideos/005717/7.png",
"winvideos/005717/0.png",
"winvideos/005717/1.png",
"winvideos/005717/2.png",
"winvideos/005717/3.png",
"winvideos/005717/4.png",
"winvideos/005717/5.png",
"winvideos/005717/6.png",
"winvideos/005717/7.png"
] |
planets moving in night sky. | [
{
"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: [planets moving in night sky.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009872/0.png",
"winvideos/009872/1.png",
"winvideos/009872/2.png",
"winvideos/009872/3.png",
"winvideos/009872/4.png",
"winvideos/009872/5.png",
"winvideos/009872/6.png",
"winvideos/009872/7.png",
"losevideos/009872/0.png",
"losevideos/009872/1.png",
"losevideos/009872/2.png",
"losevideos/009872/3.png",
"losevideos/009872/4.png",
"losevideos/009872/5.png",
"losevideos/009872/6.png",
"losevideos/009872/7.png"
] |
a black man with braided hair and a sexy black woman riding a flying car through the blue night sky. | [
{
"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 black man with braided hair and a sexy black woman riding a flying car through the blue night sky.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003209/0.png",
"winvideos/003209/1.png",
"winvideos/003209/2.png",
"winvideos/003209/3.png",
"winvideos/003209/4.png",
"winvideos/003209/5.png",
"winvideos/003209/6.png",
"winvideos/003209/7.png",
"losevideos/003209/0.png",
"losevideos/003209/1.png",
"losevideos/003209/2.png",
"losevideos/003209/3.png",
"losevideos/003209/4.png",
"losevideos/003209/5.png",
"losevideos/003209/6.png",
"losevideos/003209/7.png"
] |
Bruce Lee looking happy and smiling, zoom distance, 4k, 3d cinematic -ar 9:16 -gs 10. | [
{
"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: [Bruce Lee looking happy and smiling, zoom distance, 4k, 3d cinematic -ar 9:16 -gs 10.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004479/0.png",
"losevideos/004479/1.png",
"losevideos/004479/2.png",
"losevideos/004479/3.png",
"losevideos/004479/4.png",
"losevideos/004479/5.png",
"losevideos/004479/6.png",
"losevideos/004479/7.png",
"winvideos/004479/0.png",
"winvideos/004479/1.png",
"winvideos/004479/2.png",
"winvideos/004479/3.png",
"winvideos/004479/4.png",
"winvideos/004479/5.png",
"winvideos/004479/6.png",
"winvideos/004479/7.png"
] |
Relistic Capture the bustling Rialto Market and the stunning views of the canal. | [
{
"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: [Relistic Capture the bustling Rialto Market and the stunning views of the canal.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001495/0.png",
"winvideos/001495/1.png",
"winvideos/001495/2.png",
"winvideos/001495/3.png",
"winvideos/001495/4.png",
"winvideos/001495/5.png",
"winvideos/001495/6.png",
"winvideos/001495/7.png",
"losevideos/001495/0.png",
"losevideos/001495/1.png",
"losevideos/001495/2.png",
"losevideos/001495/3.png",
"losevideos/001495/4.png",
"losevideos/001495/5.png",
"losevideos/001495/6.png",
"losevideos/001495/7.png"
] |
camera pan up left. | [
{
"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: [camera pan up left.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001052/0.png",
"losevideos/001052/1.png",
"losevideos/001052/2.png",
"losevideos/001052/3.png",
"losevideos/001052/4.png",
"losevideos/001052/5.png",
"losevideos/001052/6.png",
"losevideos/001052/7.png",
"winvideos/001052/0.png",
"winvideos/001052/1.png",
"winvideos/001052/2.png",
"winvideos/001052/3.png",
"winvideos/001052/4.png",
"winvideos/001052/5.png",
"winvideos/001052/6.png",
"winvideos/001052/7.png"
] |
3D Illusion of fire breathing dragons, abstract design pattern, stereogram optical illusion, green colored hues, a 3D rendering, full screen image. tile. 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: [3D Illusion of fire breathing dragons, abstract design pattern, stereogram optical illusion, green colored hues, a 3D rendering, full screen image. tile. Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005369/0.png",
"winvideos/005369/1.png",
"winvideos/005369/2.png",
"winvideos/005369/3.png",
"winvideos/005369/4.png",
"winvideos/005369/5.png",
"winvideos/005369/6.png",
"winvideos/005369/7.png",
"losevideos/005369/0.png",
"losevideos/005369/1.png",
"losevideos/005369/2.png",
"losevideos/005369/3.png",
"losevideos/005369/4.png",
"losevideos/005369/5.png",
"losevideos/005369/6.png",
"losevideos/005369/7.png"
] |
90s Disney princesses walking in forest, 2d 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: [90s Disney princesses walking in forest, 2d animation.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005462/0.png",
"winvideos/005462/1.png",
"winvideos/005462/2.png",
"winvideos/005462/3.png",
"winvideos/005462/4.png",
"winvideos/005462/5.png",
"winvideos/005462/6.png",
"winvideos/005462/7.png",
"losevideos/005462/0.png",
"losevideos/005462/1.png",
"losevideos/005462/2.png",
"losevideos/005462/3.png",
"losevideos/005462/4.png",
"losevideos/005462/5.png",
"losevideos/005462/6.png",
"losevideos/005462/7.png"
] |
Darth Vader releases the wave, directing it towards the distant horizon. | [
{
"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: [Darth Vader releases the wave, directing it towards the distant horizon.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004570/0.png",
"losevideos/004570/1.png",
"losevideos/004570/2.png",
"losevideos/004570/3.png",
"losevideos/004570/4.png",
"losevideos/004570/5.png",
"losevideos/004570/6.png",
"losevideos/004570/7.png",
"winvideos/004570/0.png",
"winvideos/004570/1.png",
"winvideos/004570/2.png",
"winvideos/004570/3.png",
"winvideos/004570/4.png",
"winvideos/004570/5.png",
"winvideos/004570/6.png",
"winvideos/004570/7.png"
] |
love 4k animated. | [
{
"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: [love 4k animated.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000540/0.png",
"losevideos/000540/1.png",
"losevideos/000540/2.png",
"losevideos/000540/3.png",
"losevideos/000540/4.png",
"losevideos/000540/5.png",
"losevideos/000540/6.png",
"losevideos/000540/7.png",
"winvideos/000540/0.png",
"winvideos/000540/1.png",
"winvideos/000540/2.png",
"winvideos/000540/3.png",
"winvideos/000540/4.png",
"winvideos/000540/5.png",
"winvideos/000540/6.png",
"winvideos/000540/7.png"
] |
A cinematic shot of two woman playing chess in the park, profile 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: [A cinematic shot of two woman playing chess in the park, profile shot.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001809/0.png",
"winvideos/001809/1.png",
"winvideos/001809/2.png",
"winvideos/001809/3.png",
"winvideos/001809/4.png",
"winvideos/001809/5.png",
"winvideos/001809/6.png",
"winvideos/001809/7.png",
"losevideos/001809/0.png",
"losevideos/001809/1.png",
"losevideos/001809/2.png",
"losevideos/001809/3.png",
"losevideos/001809/4.png",
"losevideos/001809/5.png",
"losevideos/001809/6.png",
"losevideos/001809/7.png"
] |
Javanese people spread Islam to foreign traders in ancient times. | [
{
"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: [Javanese people spread Islam to foreign traders in ancient times.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001754/0.png",
"winvideos/001754/1.png",
"winvideos/001754/2.png",
"winvideos/001754/3.png",
"winvideos/001754/4.png",
"winvideos/001754/5.png",
"winvideos/001754/6.png",
"winvideos/001754/7.png",
"losevideos/001754/0.png",
"losevideos/001754/1.png",
"losevideos/001754/2.png",
"losevideos/001754/3.png",
"losevideos/001754/4.png",
"losevideos/001754/5.png",
"losevideos/001754/6.png",
"losevideos/001754/7.png"
] |
100 men cleaning womens shoes on a big field while women in black dresses dancing around with each other dark light. | [
