prompt
stringlengths 4
8.37k
| conversations
listlengths 2
2
| images
sequencelengths 16
16
|
|---|---|---|
a big girl dancing. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a big girl dancing.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004781/0.png",
"winvideos/004781/1.png",
"winvideos/004781/2.png",
"winvideos/004781/3.png",
"winvideos/004781/4.png",
"winvideos/004781/5.png",
"winvideos/004781/6.png",
"winvideos/004781/7.png",
"losevideos/004781/0.png",
"losevideos/004781/1.png",
"losevideos/004781/2.png",
"losevideos/004781/3.png",
"losevideos/004781/4.png",
"losevideos/004781/5.png",
"losevideos/004781/6.png",
"losevideos/004781/7.png"
] |
The Legend of the White Snake, the man in ancient costume is locked in the temple, the monk fights with the snake, Jinshan Temple, White Snake, Green Snake, the temple is flooded by flood, critical condition. | [
{
"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 Legend of the White Snake, the man in ancient costume is locked in the temple, the monk fights with the snake, Jinshan Temple, White Snake, Green Snake, the temple is flooded by flood, critical condition.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009339/0.png",
"winvideos/009339/1.png",
"winvideos/009339/2.png",
"winvideos/009339/3.png",
"winvideos/009339/4.png",
"winvideos/009339/5.png",
"winvideos/009339/6.png",
"winvideos/009339/7.png",
"losevideos/009339/0.png",
"losevideos/009339/1.png",
"losevideos/009339/2.png",
"losevideos/009339/3.png",
"losevideos/009339/4.png",
"losevideos/009339/5.png",
"losevideos/009339/6.png",
"losevideos/009339/7.png"
] |
Santa thumb up and says Hoho GEZHi. | [
{
"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: [Santa thumb up and says Hoho GEZHi.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006588/0.png",
"winvideos/006588/1.png",
"winvideos/006588/2.png",
"winvideos/006588/3.png",
"winvideos/006588/4.png",
"winvideos/006588/5.png",
"winvideos/006588/6.png",
"winvideos/006588/7.png",
"losevideos/006588/0.png",
"losevideos/006588/1.png",
"losevideos/006588/2.png",
"losevideos/006588/3.png",
"losevideos/006588/4.png",
"losevideos/006588/5.png",
"losevideos/006588/6.png",
"losevideos/006588/7.png"
] |
man, is bitten by thousands of marabunta ants, hyper-realistic, very realistic, 8k, close-up. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [man, is bitten by thousands of marabunta ants, hyper-realistic, very realistic, 8k, close-up.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006611/0.png",
"losevideos/006611/1.png",
"losevideos/006611/2.png",
"losevideos/006611/3.png",
"losevideos/006611/4.png",
"losevideos/006611/5.png",
"losevideos/006611/6.png",
"losevideos/006611/7.png",
"winvideos/006611/0.png",
"winvideos/006611/1.png",
"winvideos/006611/2.png",
"winvideos/006611/3.png",
"winvideos/006611/4.png",
"winvideos/006611/5.png",
"winvideos/006611/6.png",
"winvideos/006611/7.png"
] |
Close-up of children soaring up into the sky above a field in summer, Synthwave, vaporwave, 1990, VHS 90's nostalgia. | [
{
"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: [Close-up of children soaring up into the sky above a field in summer, Synthwave, vaporwave, 1990, VHS 90's nostalgia.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000450/0.png",
"losevideos/000450/1.png",
"losevideos/000450/2.png",
"losevideos/000450/3.png",
"losevideos/000450/4.png",
"losevideos/000450/5.png",
"losevideos/000450/6.png",
"losevideos/000450/7.png",
"winvideos/000450/0.png",
"winvideos/000450/1.png",
"winvideos/000450/2.png",
"winvideos/000450/3.png",
"winvideos/000450/4.png",
"winvideos/000450/5.png",
"winvideos/000450/6.png",
"winvideos/000450/7.png"
] |
a giant dragon with huge wings, awakening from it's sleep getting out of a cave in a huge mountain camera acw. | [
{
"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 giant dragon with huge wings, awakening from it's sleep getting out of a cave in a huge mountain camera acw.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003655/0.png",
"winvideos/003655/1.png",
"winvideos/003655/2.png",
"winvideos/003655/3.png",
"winvideos/003655/4.png",
"winvideos/003655/5.png",
"winvideos/003655/6.png",
"winvideos/003655/7.png",
"losevideos/003655/0.png",
"losevideos/003655/1.png",
"losevideos/003655/2.png",
"losevideos/003655/3.png",
"losevideos/003655/4.png",
"losevideos/003655/5.png",
"losevideos/003655/6.png",
"losevideos/003655/7.png"
] |
big ball flying and near playing bass quitarist , futuristic nature , message: superscript. | [
{
"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: [big ball flying and near playing bass quitarist , futuristic nature , message: superscript.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007368/0.png",
"winvideos/007368/1.png",
"winvideos/007368/2.png",
"winvideos/007368/3.png",
"winvideos/007368/4.png",
"winvideos/007368/5.png",
"winvideos/007368/6.png",
"winvideos/007368/7.png",
"losevideos/007368/0.png",
"losevideos/007368/1.png",
"losevideos/007368/2.png",
"losevideos/007368/3.png",
"losevideos/007368/4.png",
"losevideos/007368/5.png",
"losevideos/007368/6.png",
"losevideos/007368/7.png"
] |
What is Bachelor of Information Technology Degree. | [
{
"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: [What is Bachelor of Information Technology Degree.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009932/0.png",
"winvideos/009932/1.png",
"winvideos/009932/2.png",
"winvideos/009932/3.png",
"winvideos/009932/4.png",
"winvideos/009932/5.png",
"winvideos/009932/6.png",
"winvideos/009932/7.png",
"losevideos/009932/0.png",
"losevideos/009932/1.png",
"losevideos/009932/2.png",
"losevideos/009932/3.png",
"losevideos/009932/4.png",
"losevideos/009932/5.png",
"losevideos/009932/6.png",
"losevideos/009932/7.png"
] |
scrapbooking album handmade in steampunk style. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [scrapbooking album handmade in steampunk style.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006958/0.png",
"losevideos/006958/1.png",
"losevideos/006958/2.png",
"losevideos/006958/3.png",
"losevideos/006958/4.png",
"losevideos/006958/5.png",
"losevideos/006958/6.png",
"losevideos/006958/7.png",
"winvideos/006958/0.png",
"winvideos/006958/1.png",
"winvideos/006958/2.png",
"winvideos/006958/3.png",
"winvideos/006958/4.png",
"winvideos/006958/5.png",
"winvideos/006958/6.png",
"winvideos/006958/7.png"
] |
Create a dynamic and visually captivating image of Scorpion from Mortal Kombat. The focus should be on his iconic spear-throwing move, with Scorpion in mid-action, launching his spear directly toward the camera. Render Scorpion's entire body in striking detail, highlighting his fearsome attire, which includes his distinctive yellow ninja costume, mask, and the emblematic 'Scorpion' logo on his chest. Capture the intensity of the moment by depicting Scorpion's pose with determination and strength, his body coiled in a powerful stance as he releases the spear. The chain or rope attached to the spear should be dynamic and extend toward the viewer, creating a sense of depth and action. Incorporate fiery and infernal effects around Scorpion to represent his hellish origins and powers. Flames and smoke can billow behind him, adding an eerie and intense atmosphere to the scene. The result should be a high-impact portrayal of Scorpion in the midst of his iconic spear-throwing move, with a focus on his fiery and menacing characteristics.". | [
{
"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 dynamic and visually captivating image of Scorpion from Mortal Kombat. The focus should be on his iconic spear-throwing move, with Scorpion in mid-action, launching his spear directly toward the camera. Render Scorpion's entire body in striking detail, highlighting his fearsome attire, which includes his distinctive yellow ninja costume, mask, and the emblematic 'Scorpion' logo on his chest. Capture the intensity of the moment by depicting Scorpion's pose with determination and strength, his body coiled in a powerful stance as he releases the spear. The chain or rope attached to the spear should be dynamic and extend toward the viewer, creating a sense of depth and action. Incorporate fiery and infernal effects around Scorpion to represent his hellish origins and powers. Flames and smoke can billow behind him, adding an eerie and intense atmosphere to the scene. The result should be a high-impact portrayal of Scorpion in the midst of his iconic spear-throwing move, with a focus on his fiery and menacing characteristics.".]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003105/0.png",
"losevideos/003105/1.png",
"losevideos/003105/2.png",
"losevideos/003105/3.png",
"losevideos/003105/4.png",
"losevideos/003105/5.png",
"losevideos/003105/6.png",
"losevideos/003105/7.png",
"winvideos/003105/0.png",
"winvideos/003105/1.png",
"winvideos/003105/2.png",
"winvideos/003105/3.png",
"winvideos/003105/4.png",
"winvideos/003105/5.png",
"winvideos/003105/6.png",
"winvideos/003105/7.png"
] |
the lake, the dam and the spillway. | [
{
"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 lake, the dam and the spillway.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006599/0.png",
"losevideos/006599/1.png",
"losevideos/006599/2.png",
"losevideos/006599/3.png",
"losevideos/006599/4.png",
"losevideos/006599/5.png",
"losevideos/006599/6.png",
"losevideos/006599/7.png",
"winvideos/006599/0.png",
"winvideos/006599/1.png",
"winvideos/006599/2.png",
"winvideos/006599/3.png",
"winvideos/006599/4.png",
"winvideos/006599/5.png",
