prompt
stringlengths 4
8.37k
| conversations
listlengths 2
2
| images
listlengths 16
16
|
|---|---|---|
old tv, and people in the background, in the style of surrealist subconsciousness, wandering eye, inverted black and white, lasar segall, blink-and-you-miss-it detail, shiny eyes, 1970–present.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [old tv, and people in the background, in the style of surrealist subconsciousness, wandering eye, inverted black and white, lasar segall, blink-and-you-miss-it detail, shiny eyes, 1970–present.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/000564/0.png",
"winvideos/000564/1.png",
"winvideos/000564/2.png",
"winvideos/000564/3.png",
"winvideos/000564/4.png",
"winvideos/000564/5.png",
"winvideos/000564/6.png",
"winvideos/000564/7.png",
"losevideos/000564/0.png",
"losevideos/000564/1.png",
"losevideos/000564/2.png",
"losevideos/000564/3.png",
"losevideos/000564/4.png",
"losevideos/000564/5.png",
"losevideos/000564/6.png",
"losevideos/000564/7.png"
] |
disturbing person walks through field towards camera at night.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [disturbing person walks through field towards camera at night.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/002021/0.png",
"winvideos/002021/1.png",
"winvideos/002021/2.png",
"winvideos/002021/3.png",
"winvideos/002021/4.png",
"winvideos/002021/5.png",
"winvideos/002021/6.png",
"winvideos/002021/7.png",
"losevideos/002021/0.png",
"losevideos/002021/1.png",
"losevideos/002021/2.png",
"losevideos/002021/3.png",
"losevideos/002021/4.png",
"losevideos/002021/5.png",
"losevideos/002021/6.png",
"losevideos/002021/7.png"
] |
In 1970, there was an accident involving two cars.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 1970, there was an accident involving two cars.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005942/0.png",
"winvideos/005942/1.png",
"winvideos/005942/2.png",
"winvideos/005942/3.png",
"winvideos/005942/4.png",
"winvideos/005942/5.png",
"winvideos/005942/6.png",
"winvideos/005942/7.png",
"losevideos/005942/0.png",
"losevideos/005942/1.png",
"losevideos/005942/2.png",
"losevideos/005942/3.png",
"losevideos/005942/4.png",
"losevideos/005942/5.png",
"losevideos/005942/6.png",
"losevideos/005942/7.png"
] |
Pikachu snowboarding.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Pikachu snowboarding.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005578/0.png",
"winvideos/005578/1.png",
"winvideos/005578/2.png",
"winvideos/005578/3.png",
"winvideos/005578/4.png",
"winvideos/005578/5.png",
"winvideos/005578/6.png",
"winvideos/005578/7.png",
"losevideos/005578/0.png",
"losevideos/005578/1.png",
"losevideos/005578/2.png",
"losevideos/005578/3.png",
"losevideos/005578/4.png",
"losevideos/005578/5.png",
"losevideos/005578/6.png",
"losevideos/005578/7.png"
] |
cinematic,7 i want to create 10 images with jesus and his apostles talking and walking with movements.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cinematic,7 i want to create 10 images with jesus and his apostles talking and walking with movements.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008299/0.png",
"winvideos/008299/1.png",
"winvideos/008299/2.png",
"winvideos/008299/3.png",
"winvideos/008299/4.png",
"winvideos/008299/5.png",
"winvideos/008299/6.png",
"winvideos/008299/7.png",
"losevideos/008299/0.png",
"losevideos/008299/1.png",
"losevideos/008299/2.png",
"losevideos/008299/3.png",
"losevideos/008299/4.png",
"losevideos/008299/5.png",
"losevideos/008299/6.png",
"losevideos/008299/7.png"
] |
Color is arbitrary.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Color is arbitrary.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/003914/0.png",
"losevideos/003914/1.png",
"losevideos/003914/2.png",
"losevideos/003914/3.png",
"losevideos/003914/4.png",
"losevideos/003914/5.png",
"losevideos/003914/6.png",
"losevideos/003914/7.png",
"winvideos/003914/0.png",
"winvideos/003914/1.png",
"winvideos/003914/2.png",
"winvideos/003914/3.png",
"winvideos/003914/4.png",
"winvideos/003914/5.png",
"winvideos/003914/6.png",
"winvideos/003914/7.png"
] |
a begger and rich man.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 begger and rich man.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/002229/0.png",
"winvideos/002229/1.png",
"winvideos/002229/2.png",
"winvideos/002229/3.png",
"winvideos/002229/4.png",
"winvideos/002229/5.png",
"winvideos/002229/6.png",
"winvideos/002229/7.png",
"losevideos/002229/0.png",
"losevideos/002229/1.png",
"losevideos/002229/2.png",
"losevideos/002229/3.png",
"losevideos/002229/4.png",
"losevideos/002229/5.png",
"losevideos/002229/6.png",
"losevideos/002229/7.png"
] |
A shocking video captures the scene during the day in Barcelona. A disc-shaped UFO with large lights moves at high speed and intentionally hits one of the towers of the Basilica of the Sagrada Familia. The collision creates a massive explosion and a shower of burning debris rains down on the city. The towers of the Basilica abruptly collapse in an apocalyptic demolition, while the alien ship shows signs of damage with short circuits and flickering lights. The resulting explosion creates a cloud of dust and fire that spreads rapidly across the city, leaving the Basilica completely destroyed by the end of the scene. This description focuses on the collision, explosion and dramatic destruction of the Sagrada Familia Basilica, following your instructions to provide a more impactful and realistic representation of the 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: [A shocking video captures the scene during the day in Barcelona. A disc-shaped UFO with large lights moves at high speed and intentionally hits one of the towers of the Basilica of the Sagrada Familia. The collision creates a massive explosion and a shower of burning debris rains down on the city. The towers of the Basilica abruptly collapse in an apocalyptic demolition, while the alien ship shows signs of damage with short circuits and flickering lights. The resulting explosion creates a cloud of dust and fire that spreads rapidly across the city, leaving the Basilica completely destroyed by the end of the scene. This description focuses on the collision, explosion and dramatic destruction of the Sagrada Familia Basilica, following your instructions to provide a more impactful and realistic representation of the scene.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008995/0.png",
"losevideos/008995/1.png",
"losevideos/008995/2.png",
"losevideos/008995/3.png",
"losevideos/008995/4.png",
"losevideos/008995/5.png",
"losevideos/008995/6.png",
"losevideos/008995/7.png",
"winvideos/008995/0.png",
"winvideos/008995/1.png",
"winvideos/008995/2.png",
"winvideos/008995/3.png",
"winvideos/008995/4.png",
"winvideos/008995/5.png",
"winvideos/008995/6.png",
"winvideos/008995/7.png"
] |
engineer and robot performing an inspection together.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [engineer and robot performing an inspection together.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008607/0.png",
"losevideos/008607/1.png",
"losevideos/008607/2.png",
"losevideos/008607/3.png",
"losevideos/008607/4.png",
"losevideos/008607/5.png",
"losevideos/008607/6.png",
"losevideos/008607/7.png",
"winvideos/008607/0.png",
"winvideos/008607/1.png",
"winvideos/008607/2.png",
"winvideos/008607/3.png",
"winvideos/008607/4.png",
"winvideos/008607/5.png",
"winvideos/008607/6.png",
"winvideos/008607/7.png"
] |
1、 extreme loneliness,viloet and gold colors,in the style of impressionist light studies ,expressive use of line,japonisme 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: [1、\textreme loneliness,viloet and gold colors,in the style of impressionist light studies ,expressive use of line,japonisme Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/005276/0.png",
"losevideos/005276/1.png",
"losevideos/005276/2.png",
"losevideos/005276/3.png",
"losevideos/005276/4.png",
"losevideos/005276/5.png",
"losevideos/005276/6.png",
"losevideos/005276/7.png",
"winvideos/005276/0.png",
"winvideos/005276/1.png",
"winvideos/005276/2.png",
"winvideos/005276/3.png",
"winvideos/005276/4.png",
"winvideos/005276/5.png",
"winvideos/005276/6.png",
"winvideos/005276/7.png"
] |
In a circle upon the sand, the candles flame lightly dances across the dunes, shadows within shadows, a crimson river flows, 8k, high octane render.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 circle upon the sand, the candles flame lightly dances across the dunes, shadows within shadows, a crimson river flows, 8k, high octane render.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/004409/0.png",