{
"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: [100 men cleaning womens shoes on a big field while women in black dresses dancing around with each other dark light.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000409/0.png",
"winvideos/000409/1.png",
"winvideos/000409/2.png",
"winvideos/000409/3.png",
"winvideos/000409/4.png",
"winvideos/000409/5.png",
"winvideos/000409/6.png",
"winvideos/000409/7.png",
"losevideos/000409/0.png",
"losevideos/000409/1.png",
"losevideos/000409/2.png",
"losevideos/000409/3.png",
"losevideos/000409/4.png",
"losevideos/000409/5.png",
"losevideos/000409/6.png",
"losevideos/000409/7.png"
] |
Aerial shot of South African landscapes bathed in sunlight -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting. | [
{
"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: [Aerial shot of South African landscapes bathed in sunlight -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004761/0.png",
"winvideos/004761/1.png",
"winvideos/004761/2.png",
"winvideos/004761/3.png",
"winvideos/004761/4.png",
"winvideos/004761/5.png",
"winvideos/004761/6.png",
"winvideos/004761/7.png",
"losevideos/004761/0.png",
"losevideos/004761/1.png",
"losevideos/004761/2.png",
"losevideos/004761/3.png",
"losevideos/004761/4.png",
"losevideos/004761/5.png",
"losevideos/004761/6.png",
"losevideos/004761/7.png"
] |
jim morrison singing in hell. | [
{
"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: [jim morrison singing in hell.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008276/0.png",
"losevideos/008276/1.png",
"losevideos/008276/2.png",
"losevideos/008276/3.png",
"losevideos/008276/4.png",
"losevideos/008276/5.png",
"losevideos/008276/6.png",
"losevideos/008276/7.png",
"winvideos/008276/0.png",
"winvideos/008276/1.png",
"winvideos/008276/2.png",
"winvideos/008276/3.png",
"winvideos/008276/4.png",
"winvideos/008276/5.png",
"winvideos/008276/6.png",
"winvideos/008276/7.png"
] |
Create a relaxing ASMR audio recording of a softly spoken or whispered guided meditation to help listeners de-stress and find inner peace. | [
{
"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 relaxing ASMR audio recording of a softly spoken or whispered guided meditation to help listeners de-stress and find inner peace.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009773/0.png",
"winvideos/009773/1.png",
"winvideos/009773/2.png",
"winvideos/009773/3.png",
"winvideos/009773/4.png",
"winvideos/009773/5.png",
"winvideos/009773/6.png",
"winvideos/009773/7.png",
"losevideos/009773/0.png",
"losevideos/009773/1.png",
"losevideos/009773/2.png",
"losevideos/009773/3.png",
"losevideos/009773/4.png",
"losevideos/009773/5.png",
"losevideos/009773/6.png",
"losevideos/009773/7.png"
] |
As the traveler walked away, leaving Ramu fuming, the villagers who had gathered to witness the scene couldn't help but shake their heads in disappointment. Ramu had let his greed cloud his reputation, and his talent had become overshadowed by his insatiable desire for more. | [
{
"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: [As the traveler walked away, leaving Ramu fuming, the villagers who had gathered to witness the scene couldn't help but shake their heads in disappointment. Ramu had let his greed cloud his reputation, and his talent had become overshadowed by his insatiable desire for more.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001669/0.png",
"losevideos/001669/1.png",
"losevideos/001669/2.png",
"losevideos/001669/3.png",
"losevideos/001669/4.png",
"losevideos/001669/5.png",
"losevideos/001669/6.png",
"losevideos/001669/7.png",
"winvideos/001669/0.png",
"winvideos/001669/1.png",
"winvideos/001669/2.png",
"winvideos/001669/3.png",
"winvideos/001669/4.png",
"winvideos/001669/5.png",
"winvideos/001669/6.png",
"winvideos/001669/7.png"
] |
Jack Black at Thanksgiving dinner. | [
{
"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: [Jack Black at Thanksgiving dinner.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007445/0.png",
"winvideos/007445/1.png",
"winvideos/007445/2.png",
"winvideos/007445/3.png",
"winvideos/007445/4.png",
"winvideos/007445/5.png",
"winvideos/007445/6.png",
"winvideos/007445/7.png",
"losevideos/007445/0.png",
"losevideos/007445/1.png",
"losevideos/007445/2.png",
"losevideos/007445/3.png",
"losevideos/007445/4.png",
"losevideos/007445/5.png",
"losevideos/007445/6.png",
"losevideos/007445/7.png"
] |
a greyscale abstract 8-bit commodore64 game, isometric, giant robots walking, -camera zoom in -motion 1. | [
{
"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 greyscale abstract 8-bit commodore64 game, isometric, giant robots walking, -camera zoom in -motion 1.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000208/0.png",
"winvideos/000208/1.png",
"winvideos/000208/2.png",
"winvideos/000208/3.png",
"winvideos/000208/4.png",
"winvideos/000208/5.png",
"winvideos/000208/6.png",
"winvideos/000208/7.png",
"losevideos/000208/0.png",
"losevideos/000208/1.png",
"losevideos/000208/2.png",
"losevideos/000208/3.png",
"losevideos/000208/4.png",
"losevideos/000208/5.png",
"losevideos/000208/6.png",
"losevideos/000208/7.png"
] |
a moving delivery truck in township. | [
{
"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 moving delivery truck in township.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001250/0.png",
"winvideos/001250/1.png",
"winvideos/001250/2.png",
"winvideos/001250/3.png",
"winvideos/001250/4.png",
"winvideos/001250/5.png",
"winvideos/001250/6.png",
"winvideos/001250/7.png",
"losevideos/001250/0.png",
"losevideos/001250/1.png",
"losevideos/001250/2.png",
"losevideos/001250/3.png",
"losevideos/001250/4.png",
"losevideos/001250/5.png",
"losevideos/001250/6.png",
"losevideos/001250/7.png"
] |
A beautiful sunset over the sea- the water is crystal blue while the sky is purple-pink. Butterflies flying in the upper half of the screen, turning into fire, 8k -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 beautiful sunset over the sea- the water is crystal blue while the sky is purple-pink. Butterflies flying in the upper half of the screen, turning into fire, 8k -motion 2.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008182/0.png",
"winvideos/008182/1.png",
"winvideos/008182/2.png",
"winvideos/008182/3.png",
"winvideos/008182/4.png",
"winvideos/008182/5.png",
"winvideos/008182/6.png",
"winvideos/008182/7.png",
"losevideos/008182/0.png",
"losevideos/008182/1.png",
"losevideos/008182/2.png",
"losevideos/008182/3.png",
"losevideos/008182/4.png",
"losevideos/008182/5.png",
"losevideos/008182/6.png",
"losevideos/008182/7.png"
] |
A macro video of a bee pollinating a flower. | [
{
"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 macro video of a bee pollinating a flower.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006209/0.png",
"losevideos/006209/1.png",
"losevideos/006209/2.png",
"losevideos/006209/3.png",
"losevideos/006209/4.png",
"losevideos/006209/5.png",
"losevideos/006209/6.png",
"losevideos/006209/7.png",
"winvideos/006209/0.png",
"winvideos/006209/1.png",
"winvideos/006209/2.png",
"winvideos/006209/3.png",
"winvideos/006209/4.png",
"winvideos/006209/5.png",
"winvideos/006209/6.png",
"winvideos/006209/7.png"
] |
Elon Musk eating a pie shaped like an orange cat. | [
{
"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 eating a pie shaped like an orange cat.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000990/0.png",
"losevideos/000990/1.png",
"losevideos/000990/2.png",
"losevideos/000990/3.png",
"losevideos/000990/4.png",