"winvideos/006599/6.png",
"winvideos/006599/7.png"
] |
man eats 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: [man eats car.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008253/0.png",
"losevideos/008253/1.png",
"losevideos/008253/2.png",
"losevideos/008253/3.png",
"losevideos/008253/4.png",
"losevideos/008253/5.png",
"losevideos/008253/6.png",
"losevideos/008253/7.png",
"winvideos/008253/0.png",
"winvideos/008253/1.png",
"winvideos/008253/2.png",
"winvideos/008253/3.png",
"winvideos/008253/4.png",
"winvideos/008253/5.png",
"winvideos/008253/6.png",
"winvideos/008253/7.png"
] |
3D_Animation_Style_One_sunny_day_Quackers_waddled_over_to_Crun_0. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [3D_Animation_Style_One_sunny_day_Quackers_waddled_over_to_Crun_0.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003266/0.png",
"winvideos/003266/1.png",
"winvideos/003266/2.png",
"winvideos/003266/3.png",
"winvideos/003266/4.png",
"winvideos/003266/5.png",
"winvideos/003266/6.png",
"winvideos/003266/7.png",
"losevideos/003266/0.png",
"losevideos/003266/1.png",
"losevideos/003266/2.png",
"losevideos/003266/3.png",
"losevideos/003266/4.png",
"losevideos/003266/5.png",
"losevideos/003266/6.png",
"losevideos/003266/7.png"
] |
oppressed villagers huddle together, their faces marked by fear and sorrow. | [
{
"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: [oppressed villagers huddle together, their faces marked by fear and sorrow.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003276/0.png",
"winvideos/003276/1.png",
"winvideos/003276/2.png",
"winvideos/003276/3.png",
"winvideos/003276/4.png",
"winvideos/003276/5.png",
"winvideos/003276/6.png",
"winvideos/003276/7.png",
"losevideos/003276/0.png",
"losevideos/003276/1.png",
"losevideos/003276/2.png",
"losevideos/003276/3.png",
"losevideos/003276/4.png",
"losevideos/003276/5.png",
"losevideos/003276/6.png",
"losevideos/003276/7.png"
] |
we provide luxury bus. | [
{
"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: [we provide luxury bus.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001744/0.png",
"losevideos/001744/1.png",
"losevideos/001744/2.png",
"losevideos/001744/3.png",
"losevideos/001744/4.png",
"losevideos/001744/5.png",
"losevideos/001744/6.png",
"losevideos/001744/7.png",
"winvideos/001744/0.png",
"winvideos/001744/1.png",
"winvideos/001744/2.png",
"winvideos/001744/3.png",
"winvideos/001744/4.png",
"winvideos/001744/5.png",
"winvideos/001744/6.png",
"winvideos/001744/7.png"
] |
shadow of still and blurred person, full body. bottomless. | [
{
"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: [shadow of still and blurred person, full body. bottomless.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003222/0.png",
"losevideos/003222/1.png",
"losevideos/003222/2.png",
"losevideos/003222/3.png",
"losevideos/003222/4.png",
"losevideos/003222/5.png",
"losevideos/003222/6.png",
"losevideos/003222/7.png",
"winvideos/003222/0.png",
"winvideos/003222/1.png",
"winvideos/003222/2.png",
"winvideos/003222/3.png",
"winvideos/003222/4.png",
"winvideos/003222/5.png",
"winvideos/003222/6.png",
"winvideos/003222/7.png"
] |
Macaw flying in the air. | [
{
"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: [Macaw flying in the air.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005241/0.png",
"losevideos/005241/1.png",
"losevideos/005241/2.png",
"losevideos/005241/3.png",
"losevideos/005241/4.png",
"losevideos/005241/5.png",
"losevideos/005241/6.png",
"losevideos/005241/7.png",
"winvideos/005241/0.png",
"winvideos/005241/1.png",
"winvideos/005241/2.png",
"winvideos/005241/3.png",
"winvideos/005241/4.png",
"winvideos/005241/5.png",
"winvideos/005241/6.png",
"winvideos/005241/7.png"
] |
Ninja running in woods stop motion Unreal engine 5 rendering. | [
{
"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: [Ninja running in woods stop motion Unreal engine 5 rendering.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000926/0.png",
"winvideos/000926/1.png",
"winvideos/000926/2.png",
"winvideos/000926/3.png",
"winvideos/000926/4.png",
"winvideos/000926/5.png",
"winvideos/000926/6.png",
"winvideos/000926/7.png",
"losevideos/000926/0.png",
"losevideos/000926/1.png",
"losevideos/000926/2.png",
"losevideos/000926/3.png",
"losevideos/000926/4.png",
"losevideos/000926/5.png",
"losevideos/000926/6.png",
"losevideos/000926/7.png"
] |
crowd waving at drivers. | [
{
"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: [crowd waving at drivers.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006807/0.png",
"winvideos/006807/1.png",
"winvideos/006807/2.png",
"winvideos/006807/3.png",
"winvideos/006807/4.png",
"winvideos/006807/5.png",
"winvideos/006807/6.png",
"winvideos/006807/7.png",
"losevideos/006807/0.png",
"losevideos/006807/1.png",
"losevideos/006807/2.png",
"losevideos/006807/3.png",
"losevideos/006807/4.png",
"losevideos/006807/5.png",
"losevideos/006807/6.png",
"losevideos/006807/7.png"
] |
Upshot foot shot quite, frontal shot, centered, a futuristic flying spaceship with neon headlights, accelerating near the ground forward on an avenue with futuristic buildings, night lights illuminating the night, pedestrians walking on the sidewalk, 3D render -neg" distortion, reflection , rays of light, beam of light, motionless, strange movements, motionless, motionless, cars, rotate, change, alter, very fast movements, vehicles" -motion 1 -gs 12 -fps 24 -v3.0 -hide. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Upshot foot shot quite, frontal shot, centered, a futuristic flying spaceship with neon headlights, accelerating near the ground forward on an avenue with futuristic buildings, night lights illuminating the night, pedestrians walking on the sidewalk, 3D render -neg" distortion, reflection , rays of light, beam of light, motionless, strange movements, motionless, motionless, cars, rotate, change, alter, very fast movements, vehicles" -motion 1 -gs 12 -fps 24 -v3.0 -hide.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006759/0.png",
"winvideos/006759/1.png",
"winvideos/006759/2.png",
"winvideos/006759/3.png",
"winvideos/006759/4.png",
"winvideos/006759/5.png",
"winvideos/006759/6.png",
"winvideos/006759/7.png",
"losevideos/006759/0.png",
"losevideos/006759/1.png",
"losevideos/006759/2.png",
"losevideos/006759/3.png",
"losevideos/006759/4.png",
"losevideos/006759/5.png",
"losevideos/006759/6.png",
"losevideos/006759/7.png"
] |
Show the majestic Queen Selena on her lunar throne, radiating light and wisdom. | [
{
"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: [Show the majestic Queen Selena on her lunar throne, radiating light and wisdom.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005295/0.png",
"losevideos/005295/1.png",
"losevideos/005295/2.png",
"losevideos/005295/3.png",
"losevideos/005295/4.png",
"losevideos/005295/5.png",
"losevideos/005295/6.png",
"losevideos/005295/7.png",
"winvideos/005295/0.png",
"winvideos/005295/1.png",
"winvideos/005295/2.png",
"winvideos/005295/3.png",
"winvideos/005295/4.png",
"winvideos/005295/5.png",
"winvideos/005295/6.png",
"winvideos/005295/7.png"
] |
an Andrei Tarkovsky horror film, cinematic, realistic, 8k, dark and moody, vibrant. Andrei Tarkovsky kills a man and stabs him repeatedly in a house -ar 21:9 -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: [an Andrei Tarkovsky horror film, cinematic, realistic, 8k, dark and moody, vibrant. Andrei Tarkovsky kills a man and stabs him repeatedly in a house -ar 21:9 -motion 4.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003283/0.png",
"winvideos/003283/1.png",
"winvideos/003283/2.png",
"winvideos/003283/3.png",
"winvideos/003283/4.png",
"winvideos/003283/5.png",
"winvideos/003283/6.png",
"winvideos/003283/7.png",
"losevideos/003283/0.png",
"losevideos/003283/1.png",
"losevideos/003283/2.png",
"losevideos/003283/3.png",
"losevideos/003283/4.png",
"losevideos/003283/5.png",
"losevideos/003283/6.png",
"losevideos/003283/7.png"
] |
a gorgeous 18 year old supermodel walking on a luxury beach in Greece. | [
{
"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 gorgeous 18 year old supermodel walking on a luxury beach in Greece.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001785/0.png",
"winvideos/001785/1.png",
"winvideos/001785/2.png",
"winvideos/001785/3.png",
"winvideos/001785/4.png",
"winvideos/001785/5.png",
"winvideos/001785/6.png",
"winvideos/001785/7.png",
"losevideos/001785/0.png",
"losevideos/001785/1.png",
"losevideos/001785/2.png",
"losevideos/001785/3.png",
"losevideos/001785/4.png",
"losevideos/001785/5.png",
"losevideos/001785/6.png",
"losevideos/001785/7.png"
] |
a bowl with whole apples and oranges in it and A bottle of red ketshup that is in the scene, just above the bowl of fruit, is tipped to pour ketchup on the bowl of fruit. | [
{
"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 bowl with whole apples and oranges in it and A bottle of red ketshup that is in the scene, just above the bowl of fruit, is tipped to pour ketchup on the bowl of fruit.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005498/0.png",
"losevideos/005498/1.png",
"losevideos/005498/2.png",
"losevideos/005498/3.png",
"losevideos/005498/4.png",
"losevideos/005498/5.png",
"losevideos/005498/6.png",
"losevideos/005498/7.png",
"winvideos/005498/0.png",
"winvideos/005498/1.png",
"winvideos/005498/2.png",
"winvideos/005498/3.png",
"winvideos/005498/4.png",
"winvideos/005498/5.png",
"winvideos/005498/6.png",
"winvideos/005498/7.png"
] |