"losevideos/004409/1.png",
"losevideos/004409/2.png",
"losevideos/004409/3.png",
"losevideos/004409/4.png",
"losevideos/004409/5.png",
"losevideos/004409/6.png",
"losevideos/004409/7.png",
"winvideos/004409/0.png",
"winvideos/004409/1.png",
"winvideos/004409/2.png",
"winvideos/004409/3.png",
"winvideos/004409/4.png",
"winvideos/004409/5.png",
"winvideos/004409/6.png",
"winvideos/004409/7.png"
] |
3 mans with beards playing guitars sitting near the 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: [3 mans with beards playing guitars sitting near the fire.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/009929/0.png",
"winvideos/009929/1.png",
"winvideos/009929/2.png",
"winvideos/009929/3.png",
"winvideos/009929/4.png",
"winvideos/009929/5.png",
"winvideos/009929/6.png",
"winvideos/009929/7.png",
"losevideos/009929/0.png",
"losevideos/009929/1.png",
"losevideos/009929/2.png",
"losevideos/009929/3.png",
"losevideos/009929/4.png",
"losevideos/009929/5.png",
"losevideos/009929/6.png",
"losevideos/009929/7.png"
] |
realistic video of a very beautiful girl with the crown of Miss France 2023 walking towards the camera at full height. walking through the streets of Spain the temperature is +30 more realism.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [realistic video of a very beautiful girl with the crown of Miss France 2023 walking towards the camera at full height. walking through the streets of Spain the temperature is +30 more realism.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/006383/0.png",
"losevideos/006383/1.png",
"losevideos/006383/2.png",
"losevideos/006383/3.png",
"losevideos/006383/4.png",
"losevideos/006383/5.png",
"losevideos/006383/6.png",
"losevideos/006383/7.png",
"winvideos/006383/0.png",
"winvideos/006383/1.png",
"winvideos/006383/2.png",
"winvideos/006383/3.png",
"winvideos/006383/4.png",
"winvideos/006383/5.png",
"winvideos/006383/6.png",
"winvideos/006383/7.png"
] |
medieval physician treating a patient with tools. Camera moving from left to right.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [medieval physician treating a patient with tools. Camera moving from left to right.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008417/0.png",
"winvideos/008417/1.png",
"winvideos/008417/2.png",
"winvideos/008417/3.png",
"winvideos/008417/4.png",
"winvideos/008417/5.png",
"winvideos/008417/6.png",
"winvideos/008417/7.png",
"losevideos/008417/0.png",
"losevideos/008417/1.png",
"losevideos/008417/2.png",
"losevideos/008417/3.png",
"losevideos/008417/4.png",
"losevideos/008417/5.png",
"losevideos/008417/6.png",
"losevideos/008417/7.png"
] |
hntai.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [hntai.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/007113/0.png",
"winvideos/007113/1.png",
"winvideos/007113/2.png",
"winvideos/007113/3.png",
"winvideos/007113/4.png",
"winvideos/007113/5.png",
"winvideos/007113/6.png",
"winvideos/007113/7.png",
"losevideos/007113/0.png",
"losevideos/007113/1.png",
"losevideos/007113/2.png",
"losevideos/007113/3.png",
"losevideos/007113/4.png",
"losevideos/007113/5.png",
"losevideos/007113/6.png",
"losevideos/007113/7.png"
] |
Generate a highly detailed and hyper-realistic image for Halloween, capturing a serene and cozy room in a minimalist wooden style on a rainy night. The room should convey a sense of beauty and comfort. Picture a spacious room with expansive windows, all adorned with glistening raindrops. The interior should be softly illuminated with just a few scattered lights. At the center of the room, a fireplace is lit, and its fire dances with a mesmerizing flicker, casting a warm, golden glow that accentuates the room's coziness. Candles should be strategically placed around the room, providing additional subtle lighting. Halloween pumpkins should serve as decorative elements, contributing to the spooky yet inviting ambiance. The overall atmosphere should feel calm and relaxing, suggesting that it's an ideal setting for quiet activities such as reading or enjoying music on a Halloween night. Outside the window is the view of New York City, with the cityscape dark, romantic, the level of detail should be impeccable, capturing the essence of a rainy autumn night outside of the room, NO RAIN INSIDE OF THE LIVING ROOM, THE INTERIOR IS DRY, THE RAIN IS OUTSIDE OF THE LIVING ROOM, NO ZOOM MOVEMENT IN THE SCENE -- V 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: [Generate a highly detailed and hyper-realistic image for Halloween, capturing a serene and cozy room in a minimalist wooden style on a rainy night. The room should convey a sense of beauty and comfort. Picture a spacious room with expansive windows, all adorned with glistening raindrops. The interior should be softly illuminated with just a few scattered lights. At the center of the room, a fireplace is lit, and its fire dances with a mesmerizing flicker, casting a warm, golden glow that accentuates the room's coziness. Candles should be strategically placed around the room, providing additional subtle lighting. Halloween pumpkins should serve as decorative elements, contributing to the spooky yet inviting ambiance. The overall atmosphere should feel calm and relaxing, suggesting that it's an ideal setting for quiet activities such as reading or enjoying music on a Halloween night. Outside the window is the view of New York City, with the cityscape dark, romantic, the level of detail should be impeccable, capturing the essence of a rainy autumn night outside of the room, NO RAIN INSIDE OF THE LIVING ROOM, THE INTERIOR IS DRY, THE RAIN IS OUTSIDE OF THE LIVING ROOM, NO ZOOM MOVEMENT IN THE SCENE -- V 5.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/009080/0.png",
"winvideos/009080/1.png",
"winvideos/009080/2.png",
"winvideos/009080/3.png",
"winvideos/009080/4.png",
"winvideos/009080/5.png",
"winvideos/009080/6.png",
"winvideos/009080/7.png",
"losevideos/009080/0.png",
"losevideos/009080/1.png",
"losevideos/009080/2.png",
"losevideos/009080/3.png",
"losevideos/009080/4.png",
"losevideos/009080/5.png",
"losevideos/009080/6.png",
"losevideos/009080/7.png"
] |
military radar in the foreground, city of Israel in the background blurred.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [military radar in the foreground, city of Israel in the background blurred.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/001837/0.png",
"losevideos/001837/1.png",
"losevideos/001837/2.png",
"losevideos/001837/3.png",
"losevideos/001837/4.png",
"losevideos/001837/5.png",
"losevideos/001837/6.png",
"losevideos/001837/7.png",
"winvideos/001837/0.png",
"winvideos/001837/1.png",
"winvideos/001837/2.png",
"winvideos/001837/3.png",
"winvideos/001837/4.png",
"winvideos/001837/5.png",
"winvideos/001837/6.png",
"winvideos/001837/7.png"
] |
A girl is fishing by the lake, with a dog and a basket next to her Autho.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A girl is fishing by the lake, with a dog and a basket next to her Autho.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/006185/0.png",
"winvideos/006185/1.png",
"winvideos/006185/2.png",
"winvideos/006185/3.png",
"winvideos/006185/4.png",
"winvideos/006185/5.png",
"winvideos/006185/6.png",
"winvideos/006185/7.png",
"losevideos/006185/0.png",
"losevideos/006185/1.png",
"losevideos/006185/2.png",
"losevideos/006185/3.png",
"losevideos/006185/4.png",
"losevideos/006185/5.png",
"losevideos/006185/6.png",
"losevideos/006185/7.png"
] |
Mcdonalds Burger Getting Created, In The Style Of 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: [Mcdonalds Burger Getting Created, In The Style Of Horror.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/006141/0.png",
"losevideos/006141/1.png",
"losevideos/006141/2.png",
"losevideos/006141/3.png",
"losevideos/006141/4.png",
"losevideos/006141/5.png",
"losevideos/006141/6.png",
"losevideos/006141/7.png",
"winvideos/006141/0.png",
"winvideos/006141/1.png",
"winvideos/006141/2.png",
"winvideos/006141/3.png",
"winvideos/006141/4.png",
"winvideos/006141/5.png",
"winvideos/006141/6.png",
"winvideos/006141/7.png"
] |
girl dancing around in red dress vintage looking 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: [girl dancing around in red dress vintage looking ar- 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/001480/0.png",
"winvideos/001480/1.png",
"winvideos/001480/2.png",
"winvideos/001480/3.png",
"winvideos/001480/4.png",