"losevideos/000990/5.png",
"losevideos/000990/6.png",
"losevideos/000990/7.png",
"winvideos/000990/0.png",
"winvideos/000990/1.png",
"winvideos/000990/2.png",
"winvideos/000990/3.png",
"winvideos/000990/4.png",
"winvideos/000990/5.png",
"winvideos/000990/6.png",
"winvideos/000990/7.png"
] |
The image portrays a captivating scene capturing a dynamic process within a grain of molten material. The grain exhibits a porous and textured shell, which hints at its complex nature. In this mesmerizing moment, an eruption-like event unfolds as internal gases rapidly escape. The release of these gases creates a fragments of molten matter bursting outwards. Inside the grain there are unmolten grains wich are a source of new gasses. The image freezes this dynamic moment, allowing us to witness the intense transformation and the powerful forces at play. It encapsulates the captivating nature of this dynamic process, evoking a sense of awe and fascination, coal combustion, melting of mineral phase. Heating. Crystalline phase. Melting begins. Grain. Capillary effects. Surface tension. Spherical shape. Droplet-like. Suspended. Molten grain. Gas emission minerals. Increasing temperature. Gas expansion. Volume increase. Pressure. Breaking bubble. Gasses escaping. Capillary action. | [
{
"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 image portrays a captivating scene capturing a dynamic process within a grain of molten material. The grain exhibits a porous and textured shell, which hints at its complex nature. In this mesmerizing moment, an eruption-like event unfolds as internal gases rapidly escape. The release of these gases creates a fragments of molten matter bursting outwards. Inside the grain there are unmolten grains wich are a source of new gasses. The image freezes this dynamic moment, allowing us to witness the intense transformation and the powerful forces at play. It encapsulates the captivating nature of this dynamic process, evoking a sense of awe and fascination, coal combustion, melting of mineral phase. Heating. Crystalline phase. Melting begins. Grain. Capillary effects. Surface tension. Spherical shape. Droplet-like. Suspended. Molten grain. Gas emission minerals. Increasing temperature. Gas expansion. Volume increase. Pressure. Breaking bubble. Gasses escaping. Capillary action.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001462/0.png",
"winvideos/001462/1.png",
"winvideos/001462/2.png",
"winvideos/001462/3.png",
"winvideos/001462/4.png",
"winvideos/001462/5.png",
"winvideos/001462/6.png",
"winvideos/001462/7.png",
"losevideos/001462/0.png",
"losevideos/001462/1.png",
"losevideos/001462/2.png",
"losevideos/001462/3.png",
"losevideos/001462/4.png",
"losevideos/001462/5.png",
"losevideos/001462/6.png",
"losevideos/001462/7.png"
] |
a gummy pink monster walking through the city smiling and shooting with giant plastic gun. | [
{
"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 gummy pink monster walking through the city smiling and shooting with giant plastic gun.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003029/0.png",
"winvideos/003029/1.png",
"winvideos/003029/2.png",
"winvideos/003029/3.png",
"winvideos/003029/4.png",
"winvideos/003029/5.png",
"winvideos/003029/6.png",
"winvideos/003029/7.png",
"losevideos/003029/0.png",
"losevideos/003029/1.png",
"losevideos/003029/2.png",
"losevideos/003029/3.png",
"losevideos/003029/4.png",
"losevideos/003029/5.png",
"losevideos/003029/6.png",
"losevideos/003029/7.png"
] |
create a realistic live wallpaper of itachi. | [
{
"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 realistic live wallpaper of itachi.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008048/0.png",
"losevideos/008048/1.png",
"losevideos/008048/2.png",
"losevideos/008048/3.png",
"losevideos/008048/4.png",
"losevideos/008048/5.png",
"losevideos/008048/6.png",
"losevideos/008048/7.png",
"winvideos/008048/0.png",
"winvideos/008048/1.png",
"winvideos/008048/2.png",
"winvideos/008048/3.png",
"winvideos/008048/4.png",
"winvideos/008048/5.png",
"winvideos/008048/6.png",
"winvideos/008048/7.png"
] |
car on a red bridge. | [
{
"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: [car on a red bridge.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001090/0.png",
"losevideos/001090/1.png",
"losevideos/001090/2.png",
"losevideos/001090/3.png",
"losevideos/001090/4.png",
"losevideos/001090/5.png",
"losevideos/001090/6.png",
"losevideos/001090/7.png",
"winvideos/001090/0.png",
"winvideos/001090/1.png",
"winvideos/001090/2.png",
"winvideos/001090/3.png",
"winvideos/001090/4.png",
"winvideos/001090/5.png",
"winvideos/001090/6.png",
"winvideos/001090/7.png"
] |
A human wearing orange uniform falling on the 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: [A human wearing orange uniform falling on the ground.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006544/0.png",
"winvideos/006544/1.png",
"winvideos/006544/2.png",
"winvideos/006544/3.png",
"winvideos/006544/4.png",
"winvideos/006544/5.png",
"winvideos/006544/6.png",
"winvideos/006544/7.png",
"losevideos/006544/0.png",
"losevideos/006544/1.png",
"losevideos/006544/2.png",
"losevideos/006544/3.png",
"losevideos/006544/4.png",
"losevideos/006544/5.png",
"losevideos/006544/6.png",
"losevideos/006544/7.png"
] |
mercurium formation moving morphing timelapse volumetric light -camera pan right -m 4 -neg "erratic fluctuation in motion, noisy, poor quality, distorted". | [
{
"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: [mercurium formation moving morphing timelapse volumetric light -camera pan right -m 4 -neg "erratic fluctuation in motion, noisy, poor quality, distorted".]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004358/0.png",
"winvideos/004358/1.png",
"winvideos/004358/2.png",
"winvideos/004358/3.png",
"winvideos/004358/4.png",
"winvideos/004358/5.png",
"winvideos/004358/6.png",
"winvideos/004358/7.png",
"losevideos/004358/0.png",
"losevideos/004358/1.png",
"losevideos/004358/2.png",
"losevideos/004358/3.png",
"losevideos/004358/4.png",
"losevideos/004358/5.png",
"losevideos/004358/6.png",
"losevideos/004358/7.png"
] |
haunted house atmosphere with scary evil presence in the background overlooking sleeping man Message: ghost (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: [haunted house atmosphere with scary evil presence in the background overlooking sleeping man Message: ghost (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005047/0.png",
"losevideos/005047/1.png",
"losevideos/005047/2.png",
"losevideos/005047/3.png",
"losevideos/005047/4.png",
"losevideos/005047/5.png",
"losevideos/005047/6.png",
"losevideos/005047/7.png",
"winvideos/005047/0.png",
"winvideos/005047/1.png",
"winvideos/005047/2.png",
"winvideos/005047/3.png",
"winvideos/005047/4.png",
"winvideos/005047/5.png",
"winvideos/005047/6.png",
"winvideos/005047/7.png"
] |
ballet dancer hippo. | [
{
"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: [ballet dancer hippo.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008525/0.png",
"losevideos/008525/1.png",
"losevideos/008525/2.png",
"losevideos/008525/3.png",
"losevideos/008525/4.png",
"losevideos/008525/5.png",
"losevideos/008525/6.png",
"losevideos/008525/7.png",
"winvideos/008525/0.png",
"winvideos/008525/1.png",
"winvideos/008525/2.png",
"winvideos/008525/3.png",
"winvideos/008525/4.png",
"winvideos/008525/5.png",
"winvideos/008525/6.png",
"winvideos/008525/7.png"
] |
1: A person reading. | [
{
"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: [1: A person reading.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003613/0.png",