dark forest,moving trees,mahadev,shivling,beautifull statue of lord shiva,rainfall,full hd,closeup,zoom. | [
{
"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 forest,moving trees,mahadev,shivling,beautifull statue of lord shiva,rainfall,full hd,closeup,zoom.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004215/0.png",
"winvideos/004215/1.png",
"winvideos/004215/2.png",
"winvideos/004215/3.png",
"winvideos/004215/4.png",
"winvideos/004215/5.png",
"winvideos/004215/6.png",
"winvideos/004215/7.png",
"losevideos/004215/0.png",
"losevideos/004215/1.png",
"losevideos/004215/2.png",
"losevideos/004215/3.png",
"losevideos/004215/4.png",
"losevideos/004215/5.png",
"losevideos/004215/6.png",
"losevideos/004215/7.png"
] |
scene from The Amazing Spider-Man 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: [scene from The Amazing Spider-Man 2.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008153/0.png",
"losevideos/008153/1.png",
"losevideos/008153/2.png",
"losevideos/008153/3.png",
"losevideos/008153/4.png",
"losevideos/008153/5.png",
"losevideos/008153/6.png",
"losevideos/008153/7.png",
"winvideos/008153/0.png",
"winvideos/008153/1.png",
"winvideos/008153/2.png",
"winvideos/008153/3.png",
"winvideos/008153/4.png",
"winvideos/008153/5.png",
"winvideos/008153/6.png",
"winvideos/008153/7.png"
] |
brightly lit person doing somersault in mid-air minimalist background in the style of Wolfgang tillmans - neg ugly clothing, clutter. | [
{
"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: [brightly lit person doing somersault in mid-air minimalist background in the style of Wolfgang tillmans - neg ugly clothing, clutter.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001344/0.png",
"winvideos/001344/1.png",
"winvideos/001344/2.png",
"winvideos/001344/3.png",
"winvideos/001344/4.png",
"winvideos/001344/5.png",
"winvideos/001344/6.png",
"winvideos/001344/7.png",
"losevideos/001344/0.png",
"losevideos/001344/1.png",
"losevideos/001344/2.png",
"losevideos/001344/3.png",
"losevideos/001344/4.png",
"losevideos/001344/5.png",
"losevideos/001344/6.png",
"losevideos/001344/7.png"
] |
Farm. | [
{
"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: [Farm.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002466/0.png",
"winvideos/002466/1.png",
"winvideos/002466/2.png",
"winvideos/002466/3.png",
"winvideos/002466/4.png",
"winvideos/002466/5.png",
"winvideos/002466/6.png",
"winvideos/002466/7.png",
"losevideos/002466/0.png",
"losevideos/002466/1.png",
"losevideos/002466/2.png",
"losevideos/002466/3.png",
"losevideos/002466/4.png",
"losevideos/002466/5.png",
"losevideos/002466/6.png",
"losevideos/002466/7.png"
] |
a small toy action figure in the style of 90's japanese action, the toy is of a lobster action figure, bright studio lighting, white studio enviornment, 8k. | [
{
"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 small toy action figure in the style of 90's japanese action, the toy is of a lobster action figure, bright studio lighting, white studio enviornment, 8k.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009406/0.png",
"winvideos/009406/1.png",
"winvideos/009406/2.png",
"winvideos/009406/3.png",
"winvideos/009406/4.png",
"winvideos/009406/5.png",
"winvideos/009406/6.png",
"winvideos/009406/7.png",
"losevideos/009406/0.png",
"losevideos/009406/1.png",
"losevideos/009406/2.png",
"losevideos/009406/3.png",
"losevideos/009406/4.png",
"losevideos/009406/5.png",
"losevideos/009406/6.png",
"losevideos/009406/7.png"
] |
An Arab man from the pre-Islamic era holds a stick and waves it in front of his house in the village. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [An Arab man from the pre-Islamic era holds a stick and waves it in front of his house in the village.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008077/0.png",
"winvideos/008077/1.png",
"winvideos/008077/2.png",
"winvideos/008077/3.png",
"winvideos/008077/4.png",
"winvideos/008077/5.png",
"winvideos/008077/6.png",
"winvideos/008077/7.png",
"losevideos/008077/0.png",
"losevideos/008077/1.png",
"losevideos/008077/2.png",
"losevideos/008077/3.png",
"losevideos/008077/4.png",
"losevideos/008077/5.png",
"losevideos/008077/6.png",
"losevideos/008077/7.png"
] |
a pickle pickling. | [
{
"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 pickle pickling.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003048/0.png",
"losevideos/003048/1.png",
"losevideos/003048/2.png",
"losevideos/003048/3.png",
"losevideos/003048/4.png",
"losevideos/003048/5.png",
"losevideos/003048/6.png",
"losevideos/003048/7.png",
"winvideos/003048/0.png",
"winvideos/003048/1.png",
"winvideos/003048/2.png",
"winvideos/003048/3.png",
"winvideos/003048/4.png",
"winvideos/003048/5.png",
"winvideos/003048/6.png",
"winvideos/003048/7.png"
] |
toddlers arguing about taxes -ar 4:5. | [
{
"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: [toddlers arguing about taxes -ar 4:5.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008785/0.png",
"losevideos/008785/1.png",
"losevideos/008785/2.png",
"losevideos/008785/3.png",
"losevideos/008785/4.png",
"losevideos/008785/5.png",
"losevideos/008785/6.png",
"losevideos/008785/7.png",
"winvideos/008785/0.png",
"winvideos/008785/1.png",
"winvideos/008785/2.png",
"winvideos/008785/3.png",
"winvideos/008785/4.png",
"winvideos/008785/5.png",
"winvideos/008785/6.png",
"winvideos/008785/7.png"
] |
<a href="https://cdn.discordapp.com/attachments/1123665843365093487/1130907412417753159/W_D_bralynnb_rough_dirty_detective_leather_jacket_with_eyes_flea_ma_52a8a6b6-7596-4bdc-9e21-31b720ca0799.png">https://cdn.discordapp.com/attachments/1123665843365093487/1130907412417753159/W_D_bralynnb_rough_dirty_detective_leather_jacket_with_eyes_flea_ma_52a8a6b6-7596-4bdc-9e21-31b720ca0799.png</a> eye on jacket, blinking. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [<a href=\"https://cdn.discordapp.com/attachments/1123665843365093487/1130907412417753159/W_D_bralynnb_rough_dirty_detective_leather_jacket_with_eyes_flea_ma_52a8a6b6-7596-4bdc-9e21-31b720ca0799.png\">https://cdn.discordapp.com/attachments/1123665843365093487/1130907412417753159/W_D_bralynnb_rough_dirty_detective_leather_jacket_with_eyes_flea_ma_52a8a6b6-7596-4bdc-9e21-31b720ca0799.png</a> eye on jacket, blinking.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004361/0.png",
"winvideos/004361/1.png",
"winvideos/004361/2.png",
"winvideos/004361/3.png",
"winvideos/004361/4.png",
"winvideos/004361/5.png",
"winvideos/004361/6.png",
"winvideos/004361/7.png",
"losevideos/004361/0.png",
"losevideos/004361/1.png",
"losevideos/004361/2.png",
"losevideos/004361/3.png",
"losevideos/004361/4.png",
"losevideos/004361/5.png",
"losevideos/004361/6.png",
"losevideos/004361/7.png"
] |
cute ant , 3d animation , 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: [cute ant , 3d animation , 4k.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008505/0.png",
"winvideos/008505/1.png",
"winvideos/008505/2.png",
"winvideos/008505/3.png",
"winvideos/008505/4.png",
"winvideos/008505/5.png",
"winvideos/008505/6.png",
"winvideos/008505/7.png",
"losevideos/008505/0.png",
"losevideos/008505/1.png",
"losevideos/008505/2.png",
"losevideos/008505/3.png",
"losevideos/008505/4.png",
"losevideos/008505/5.png",
"losevideos/008505/6.png",
"losevideos/008505/7.png"
] |
man lifting off the ground with otherd dancing around him , 8k, cinamatic -ar 16:9 -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: [man lifting off the ground with otherd dancing around him , 8k, cinamatic -ar 16:9 -motion 4.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007230/0.png",
"losevideos/007230/1.png",
"losevideos/007230/2.png",
"losevideos/007230/3.png",
"losevideos/007230/4.png",
"losevideos/007230/5.png",
"losevideos/007230/6.png",
"losevideos/007230/7.png",
"winvideos/007230/0.png",
"winvideos/007230/1.png",
"winvideos/007230/2.png",
"winvideos/007230/3.png",
"winvideos/007230/4.png",
"winvideos/007230/5.png",
"winvideos/007230/6.png",
"winvideos/007230/7.png"
] |
Kings period Soldiers. | [
{
"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: [Kings period Soldiers.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001713/0.png",
"losevideos/001713/1.png",
"losevideos/001713/2.png",
"losevideos/001713/3.png",
"losevideos/001713/4.png",
"losevideos/001713/5.png",
"losevideos/001713/6.png",
"losevideos/001713/7.png",
"winvideos/001713/0.png",
"winvideos/001713/1.png",
"winvideos/001713/2.png",
"winvideos/001713/3.png",
"winvideos/001713/4.png",
"winvideos/001713/5.png",
"winvideos/001713/6.png",
"winvideos/001713/7.png"
] |
sushi and pizza flying in the air, dolly 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: [sushi and pizza flying in the air, dolly in.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009858/0.png",
"losevideos/009858/1.png",
"losevideos/009858/2.png",
"losevideos/009858/3.png",
"losevideos/009858/4.png",
"losevideos/009858/5.png",
"losevideos/009858/6.png",
"losevideos/009858/7.png",
"winvideos/009858/0.png",
"winvideos/009858/1.png",
"winvideos/009858/2.png",
"winvideos/009858/3.png",
"winvideos/009858/4.png",
"winvideos/009858/5.png",
"winvideos/009858/6.png",
"winvideos/009858/7.png"
] |
woman sleeping in bedroom cominstyle. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [woman sleeping in bedroom cominstyle.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005668/0.png",
"winvideos/005668/1.png",
"winvideos/005668/2.png",
"winvideos/005668/3.png",
"winvideos/005668/4.png",
"winvideos/005668/5.png",