"winvideos/001480/5.png",
"winvideos/001480/6.png",
"winvideos/001480/7.png",
"losevideos/001480/0.png",
"losevideos/001480/1.png",
"losevideos/001480/2.png",
"losevideos/001480/3.png",
"losevideos/001480/4.png",
"losevideos/001480/5.png",
"losevideos/001480/6.png",
"losevideos/001480/7.png"
] |
a rocker in the middle of a concert.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 rocker in the middle of a concert.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/000369/0.png",
"winvideos/000369/1.png",
"winvideos/000369/2.png",
"winvideos/000369/3.png",
"winvideos/000369/4.png",
"winvideos/000369/5.png",
"winvideos/000369/6.png",
"winvideos/000369/7.png",
"losevideos/000369/0.png",
"losevideos/000369/1.png",
"losevideos/000369/2.png",
"losevideos/000369/3.png",
"losevideos/000369/4.png",
"losevideos/000369/5.png",
"losevideos/000369/6.png",
"losevideos/000369/7.png"
] |
frame by frame avant-garde 8K detailed shots of a monochromatic commercial video in Filmic portraiture style, frame captures a close-up portrait shot of an ethereal black model covered in a veil net. The background is a wide-angle shot of religious iconography, with a worms-eye Pov on the model, creating a mesmerizing visual effect. The video symbolizes the combined ethos of Balenciaga and Yeezy, serving as a commercial inspiration. The scene is cinematic and vogue-esque, with an emphasis on colored and high-quality highlighted accessories that add a touch of luxury. The camera settings include a specific camera model (Canon EOS R), a specific color film type (Kodak Portra 400), and lens details (Canon RF 24-70mm f/2.8L IS USM). The techniques employed are long exposure to capture the intricate details and shallow depth of field to enhance the model's presence. The video is directed by the visionary trio of David Fincher, Wes Anderson, and Sofia Coppola, with cinematography by the acclaimed Emmanuel Lubezki, Roger Deakins, and Christopher Doyle. The renowned photographers Tim Walker, Annie Leibovitz, and Mario Testino contribute their artistic expertise. The fashion designers collaborating on this remarkable project are Demna Gvasalia (Balenciaga), Kanye West (Yeezy), and Alexander Wang. The final output is of the highest quality, presented in 4K resolution, showcasing the meticulous attention to detail and capturing the essence of the brands.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [frame by frame avant-garde 8K detailed shots of a monochromatic commercial video in Filmic portraiture style, frame captures a close-up portrait shot of an ethereal black model covered in a veil net. The background is a wide-angle shot of religious iconography, with a worms-eye Pov on the model, creating a mesmerizing visual effect. The video symbolizes the combined ethos of Balenciaga and Yeezy, serving as a commercial inspiration. The scene is cinematic and vogue-esque, with an emphasis on colored and high-quality highlighted accessories that add a touch of luxury. The camera settings include a specific camera model (Canon EOS R), a specific color film type (Kodak Portra 400), and lens details (Canon RF 24-70mm f/2.8L IS USM). The techniques employed are long exposure to capture the intricate details and shallow depth of field to enhance the model's presence. The video is directed by the visionary trio of David Fincher, Wes Anderson, and Sofia Coppola, with cinematography by the acclaimed Emmanuel Lubezki, Roger Deakins, and Christopher Doyle. The renowned photographers Tim Walker, Annie Leibovitz, and Mario Testino contribute their artistic expertise. The fashion designers collaborating on this remarkable project are Demna Gvasalia (Balenciaga), Kanye West (Yeezy), and Alexander Wang. The final output is of the highest quality, presented in 4K resolution, showcasing the meticulous attention to detail and capturing the essence of the brands.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008013/0.png",
"winvideos/008013/1.png",
"winvideos/008013/2.png",
"winvideos/008013/3.png",
"winvideos/008013/4.png",
"winvideos/008013/5.png",
"winvideos/008013/6.png",
"winvideos/008013/7.png",
"losevideos/008013/0.png",
"losevideos/008013/1.png",
"losevideos/008013/2.png",
"losevideos/008013/3.png",
"losevideos/008013/4.png",
"losevideos/008013/5.png",
"losevideos/008013/6.png",
"losevideos/008013/7.png"
] |
young pirate looking at the horizon on top of the mat.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [young pirate looking at the horizon on top of the mat.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008372/0.png",
"winvideos/008372/1.png",
"winvideos/008372/2.png",
"winvideos/008372/3.png",
"winvideos/008372/4.png",
"winvideos/008372/5.png",
"winvideos/008372/6.png",
"winvideos/008372/7.png",
"losevideos/008372/0.png",
"losevideos/008372/1.png",
"losevideos/008372/2.png",
"losevideos/008372/3.png",
"losevideos/008372/4.png",
"losevideos/008372/5.png",
"losevideos/008372/6.png",
"losevideos/008372/7.png"
] |
Jackie chan with a cowboy hat pushing a man in a wheel chair slowly.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Jackie chan with a cowboy hat pushing a man in a wheel chair slowly.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/003337/0.png",
"losevideos/003337/1.png",
"losevideos/003337/2.png",
"losevideos/003337/3.png",
"losevideos/003337/4.png",
"losevideos/003337/5.png",
"losevideos/003337/6.png",
"losevideos/003337/7.png",
"winvideos/003337/0.png",
"winvideos/003337/1.png",
"winvideos/003337/2.png",
"winvideos/003337/3.png",
"winvideos/003337/4.png",
"winvideos/003337/5.png",
"winvideos/003337/6.png",
"winvideos/003337/7.png"
] |
serene sunrise over the village, symbolizing a new beginning.
Remember, you can search for royalty-free images on stock photo websites to find visuals that closely match the scene descriptions. Adjust the prompts based on your vision for the video.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [serene sunrise over the village, symbolizing a new beginning.\n\nRemember, you can search for royalty-free images on stock photo websites to find visuals that closely match the scene descriptions. Adjust the prompts based on your vision for the video.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/006035/0.png",
"losevideos/006035/1.png",
"losevideos/006035/2.png",
"losevideos/006035/3.png",
"losevideos/006035/4.png",
"losevideos/006035/5.png",
"losevideos/006035/6.png",
"losevideos/006035/7.png",
"winvideos/006035/0.png",
"winvideos/006035/1.png",
"winvideos/006035/2.png",
"winvideos/006035/3.png",
"winvideos/006035/4.png",
"winvideos/006035/5.png",
"winvideos/006035/6.png",
"winvideos/006035/7.png"
] |
adventure film, portrait scene, what can only be described as the most beautiful elf woman to ever live dressed in a cute essential little black dress in a park, she is sexy and confidently feminine, I can't believe how beautiful this is, dynamic pose, glamour shot, hyperminimalist, beauty photography, 35mm, 100 ISO, Canon 6D Mark II, 85mm f/2 lens, clean sharp focus, HDR -ar 16:9 -motion 3 -gs 20 -camera zoom out -neg deformities, extra limbs, floating heads, hats, poles, clouds, elongations, inverse angle, obtuse angles, over saturations, blur, graininess, fog, improper body dimensions, cartoons, missing fingers, missing toes, curly hair.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [adventure film, portrait scene, what can only be described as the most beautiful elf woman to ever live dressed in a cute essential little black dress in a park, she is sexy and confidently feminine, I can't believe how beautiful this is, dynamic pose, glamour shot, hyperminimalist, beauty photography, 35mm, 100 ISO, Canon 6D Mark II, 85mm f/2 lens, clean sharp focus, HDR -ar 16:9 -motion 3 -gs 20 -camera zoom out -neg deformities, extra limbs, floating heads, hats, poles, clouds, elongations, inverse angle, obtuse angles, over saturations, blur, graininess, fog, improper body dimensions, cartoons, missing fingers, missing toes, curly hair.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005027/0.png",
"winvideos/005027/1.png",
"winvideos/005027/2.png",
"winvideos/005027/3.png",
"winvideos/005027/4.png",
"winvideos/005027/5.png",
"winvideos/005027/6.png",
"winvideos/005027/7.png",
"losevideos/005027/0.png",
"losevideos/005027/1.png",
"losevideos/005027/2.png",
"losevideos/005027/3.png",
"losevideos/005027/4.png",
"losevideos/005027/5.png",
"losevideos/005027/6.png",
"losevideos/005027/7.png"
] |
"muscular man," "petite woman," "UFC octagon," "fight," "woman grappling," and "man's arm.".