"winvideos/003613/1.png",
"winvideos/003613/2.png",
"winvideos/003613/3.png",
"winvideos/003613/4.png",
"winvideos/003613/5.png",
"winvideos/003613/6.png",
"winvideos/003613/7.png",
"losevideos/003613/0.png",
"losevideos/003613/1.png",
"losevideos/003613/2.png",
"losevideos/003613/3.png",
"losevideos/003613/4.png",
"losevideos/003613/5.png",
"losevideos/003613/6.png",
"losevideos/003613/7.png"
] |
Master Buddha with long hair and beard talking to his monks, hyper-realistic cinematic -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: [Master Buddha with long hair and beard talking to his monks, hyper-realistic cinematic -16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005368/0.png",
"winvideos/005368/1.png",
"winvideos/005368/2.png",
"winvideos/005368/3.png",
"winvideos/005368/4.png",
"winvideos/005368/5.png",
"winvideos/005368/6.png",
"winvideos/005368/7.png",
"losevideos/005368/0.png",
"losevideos/005368/1.png",
"losevideos/005368/2.png",
"losevideos/005368/3.png",
"losevideos/005368/4.png",
"losevideos/005368/5.png",
"losevideos/005368/6.png",
"losevideos/005368/7.png"
] |
CTI Orange Kamen Rider shoots a beam, jumps up and kicks, exits at a 45-degree angle, orange suit, special shot character, side view. | [
{
"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: [CTI Orange Kamen Rider shoots a beam, jumps up and kicks, exits at a 45-degree angle, orange suit, special shot character, side view.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008405/0.png",
"losevideos/008405/1.png",
"losevideos/008405/2.png",
"losevideos/008405/3.png",
"losevideos/008405/4.png",
"losevideos/008405/5.png",
"losevideos/008405/6.png",
"losevideos/008405/7.png",
"winvideos/008405/0.png",
"winvideos/008405/1.png",
"winvideos/008405/2.png",
"winvideos/008405/3.png",
"winvideos/008405/4.png",
"winvideos/008405/5.png",
"winvideos/008405/6.png",
"winvideos/008405/7.png"
] |
dark fantsy style "A sinister and massive spider-like creature, its legs dripping with venom as it lurks in the shadows."dark hell the devil evil terrifying scary horror fear anxiety scorn lovecraftian monsters. | [
{
"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: [dark fantsy style "A sinister and massive spider-like creature, its legs dripping with venom as it lurks in the shadows."dark hell the devil evil terrifying scary horror fear anxiety scorn lovecraftian monsters.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002841/0.png",
"winvideos/002841/1.png",
"winvideos/002841/2.png",
"winvideos/002841/3.png",
"winvideos/002841/4.png",
"winvideos/002841/5.png",
"winvideos/002841/6.png",
"winvideos/002841/7.png",
"losevideos/002841/0.png",
"losevideos/002841/1.png",
"losevideos/002841/2.png",
"losevideos/002841/3.png",
"losevideos/002841/4.png",
"losevideos/002841/5.png",
"losevideos/002841/6.png",
"losevideos/002841/7.png"
] |
A huge cluster of strawberrie the size of a disintegrating asteroid strikes buildings and skyscrapers. Strawberries crash into buildings and destroying property. The situation is dramatic. 8k,hyper realistic, hyper detailed, as a real, Unreal engine 5. -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: [A huge cluster of strawberrie the size of a disintegrating asteroid strikes buildings and skyscrapers. Strawberries crash into buildings and destroying property. The situation is dramatic. 8k,hyper realistic, hyper detailed, as a real, Unreal engine 5. -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007278/0.png",
"winvideos/007278/1.png",
"winvideos/007278/2.png",
"winvideos/007278/3.png",
"winvideos/007278/4.png",
"winvideos/007278/5.png",
"winvideos/007278/6.png",
"winvideos/007278/7.png",
"losevideos/007278/0.png",
"losevideos/007278/1.png",
"losevideos/007278/2.png",
"losevideos/007278/3.png",
"losevideos/007278/4.png",
"losevideos/007278/5.png",
"losevideos/007278/6.png",
"losevideos/007278/7.png"
] |
A business man doing trading. | [
{
"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 business man doing trading.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001948/0.png",
"losevideos/001948/1.png",
"losevideos/001948/2.png",
"losevideos/001948/3.png",
"losevideos/001948/4.png",
"losevideos/001948/5.png",
"losevideos/001948/6.png",
"losevideos/001948/7.png",
"winvideos/001948/0.png",
"winvideos/001948/1.png",
"winvideos/001948/2.png",
"winvideos/001948/3.png",
"winvideos/001948/4.png",
"winvideos/001948/5.png",
"winvideos/001948/6.png",
"winvideos/001948/7.png"
] |
lemon explodes. | [
{
"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: [lemon explodes.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006498/0.png",
"losevideos/006498/1.png",
"losevideos/006498/2.png",
"losevideos/006498/3.png",
"losevideos/006498/4.png",
"losevideos/006498/5.png",
"losevideos/006498/6.png",
"losevideos/006498/7.png",
"winvideos/006498/0.png",
"winvideos/006498/1.png",
"winvideos/006498/2.png",
"winvideos/006498/3.png",
"winvideos/006498/4.png",
"winvideos/006498/5.png",
"winvideos/006498/6.png",
"winvideos/006498/7.png"
] |
ugly and broken pokémon screaming and jumping in the middle of the street. The pokémon looks a little bit drunk and violente, and very upset -ar 9:16 -motion 4 -gs 1. | [
{
"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: [ugly and broken pokémon screaming and jumping in the middle of the street. The pokémon looks a little bit drunk and violente, and very upset -ar 9:16 -motion 4 -gs 1.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003250/0.png",
"winvideos/003250/1.png",
"winvideos/003250/2.png",
"winvideos/003250/3.png",
"winvideos/003250/4.png",
"winvideos/003250/5.png",
"winvideos/003250/6.png",
"winvideos/003250/7.png",
"losevideos/003250/0.png",
"losevideos/003250/1.png",
"losevideos/003250/2.png",
"losevideos/003250/3.png",
"losevideos/003250/4.png",
"losevideos/003250/5.png",
"losevideos/003250/6.png",
"losevideos/003250/7.png"
] |
eine schlanke Frau steht in der Küche und schneidet Gemüse auf einem Brett. Sie lächelt. Dauer 10 sekunden. | [
{
"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: [eine schlanke Frau steht in der Küche und schneidet Gemüse auf einem Brett. Sie lächelt. Dauer 10 sekunden.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003056/0.png",
"winvideos/003056/1.png",
"winvideos/003056/2.png",
"winvideos/003056/3.png",
"winvideos/003056/4.png",
"winvideos/003056/5.png",
"winvideos/003056/6.png",
"winvideos/003056/7.png",
"losevideos/003056/0.png",
"losevideos/003056/1.png",
"losevideos/003056/2.png",
"losevideos/003056/3.png",
"losevideos/003056/4.png",
"losevideos/003056/5.png",
"losevideos/003056/6.png",
"losevideos/003056/7.png"
] |
zeppelins flying in the sunny skies above the flowered 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: [zeppelins flying in the sunny skies above the flowered city.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000800/0.png",
"winvideos/000800/1.png",
"winvideos/000800/2.png",
"winvideos/000800/3.png",
"winvideos/000800/4.png",
"winvideos/000800/5.png",
"winvideos/000800/6.png",
"winvideos/000800/7.png",
"losevideos/000800/0.png",
"losevideos/000800/1.png",
"losevideos/000800/2.png",
"losevideos/000800/3.png",
"losevideos/000800/4.png",
"losevideos/000800/5.png",
"losevideos/000800/6.png",
"losevideos/000800/7.png"
] |
"In the heart of the enchanted forest, bathed in the soft, dappled sunlight filtering through the ancient trees, a young lion cub named Leo stands on the edge of a glistening stream. | [
{