"winvideos/005668/6.png",
"winvideos/005668/7.png",
"losevideos/005668/0.png",
"losevideos/005668/1.png",
"losevideos/005668/2.png",
"losevideos/005668/3.png",
"losevideos/005668/4.png",
"losevideos/005668/5.png",
"losevideos/005668/6.png",
"losevideos/005668/7.png"
] |
A truck is driving in the desert with camels passing by. | [
{
"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 truck is driving in the desert with camels passing by.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004590/0.png",
"winvideos/004590/1.png",
"winvideos/004590/2.png",
"winvideos/004590/3.png",
"winvideos/004590/4.png",
"winvideos/004590/5.png",
"winvideos/004590/6.png",
"winvideos/004590/7.png",
"losevideos/004590/0.png",
"losevideos/004590/1.png",
"losevideos/004590/2.png",
"losevideos/004590/3.png",
"losevideos/004590/4.png",
"losevideos/004590/5.png",
"losevideos/004590/6.png",
"losevideos/004590/7.png"
] |
A Dog, 3D video and 4K quality. | [
{
"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 Dog, 3D video and 4K quality.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005841/0.png",
"losevideos/005841/1.png",
"losevideos/005841/2.png",
"losevideos/005841/3.png",
"losevideos/005841/4.png",
"losevideos/005841/5.png",
"losevideos/005841/6.png",
"losevideos/005841/7.png",
"winvideos/005841/0.png",
"winvideos/005841/1.png",
"winvideos/005841/2.png",
"winvideos/005841/3.png",
"winvideos/005841/4.png",
"winvideos/005841/5.png",
"winvideos/005841/6.png",
"winvideos/005841/7.png"
] |
Austrian traditional crowded Bar, Barkeeper behind bar looking at drunk guest k sitting on Bar hockers at bar, female waitress with blond hair walking to guest, behind Bar a logo of the beer brand "fukc-IT". | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Austrian traditional crowded Bar, Barkeeper behind bar looking at drunk guest k sitting on Bar hockers at bar, female waitress with blond hair walking to guest, behind Bar a logo of the beer brand "fukc-IT".]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003982/0.png",
"winvideos/003982/1.png",
"winvideos/003982/2.png",
"winvideos/003982/3.png",
"winvideos/003982/4.png",
"winvideos/003982/5.png",
"winvideos/003982/6.png",
"winvideos/003982/7.png",
"losevideos/003982/0.png",
"losevideos/003982/1.png",
"losevideos/003982/2.png",
"losevideos/003982/3.png",
"losevideos/003982/4.png",
"losevideos/003982/5.png",
"losevideos/003982/6.png",
"losevideos/003982/7.png"
] |
Once upon a time, there was a girl named Ajiao who lived in a small mountain village. Ajiao is a very smart and hardworking girl who often helps her parents with farming. Her parents left this world two years ago, leaving only Ajiao and her grandmother behind. Every day, my grandmother tells a mythological story to Ajiao, and she believes that these stories can prevent some misfortunes and diseases. But Ajiao doesn't believe these stories because she thinks they are all fictional and completely different from reality. Until one day, in a cave near the countryside, Ajiao discovered a strange field. There are many withered and yellow lotus flowers in the field, which Ajiao has never seen before. She knew that this flower had a very important meaning, but she didn't know what the secret was. Ajiao decided to rely on her intelligence to unravel this secret. After much consideration, she finally thought of searching for ancient books to find answers. She walked through the entire village and finally found an old book in an antique shop in the village. In the book,. | [
{
"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: [Once upon a time, there was a girl named Ajiao who lived in a small mountain village. Ajiao is a very smart and hardworking girl who often helps her parents with farming. Her parents left this world two years ago, leaving only Ajiao and her grandmother behind. Every day, my grandmother tells a mythological story to Ajiao, and she believes that these stories can prevent some misfortunes and diseases. But Ajiao doesn't believe these stories because she thinks they are all fictional and completely different from reality. Until one day, in a cave near the countryside, Ajiao discovered a strange field. There are many withered and yellow lotus flowers in the field, which Ajiao has never seen before. She knew that this flower had a very important meaning, but she didn't know what the secret was. Ajiao decided to rely on her intelligence to unravel this secret. After much consideration, she finally thought of searching for ancient books to find answers. She walked through the entire village and finally found an old book in an antique shop in the village. In the book,.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007317/0.png",
"losevideos/007317/1.png",
"losevideos/007317/2.png",
"losevideos/007317/3.png",
"losevideos/007317/4.png",
"losevideos/007317/5.png",
"losevideos/007317/6.png",
"losevideos/007317/7.png",
"winvideos/007317/0.png",
"winvideos/007317/1.png",
"winvideos/007317/2.png",
"winvideos/007317/3.png",
"winvideos/007317/4.png",
"winvideos/007317/5.png",
"winvideos/007317/6.png",
"winvideos/007317/7.png"
] |
Apollo 11's Journey: From Earth to the Moon" Take a detailed look at the timeline of events during the Apollo 11 mission, from liftoff to the lunar landing and return to Earth. | [
{
"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: [Apollo 11's Journey: From Earth to the Moon" Take a detailed look at the timeline of events during the Apollo 11 mission, from liftoff to the lunar landing and return to Earth.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006705/0.png",
"winvideos/006705/1.png",
"winvideos/006705/2.png",
"winvideos/006705/3.png",
"winvideos/006705/4.png",
"winvideos/006705/5.png",
"winvideos/006705/6.png",
"winvideos/006705/7.png",
"losevideos/006705/0.png",
"losevideos/006705/1.png",
"losevideos/006705/2.png",
"losevideos/006705/3.png",
"losevideos/006705/4.png",
"losevideos/006705/5.png",
"losevideos/006705/6.png",
"losevideos/006705/7.png"
] |
Donald trump kissing a horse, extremely romantic scene. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Donald trump kissing a horse, extremely romantic scene.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008142/0.png",
"losevideos/008142/1.png",
"losevideos/008142/2.png",
"losevideos/008142/3.png",
"losevideos/008142/4.png",
"losevideos/008142/5.png",
"losevideos/008142/6.png",
"losevideos/008142/7.png",
"winvideos/008142/0.png",
"winvideos/008142/1.png",
"winvideos/008142/2.png",
"winvideos/008142/3.png",
"winvideos/008142/4.png",
"winvideos/008142/5.png",
"winvideos/008142/6.png",
"winvideos/008142/7.png"
] |
terrifying demon face reveal horror. | [
{
"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: [terrifying demon face reveal horror.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002652/0.png",
"losevideos/002652/1.png",
"losevideos/002652/2.png",
"losevideos/002652/3.png",
"losevideos/002652/4.png",
"losevideos/002652/5.png",
"losevideos/002652/6.png",
"losevideos/002652/7.png",
"winvideos/002652/0.png",
"winvideos/002652/1.png",
"winvideos/002652/2.png",
"winvideos/002652/3.png",
"winvideos/002652/4.png",
"winvideos/002652/5.png",
"winvideos/002652/6.png",
"winvideos/002652/7.png"
] |
make move Message: 1 Attachment. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [make move Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001103/0.png",
"winvideos/001103/1.png",
"winvideos/001103/2.png",
"winvideos/001103/3.png",
"winvideos/001103/4.png",
"winvideos/001103/5.png",
"winvideos/001103/6.png",
"winvideos/001103/7.png",
"losevideos/001103/0.png",
"losevideos/001103/1.png",
"losevideos/001103/2.png",
"losevideos/001103/3.png",
"losevideos/001103/4.png",
"losevideos/001103/5.png",
"losevideos/001103/6.png",
"losevideos/001103/7.png"
] |
Craft an engaging, ultra-realistic video in ultra HD quality of friends at a rooftop café in Karachi. Set the camera with a wide aperture (f/2.8) for detailed shots of the friends' expressions and interactions, and a narrower aperture (f/8) for wider shots of the café setting. The ISO should be adjusted to capture the nighttime ambiance. Focus on the authenticity of the friends' emotions and the café’s atmosphere, integrating high-quality audio to mimic real conversations and laughter. | [
{
"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: [Craft an engaging, ultra-realistic video in ultra HD quality of friends at a rooftop café in Karachi. Set the camera with a wide aperture (f/2.8) for detailed shots of the friends' expressions and interactions, and a narrower aperture (f/8) for wider shots of the café setting. The ISO should be adjusted to capture the nighttime ambiance. Focus on the authenticity of the friends' emotions and the café’s atmosphere, integrating high-quality audio to mimic real conversations and laughter.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000745/0.png",
"losevideos/000745/1.png",
"losevideos/000745/2.png",
"losevideos/000745/3.png",
"losevideos/000745/4.png",
"losevideos/000745/5.png",
"losevideos/000745/6.png",
"losevideos/000745/7.png",
"winvideos/000745/0.png",
"winvideos/000745/1.png",
"winvideos/000745/2.png",
"winvideos/000745/3.png",
"winvideos/000745/4.png",
"winvideos/000745/5.png",
"winvideos/000745/6.png",
"winvideos/000745/7.png"
] |
city in the sky, camera rotate oclockwise Message: wilmar (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: [city in the sky, camera rotate oclockwise Message: wilmar (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006104/0.png",