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: ["muscular man," "petite woman," "UFC octagon," "fight," "woman grappling," and "man's arm.".]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/000803/0.png",
"losevideos/000803/1.png",
"losevideos/000803/2.png",
"losevideos/000803/3.png",
"losevideos/000803/4.png",
"losevideos/000803/5.png",
"losevideos/000803/6.png",
"losevideos/000803/7.png",
"winvideos/000803/0.png",
"winvideos/000803/1.png",
"winvideos/000803/2.png",
"winvideos/000803/3.png",
"winvideos/000803/4.png",
"winvideos/000803/5.png",
"winvideos/000803/6.png",
"winvideos/000803/7.png"
] |
"Create a 20-30 second video scene showcasing a user struggling with multiple demat accounts. The scene should emphasize the user's frustration as they attempt to log in separately to these accounts and fill out lengthy forms for IPO applications. The stress and time-consuming nature of the process should be evident. The visuals should capture the user's facial expressions, the cluttered computer screen with multiple login prompts, and perhaps a calendar with deadlines to emphasize the time pressure. The scene should convey the common challenges people face when managing multiple demat accounts for IPOs, creating a relatable and empathetic tone. This sets the stage for the solution to be introduced in the following part of the video." 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: ["Create a 20-30 second video scene showcasing a user struggling with multiple demat accounts. The scene should emphasize the user's frustration as they attempt to log in separately to these accounts and fill out lengthy forms for IPO applications. The stress and time-consuming nature of the process should be evident. The visuals should capture the user's facial expressions, the cluttered computer screen with multiple login prompts, and perhaps a calendar with deadlines to emphasize the time pressure. The scene should convey the common challenges people face when managing multiple demat accounts for IPOs, creating a relatable and empathetic tone. This sets the stage for the solution to be introduced in the following part of the video." 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008804/0.png",
"winvideos/008804/1.png",
"winvideos/008804/2.png",
"winvideos/008804/3.png",
"winvideos/008804/4.png",
"winvideos/008804/5.png",
"winvideos/008804/6.png",
"winvideos/008804/7.png",
"losevideos/008804/0.png",
"losevideos/008804/1.png",
"losevideos/008804/2.png",
"losevideos/008804/3.png",
"losevideos/008804/4.png",
"losevideos/008804/5.png",
"losevideos/008804/6.png",
"losevideos/008804/7.png"
] |
a beautiful young hand kneading dough, cinematic lighting.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a beautiful young hand kneading dough, cinematic lighting.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008861/0.png",
"losevideos/008861/1.png",
"losevideos/008861/2.png",
"losevideos/008861/3.png",
"losevideos/008861/4.png",
"losevideos/008861/5.png",
"losevideos/008861/6.png",
"losevideos/008861/7.png",
"winvideos/008861/0.png",
"winvideos/008861/1.png",
"winvideos/008861/2.png",
"winvideos/008861/3.png",
"winvideos/008861/4.png",
"winvideos/008861/5.png",
"winvideos/008861/6.png",
"winvideos/008861/7.png"
] |
Lorsque la passion est en jeu, comment apprendre à la canaliser ? Avec elle, je n’ai jamais su.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Lorsque la passion est en jeu, comment apprendre à la canaliser ? Avec elle, je n’ai jamais su.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008869/0.png",
"winvideos/008869/1.png",
"winvideos/008869/2.png",
"winvideos/008869/3.png",
"winvideos/008869/4.png",
"winvideos/008869/5.png",
"winvideos/008869/6.png",
"winvideos/008869/7.png",
"losevideos/008869/0.png",
"losevideos/008869/1.png",
"losevideos/008869/2.png",
"losevideos/008869/3.png",
"losevideos/008869/4.png",
"losevideos/008869/5.png",
"losevideos/008869/6.png",
"losevideos/008869/7.png"
] |
close-up medium, frontal shot, centered, an iron mammoth alien, walking on a flat terrain with rocks and grass, behind fog and green background, 3d render -neg "deformation, distortion, light beam, light rays, strange movement , unreal body, more than 4 legs, missing paws, people, change, add, people, multiple mammoths" -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: [close-up medium, frontal shot, centered, an iron mammoth alien, walking on a flat terrain with rocks and grass, behind fog and green background, 3d render -neg "deformation, distortion, light beam, light rays, strange movement , unreal body, more than 4 legs, missing paws, people, change, add, people, multiple mammoths" -motion 1 -gs 12 -fps 24 -hide.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/001787/0.png",
"losevideos/001787/1.png",
"losevideos/001787/2.png",
"losevideos/001787/3.png",
"losevideos/001787/4.png",
"losevideos/001787/5.png",
"losevideos/001787/6.png",
"losevideos/001787/7.png",
"winvideos/001787/0.png",
"winvideos/001787/1.png",
"winvideos/001787/2.png",
"winvideos/001787/3.png",
"winvideos/001787/4.png",
"winvideos/001787/5.png",
"winvideos/001787/6.png",
"winvideos/001787/7.png"
] |
the children happy and funny in birthday party at restaurant, ultrarealist, -m 2 -w 2 -gs 16 -fps 24 -ar 9:16 -camera zoom out Message: HAPPY BIRTHDAY (Font: SANS SERIF).
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 children happy and funny in birthday party at restaurant, ultrarealist, -m 2 -w 2 -gs 16 -fps 24 -ar 9:16 -camera zoom out Message: HAPPY BIRTHDAY (Font: SANS SERIF).]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008921/0.png",
"losevideos/008921/1.png",
"losevideos/008921/2.png",
"losevideos/008921/3.png",
"losevideos/008921/4.png",
"losevideos/008921/5.png",
"losevideos/008921/6.png",
"losevideos/008921/7.png",
"winvideos/008921/0.png",
"winvideos/008921/1.png",
"winvideos/008921/2.png",
"winvideos/008921/3.png",
"winvideos/008921/4.png",
"winvideos/008921/5.png",
"winvideos/008921/6.png",
"winvideos/008921/7.png"
] |
hacker hacking a computer, nerd look, messy hair, handsome, unreal engine, get up from the chair, lot of computer monitors with code running here and there -camera zoom in.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [hacker hacking a computer, nerd look, messy hair, handsome, unreal engine, get up from the chair, lot of computer monitors with code running here and there -camera zoom in.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/001959/0.png",
"losevideos/001959/1.png",
"losevideos/001959/2.png",
"losevideos/001959/3.png",
"losevideos/001959/4.png",
"losevideos/001959/5.png",
"losevideos/001959/6.png",
"losevideos/001959/7.png",
"winvideos/001959/0.png",
"winvideos/001959/1.png",
"winvideos/001959/2.png",
"winvideos/001959/3.png",
"winvideos/001959/4.png",
"winvideos/001959/5.png",
"winvideos/001959/6.png",
"winvideos/001959/7.png"
] |
ghost hovering over bed.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [ghost hovering over bed.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/002010/0.png",
"losevideos/002010/1.png",
"losevideos/002010/2.png",
"losevideos/002010/3.png",
"losevideos/002010/4.png",
"losevideos/002010/5.png",
"losevideos/002010/6.png",
"losevideos/002010/7.png",
"winvideos/002010/0.png",
"winvideos/002010/1.png",
"winvideos/002010/2.png",
"winvideos/002010/3.png",
"winvideos/002010/4.png",
"winvideos/002010/5.png",
"winvideos/002010/6.png",
"winvideos/002010/7.png"
] |
*motion 4 The idols of the people of Num (Wud, Suwa', Yaghuts, Ya'uq, and Nasr) are submerged in Jeddah.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [*motion 4 The idols of the people of Num (Wud, Suwa', Yaghuts, Ya'uq, and Nasr) are submerged in Jeddah.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/006864/0.png",
"losevideos/006864/1.png",
"losevideos/006864/2.png",
"losevideos/006864/3.png",
"losevideos/006864/4.png",
"losevideos/006864/5.png",
"losevideos/006864/6.png",
"losevideos/006864/7.png",
"winvideos/006864/0.png",
"winvideos/006864/1.png",
"winvideos/006864/2.png",
"winvideos/006864/3.png",
"winvideos/006864/4.png",
"winvideos/006864/5.png",
"winvideos/006864/6.png",
"winvideos/006864/7.png"
] |
letter'C' for kids.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [letter'C' for kids.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/003584/0.png",
"losevideos/003584/1.png",
"losevideos/003584/2.png",
"losevideos/003584/3.png",
"losevideos/003584/4.png",
"losevideos/003584/5.png",
"losevideos/003584/6.png",
"losevideos/003584/7.png",
"winvideos/003584/0.png",
"winvideos/003584/1.png",
"winvideos/003584/2.png",
"winvideos/003584/3.png",
"winvideos/003584/4.png",
"winvideos/003584/5.png",
"winvideos/003584/6.png",
"winvideos/003584/7.png"
] |
Lungcancer Screening by Computertomographie,fps 15 , Zoom out , Motion 3 Seed1 -neg distortion.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Lungcancer Screening by Computertomographie,fps 15 , Zoom out , Motion 3 Seed1 -neg distortion.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/000355/0.png",
"winvideos/000355/1.png",
"winvideos/000355/2.png",