"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: ["In the heart of the enchanted forest, bathed in the soft, dappled sunlight filtering through the ancient trees, a young lion cub named Leo stands on the edge of a glistening stream.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002812/0.png",
"winvideos/002812/1.png",
"winvideos/002812/2.png",
"winvideos/002812/3.png",
"winvideos/002812/4.png",
"winvideos/002812/5.png",
"winvideos/002812/6.png",
"winvideos/002812/7.png",
"losevideos/002812/0.png",
"losevideos/002812/1.png",
"losevideos/002812/2.png",
"losevideos/002812/3.png",
"losevideos/002812/4.png",
"losevideos/002812/5.png",
"losevideos/002812/6.png",
"losevideos/002812/7.png"
] |
In the past, Ireland was part of the British Empire. It was ruled by the British for centuries, and the Irish people suffered greatly under British rule. -ar 9:16 -motion 4. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [In the past, Ireland was part of the British Empire. It was ruled by the British for centuries, and the Irish people suffered greatly under British rule. -ar 9:16 -motion 4.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000508/0.png",
"losevideos/000508/1.png",
"losevideos/000508/2.png",
"losevideos/000508/3.png",
"losevideos/000508/4.png",
"losevideos/000508/5.png",
"losevideos/000508/6.png",
"losevideos/000508/7.png",
"winvideos/000508/0.png",
"winvideos/000508/1.png",
"winvideos/000508/2.png",
"winvideos/000508/3.png",
"winvideos/000508/4.png",
"winvideos/000508/5.png",
"winvideos/000508/6.png",
"winvideos/000508/7.png"
] |
blond streamer man gaming , 80s retro. | [
{
"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: [blond streamer man gaming , 80s retro.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003272/0.png",
"losevideos/003272/1.png",
"losevideos/003272/2.png",
"losevideos/003272/3.png",
"losevideos/003272/4.png",
"losevideos/003272/5.png",
"losevideos/003272/6.png",
"losevideos/003272/7.png",
"winvideos/003272/0.png",
"winvideos/003272/1.png",
"winvideos/003272/2.png",
"winvideos/003272/3.png",
"winvideos/003272/4.png",
"winvideos/003272/5.png",
"winvideos/003272/6.png",
"winvideos/003272/7.png"
] |
Grandpa talked to me. | [
{
"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: [Grandpa talked to me.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002868/0.png",
"losevideos/002868/1.png",
"losevideos/002868/2.png",
"losevideos/002868/3.png",
"losevideos/002868/4.png",
"losevideos/002868/5.png",
"losevideos/002868/6.png",
"losevideos/002868/7.png",
"winvideos/002868/0.png",
"winvideos/002868/1.png",
"winvideos/002868/2.png",
"winvideos/002868/3.png",
"winvideos/002868/4.png",
"winvideos/002868/5.png",
"winvideos/002868/6.png",
"winvideos/002868/7.png"
] |
landscape destroyed. | [
{
"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: [landscape destroyed.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009647/0.png",
"losevideos/009647/1.png",
"losevideos/009647/2.png",
"losevideos/009647/3.png",
"losevideos/009647/4.png",
"losevideos/009647/5.png",
"losevideos/009647/6.png",
"losevideos/009647/7.png",
"winvideos/009647/0.png",
"winvideos/009647/1.png",
"winvideos/009647/2.png",
"winvideos/009647/3.png",
"winvideos/009647/4.png",
"winvideos/009647/5.png",
"winvideos/009647/6.png",
"winvideos/009647/7.png"
] |
sheeps driking water from a stream , NATURAL LIGHT, 4K photography, 50mm f/1.8 lens, , studio illumination, desert oasis background, Message: SALMO 23 (Font: SANS SERIF) -neg "morphing, erratic fluctuation in motion, motion blur, noisy, poor quality, distorted, bad quality, distorting, poorly drawn, blurring, graining, low resolution, oversaturating, lack of detail, inconsistent lighting, deforming face, extra limbs, distortion, deforming eyes". | [
{
"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: [sheeps driking water from a stream , NATURAL LIGHT, 4K photography, 50mm f/1.8 lens, , studio illumination, desert oasis background, Message: SALMO 23 (Font: SANS SERIF) -neg "morphing, erratic fluctuation in motion, motion blur, noisy, poor quality, distorted, bad quality, distorting, poorly drawn, blurring, graining, low resolution, oversaturating, lack of detail, inconsistent lighting, deforming face, extra limbs, distortion, deforming eyes".]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000339/0.png",
"losevideos/000339/1.png",
"losevideos/000339/2.png",
"losevideos/000339/3.png",
"losevideos/000339/4.png",
"losevideos/000339/5.png",
"losevideos/000339/6.png",
"losevideos/000339/7.png",
"winvideos/000339/0.png",
"winvideos/000339/1.png",
"winvideos/000339/2.png",
"winvideos/000339/3.png",
"winvideos/000339/4.png",
"winvideos/000339/5.png",
"winvideos/000339/6.png",
"winvideos/000339/7.png"
] |
Jack and Jill, two young children, walk hand in hand up a grassy hill towards a stone well. Jack carries a bucket, and Jill carries a pail. The sun shines brightly in the sky, and flowers bloom along the path., sunset -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: [Jack and Jill, two young children, walk hand in hand up a grassy hill towards a stone well. Jack carries a bucket, and Jill carries a pail. The sun shines brightly in the sky, and flowers bloom along the path., sunset -ar 16:9 -motion 2.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000175/0.png",
"winvideos/000175/1.png",
"winvideos/000175/2.png",
"winvideos/000175/3.png",
"winvideos/000175/4.png",
"winvideos/000175/5.png",
"winvideos/000175/6.png",
"winvideos/000175/7.png",
"losevideos/000175/0.png",
"losevideos/000175/1.png",
"losevideos/000175/2.png",
"losevideos/000175/3.png",
"losevideos/000175/4.png",
"losevideos/000175/5.png",
"losevideos/000175/6.png",
"losevideos/000175/7.png"
] |
Entering through a makeshift door, the vastness of the warehouse becomes evident. Revellers dance energetically, their bodies moving rhythmically to the beat, their shadows dancing on the brick walls. Green beam stage lighs moving, big led screen showing war tv news. | [
{
"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: [Entering through a makeshift door, the vastness of the warehouse becomes evident. Revellers dance energetically, their bodies moving rhythmically to the beat, their shadows dancing on the brick walls. Green beam stage lighs moving, big led screen showing war tv news.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008472/0.png",
"winvideos/008472/1.png",
"winvideos/008472/2.png",
"winvideos/008472/3.png",
"winvideos/008472/4.png",
"winvideos/008472/5.png",
"winvideos/008472/6.png",
"winvideos/008472/7.png",
"losevideos/008472/0.png",
"losevideos/008472/1.png",
"losevideos/008472/2.png",
"losevideos/008472/3.png",
"losevideos/008472/4.png",
"losevideos/008472/5.png",
"losevideos/008472/6.png",
"losevideos/008472/7.png"
] |
goku vc vegeta live action. | [
{
"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 vc vegeta live action.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001167/0.png",
"losevideos/001167/1.png",
"losevideos/001167/2.png",
"losevideos/001167/3.png",
"losevideos/001167/4.png",
"losevideos/001167/5.png",
"losevideos/001167/6.png",
"losevideos/001167/7.png",
"winvideos/001167/0.png",
"winvideos/001167/1.png",
"winvideos/001167/2.png",
"winvideos/001167/3.png",
"winvideos/001167/4.png",
"winvideos/001167/5.png",
"winvideos/001167/6.png",
"winvideos/001167/7.png"
] |
president of the philippines executing drug trafficker. | [
{
"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: [president of the philippines executing drug trafficker.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002798/0.png",
"losevideos/002798/1.png",
"losevideos/002798/2.png",
"losevideos/002798/3.png",
"losevideos/002798/4.png",