"winvideos/006104/1.png",
"winvideos/006104/2.png",
"winvideos/006104/3.png",
"winvideos/006104/4.png",
"winvideos/006104/5.png",
"winvideos/006104/6.png",
"winvideos/006104/7.png",
"losevideos/006104/0.png",
"losevideos/006104/1.png",
"losevideos/006104/2.png",
"losevideos/006104/3.png",
"losevideos/006104/4.png",
"losevideos/006104/5.png",
"losevideos/006104/6.png",
"losevideos/006104/7.png"
] |
Giras blooming on the ground of the moon, background of galaxies and stars rotating around. | [
{
"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: [Giras blooming on the ground of the moon, background of galaxies and stars rotating around.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001936/0.png",
"losevideos/001936/1.png",
"losevideos/001936/2.png",
"losevideos/001936/3.png",
"losevideos/001936/4.png",
"losevideos/001936/5.png",
"losevideos/001936/6.png",
"losevideos/001936/7.png",
"winvideos/001936/0.png",
"winvideos/001936/1.png",
"winvideos/001936/2.png",
"winvideos/001936/3.png",
"winvideos/001936/4.png",
"winvideos/001936/5.png",
"winvideos/001936/6.png",
"winvideos/001936/7.png"
] |
futuristic interior-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: [futuristic interior-16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002563/0.png",
"losevideos/002563/1.png",
"losevideos/002563/2.png",
"losevideos/002563/3.png",
"losevideos/002563/4.png",
"losevideos/002563/5.png",
"losevideos/002563/6.png",
"losevideos/002563/7.png",
"winvideos/002563/0.png",
"winvideos/002563/1.png",
"winvideos/002563/2.png",
"winvideos/002563/3.png",
"winvideos/002563/4.png",
"winvideos/002563/5.png",
"winvideos/002563/6.png",
"winvideos/002563/7.png"
] |
fire smoking in the background
Dust in the air,ancient tamil fight their enemies sitting his horse,running man arounded in the background. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [fire smoking in the background\nDust in the air,ancient tamil fight their enemies sitting his horse,running man arounded in the background.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006446/0.png",
"winvideos/006446/1.png",
"winvideos/006446/2.png",
"winvideos/006446/3.png",
"winvideos/006446/4.png",
"winvideos/006446/5.png",
"winvideos/006446/6.png",
"winvideos/006446/7.png",
"losevideos/006446/0.png",
"losevideos/006446/1.png",
"losevideos/006446/2.png",
"losevideos/006446/3.png",
"losevideos/006446/4.png",
"losevideos/006446/5.png",
"losevideos/006446/6.png",
"losevideos/006446/7.png"
] |
(Spring has arrived, and all things are growing. Plants are growing, and pink flowers are blooming in a green leaf) -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: [(Spring has arrived, and all things are growing. Plants are growing, and pink flowers are blooming in a green leaf) -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002903/0.png",
"losevideos/002903/1.png",
"losevideos/002903/2.png",
"losevideos/002903/3.png",
"losevideos/002903/4.png",
"losevideos/002903/5.png",
"losevideos/002903/6.png",
"losevideos/002903/7.png",
"winvideos/002903/0.png",
"winvideos/002903/1.png",
"winvideos/002903/2.png",
"winvideos/002903/3.png",
"winvideos/002903/4.png",
"winvideos/002903/5.png",
"winvideos/002903/6.png",
"winvideos/002903/7.png"
] |
School, students go home, evening. | [
{
"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: [School, students go home, evening.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002067/0.png",
"losevideos/002067/1.png",
"losevideos/002067/2.png",
"losevideos/002067/3.png",
"losevideos/002067/4.png",
"losevideos/002067/5.png",
"losevideos/002067/6.png",
"losevideos/002067/7.png",
"winvideos/002067/0.png",
"winvideos/002067/1.png",
"winvideos/002067/2.png",
"winvideos/002067/3.png",
"winvideos/002067/4.png",
"winvideos/002067/5.png",
"winvideos/002067/6.png",
"winvideos/002067/7.png"
] |
Willem Dafoe destroying Israel like green goblin. | [
{
"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: [Willem Dafoe destroying Israel like green goblin.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005706/0.png",
"losevideos/005706/1.png",
"losevideos/005706/2.png",
"losevideos/005706/3.png",
"losevideos/005706/4.png",
"losevideos/005706/5.png",
"losevideos/005706/6.png",
"losevideos/005706/7.png",
"winvideos/005706/0.png",
"winvideos/005706/1.png",
"winvideos/005706/2.png",
"winvideos/005706/3.png",
"winvideos/005706/4.png",
"winvideos/005706/5.png",
"winvideos/005706/6.png",
"winvideos/005706/7.png"
] |
Hungry lione eat animal. | [
{
"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: [Hungry lione eat animal.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000757/0.png",
"losevideos/000757/1.png",
"losevideos/000757/2.png",
"losevideos/000757/3.png",
"losevideos/000757/4.png",
"losevideos/000757/5.png",
"losevideos/000757/6.png",
"losevideos/000757/7.png",
"winvideos/000757/0.png",
"winvideos/000757/1.png",
"winvideos/000757/2.png",
"winvideos/000757/3.png",
"winvideos/000757/4.png",
"winvideos/000757/5.png",
"winvideos/000757/6.png",
"winvideos/000757/7.png"
] |
CITY LIGHTS,NIGHT Message: VINCE AND IRA (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: [CITY LIGHTS,NIGHT Message: VINCE AND IRA (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000537/0.png",
"winvideos/000537/1.png",
"winvideos/000537/2.png",
"winvideos/000537/3.png",
"winvideos/000537/4.png",
"winvideos/000537/5.png",
"winvideos/000537/6.png",
"winvideos/000537/7.png",
"losevideos/000537/0.png",
"losevideos/000537/1.png",
"losevideos/000537/2.png",
"losevideos/000537/3.png",
"losevideos/000537/4.png",
"losevideos/000537/5.png",
"losevideos/000537/6.png",
"losevideos/000537/7.png"
] |
POV floating down a lazy river in a tropical resort in Cancun 4K -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: [POV floating down a lazy river in a tropical resort in Cancun 4K -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000506/0.png",
"winvideos/000506/1.png",
"winvideos/000506/2.png",
"winvideos/000506/3.png",
"winvideos/000506/4.png",
"winvideos/000506/5.png",
"winvideos/000506/6.png",
"winvideos/000506/7.png",
"losevideos/000506/0.png",
"losevideos/000506/1.png",
"losevideos/000506/2.png",
"losevideos/000506/3.png",
"losevideos/000506/4.png",
"losevideos/000506/5.png",
"losevideos/000506/6.png",
"losevideos/000506/7.png"
] |
nicola tesla creating a new invention. | [
{
"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: [nicola tesla creating a new invention.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002211/0.png",
"winvideos/002211/1.png",
"winvideos/002211/2.png",
"winvideos/002211/3.png",
"winvideos/002211/4.png",
"winvideos/002211/5.png",
"winvideos/002211/6.png",
"winvideos/002211/7.png",
"losevideos/002211/0.png",
"losevideos/002211/1.png",
"losevideos/002211/2.png",
"losevideos/002211/3.png",
"losevideos/002211/4.png",
"losevideos/002211/5.png",
"losevideos/002211/6.png",
"losevideos/002211/7.png"
] |
describe a very realistic symbolic image of demons in the lake of fire. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [describe a very realistic symbolic image of demons in the lake of fire.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007889/0.png",
"winvideos/007889/1.png",
"winvideos/007889/2.png",
"winvideos/007889/3.png",
"winvideos/007889/4.png",
"winvideos/007889/5.png",
"winvideos/007889/6.png",
"winvideos/007889/7.png",
"losevideos/007889/0.png",
"losevideos/007889/1.png",
"losevideos/007889/2.png",
"losevideos/007889/3.png",
"losevideos/007889/4.png",
"losevideos/007889/5.png",
"losevideos/007889/6.png",
"losevideos/007889/7.png"
] |
3d image Whimsical forest creatures, including a singing bluebird, gathering around the tea party. animation gs 20 motion 4 ,5 second long. | [
{
"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 image Whimsical forest creatures, including a singing bluebird, gathering around the tea party. animation gs 20 motion 4 ,5 second long.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000354/0.png",
"winvideos/000354/1.png",
"winvideos/000354/2.png",
"winvideos/000354/3.png",
"winvideos/000354/4.png",
"winvideos/000354/5.png",
"winvideos/000354/6.png",
"winvideos/000354/7.png",
"losevideos/000354/0.png",
"losevideos/000354/1.png",
"losevideos/000354/2.png",
"losevideos/000354/3.png",
"losevideos/000354/4.png",
"losevideos/000354/5.png",
"losevideos/000354/6.png",
"losevideos/000354/7.png"
] |
Joe Biden panic attack. | [
{
"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: [Joe Biden panic attack.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002099/0.png",
"losevideos/002099/1.png",
"losevideos/002099/2.png",
"losevideos/002099/3.png",
"losevideos/002099/4.png",
"losevideos/002099/5.png",
"losevideos/002099/6.png",
"losevideos/002099/7.png",
"winvideos/002099/0.png",
"winvideos/002099/1.png",
"winvideos/002099/2.png",
"winvideos/002099/3.png",
"winvideos/002099/4.png",
"winvideos/002099/5.png",
"winvideos/002099/6.png",
"winvideos/002099/7.png"
] |
mountains, blue sky, clouds --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: [mountains, blue sky, clouds --ar 9:16 -motion 4.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003039/0.png",
"winvideos/003039/1.png",
"winvideos/003039/2.png",
"winvideos/003039/3.png",
"winvideos/003039/4.png",
"winvideos/003039/5.png",
"winvideos/003039/6.png",
"winvideos/003039/7.png",
"losevideos/003039/0.png",
"losevideos/003039/1.png",
"losevideos/003039/2.png",
"losevideos/003039/3.png",
"losevideos/003039/4.png",
"losevideos/003039/5.png",