"winvideos/000355/3.png",
"winvideos/000355/4.png",
"winvideos/000355/5.png",
"winvideos/000355/6.png",
"winvideos/000355/7.png",
"losevideos/000355/0.png",
"losevideos/000355/1.png",
"losevideos/000355/2.png",
"losevideos/000355/3.png",
"losevideos/000355/4.png",
"losevideos/000355/5.png",
"losevideos/000355/6.png",
"losevideos/000355/7.png"
] |
Homeless Colombians fat teenages big party, wearing tattered and dirty clothes, dancing in modern neon city night. everybody dancing. -camera rotate clockwise. -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Homeless Colombians fat teenages big party, wearing tattered and dirty clothes, dancing in modern neon city night. everybody dancing. -camera rotate clockwise. -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/005844/0.png",
"losevideos/005844/1.png",
"losevideos/005844/2.png",
"losevideos/005844/3.png",
"losevideos/005844/4.png",
"losevideos/005844/5.png",
"losevideos/005844/6.png",
"losevideos/005844/7.png",
"winvideos/005844/0.png",
"winvideos/005844/1.png",
"winvideos/005844/2.png",
"winvideos/005844/3.png",
"winvideos/005844/4.png",
"winvideos/005844/5.png",
"winvideos/005844/6.png",
"winvideos/005844/7.png"
] |
A character from a different era (e.g., medieval, future) bakes a cake using modern ingredients.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 character from a different era (e.g., medieval, future) bakes a cake using modern ingredients.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/002991/0.png",
"winvideos/002991/1.png",
"winvideos/002991/2.png",
"winvideos/002991/3.png",
"winvideos/002991/4.png",
"winvideos/002991/5.png",
"winvideos/002991/6.png",
"winvideos/002991/7.png",
"losevideos/002991/0.png",
"losevideos/002991/1.png",
"losevideos/002991/2.png",
"losevideos/002991/3.png",
"losevideos/002991/4.png",
"losevideos/002991/5.png",
"losevideos/002991/6.png",
"losevideos/002991/7.png"
] |
an A frame wood and glass cottage off the coast of Mexico.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 A frame wood and glass cottage off the coast of Mexico.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/000039/0.png",
"winvideos/000039/1.png",
"winvideos/000039/2.png",
"winvideos/000039/3.png",
"winvideos/000039/4.png",
"winvideos/000039/5.png",
"winvideos/000039/6.png",
"winvideos/000039/7.png",
"losevideos/000039/0.png",
"losevideos/000039/1.png",
"losevideos/000039/2.png",
"losevideos/000039/3.png",
"losevideos/000039/4.png",
"losevideos/000039/5.png",
"losevideos/000039/6.png",
"losevideos/000039/7.png"
] |
ryan rainolds, acting , monkey, jumping on table, angry, people looking at the monkey, plane flying over 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: [ryan rainolds, acting , monkey, jumping on table, angry, people looking at the monkey, plane flying over the horizon.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008752/0.png",
"winvideos/008752/1.png",
"winvideos/008752/2.png",
"winvideos/008752/3.png",
"winvideos/008752/4.png",
"winvideos/008752/5.png",
"winvideos/008752/6.png",
"winvideos/008752/7.png",
"losevideos/008752/0.png",
"losevideos/008752/1.png",
"losevideos/008752/2.png",
"losevideos/008752/3.png",
"losevideos/008752/4.png",
"losevideos/008752/5.png",
"losevideos/008752/6.png",
"losevideos/008752/7.png"
] |
Create an animated sequence featuring Twinkle meeting friendly animals – a wise old owl, a playful bunny, and a giggling squirrel. Show them engaging in activities that depict friendship and kindness, like sharing, playing, and laughing together.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Create an animated sequence featuring Twinkle meeting friendly animals – a wise old owl, a playful bunny, and a giggling squirrel. Show them engaging in activities that depict friendship and kindness, like sharing, playing, and laughing together.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/006637/0.png",
"winvideos/006637/1.png",
"winvideos/006637/2.png",
"winvideos/006637/3.png",
"winvideos/006637/4.png",
"winvideos/006637/5.png",
"winvideos/006637/6.png",
"winvideos/006637/7.png",
"losevideos/006637/0.png",
"losevideos/006637/1.png",
"losevideos/006637/2.png",
"losevideos/006637/3.png",
"losevideos/006637/4.png",
"losevideos/006637/5.png",
"losevideos/006637/6.png",
"losevideos/006637/7.png"
] |
three monsters playing music from the 80s.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [three monsters playing music from the 80s.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/004657/0.png",
"winvideos/004657/1.png",
"winvideos/004657/2.png",
"winvideos/004657/3.png",
"winvideos/004657/4.png",
"winvideos/004657/5.png",
"winvideos/004657/6.png",
"winvideos/004657/7.png",
"losevideos/004657/0.png",
"losevideos/004657/1.png",
"losevideos/004657/2.png",
"losevideos/004657/3.png",
"losevideos/004657/4.png",
"losevideos/004657/5.png",
"losevideos/004657/6.png",
"losevideos/004657/7.png"
] |
giant hippo with wings in a cavern.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [giant hippo with wings in a cavern.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/000797/0.png",
"losevideos/000797/1.png",
"losevideos/000797/2.png",
"losevideos/000797/3.png",
"losevideos/000797/4.png",
"losevideos/000797/5.png",
"losevideos/000797/6.png",
"losevideos/000797/7.png",
"winvideos/000797/0.png",
"winvideos/000797/1.png",
"winvideos/000797/2.png",
"winvideos/000797/3.png",
"winvideos/000797/4.png",
"winvideos/000797/5.png",
"winvideos/000797/6.png",
"winvideos/000797/7.png"
] |
create a video of car repair services.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [create a video of car repair services.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/003774/0.png",
"winvideos/003774/1.png",
"winvideos/003774/2.png",
"winvideos/003774/3.png",
"winvideos/003774/4.png",
"winvideos/003774/5.png",
"winvideos/003774/6.png",
"winvideos/003774/7.png",
"losevideos/003774/0.png",
"losevideos/003774/1.png",
"losevideos/003774/2.png",
"losevideos/003774/3.png",
"losevideos/003774/4.png",
"losevideos/003774/5.png",
"losevideos/003774/6.png",
"losevideos/003774/7.png"
] |
girls 3d in skirt Hayao Miyazaki style -m 4 cinematic -fps 24.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [girls 3d in skirt Hayao Miyazaki style -m 4 cinematic -fps 24.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005910/0.png",
"winvideos/005910/1.png",
"winvideos/005910/2.png",
"winvideos/005910/3.png",
"winvideos/005910/4.png",
"winvideos/005910/5.png",
"winvideos/005910/6.png",
"winvideos/005910/7.png",
"losevideos/005910/0.png",
"losevideos/005910/1.png",
"losevideos/005910/2.png",
"losevideos/005910/3.png",
"losevideos/005910/4.png",
"losevideos/005910/5.png",
"losevideos/005910/6.png",
"losevideos/005910/7.png"
] |
closeup of face of a raven in a medieval claymation hellscape surreal black and white, 16 mm, 2 ravens, realism, -gs24, -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: [closeup of face of a raven in a medieval claymation hellscape surreal black and white, 16 mm, 2 ravens, realism, -gs24, -motion 4.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008366/0.png",
"losevideos/008366/1.png",
"losevideos/008366/2.png",
"losevideos/008366/3.png",
"losevideos/008366/4.png",
"losevideos/008366/5.png",
"losevideos/008366/6.png",
"losevideos/008366/7.png",
"winvideos/008366/0.png",
"winvideos/008366/1.png",
"winvideos/008366/2.png",
"winvideos/008366/3.png",
"winvideos/008366/4.png",
"winvideos/008366/5.png",
"winvideos/008366/6.png",
"winvideos/008366/7.png"
] |
mycelium in motion ar 9:16 motion 25.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [mycelium in motion ar 9:16 motion 25.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/006276/0.png",
"winvideos/006276/1.png",
"winvideos/006276/2.png",
"winvideos/006276/3.png",
"winvideos/006276/4.png",
"winvideos/006276/5.png",
"winvideos/006276/6.png",
"winvideos/006276/7.png",
"losevideos/006276/0.png",
"losevideos/006276/1.png",
"losevideos/006276/2.png",
"losevideos/006276/3.png",
"losevideos/006276/4.png",
"losevideos/006276/5.png",
"losevideos/006276/6.png",
"losevideos/006276/7.png"
] |
baroqueart nouveau, magical, world war 2, photorealistic dramatic anime boy, art by gaston bussiere, fanbox, scary art, post-apocalypse, Korean light novel, flowers.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [baroqueart nouveau, magical, world war 2, photorealistic dramatic anime boy, art by gaston bussiere, fanbox, scary art, post-apocalypse, Korean light novel, flowers.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/004717/0.png",
"winvideos/004717/1.png",
"winvideos/004717/2.png",
"winvideos/004717/3.png",
"winvideos/004717/4.png",
"winvideos/004717/5.png",
"winvideos/004717/6.png",
"winvideos/004717/7.png",
"losevideos/004717/0.png",
"losevideos/004717/1.png",
"losevideos/004717/2.png",
"losevideos/004717/3.png",
"losevideos/004717/4.png",
"losevideos/004717/5.png",
"losevideos/004717/6.png",
"losevideos/004717/7.png"
] |
"Generate a scene showing the consequences of Mephisto's arrival, with dark magic causing chaos and destruction in the city streets.".