"losevideos/002798/5.png",
"losevideos/002798/6.png",
"losevideos/002798/7.png",
"winvideos/002798/0.png",
"winvideos/002798/1.png",
"winvideos/002798/2.png",
"winvideos/002798/3.png",
"winvideos/002798/4.png",
"winvideos/002798/5.png",
"winvideos/002798/6.png",
"winvideos/002798/7.png"
] |
carriage with 2 horses crossing the marketplace in an european city in the middle age. | [
{
"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: [carriage with 2 horses crossing the marketplace in an european city in the middle age.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003828/0.png",
"winvideos/003828/1.png",
"winvideos/003828/2.png",
"winvideos/003828/3.png",
"winvideos/003828/4.png",
"winvideos/003828/5.png",
"winvideos/003828/6.png",
"winvideos/003828/7.png",
"losevideos/003828/0.png",
"losevideos/003828/1.png",
"losevideos/003828/2.png",
"losevideos/003828/3.png",
"losevideos/003828/4.png",
"losevideos/003828/5.png",
"losevideos/003828/6.png",
"losevideos/003828/7.png"
] |
3d animation ,A cute, curious, adventurous dog walking at forest at the break of dawn, where sunlight filters through ancient trees, illuminating a mossy forest floor, , Photography, DSLR with a wide-angle lens, golden hour lighting, Disney style, pixel style, 3d animation adorable, lovely, 3d vector art, cute and quirky, watercolor effect, bokeh, adobe illustrator, hand drawn, digital painting, low-poly, low-lighting, dog-eye view, isometric style, character-focused, 6K resolution, photorealistic rendering. using cinema 4D, studio, hyper detailed. | [
{
"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 ,A cute, curious, adventurous dog walking at forest at the break of dawn, where sunlight filters through ancient trees, illuminating a mossy forest floor, , Photography, DSLR with a wide-angle lens, golden hour lighting, Disney style, pixel style, 3d animation adorable, lovely, 3d vector art, cute and quirky, watercolor effect, bokeh, adobe illustrator, hand drawn, digital painting, low-poly, low-lighting, dog-eye view, isometric style, character-focused, 6K resolution, photorealistic rendering. using cinema 4D, studio, hyper detailed.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007514/0.png",
"winvideos/007514/1.png",
"winvideos/007514/2.png",
"winvideos/007514/3.png",
"winvideos/007514/4.png",
"winvideos/007514/5.png",
"winvideos/007514/6.png",
"winvideos/007514/7.png",
"losevideos/007514/0.png",
"losevideos/007514/1.png",
"losevideos/007514/2.png",
"losevideos/007514/3.png",
"losevideos/007514/4.png",
"losevideos/007514/5.png",
"losevideos/007514/6.png",
"losevideos/007514/7.png"
] |
a robot is walking in the forest, dramatic scene, sunset, watching him phone (no show the screen) 15 sec -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 robot is walking in the forest, dramatic scene, sunset, watching him phone (no show the screen) 15 sec -ar 16:9 -motion 2.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002119/0.png",
"winvideos/002119/1.png",
"winvideos/002119/2.png",
"winvideos/002119/3.png",
"winvideos/002119/4.png",
"winvideos/002119/5.png",
"winvideos/002119/6.png",
"winvideos/002119/7.png",
"losevideos/002119/0.png",
"losevideos/002119/1.png",
"losevideos/002119/2.png",
"losevideos/002119/3.png",
"losevideos/002119/4.png",
"losevideos/002119/5.png",
"losevideos/002119/6.png",
"losevideos/002119/7.png"
] |
American evening from bedroom. | [
{
"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: [American evening from bedroom.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004420/0.png",
"winvideos/004420/1.png",
"winvideos/004420/2.png",
"winvideos/004420/3.png",
"winvideos/004420/4.png",
"winvideos/004420/5.png",
"winvideos/004420/6.png",
"winvideos/004420/7.png",
"losevideos/004420/0.png",
"losevideos/004420/1.png",
"losevideos/004420/2.png",
"losevideos/004420/3.png",
"losevideos/004420/4.png",
"losevideos/004420/5.png",
"losevideos/004420/6.png",
"losevideos/004420/7.png"
] |
figure with mask is looking around in a forest and then turns to the spectator. the forest is scary and there are ravens in the sky. the figure is like a ghist without legs. all figure. with horns. dark surrealism horror low quality. black and white. | [
{
"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: [figure with mask is looking around in a forest and then turns to the spectator. the forest is scary and there are ravens in the sky. the figure is like a ghist without legs. all figure. with horns. dark surrealism horror low quality. black and white.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005719/0.png",
"winvideos/005719/1.png",
"winvideos/005719/2.png",
"winvideos/005719/3.png",
"winvideos/005719/4.png",
"winvideos/005719/5.png",
"winvideos/005719/6.png",
"winvideos/005719/7.png",
"losevideos/005719/0.png",
"losevideos/005719/1.png",
"losevideos/005719/2.png",
"losevideos/005719/3.png",
"losevideos/005719/4.png",
"losevideos/005719/5.png",
"losevideos/005719/6.png",
"losevideos/005719/7.png"
] |
head and face sped up , cursed video, creepypasta, horror, pure dread, eerie, dark, dark hospital room VHS found footage. | [
{
"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: [head and face sped up , cursed video, creepypasta, horror, pure dread, eerie, dark, dark hospital room VHS found footage.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005732/0.png",
"winvideos/005732/1.png",
"winvideos/005732/2.png",
"winvideos/005732/3.png",
"winvideos/005732/4.png",
"winvideos/005732/5.png",
"winvideos/005732/6.png",
"winvideos/005732/7.png",
"losevideos/005732/0.png",
"losevideos/005732/1.png",
"losevideos/005732/2.png",
"losevideos/005732/3.png",
"losevideos/005732/4.png",
"losevideos/005732/5.png",
"losevideos/005732/6.png",
"losevideos/005732/7.png"
] |
a sailor hold a rope on the deck of a ship, swinging the rope. | [
{
"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 sailor hold a rope on the deck of a ship, swinging the rope.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008076/0.png",
"losevideos/008076/1.png",
"losevideos/008076/2.png",
"losevideos/008076/3.png",
"losevideos/008076/4.png",
"losevideos/008076/5.png",
"losevideos/008076/6.png",
"losevideos/008076/7.png",
"winvideos/008076/0.png",
"winvideos/008076/1.png",
"winvideos/008076/2.png",
"winvideos/008076/3.png",
"winvideos/008076/4.png",
"winvideos/008076/5.png",
"winvideos/008076/6.png",
"winvideos/008076/7.png"
] |
a bear is painting a picture. | [
{
"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 bear is painting a picture.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005395/0.png",
"winvideos/005395/1.png",
"winvideos/005395/2.png",
"winvideos/005395/3.png",
"winvideos/005395/4.png",
"winvideos/005395/5.png",
"winvideos/005395/6.png",
"winvideos/005395/7.png",
"losevideos/005395/0.png",
"losevideos/005395/1.png",
"losevideos/005395/2.png",
"losevideos/005395/3.png",
"losevideos/005395/4.png",
"losevideos/005395/5.png",
"losevideos/005395/6.png",
"losevideos/005395/7.png"
] |
blind young father holding a cane and playing with his son during biblical time period. | [
{
"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: [blind young father holding a cane and playing with his son during biblical time period.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004766/0.png",
"losevideos/004766/1.png",
"losevideos/004766/2.png",
"losevideos/004766/3.png",
"losevideos/004766/4.png",
"losevideos/004766/5.png",
"losevideos/004766/6.png",
"losevideos/004766/7.png",
"winvideos/004766/0.png",
"winvideos/004766/1.png",
"winvideos/004766/2.png",
"winvideos/004766/3.png",