"losevideos/003039/6.png",
"losevideos/003039/7.png"
] |
HALLOWEEN PUMPKINS 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: [HALLOWEEN PUMPKINS Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004927/0.png",
"losevideos/004927/1.png",
"losevideos/004927/2.png",
"losevideos/004927/3.png",
"losevideos/004927/4.png",
"losevideos/004927/5.png",
"losevideos/004927/6.png",
"losevideos/004927/7.png",
"winvideos/004927/0.png",
"winvideos/004927/1.png",
"winvideos/004927/2.png",
"winvideos/004927/3.png",
"winvideos/004927/4.png",
"winvideos/004927/5.png",
"winvideos/004927/6.png",
"winvideos/004927/7.png"
] |
motorcycle is moving fast and man has no facial expression and no eyes closing, make younger -gs 22. | [
{
"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: [motorcycle is moving fast and man has no facial expression and no eyes closing, make younger -gs 22.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001914/0.png",
"losevideos/001914/1.png",
"losevideos/001914/2.png",
"losevideos/001914/3.png",
"losevideos/001914/4.png",
"losevideos/001914/5.png",
"losevideos/001914/6.png",
"losevideos/001914/7.png",
"winvideos/001914/0.png",
"winvideos/001914/1.png",
"winvideos/001914/2.png",
"winvideos/001914/3.png",
"winvideos/001914/4.png",
"winvideos/001914/5.png",
"winvideos/001914/6.png",
"winvideos/001914/7.png"
] |
ancient boat in the sea, Cinematic, realism, old movie style, old film style, Blair witch project style, vhs, 1970, the ring movie style -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: [ancient boat in the sea, Cinematic, realism, old movie style, old film style, Blair witch project style, vhs, 1970, the ring movie style -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009438/0.png",
"winvideos/009438/1.png",
"winvideos/009438/2.png",
"winvideos/009438/3.png",
"winvideos/009438/4.png",
"winvideos/009438/5.png",
"winvideos/009438/6.png",
"winvideos/009438/7.png",
"losevideos/009438/0.png",
"losevideos/009438/1.png",
"losevideos/009438/2.png",
"losevideos/009438/3.png",
"losevideos/009438/4.png",
"losevideos/009438/5.png",
"losevideos/009438/6.png",
"losevideos/009438/7.png"
] |
white background, white tiny minimal house model moving, motion-2 -ar 19:18. | [
{
"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: [white background, white tiny minimal house model moving, motion-2 -ar 19:18.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008518/0.png",
"winvideos/008518/1.png",
"winvideos/008518/2.png",
"winvideos/008518/3.png",
"winvideos/008518/4.png",
"winvideos/008518/5.png",
"winvideos/008518/6.png",
"winvideos/008518/7.png",
"losevideos/008518/0.png",
"losevideos/008518/1.png",
"losevideos/008518/2.png",
"losevideos/008518/3.png",
"losevideos/008518/4.png",
"losevideos/008518/5.png",
"losevideos/008518/6.png",
"losevideos/008518/7.png"
] |
Donut flying space. | [
{
"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: [Donut flying space.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000304/0.png",
"winvideos/000304/1.png",
"winvideos/000304/2.png",
"winvideos/000304/3.png",
"winvideos/000304/4.png",
"winvideos/000304/5.png",
"winvideos/000304/6.png",
"winvideos/000304/7.png",
"losevideos/000304/0.png",
"losevideos/000304/1.png",
"losevideos/000304/2.png",
"losevideos/000304/3.png",
"losevideos/000304/4.png",
"losevideos/000304/5.png",
"losevideos/000304/6.png",
"losevideos/000304/7.png"
] |
In Unreachable Worlds.
The planet of giant octopuses ecosystem, levitating in the air and underwater has an amazing fantasy atmosphere. | [
{
"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 Unreachable Worlds.\nThe planet of giant octopuses ecosystem, levitating in the air and underwater has an amazing fantasy atmosphere.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006376/0.png",
"losevideos/006376/1.png",
"losevideos/006376/2.png",
"losevideos/006376/3.png",
"losevideos/006376/4.png",
"losevideos/006376/5.png",
"losevideos/006376/6.png",
"losevideos/006376/7.png",
"winvideos/006376/0.png",
"winvideos/006376/1.png",
"winvideos/006376/2.png",
"winvideos/006376/3.png",
"winvideos/006376/4.png",
"winvideos/006376/5.png",
"winvideos/006376/6.png",
"winvideos/006376/7.png"
] |
a group of witches fighting a three-headed dragon 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: [a group of witches fighting a three-headed dragon in a forest.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004770/0.png",
"winvideos/004770/1.png",
"winvideos/004770/2.png",
"winvideos/004770/3.png",
"winvideos/004770/4.png",
"winvideos/004770/5.png",
"winvideos/004770/6.png",
"winvideos/004770/7.png",
"losevideos/004770/0.png",
"losevideos/004770/1.png",
"losevideos/004770/2.png",
"losevideos/004770/3.png",
"losevideos/004770/4.png",
"losevideos/004770/5.png",
"losevideos/004770/6.png",
"losevideos/004770/7.png"
] |
disease Message: CRISP AI (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: [disease Message: CRISP AI (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006730/0.png",
"losevideos/006730/1.png",
"losevideos/006730/2.png",
"losevideos/006730/3.png",
"losevideos/006730/4.png",
"losevideos/006730/5.png",
"losevideos/006730/6.png",
"losevideos/006730/7.png",
"winvideos/006730/0.png",
"winvideos/006730/1.png",
"winvideos/006730/2.png",
"winvideos/006730/3.png",
"winvideos/006730/4.png",
"winvideos/006730/5.png",
"winvideos/006730/6.png",
"winvideos/006730/7.png"
] |
early internet gif art. | [
{
"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: [early internet gif art.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000958/0.png",
"winvideos/000958/1.png",
"winvideos/000958/2.png",
"winvideos/000958/3.png",
"winvideos/000958/4.png",
"winvideos/000958/5.png",
"winvideos/000958/6.png",
"winvideos/000958/7.png",
"losevideos/000958/0.png",
"losevideos/000958/1.png",
"losevideos/000958/2.png",
"losevideos/000958/3.png",
"losevideos/000958/4.png",
"losevideos/000958/5.png",
"losevideos/000958/6.png",
"losevideos/000958/7.png"
] |
Ant-Man's sneakers. | [
{
"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: [Ant-Man's sneakers.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000747/0.png",
"losevideos/000747/1.png",
"losevideos/000747/2.png",
"losevideos/000747/3.png",
"losevideos/000747/4.png",
"losevideos/000747/5.png",
"losevideos/000747/6.png",
"losevideos/000747/7.png",
"winvideos/000747/0.png",
"winvideos/000747/1.png",
"winvideos/000747/2.png",
"winvideos/000747/3.png",
"winvideos/000747/4.png",
"winvideos/000747/5.png",
"winvideos/000747/6.png",
"winvideos/000747/7.png"
] |
black computer screen green display text programing user id numbers cinematic high quality. | [
{
"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 computer screen green display text programing user id numbers cinematic high quality.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000382/0.png",
"winvideos/000382/1.png",
"winvideos/000382/2.png",
"winvideos/000382/3.png",
"winvideos/000382/4.png",
"winvideos/000382/5.png",
"winvideos/000382/6.png",
"winvideos/000382/7.png",
"losevideos/000382/0.png",
"losevideos/000382/1.png",
"losevideos/000382/2.png",
"losevideos/000382/3.png",
"losevideos/000382/4.png",
"losevideos/000382/5.png",
"losevideos/000382/6.png",
"losevideos/000382/7.png"
] |
foto realista de um alienígena com um coelho no colo. | [
{
"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: [foto realista de um alienígena com um coelho no colo.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001913/0.png",
"losevideos/001913/1.png",
"losevideos/001913/2.png",
"losevideos/001913/3.png",
"losevideos/001913/4.png",
"losevideos/001913/5.png",
"losevideos/001913/6.png",
"losevideos/001913/7.png",
"winvideos/001913/0.png",
"winvideos/001913/1.png",
"winvideos/001913/2.png",
"winvideos/001913/3.png",
"winvideos/001913/4.png",
"winvideos/001913/5.png",
"winvideos/001913/6.png",
"winvideos/001913/7.png"
] |
Tom Hanks doing the washing up. Rubber gloves on. Old fashioned kitchen. Retro. Cinematic. HD. | [
{
"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: [Tom Hanks doing the washing up. Rubber gloves on. Old fashioned kitchen. Retro. Cinematic. HD.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006510/0.png",
"losevideos/006510/1.png",
"losevideos/006510/2.png",
"losevideos/006510/3.png",
"losevideos/006510/4.png",
"losevideos/006510/5.png",
"losevideos/006510/6.png",
"losevideos/006510/7.png",
"winvideos/006510/0.png",
"winvideos/006510/1.png",
"winvideos/006510/2.png",
"winvideos/006510/3.png",
"winvideos/006510/4.png",
"winvideos/006510/5.png",
"winvideos/006510/6.png",
"winvideos/006510/7.png"
] |
In a mesmerizing display of illuminated artistry, a digitally rendered modular migrant emerges amidst streaks of vibrant light in a captivating light painting photograph. The main subject of the image is Lord ram from Indian mythology, glowing with a pulsating, ethereal blue hue. This extraordinary image effortlessly immerses viewers in its remarkable quality, transporting them to a realm of ancient india. | [
{
"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 a mesmerizing display of illuminated artistry, a digitally rendered modular migrant emerges amidst streaks of vibrant light in a captivating light painting photograph. The main subject of the image is Lord ram from Indian mythology, glowing with a pulsating, ethereal blue hue. This extraordinary image effortlessly immerses viewers in its remarkable quality, transporting them to a realm of ancient india.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002474/0.png",