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: ["Generate a scene showing the consequences of Mephisto's arrival, with dark magic causing chaos and destruction in the city streets.".]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/002382/0.png",
"winvideos/002382/1.png",
"winvideos/002382/2.png",
"winvideos/002382/3.png",
"winvideos/002382/4.png",
"winvideos/002382/5.png",
"winvideos/002382/6.png",
"winvideos/002382/7.png",
"losevideos/002382/0.png",
"losevideos/002382/1.png",
"losevideos/002382/2.png",
"losevideos/002382/3.png",
"losevideos/002382/4.png",
"losevideos/002382/5.png",
"losevideos/002382/6.png",
"losevideos/002382/7.png"
] |
Snow-covered forests and wastelands, aerial footage, Game of Thrones movie 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: [Snow-covered forests and wastelands, aerial footage, Game of Thrones movie style.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/009853/0.png",
"winvideos/009853/1.png",
"winvideos/009853/2.png",
"winvideos/009853/3.png",
"winvideos/009853/4.png",
"winvideos/009853/5.png",
"winvideos/009853/6.png",
"winvideos/009853/7.png",
"losevideos/009853/0.png",
"losevideos/009853/1.png",
"losevideos/009853/2.png",
"losevideos/009853/3.png",
"losevideos/009853/4.png",
"losevideos/009853/5.png",
"losevideos/009853/6.png",
"losevideos/009853/7.png"
] |
Rosie directed him with precision, making sure they followed the path towards the finish line. , different animals stading by the track to warm the contests of the race.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Rosie directed him with precision, making sure they followed the path towards the finish line. , different animals stading by the track to warm the contests of the race.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/006989/0.png",
"losevideos/006989/1.png",
"losevideos/006989/2.png",
"losevideos/006989/3.png",
"losevideos/006989/4.png",
"losevideos/006989/5.png",
"losevideos/006989/6.png",
"losevideos/006989/7.png",
"winvideos/006989/0.png",
"winvideos/006989/1.png",
"winvideos/006989/2.png",
"winvideos/006989/3.png",
"winvideos/006989/4.png",
"winvideos/006989/5.png",
"winvideos/006989/6.png",
"winvideos/006989/7.png"
] |
cartoon dog sitting near a man watching tv.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cartoon dog sitting near a man watching tv.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/007340/0.png",
"winvideos/007340/1.png",
"winvideos/007340/2.png",
"winvideos/007340/3.png",
"winvideos/007340/4.png",
"winvideos/007340/5.png",
"winvideos/007340/6.png",
"winvideos/007340/7.png",
"losevideos/007340/0.png",
"losevideos/007340/1.png",
"losevideos/007340/2.png",
"losevideos/007340/3.png",
"losevideos/007340/4.png",
"losevideos/007340/5.png",
"losevideos/007340/6.png",
"losevideos/007340/7.png"
] |
Leena and Sameer's love.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Leena and Sameer's love.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/003451/0.png",
"losevideos/003451/1.png",
"losevideos/003451/2.png",
"losevideos/003451/3.png",
"losevideos/003451/4.png",
"losevideos/003451/5.png",
"losevideos/003451/6.png",
"losevideos/003451/7.png",
"winvideos/003451/0.png",
"winvideos/003451/1.png",
"winvideos/003451/2.png",
"winvideos/003451/3.png",
"winvideos/003451/4.png",
"winvideos/003451/5.png",
"winvideos/003451/6.png",
"winvideos/003451/7.png"
] |
Boston street at night with rain.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Boston street at night with rain.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/009869/0.png",
"winvideos/009869/1.png",
"winvideos/009869/2.png",
"winvideos/009869/3.png",
"winvideos/009869/4.png",
"winvideos/009869/5.png",
"winvideos/009869/6.png",
"winvideos/009869/7.png",
"losevideos/009869/0.png",
"losevideos/009869/1.png",
"losevideos/009869/2.png",
"losevideos/009869/3.png",
"losevideos/009869/4.png",
"losevideos/009869/5.png",
"losevideos/009869/6.png",
"losevideos/009869/7.png"
] |
going down a waterslide into a pool in a basement scary dark.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [going down a waterslide into a pool in a basement scary dark.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/003698/0.png",
"winvideos/003698/1.png",
"winvideos/003698/2.png",
"winvideos/003698/3.png",
"winvideos/003698/4.png",
"winvideos/003698/5.png",
"winvideos/003698/6.png",
"winvideos/003698/7.png",
"losevideos/003698/0.png",
"losevideos/003698/1.png",
"losevideos/003698/2.png",
"losevideos/003698/3.png",
"losevideos/003698/4.png",
"losevideos/003698/5.png",
"losevideos/003698/6.png",
"losevideos/003698/7.png"
] |
realistic gruesome creaure with no hair, translucent skin, a virtical mouth, contorting -movement 3.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [realistic gruesome creaure with no hair, translucent skin, a virtical mouth, contorting -movement 3.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/009753/0.png",
"losevideos/009753/1.png",
"losevideos/009753/2.png",
"losevideos/009753/3.png",
"losevideos/009753/4.png",
"losevideos/009753/5.png",
"losevideos/009753/6.png",
"losevideos/009753/7.png",
"winvideos/009753/0.png",
"winvideos/009753/1.png",
"winvideos/009753/2.png",
"winvideos/009753/3.png",
"winvideos/009753/4.png",
"winvideos/009753/5.png",
"winvideos/009753/6.png",
"winvideos/009753/7.png"
] |
Gloomy surrounded by an aura of darkness as he wrestles with his own insecurities and fears while touching the Glimmerstone.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Gloomy surrounded by an aura of darkness as he wrestles with his own insecurities and fears while touching the Glimmerstone.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/004031/0.png",
"winvideos/004031/1.png",
"winvideos/004031/2.png",
"winvideos/004031/3.png",
"winvideos/004031/4.png",
"winvideos/004031/5.png",
"winvideos/004031/6.png",
"winvideos/004031/7.png",
"losevideos/004031/0.png",
"losevideos/004031/1.png",
"losevideos/004031/2.png",
"losevideos/004031/3.png",
"losevideos/004031/4.png",
"losevideos/004031/5.png",
"losevideos/004031/6.png",
"losevideos/004031/7.png"
] |
in universe a lady with cosmic power.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 universe a lady with cosmic power.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/007271/0.png",
"losevideos/007271/1.png",
"losevideos/007271/2.png",
"losevideos/007271/3.png",
"losevideos/007271/4.png",
"losevideos/007271/5.png",
"losevideos/007271/6.png",
"losevideos/007271/7.png",
"winvideos/007271/0.png",
"winvideos/007271/1.png",
"winvideos/007271/2.png",
"winvideos/007271/3.png",
"winvideos/007271/4.png",
"winvideos/007271/5.png",
"winvideos/007271/6.png",
"winvideos/007271/7.png"
] |
a tree house with creepy looking doors and windows.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 tree house with creepy looking doors and windows.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008257/0.png",
"losevideos/008257/1.png",
"losevideos/008257/2.png",
"losevideos/008257/3.png",
"losevideos/008257/4.png",
"losevideos/008257/5.png",
"losevideos/008257/6.png",
"losevideos/008257/7.png",
"winvideos/008257/0.png",
"winvideos/008257/1.png",
"winvideos/008257/2.png",
"winvideos/008257/3.png",
"winvideos/008257/4.png",
"winvideos/008257/5.png",
"winvideos/008257/6.png",
"winvideos/008257/7.png"
] |
white woman hugging an African man.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 woman hugging an African man.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/003269/0.png",
"winvideos/003269/1.png",
"winvideos/003269/2.png",
"winvideos/003269/3.png",
"winvideos/003269/4.png",
"winvideos/003269/5.png",
"winvideos/003269/6.png",
"winvideos/003269/7.png",
"losevideos/003269/0.png",
"losevideos/003269/1.png",
"losevideos/003269/2.png",
"losevideos/003269/3.png",
"losevideos/003269/4.png",
"losevideos/003269/5.png",
"losevideos/003269/6.png",
"losevideos/003269/7.png"
] |
Generate a Zelda Breath of the Wild avatar.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Generate a Zelda Breath of the Wild avatar.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/009194/0.png",
"winvideos/009194/1.png",
"winvideos/009194/2.png",
"winvideos/009194/3.png",
"winvideos/009194/4.png",
"winvideos/009194/5.png",
"winvideos/009194/6.png",
"winvideos/009194/7.png",
"losevideos/009194/0.png",
"losevideos/009194/1.png",
"losevideos/009194/2.png",
"losevideos/009194/3.png",
"losevideos/009194/4.png",
"losevideos/009194/5.png",
"losevideos/009194/6.png",
"losevideos/009194/7.png"
] |
dreamlike, a 85mm f/1.4, 4k, high resolution, 8k, hd, full colour, 8k, high definition” untill nothing remains.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [dreamlike, a 85mm f/1.4, 4k, high resolution, 8k, hd, full colour, 8k, high definition” untill nothing remains.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008524/0.png",
"losevideos/008524/1.png",
"losevideos/008524/2.png",
"losevideos/008524/3.png",
"losevideos/008524/4.png",
"losevideos/008524/5.png",
"losevideos/008524/6.png",
"losevideos/008524/7.png",
"winvideos/008524/0.png",
"winvideos/008524/1.png",
"winvideos/008524/2.png",
"winvideos/008524/3.png",
"winvideos/008524/4.png",
"winvideos/008524/5.png",
"winvideos/008524/6.png",
"winvideos/008524/7.png"
] |
Spring , iranian women , princess , dating , darkness , mythology , wind blowing hair.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 , iranian women , princess , dating , darkness , mythology , wind blowing hair.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005655/0.png",
"winvideos/005655/1.png",
"winvideos/005655/2.png",
"winvideos/005655/3.png",
"winvideos/005655/4.png",
"winvideos/005655/5.png",
"winvideos/005655/6.png",
"winvideos/005655/7.png",
"losevideos/005655/0.png",
"losevideos/005655/1.png",
"losevideos/005655/2.png",
"losevideos/005655/3.png",
"losevideos/005655/4.png",
"losevideos/005655/5.png",
"losevideos/005655/6.png",