"winvideos/004766/4.png",
"winvideos/004766/5.png",
"winvideos/004766/6.png",
"winvideos/004766/7.png"
] |
There lived a cunning fox in 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: [There lived a cunning fox in a forest.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003237/0.png",
"winvideos/003237/1.png",
"winvideos/003237/2.png",
"winvideos/003237/3.png",
"winvideos/003237/4.png",
"winvideos/003237/5.png",
"winvideos/003237/6.png",
"winvideos/003237/7.png",
"losevideos/003237/0.png",
"losevideos/003237/1.png",
"losevideos/003237/2.png",
"losevideos/003237/3.png",
"losevideos/003237/4.png",
"losevideos/003237/5.png",
"losevideos/003237/6.png",
"losevideos/003237/7.png"
] |
a happy Spanish man winning in casino a lot of money. | [
{
"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 happy Spanish man winning in casino a lot of money.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008535/0.png",
"winvideos/008535/1.png",
"winvideos/008535/2.png",
"winvideos/008535/3.png",
"winvideos/008535/4.png",
"winvideos/008535/5.png",
"winvideos/008535/6.png",
"winvideos/008535/7.png",
"losevideos/008535/0.png",
"losevideos/008535/1.png",
"losevideos/008535/2.png",
"losevideos/008535/3.png",
"losevideos/008535/4.png",
"losevideos/008535/5.png",
"losevideos/008535/6.png",
"losevideos/008535/7.png"
] |
Generate the video of bacon sunbathing on the beach, related to the animated movie Frozen Eggs - fps 16 - 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: [Generate the video of bacon sunbathing on the beach, related to the animated movie Frozen Eggs - fps 16 - motion 2.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004956/0.png",
"winvideos/004956/1.png",
"winvideos/004956/2.png",
"winvideos/004956/3.png",
"winvideos/004956/4.png",
"winvideos/004956/5.png",
"winvideos/004956/6.png",
"winvideos/004956/7.png",
"losevideos/004956/0.png",
"losevideos/004956/1.png",
"losevideos/004956/2.png",
"losevideos/004956/3.png",
"losevideos/004956/4.png",
"losevideos/004956/5.png",
"losevideos/004956/6.png",
"losevideos/004956/7.png"
] |
Create a 4-second shot for a travel advertisement that encapsulates the tranquility of a nature retreat. The shot features a lush forest with dappled sunlight, a bubbling stream, and a cozy cabin. Birds chirp softly as the camera pans over vibrant wildflowers. The shot focuses on a wooden deck where a cup of steaming herbal tea sits on a table beside a journal. Incorporate a gentle zoom-in to highlight the inviting scene. Use ambient forest sounds and acoustic guitar music to evoke relaxation and the allure of the retreat. Convey the retreat's serenity and connection with nature, inviting viewers to escape and rejuvenate. | [
{
"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 4-second shot for a travel advertisement that encapsulates the tranquility of a nature retreat. The shot features a lush forest with dappled sunlight, a bubbling stream, and a cozy cabin. Birds chirp softly as the camera pans over vibrant wildflowers. The shot focuses on a wooden deck where a cup of steaming herbal tea sits on a table beside a journal. Incorporate a gentle zoom-in to highlight the inviting scene. Use ambient forest sounds and acoustic guitar music to evoke relaxation and the allure of the retreat. Convey the retreat's serenity and connection with nature, inviting viewers to escape and rejuvenate.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000129/0.png",
"losevideos/000129/1.png",
"losevideos/000129/2.png",
"losevideos/000129/3.png",
"losevideos/000129/4.png",
"losevideos/000129/5.png",
"losevideos/000129/6.png",
"losevideos/000129/7.png",
"winvideos/000129/0.png",
"winvideos/000129/1.png",
"winvideos/000129/2.png",
"winvideos/000129/3.png",
"winvideos/000129/4.png",
"winvideos/000129/5.png",
"winvideos/000129/6.png",
"winvideos/000129/7.png"
] |
the walking dead, dead city, zombies, wide angle, 14mm, clouds, dogs. | [
{
"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 walking dead, dead city, zombies, wide angle, 14mm, clouds, dogs.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003989/0.png",
"winvideos/003989/1.png",
"winvideos/003989/2.png",
"winvideos/003989/3.png",
"winvideos/003989/4.png",
"winvideos/003989/5.png",
"winvideos/003989/6.png",
"winvideos/003989/7.png",
"losevideos/003989/0.png",
"losevideos/003989/1.png",
"losevideos/003989/2.png",
"losevideos/003989/3.png",
"losevideos/003989/4.png",
"losevideos/003989/5.png",
"losevideos/003989/6.png",
"losevideos/003989/7.png"
] |
Atari Console with arms and legs smoking a cigarette. | [
{
"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: [Atari Console with arms and legs smoking a cigarette.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005967/0.png",
"winvideos/005967/1.png",
"winvideos/005967/2.png",
"winvideos/005967/3.png",
"winvideos/005967/4.png",
"winvideos/005967/5.png",
"winvideos/005967/6.png",
"winvideos/005967/7.png",
"losevideos/005967/0.png",
"losevideos/005967/1.png",
"losevideos/005967/2.png",
"losevideos/005967/3.png",
"losevideos/005967/4.png",
"losevideos/005967/5.png",
"losevideos/005967/6.png",
"losevideos/005967/7.png"
] |
Picture the town of Ravenbrook, with its quaint houses and ancient oaks, the atmosphere thick with the anticipation of Halloween 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: [Picture the town of Ravenbrook, with its quaint houses and ancient oaks, the atmosphere thick with the anticipation of Halloween night.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002003/0.png",
"losevideos/002003/1.png",
"losevideos/002003/2.png",
"losevideos/002003/3.png",
"losevideos/002003/4.png",
"losevideos/002003/5.png",
"losevideos/002003/6.png",
"losevideos/002003/7.png",
"winvideos/002003/0.png",
"winvideos/002003/1.png",
"winvideos/002003/2.png",
"winvideos/002003/3.png",
"winvideos/002003/4.png",
"winvideos/002003/5.png",
"winvideos/002003/6.png",
"winvideos/002003/7.png"
] |
teletubies singing and dancing at a vintage motel pool party. | [
{
"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: [teletubies singing and dancing at a vintage motel pool party.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006625/0.png",
"winvideos/006625/1.png",
"winvideos/006625/2.png",
"winvideos/006625/3.png",
"winvideos/006625/4.png",
"winvideos/006625/5.png",
"winvideos/006625/6.png",
"winvideos/006625/7.png",
"losevideos/006625/0.png",
"losevideos/006625/1.png",
"losevideos/006625/2.png",
"losevideos/006625/3.png",
"losevideos/006625/4.png",
"losevideos/006625/5.png",
"losevideos/006625/6.png",
"losevideos/006625/7.png"
] |
a young gender and race ambiguous model walks in the street of paris while wearing an enourmous amount of brown leather luxury goods by the fashion brand chloé, - camera pan shot - motion 3. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a young gender and race ambiguous model walks in the street of paris while wearing an enourmous amount of brown leather luxury goods by the fashion brand chloé, - camera pan shot - motion 3.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006267/0.png",
"losevideos/006267/1.png",
"losevideos/006267/2.png",
"losevideos/006267/3.png",
"losevideos/006267/4.png",
"losevideos/006267/5.png",
"losevideos/006267/6.png",
"losevideos/006267/7.png",
"winvideos/006267/0.png",
"winvideos/006267/1.png",
"winvideos/006267/2.png",
"winvideos/006267/3.png",
"winvideos/006267/4.png",
"winvideos/006267/5.png",
"winvideos/006267/6.png",
"winvideos/006267/7.png"
] |
girl model modeling the eyewear. | [
{