"winvideos/002474/1.png",
"winvideos/002474/2.png",
"winvideos/002474/3.png",
"winvideos/002474/4.png",
"winvideos/002474/5.png",
"winvideos/002474/6.png",
"winvideos/002474/7.png",
"losevideos/002474/0.png",
"losevideos/002474/1.png",
"losevideos/002474/2.png",
"losevideos/002474/3.png",
"losevideos/002474/4.png",
"losevideos/002474/5.png",
"losevideos/002474/6.png",
"losevideos/002474/7.png"
] |
Liminal Space of tall surreal monsters, bright colors, 1960s film quality and grain valley of the living, —ar 3:2. | [
{
"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: [Liminal Space of tall surreal monsters, bright colors, 1960s film quality and grain valley of the living, —ar 3:2.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000599/0.png",
"losevideos/000599/1.png",
"losevideos/000599/2.png",
"losevideos/000599/3.png",
"losevideos/000599/4.png",
"losevideos/000599/5.png",
"losevideos/000599/6.png",
"losevideos/000599/7.png",
"winvideos/000599/0.png",
"winvideos/000599/1.png",
"winvideos/000599/2.png",
"winvideos/000599/3.png",
"winvideos/000599/4.png",
"winvideos/000599/5.png",
"winvideos/000599/6.png",
"winvideos/000599/7.png"
] |
relaxing old vhs footage talks you to sleep weird adult swim commercial pop up ad comforting scary. | [
{
"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: [relaxing old vhs footage talks you to sleep weird adult swim commercial pop up ad comforting scary.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002638/0.png",
"winvideos/002638/1.png",
"winvideos/002638/2.png",
"winvideos/002638/3.png",
"winvideos/002638/4.png",
"winvideos/002638/5.png",
"winvideos/002638/6.png",
"winvideos/002638/7.png",
"losevideos/002638/0.png",
"losevideos/002638/1.png",
"losevideos/002638/2.png",
"losevideos/002638/3.png",
"losevideos/002638/4.png",
"losevideos/002638/5.png",
"losevideos/002638/6.png",
"losevideos/002638/7.png"
] |
a very beautiful young woman with long black hair, beautiful body shape volumous chest Wearing a saree. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a very beautiful young woman with long black hair, beautiful body shape volumous chest Wearing a saree.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003764/0.png",
"winvideos/003764/1.png",
"winvideos/003764/2.png",
"winvideos/003764/3.png",
"winvideos/003764/4.png",
"winvideos/003764/5.png",
"winvideos/003764/6.png",
"winvideos/003764/7.png",
"losevideos/003764/0.png",
"losevideos/003764/1.png",
"losevideos/003764/2.png",
"losevideos/003764/3.png",
"losevideos/003764/4.png",
"losevideos/003764/5.png",
"losevideos/003764/6.png",
"losevideos/003764/7.png"
] |
1950s super 8 psychedelic colorful footage of an otherworldy sunset in space, liminal, with a line of trees on the 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: [1950s super 8 psychedelic colorful footage of an otherworldy sunset in space, liminal, with a line of trees on the horizon.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007456/0.png",
"winvideos/007456/1.png",
"winvideos/007456/2.png",
"winvideos/007456/3.png",
"winvideos/007456/4.png",
"winvideos/007456/5.png",
"winvideos/007456/6.png",
"winvideos/007456/7.png",
"losevideos/007456/0.png",
"losevideos/007456/1.png",
"losevideos/007456/2.png",
"losevideos/007456/3.png",
"losevideos/007456/4.png",
"losevideos/007456/5.png",
"losevideos/007456/6.png",
"losevideos/007456/7.png"
] |
zerstören straßenblockade Panzer Jugoslawien Photorealismus. | [
{
"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: [zerstören straßenblockade Panzer Jugoslawien Photorealismus.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009244/0.png",
"winvideos/009244/1.png",
"winvideos/009244/2.png",
"winvideos/009244/3.png",
"winvideos/009244/4.png",
"winvideos/009244/5.png",
"winvideos/009244/6.png",
"winvideos/009244/7.png",
"losevideos/009244/0.png",
"losevideos/009244/1.png",
"losevideos/009244/2.png",
"losevideos/009244/3.png",
"losevideos/009244/4.png",
"losevideos/009244/5.png",
"losevideos/009244/6.png",
"losevideos/009244/7.png"
] |
Trading view that goes high up. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Trading view that goes high up.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003449/0.png",
"winvideos/003449/1.png",
"winvideos/003449/2.png",
"winvideos/003449/3.png",
"winvideos/003449/4.png",
"winvideos/003449/5.png",
"winvideos/003449/6.png",
"winvideos/003449/7.png",
"losevideos/003449/0.png",
"losevideos/003449/1.png",
"losevideos/003449/2.png",
"losevideos/003449/3.png",
"losevideos/003449/4.png",
"losevideos/003449/5.png",
"losevideos/003449/6.png",
"losevideos/003449/7.png"
] |
long shot, front view, centered, daytime, an alien with the head of a gray shark, with a muscular appearance, with a serious look, walking in a futuristic metropolis alien primary tones, realistic -neg "deformation, distortion, rays of light, beam of light, smoke, duplicate car, side camera, rear view camera, rear photo, coastal photo, rear photo, deformed body, deformed hand, people" -motion 1 -gs 12 -fps 24 -hide. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [long shot, front view, centered, daytime, an alien with the head of a gray shark, with a muscular appearance, with a serious look, walking in a futuristic metropolis alien primary tones, realistic -neg "deformation, distortion, rays of light, beam of light, smoke, duplicate car, side camera, rear view camera, rear photo, coastal photo, rear photo, deformed body, deformed hand, people" -motion 1 -gs 12 -fps 24 -hide.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004625/0.png",
"winvideos/004625/1.png",
"winvideos/004625/2.png",
"winvideos/004625/3.png",
"winvideos/004625/4.png",
"winvideos/004625/5.png",
"winvideos/004625/6.png",
"winvideos/004625/7.png",
"losevideos/004625/0.png",
"losevideos/004625/1.png",
"losevideos/004625/2.png",
"losevideos/004625/3.png",
"losevideos/004625/4.png",
"losevideos/004625/5.png",
"losevideos/004625/6.png",
"losevideos/004625/7.png"
] |
lofi albumart -ar 9:16 -motion 2 Message: avataum (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: [lofi albumart -ar 9:16 -motion 2 Message: avataum (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000496/0.png",
"losevideos/000496/1.png",
"losevideos/000496/2.png",
"losevideos/000496/3.png",
"losevideos/000496/4.png",
"losevideos/000496/5.png",
"losevideos/000496/6.png",
"losevideos/000496/7.png",
"winvideos/000496/0.png",
"winvideos/000496/1.png",
"winvideos/000496/2.png",
"winvideos/000496/3.png",
"winvideos/000496/4.png",
"winvideos/000496/5.png",
"winvideos/000496/6.png",
"winvideos/000496/7.png"
] |
cartoon style armor girl in school. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cartoon style armor girl in school.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007189/0.png",
"winvideos/007189/1.png",
"winvideos/007189/2.png",
"winvideos/007189/3.png",
"winvideos/007189/4.png",
"winvideos/007189/5.png",
"winvideos/007189/6.png",
"winvideos/007189/7.png",
"losevideos/007189/0.png",
"losevideos/007189/1.png",
"losevideos/007189/2.png",
"losevideos/007189/3.png",
"losevideos/007189/4.png",
"losevideos/007189/5.png",
"losevideos/007189/6.png",
"losevideos/007189/7.png"
] |
Depict microorganisms as vibrant, glowing fireflies, creating a lively display of colors around the trio. | [
{
"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: [Depict microorganisms as vibrant, glowing fireflies, creating a lively display of colors around the trio.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003694/0.png",
"winvideos/003694/1.png",
"winvideos/003694/2.png",
"winvideos/003694/3.png",
"winvideos/003694/4.png",
"winvideos/003694/5.png",
"winvideos/003694/6.png",
"winvideos/003694/7.png",
"losevideos/003694/0.png",
"losevideos/003694/1.png",
"losevideos/003694/2.png",
"losevideos/003694/3.png",
"losevideos/003694/4.png",
"losevideos/003694/5.png",
"losevideos/003694/6.png",
"losevideos/003694/7.png"
] |
image:3D_Animation_Style_Illustrate_the_significance_of_the_Stoning_3.jpg. | [
{
"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: [image:3D_Animation_Style_Illustrate_the_significance_of_the_Stoning_3.jpg.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009314/0.png",
"losevideos/009314/1.png",
"losevideos/009314/2.png",
"losevideos/009314/3.png",
"losevideos/009314/4.png",
"losevideos/009314/5.png",
"losevideos/009314/6.png",
"losevideos/009314/7.png",
"winvideos/009314/0.png",
"winvideos/009314/1.png",
"winvideos/009314/2.png",
"winvideos/009314/3.png",
"winvideos/009314/4.png",
"winvideos/009314/5.png",
"winvideos/009314/6.png",
"winvideos/009314/7.png"
] |
a man is walking in the belly of a snake. | [
{
"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 man is walking in the belly of a snake.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000646/0.png",
"losevideos/000646/1.png",
"losevideos/000646/2.png",
"losevideos/000646/3.png",
"losevideos/000646/4.png",
"losevideos/000646/5.png",
"losevideos/000646/6.png",
"losevideos/000646/7.png",
"winvideos/000646/0.png",
"winvideos/000646/1.png",
"winvideos/000646/2.png",
"winvideos/000646/3.png",
"winvideos/000646/4.png",
"winvideos/000646/5.png",
"winvideos/000646/6.png",
"winvideos/000646/7.png"
] |
uma toranja usando um o fone de ouvido dentro de um quarto, estilo cartoon pixar. | [
{
"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: [uma toranja usando um o fone de ouvido dentro de um quarto, estilo cartoon pixar.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002656/0.png",