"losevideos/005655/7.png"
] |
Hero stands beneath the castle, a panoramic view. the castle overlooks a breathtaking landscape, cinematic, high resolution, a wide view, award winning cinematography, 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: [Hero stands beneath the castle, a panoramic view. the castle overlooks a breathtaking landscape, cinematic, high resolution, a wide view, award winning cinematography, 8k.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005555/0.png",
"winvideos/005555/1.png",
"winvideos/005555/2.png",
"winvideos/005555/3.png",
"winvideos/005555/4.png",
"winvideos/005555/5.png",
"winvideos/005555/6.png",
"winvideos/005555/7.png",
"losevideos/005555/0.png",
"losevideos/005555/1.png",
"losevideos/005555/2.png",
"losevideos/005555/3.png",
"losevideos/005555/4.png",
"losevideos/005555/5.png",
"losevideos/005555/6.png",
"losevideos/005555/7.png"
] |
a sushi shop in modern french city -motion 2 -fps 24 -camera zoom in.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a sushi shop in modern french city -motion 2 -fps 24 -camera zoom in.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/000769/0.png",
"winvideos/000769/1.png",
"winvideos/000769/2.png",
"winvideos/000769/3.png",
"winvideos/000769/4.png",
"winvideos/000769/5.png",
"winvideos/000769/6.png",
"winvideos/000769/7.png",
"losevideos/000769/0.png",
"losevideos/000769/1.png",
"losevideos/000769/2.png",
"losevideos/000769/3.png",
"losevideos/000769/4.png",
"losevideos/000769/5.png",
"losevideos/000769/6.png",
"losevideos/000769/7.png"
] |
faceless divine person, with rays all around, several people come out of this person.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [faceless divine person, with rays all around, several people come out of this person.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/001831/0.png",
"winvideos/001831/1.png",
"winvideos/001831/2.png",
"winvideos/001831/3.png",
"winvideos/001831/4.png",
"winvideos/001831/5.png",
"winvideos/001831/6.png",
"winvideos/001831/7.png",
"losevideos/001831/0.png",
"losevideos/001831/1.png",
"losevideos/001831/2.png",
"losevideos/001831/3.png",
"losevideos/001831/4.png",
"losevideos/001831/5.png",
"losevideos/001831/6.png",
"losevideos/001831/7.png"
] |
realistic spectre of rainbow emerge into wet sexy kiss into a four wet ultra realistic animal faces with mouths and breast and hands and ultrarealistic animal faces -neg_cartoon_3d_funny.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [realistic spectre of rainbow emerge into wet sexy kiss into a four wet ultra realistic animal faces with mouths and breast and hands and ultrarealistic animal faces -neg_cartoon_3d_funny.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/004530/0.png",
"losevideos/004530/1.png",
"losevideos/004530/2.png",
"losevideos/004530/3.png",
"losevideos/004530/4.png",
"losevideos/004530/5.png",
"losevideos/004530/6.png",
"losevideos/004530/7.png",
"winvideos/004530/0.png",
"winvideos/004530/1.png",
"winvideos/004530/2.png",
"winvideos/004530/3.png",
"winvideos/004530/4.png",
"winvideos/004530/5.png",
"winvideos/004530/6.png",
"winvideos/004530/7.png"
] |
flat chested woman removes t-shirt -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: [flat chested woman removes t-shirt -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005940/0.png",
"winvideos/005940/1.png",
"winvideos/005940/2.png",
"winvideos/005940/3.png",
"winvideos/005940/4.png",
"winvideos/005940/5.png",
"winvideos/005940/6.png",
"winvideos/005940/7.png",
"losevideos/005940/0.png",
"losevideos/005940/1.png",
"losevideos/005940/2.png",
"losevideos/005940/3.png",
"losevideos/005940/4.png",
"losevideos/005940/5.png",
"losevideos/005940/6.png",
"losevideos/005940/7.png"
] |
roots of a tree digging into the soil.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [roots of a tree digging into the soil.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/002721/0.png",
"winvideos/002721/1.png",
"winvideos/002721/2.png",
"winvideos/002721/3.png",
"winvideos/002721/4.png",
"winvideos/002721/5.png",
"winvideos/002721/6.png",
"winvideos/002721/7.png",
"losevideos/002721/0.png",
"losevideos/002721/1.png",
"losevideos/002721/2.png",
"losevideos/002721/3.png",
"losevideos/002721/4.png",
"losevideos/002721/5.png",
"losevideos/002721/6.png",
"losevideos/002721/7.png"
] |
leprechaun giving instructions.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [leprechaun giving instructions.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/000114/0.png",
"winvideos/000114/1.png",
"winvideos/000114/2.png",
"winvideos/000114/3.png",
"winvideos/000114/4.png",
"winvideos/000114/5.png",
"winvideos/000114/6.png",
"winvideos/000114/7.png",
"losevideos/000114/0.png",
"losevideos/000114/1.png",
"losevideos/000114/2.png",
"losevideos/000114/3.png",
"losevideos/000114/4.png",
"losevideos/000114/5.png",
"losevideos/000114/6.png",
"losevideos/000114/7.png"
] |
Crowned majestic legion of Lions in hundreds roaring towards a Huge sumpreme Crowned lion in the sky in homage, animated realistic cinematic setting.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Crowned majestic legion of Lions in hundreds roaring towards a Huge sumpreme Crowned lion in the sky in homage, animated realistic cinematic setting.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/006956/0.png",
"losevideos/006956/1.png",
"losevideos/006956/2.png",
"losevideos/006956/3.png",
"losevideos/006956/4.png",
"losevideos/006956/5.png",
"losevideos/006956/6.png",
"losevideos/006956/7.png",
"winvideos/006956/0.png",
"winvideos/006956/1.png",
"winvideos/006956/2.png",
"winvideos/006956/3.png",
"winvideos/006956/4.png",
"winvideos/006956/5.png",
"winvideos/006956/6.png",
"winvideos/006956/7.png"
] |
Superwoman's encounters with Dr. Nebula were epic battles of intellect and strength. Each confrontation pushed her to new limits, testing her resolve and forcing her to dig deeper into her own potential. With her quick wit and unyielding determination, Superwoman managed to thwart Dr. Nebula's plans time and time again, preventing catastrophe and safeguarding the future of New Horizons City.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Superwoman's encounters with Dr. Nebula were epic battles of intellect and strength. Each confrontation pushed her to new limits, testing her resolve and forcing her to dig deeper into her own potential. With her quick wit and unyielding determination, Superwoman managed to thwart Dr. Nebula's plans time and time again, preventing catastrophe and safeguarding the future of New Horizons City.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008137/0.png",
"losevideos/008137/1.png",
"losevideos/008137/2.png",
"losevideos/008137/3.png",
"losevideos/008137/4.png",
"losevideos/008137/5.png",
"losevideos/008137/6.png",
"losevideos/008137/7.png",
"winvideos/008137/0.png",
"winvideos/008137/1.png",
"winvideos/008137/2.png",
"winvideos/008137/3.png",
"winvideos/008137/4.png",
"winvideos/008137/5.png",
"winvideos/008137/6.png",
"winvideos/008137/7.png"
] |
A tiger in the forest, chasing a little rabbit all the way.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 tiger in the forest, chasing a little rabbit all the way.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/007904/0.png",
"losevideos/007904/1.png",
"losevideos/007904/2.png",
"losevideos/007904/3.png",
"losevideos/007904/4.png",
"losevideos/007904/5.png",
"losevideos/007904/6.png",
"losevideos/007904/7.png",
"winvideos/007904/0.png",
"winvideos/007904/1.png",
"winvideos/007904/2.png",
"winvideos/007904/3.png",
"winvideos/007904/4.png",
"winvideos/007904/5.png",
"winvideos/007904/6.png",
"winvideos/007904/7.png"
] |
magic clouds of various colors, camera zoom out Message: CREAR (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: [magic clouds of various colors, camera zoom out Message: CREAR (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/007022/0.png",
"winvideos/007022/1.png",
"winvideos/007022/2.png",
"winvideos/007022/3.png",
"winvideos/007022/4.png",
"winvideos/007022/5.png",
"winvideos/007022/6.png",
"winvideos/007022/7.png",
"losevideos/007022/0.png",
"losevideos/007022/1.png",
"losevideos/007022/2.png",
"losevideos/007022/3.png",
"losevideos/007022/4.png",
"losevideos/007022/5.png",
"losevideos/007022/6.png",
"losevideos/007022/7.png"
] |
a stoic character in ancient greece, walking through the streets of athens, photorealistic, 4K -neg "no animals" -ar 16:9 -motion 1 -fps 24 -w 2 -size 70 -camera zoom in -seed 4567 Message: WILD (Source: SANS SERIF) 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: [a stoic character in ancient greece, walking through the streets of athens, photorealistic, 4K -neg "no animals" -ar 16:9 -motion 1 -fps 24 -w 2 -size 70 -camera zoom in -seed 4567 Message: WILD (Source: SANS SERIF) Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/003822/0.png",
"losevideos/003822/1.png",
"losevideos/003822/2.png",
"losevideos/003822/3.png",
"losevideos/003822/4.png",
"losevideos/003822/5.png",
"losevideos/003822/6.png",
"losevideos/003822/7.png",
"winvideos/003822/0.png",
"winvideos/003822/1.png",
"winvideos/003822/2.png",
"winvideos/003822/3.png",
"winvideos/003822/4.png",
"winvideos/003822/5.png",
"winvideos/003822/6.png",
"winvideos/003822/7.png"
] |
make fire alive.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 fire alive.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/006947/0.png",
"winvideos/006947/1.png",
"winvideos/006947/2.png",
"winvideos/006947/3.png",
"winvideos/006947/4.png",
"winvideos/006947/5.png",
"winvideos/006947/6.png",
"winvideos/006947/7.png",
"losevideos/006947/0.png",
"losevideos/006947/1.png",
"losevideos/006947/2.png",
"losevideos/006947/3.png",
"losevideos/006947/4.png",
"losevideos/006947/5.png",
"losevideos/006947/6.png",
"losevideos/006947/7.png"
] |
drone shot, flying over medieval mountain village, blue sky --ar 1:1.