"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 model modeling the eyewear.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009954/0.png",
"losevideos/009954/1.png",
"losevideos/009954/2.png",
"losevideos/009954/3.png",
"losevideos/009954/4.png",
"losevideos/009954/5.png",
"losevideos/009954/6.png",
"losevideos/009954/7.png",
"winvideos/009954/0.png",
"winvideos/009954/1.png",
"winvideos/009954/2.png",
"winvideos/009954/3.png",
"winvideos/009954/4.png",
"winvideos/009954/5.png",
"winvideos/009954/6.png",
"winvideos/009954/7.png"
] |
Imagine an expansive space hangar. In the center, an ethereal, bioluminescent jellyfish, tethered to a spaceship, seems to power it. On another side, scientists release a swarm of tiny microbes onto a soil sample, which immediately starts sprouting plant life, symbolizing terraforming., 4k, --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: [Imagine an expansive space hangar. In the center, an ethereal, bioluminescent jellyfish, tethered to a spaceship, seems to power it. On another side, scientists release a swarm of tiny microbes onto a soil sample, which immediately starts sprouting plant life, symbolizing terraforming., 4k, --ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005219/0.png",
"winvideos/005219/1.png",
"winvideos/005219/2.png",
"winvideos/005219/3.png",
"winvideos/005219/4.png",
"winvideos/005219/5.png",
"winvideos/005219/6.png",
"winvideos/005219/7.png",
"losevideos/005219/0.png",
"losevideos/005219/1.png",
"losevideos/005219/2.png",
"losevideos/005219/3.png",
"losevideos/005219/4.png",
"losevideos/005219/5.png",
"losevideos/005219/6.png",
"losevideos/005219/7.png"
] |
Montevideo, lluvioso, año 1980, neón. | [
{
"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: [Montevideo, lluvioso, año 1980, neón.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004641/0.png",
"losevideos/004641/1.png",
"losevideos/004641/2.png",
"losevideos/004641/3.png",
"losevideos/004641/4.png",
"losevideos/004641/5.png",
"losevideos/004641/6.png",
"losevideos/004641/7.png",
"winvideos/004641/0.png",
"winvideos/004641/1.png",
"winvideos/004641/2.png",
"winvideos/004641/3.png",
"winvideos/004641/4.png",
"winvideos/004641/5.png",
"winvideos/004641/6.png",
"winvideos/004641/7.png"
] |
treasure trove of life lessons. | [
{
"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: [treasure trove of life lessons.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000870/0.png",
"losevideos/000870/1.png",
"losevideos/000870/2.png",
"losevideos/000870/3.png",
"losevideos/000870/4.png",
"losevideos/000870/5.png",
"losevideos/000870/6.png",
"losevideos/000870/7.png",
"winvideos/000870/0.png",
"winvideos/000870/1.png",
"winvideos/000870/2.png",
"winvideos/000870/3.png",
"winvideos/000870/4.png",
"winvideos/000870/5.png",
"winvideos/000870/6.png",
"winvideos/000870/7.png"
] |
eye of a cat. | [
{
"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: [eye of a cat.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000180/0.png",
"winvideos/000180/1.png",
"winvideos/000180/2.png",
"winvideos/000180/3.png",
"winvideos/000180/4.png",
"winvideos/000180/5.png",
"winvideos/000180/6.png",
"winvideos/000180/7.png",
"losevideos/000180/0.png",
"losevideos/000180/1.png",
"losevideos/000180/2.png",
"losevideos/000180/3.png",
"losevideos/000180/4.png",
"losevideos/000180/5.png",
"losevideos/000180/6.png",
"losevideos/000180/7.png"
] |
blonde mom with grocery shopping cart parked by produce isle, rolling forward. | [
{
"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: [blonde mom with grocery shopping cart parked by produce isle, rolling forward.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006464/0.png",
"losevideos/006464/1.png",
"losevideos/006464/2.png",
"losevideos/006464/3.png",
"losevideos/006464/4.png",
"losevideos/006464/5.png",
"losevideos/006464/6.png",
"losevideos/006464/7.png",
"winvideos/006464/0.png",
"winvideos/006464/1.png",
"winvideos/006464/2.png",
"winvideos/006464/3.png",
"winvideos/006464/4.png",
"winvideos/006464/5.png",
"winvideos/006464/6.png",
"winvideos/006464/7.png"
] |
: set of 5 playmobil everdreamerz of different colors and designs dancing on a stage. | [
{
"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: [: set of 5 playmobil everdreamerz of different colors and designs dancing on a stage.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000359/0.png",
"winvideos/000359/1.png",
"winvideos/000359/2.png",
"winvideos/000359/3.png",
"winvideos/000359/4.png",
"winvideos/000359/5.png",
"winvideos/000359/6.png",
"winvideos/000359/7.png",
"losevideos/000359/0.png",
"losevideos/000359/1.png",
"losevideos/000359/2.png",
"losevideos/000359/3.png",
"losevideos/000359/4.png",
"losevideos/000359/5.png",
"losevideos/000359/6.png",
"losevideos/000359/7.png"
] |
time lapse drone footage of happy people of all ages in colorful homemade tracksuits building a multi colored 10 story half-timbered house, 1930, kodachorme, denmark, summer day in the danish countryside. | [
{
"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: [time lapse drone footage of happy people of all ages in colorful homemade tracksuits building a multi colored 10 story half-timbered house, 1930, kodachorme, denmark, summer day in the danish countryside.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002219/0.png",
"winvideos/002219/1.png",
"winvideos/002219/2.png",
"winvideos/002219/3.png",
"winvideos/002219/4.png",
"winvideos/002219/5.png",
"winvideos/002219/6.png",
"winvideos/002219/7.png",
"losevideos/002219/0.png",
"losevideos/002219/1.png",
"losevideos/002219/2.png",
"losevideos/002219/3.png",
"losevideos/002219/4.png",
"losevideos/002219/5.png",
"losevideos/002219/6.png",
"losevideos/002219/7.png"
] |
+ Here are 11 health benefits of bee pollen, backed by science. | [
{
"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: [+ Here are 11 health benefits of bee pollen, backed by science.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007357/0.png",
"losevideos/007357/1.png",
"losevideos/007357/2.png",
"losevideos/007357/3.png",
"losevideos/007357/4.png",
"losevideos/007357/5.png",
"losevideos/007357/6.png",
"losevideos/007357/7.png",
"winvideos/007357/0.png",
"winvideos/007357/1.png",
"winvideos/007357/2.png",
"winvideos/007357/3.png",
"winvideos/007357/4.png",
"winvideos/007357/5.png",
"winvideos/007357/6.png",
"winvideos/007357/7.png"
] |
Aragorn and the hobbits walk through the night 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: [Aragorn and the hobbits walk through the night forest.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003973/0.png",
"losevideos/003973/1.png",
"losevideos/003973/2.png",
"losevideos/003973/3.png",
"losevideos/003973/4.png",
"losevideos/003973/5.png",
"losevideos/003973/6.png",
"losevideos/003973/7.png",
"winvideos/003973/0.png",
"winvideos/003973/1.png",
"winvideos/003973/2.png",
"winvideos/003973/3.png",
"winvideos/003973/4.png",
"winvideos/003973/5.png",
"winvideos/003973/6.png",
"winvideos/003973/7.png"
] |
beauty woman driving in car. | [
{
"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: [beauty woman driving in car.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003197/0.png",
"winvideos/003197/1.png",
"winvideos/003197/2.png",
"winvideos/003197/3.png",
"winvideos/003197/4.png",
"winvideos/003197/5.png",
"winvideos/003197/6.png",
"winvideos/003197/7.png",
"losevideos/003197/0.png",
"losevideos/003197/1.png",
"losevideos/003197/2.png",
"losevideos/003197/3.png",
"losevideos/003197/4.png",
"losevideos/003197/5.png",
"losevideos/003197/6.png",
"losevideos/003197/7.png"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.