"winvideos/002656/1.png",
"winvideos/002656/2.png",
"winvideos/002656/3.png",
"winvideos/002656/4.png",
"winvideos/002656/5.png",
"winvideos/002656/6.png",
"winvideos/002656/7.png",
"losevideos/002656/0.png",
"losevideos/002656/1.png",
"losevideos/002656/2.png",
"losevideos/002656/3.png",
"losevideos/002656/4.png",
"losevideos/002656/5.png",
"losevideos/002656/6.png",
"losevideos/002656/7.png"
] |
Monkey D. Luffy play basketball with kobe. | [
{
"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: [Monkey D. Luffy play basketball with kobe.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001313/0.png",
"losevideos/001313/1.png",
"losevideos/001313/2.png",
"losevideos/001313/3.png",
"losevideos/001313/4.png",
"losevideos/001313/5.png",
"losevideos/001313/6.png",
"losevideos/001313/7.png",
"winvideos/001313/0.png",
"winvideos/001313/1.png",
"winvideos/001313/2.png",
"winvideos/001313/3.png",
"winvideos/001313/4.png",
"winvideos/001313/5.png",
"winvideos/001313/6.png",
"winvideos/001313/7.png"
] |
taking images full clearly. | [
{
"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: [taking images full clearly.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009580/0.png",
"losevideos/009580/1.png",
"losevideos/009580/2.png",
"losevideos/009580/3.png",
"losevideos/009580/4.png",
"losevideos/009580/5.png",
"losevideos/009580/6.png",
"losevideos/009580/7.png",
"winvideos/009580/0.png",
"winvideos/009580/1.png",
"winvideos/009580/2.png",
"winvideos/009580/3.png",
"winvideos/009580/4.png",
"winvideos/009580/5.png",
"winvideos/009580/6.png",
"winvideos/009580/7.png"
] |
photograph of dancing ballerina in yellow tulle.Arabesque pose. -motion 2 -ar 2:1. | [
{
"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: [photograph of dancing ballerina in yellow tulle.Arabesque pose. -motion 2 -ar 2:1.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006629/0.png",
"losevideos/006629/1.png",
"losevideos/006629/2.png",
"losevideos/006629/3.png",
"losevideos/006629/4.png",
"losevideos/006629/5.png",
"losevideos/006629/6.png",
"losevideos/006629/7.png",
"winvideos/006629/0.png",
"winvideos/006629/1.png",
"winvideos/006629/2.png",
"winvideos/006629/3.png",
"winvideos/006629/4.png",
"winvideos/006629/5.png",
"winvideos/006629/6.png",
"winvideos/006629/7.png"
] |
Transition to 3D-animated friends: Diverse friends gather by a reflective pond, their cool-toned reflections shimmering on the water's surface. They engage in various tranquil activities.],Duration: 15 seconds,ratio 16:9, front 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: [Transition to 3D-animated friends: Diverse friends gather by a reflective pond, their cool-toned reflections shimmering on the water's surface. They engage in various tranquil activities.],Duration: 15 seconds,ratio 16:9, front view.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001337/0.png",
"losevideos/001337/1.png",
"losevideos/001337/2.png",
"losevideos/001337/3.png",
"losevideos/001337/4.png",
"losevideos/001337/5.png",
"losevideos/001337/6.png",
"losevideos/001337/7.png",
"winvideos/001337/0.png",
"winvideos/001337/1.png",
"winvideos/001337/2.png",
"winvideos/001337/3.png",
"winvideos/001337/4.png",
"winvideos/001337/5.png",
"winvideos/001337/6.png",
"winvideos/001337/7.png"
] |
Autumn, sunny, girl smiling, 4k, high detail and contrast -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: [Autumn, sunny, girl smiling, 4k, high detail and contrast -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007758/0.png",
"losevideos/007758/1.png",
"losevideos/007758/2.png",
"losevideos/007758/3.png",
"losevideos/007758/4.png",
"losevideos/007758/5.png",
"losevideos/007758/6.png",
"losevideos/007758/7.png",
"winvideos/007758/0.png",
"winvideos/007758/1.png",
"winvideos/007758/2.png",
"winvideos/007758/3.png",
"winvideos/007758/4.png",
"winvideos/007758/5.png",
"winvideos/007758/6.png",
"winvideos/007758/7.png"
] |
Arjun performing his daily Bhakti Puja, surrounded by vibrant flowers and a serene atmosphere. The sunlight streaming in symbolizes the divine presence. Arjun's devotion grew stronger with each passing day. He believed that through Bhakti Puja, he could establish a direct connection with the divine and find solace in the trials of life. | [
{
"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: [Arjun performing his daily Bhakti Puja, surrounded by vibrant flowers and a serene atmosphere. The sunlight streaming in symbolizes the divine presence. Arjun's devotion grew stronger with each passing day. He believed that through Bhakti Puja, he could establish a direct connection with the divine and find solace in the trials of life.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006037/0.png",
"winvideos/006037/1.png",
"winvideos/006037/2.png",
"winvideos/006037/3.png",
"winvideos/006037/4.png",
"winvideos/006037/5.png",
"winvideos/006037/6.png",
"winvideos/006037/7.png",
"losevideos/006037/0.png",
"losevideos/006037/1.png",
"losevideos/006037/2.png",
"losevideos/006037/3.png",
"losevideos/006037/4.png",
"losevideos/006037/5.png",
"losevideos/006037/6.png",
"losevideos/006037/7.png"
] |
extreme details of a hyper realistic growing red and white dotted mushrooms with a katana blade on a pebble beach with splashing white slime and clashing slime waves with haunting horror lighting outdoors in the style of an expensive action movie, 8k, realistic -ar 16:9. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [extreme details of a hyper realistic growing red and white dotted mushrooms with a katana blade on a pebble beach with splashing white slime and clashing slime waves with haunting horror lighting outdoors in the style of an expensive action movie, 8k, realistic -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006466/0.png",
"losevideos/006466/1.png",
"losevideos/006466/2.png",
"losevideos/006466/3.png",
"losevideos/006466/4.png",
"losevideos/006466/5.png",
"losevideos/006466/6.png",
"losevideos/006466/7.png",
"winvideos/006466/0.png",
"winvideos/006466/1.png",
"winvideos/006466/2.png",
"winvideos/006466/3.png",
"winvideos/006466/4.png",
"winvideos/006466/5.png",
"winvideos/006466/6.png",
"winvideos/006466/7.png"
] |
Vegas years Elvis Presley as Santa flying sleigh pull by reindeers, xmas card style. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Vegas years Elvis Presley as Santa flying sleigh pull by reindeers, xmas card style.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009285/0.png",
"losevideos/009285/1.png",
"losevideos/009285/2.png",
"losevideos/009285/3.png",
"losevideos/009285/4.png",
"losevideos/009285/5.png",
"losevideos/009285/6.png",
"losevideos/009285/7.png",
"winvideos/009285/0.png",
"winvideos/009285/1.png",
"winvideos/009285/2.png",
"winvideos/009285/3.png",
"winvideos/009285/4.png",
"winvideos/009285/5.png",
"winvideos/009285/6.png",
"winvideos/009285/7.png"
] |
A close up of a giant collection of dozens of boxes of cereal Message: COLLECTORS IN SPACE (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: [A close up of a giant collection of dozens of boxes of cereal Message: COLLECTORS IN SPACE (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001175/0.png",
"losevideos/001175/1.png",
"losevideos/001175/2.png",
"losevideos/001175/3.png",
"losevideos/001175/4.png",
"losevideos/001175/5.png",
"losevideos/001175/6.png",
"losevideos/001175/7.png",
"winvideos/001175/0.png",
"winvideos/001175/1.png",
"winvideos/001175/2.png",
"winvideos/001175/3.png",
"winvideos/001175/4.png",
"winvideos/001175/5.png",
"winvideos/001175/6.png",
"winvideos/001175/7.png"
] |
以航拍的空中俯视视角，一辆汽车以从下至上的方向，行驶在一片广袤无垠的深林中的一条笔直的公路上，行使过程中每5秒钟体现一个季节变化，四个季节依次是春、夏、秋、冬，车辆不断往前行驶，只有季节场景在变化。. | [
{
"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: [以航拍的空中俯视视角，一辆汽车以从下至上的方向，行驶在一片广袤无垠的深林中的一条笔直的公路上，行使过程中每5秒钟体现一个季节变化，四个季节依次是春、夏、秋、冬，车辆不断往前行驶，只有季节场景在变化。.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004058/0.png",
"winvideos/004058/1.png",
"winvideos/004058/2.png",
"winvideos/004058/3.png",
"winvideos/004058/4.png",
"winvideos/004058/5.png",
"winvideos/004058/6.png",
"winvideos/004058/7.png",
"losevideos/004058/0.png",
"losevideos/004058/1.png",
"losevideos/004058/2.png",
"losevideos/004058/3.png",
"losevideos/004058/4.png",
"losevideos/004058/5.png",
"losevideos/004058/6.png",
"losevideos/004058/7.png"
] |
A horror 90s film from a 1990s Screen grab 90s, about a alien species of Giant Brains Floating At The lake, a son gets taken away by creatures tendrils, dark scene moment,their terror an, Uncanny, Dark Horror , liminal aesthetic with 360p graphics, Surrealism, intricately detailed, dark web video, realistic Occult film. | [
{
"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 horror 90s film from a 1990s Screen grab 90s, about a alien species of Giant Brains Floating At The lake, a son gets taken away by creatures tendrils, dark scene moment,their terror an, Uncanny, Dark Horror , liminal aesthetic with 360p graphics, Surrealism, intricately detailed, dark web video, realistic Occult film.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005824/0.png",
"losevideos/005824/1.png",
"losevideos/005824/2.png",
"losevideos/005824/3.png",
"losevideos/005824/4.png",
"losevideos/005824/5.png",
"losevideos/005824/6.png",
"losevideos/005824/7.png",
"winvideos/005824/0.png",
"winvideos/005824/1.png",
"winvideos/005824/2.png",
"winvideos/005824/3.png",
"winvideos/005824/4.png",
"winvideos/005824/5.png",
"winvideos/005824/6.png",
"winvideos/005824/7.png"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.