|
[
{
"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: [drone shot, flying over medieval mountain village, blue sky --ar 1:1.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/003333/0.png",
"winvideos/003333/1.png",
"winvideos/003333/2.png",
"winvideos/003333/3.png",
"winvideos/003333/4.png",
"winvideos/003333/5.png",
"winvideos/003333/6.png",
"winvideos/003333/7.png",
"losevideos/003333/0.png",
"losevideos/003333/1.png",
"losevideos/003333/2.png",
"losevideos/003333/3.png",
"losevideos/003333/4.png",
"losevideos/003333/5.png",
"losevideos/003333/6.png",
"losevideos/003333/7.png"
] |
an alarm sounding -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: [an alarm sounding -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/002887/0.png",
"losevideos/002887/1.png",
"losevideos/002887/2.png",
"losevideos/002887/3.png",
"losevideos/002887/4.png",
"losevideos/002887/5.png",
"losevideos/002887/6.png",
"losevideos/002887/7.png",
"winvideos/002887/0.png",
"winvideos/002887/1.png",
"winvideos/002887/2.png",
"winvideos/002887/3.png",
"winvideos/002887/4.png",
"winvideos/002887/5.png",
"winvideos/002887/6.png",
"winvideos/002887/7.png"
] |
cartoon comedy.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 comedy.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/007376/0.png",
"losevideos/007376/1.png",
"losevideos/007376/2.png",
"losevideos/007376/3.png",
"losevideos/007376/4.png",
"losevideos/007376/5.png",
"losevideos/007376/6.png",
"losevideos/007376/7.png",
"winvideos/007376/0.png",
"winvideos/007376/1.png",
"winvideos/007376/2.png",
"winvideos/007376/3.png",
"winvideos/007376/4.png",
"winvideos/007376/5.png",
"winvideos/007376/6.png",
"winvideos/007376/7.png"
] |
1910s film vintage look, wolf in a desert, foggy, night time, moon, dark clouds, old photo, real photo, sepia photo, historical photo. dark 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: [1910s film vintage look, wolf in a desert, foggy, night time, moon, dark clouds, old photo, real photo, sepia photo, historical photo. dark scene.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008067/0.png",
"winvideos/008067/1.png",
"winvideos/008067/2.png",
"winvideos/008067/3.png",
"winvideos/008067/4.png",
"winvideos/008067/5.png",
"winvideos/008067/6.png",
"winvideos/008067/7.png",
"losevideos/008067/0.png",
"losevideos/008067/1.png",
"losevideos/008067/2.png",
"losevideos/008067/3.png",
"losevideos/008067/4.png",
"losevideos/008067/5.png",
"losevideos/008067/6.png",
"losevideos/008067/7.png"
] |
Satelite above moon.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Satelite above moon.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/000313/0.png",
"losevideos/000313/1.png",
"losevideos/000313/2.png",
"losevideos/000313/3.png",
"losevideos/000313/4.png",
"losevideos/000313/5.png",
"losevideos/000313/6.png",
"losevideos/000313/7.png",
"winvideos/000313/0.png",
"winvideos/000313/1.png",
"winvideos/000313/2.png",
"winvideos/000313/3.png",
"winvideos/000313/4.png",
"winvideos/000313/5.png",
"winvideos/000313/6.png",
"winvideos/000313/7.png"
] |
in front of the cute pink house, cartoon, 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: [in front of the cute pink house, cartoon, 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/004743/0.png",
"winvideos/004743/1.png",
"winvideos/004743/2.png",
"winvideos/004743/3.png",
"winvideos/004743/4.png",
"winvideos/004743/5.png",
"winvideos/004743/6.png",
"winvideos/004743/7.png",
"losevideos/004743/0.png",
"losevideos/004743/1.png",
"losevideos/004743/2.png",
"losevideos/004743/3.png",
"losevideos/004743/4.png",
"losevideos/004743/5.png",
"losevideos/004743/6.png",
"losevideos/004743/7.png"
] |
alice liddell in the middle of a school playground, she is holding syringes, rabbits are running around her -ar 9:16 -motion 3 -camera rotate clockwise.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [alice liddell in the middle of a school playground, she is holding syringes, rabbits are running around her -ar 9:16 -motion 3 -camera rotate clockwise.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/005864/0.png",
"losevideos/005864/1.png",
"losevideos/005864/2.png",
"losevideos/005864/3.png",
"losevideos/005864/4.png",
"losevideos/005864/5.png",
"losevideos/005864/6.png",
"losevideos/005864/7.png",
"winvideos/005864/0.png",
"winvideos/005864/1.png",
"winvideos/005864/2.png",
"winvideos/005864/3.png",
"winvideos/005864/4.png",
"winvideos/005864/5.png",
"winvideos/005864/6.png",
"winvideos/005864/7.png"
] |
high angle shot, frontal shot, centered, a round triangular spaceship vehicle with neon details is accelerating on a track with futuristic buildings, city with tron legacy movie style lines, photorealistic -neg "deformation, occasional, rays of light, beam of light, smoke, duplicate car, stopped, no movement, extravagant movement, spinning, unreal movement, rear camera, side camera, camera pan, wheels without movement, unreal hands and body, unfinished motorcycle, motorcycle sideways on the track, man sideways on motorcycle, motorcycle in reverse, motorcycles, lightning, lightning, multiple motorcycles, man moving, returning with the motorcycle, strange objects, change, man backwards, without motorcycle, hands and feet outside the motorcycle" -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: [high angle shot, frontal shot, centered, a round triangular spaceship vehicle with neon details is accelerating on a track with futuristic buildings, city with tron legacy movie style lines, photorealistic -neg "deformation, occasional, rays of light, beam of light, smoke, duplicate car, stopped, no movement, extravagant movement, spinning, unreal movement, rear camera, side camera, camera pan, wheels without movement, unreal hands and body, unfinished motorcycle, motorcycle sideways on the track, man sideways on motorcycle, motorcycle in reverse, motorcycles, lightning, lightning, multiple motorcycles, man moving, returning with the motorcycle, strange objects, change, man backwards, without motorcycle, hands and feet outside the motorcycle" -motion 1 -gs 12 - fps 24 -hide.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/008875/0.png",
"winvideos/008875/1.png",
"winvideos/008875/2.png",
"winvideos/008875/3.png",
"winvideos/008875/4.png",
"winvideos/008875/5.png",
"winvideos/008875/6.png",
"winvideos/008875/7.png",
"losevideos/008875/0.png",
"losevideos/008875/1.png",
"losevideos/008875/2.png",
"losevideos/008875/3.png",
"losevideos/008875/4.png",
"losevideos/008875/5.png",
"losevideos/008875/6.png",
"losevideos/008875/7.png"
] |
Content: A mermaid perched on a rock, her tail shimmering in the sunlight, surrounded by colorful coral reefs and schools of fish.
Medium: Underwater Fantasy Photography
Style: A blend of the ethereal aesthetic of Annie Leibovitz's fairy tale series and the vibrant colors of Lisa Frank.
Lighting: Sunlight filtering through the water, casting golden rays on the mermaid and the surrounding marine life.
Colors: Vibrant teals and blues for the ocean, iridescent greens and purples for the mermaid's tail, and a rainbow of colors for the coral and fish.
Composition: Shot on a Fujifilm GFX 100S, GF 32-64mm f/4 R LM WR lens, Resolution 102 megapixels, ISO sensitivity: 12,800, Shutter speed 1/4000 second.
--ar 16:9 --v 5.1 --style raw --q 2 --s 750.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Content: A mermaid perched on a rock, her tail shimmering in the sunlight, surrounded by colorful coral reefs and schools of fish.\nMedium: Underwater Fantasy Photography\nStyle: A blend of the ethereal aesthetic of Annie Leibovitz's fairy tale series and the vibrant colors of Lisa Frank.\nLighting: Sunlight filtering through the water, casting golden rays on the mermaid and the surrounding marine life.\nColors: Vibrant teals and blues for the ocean, iridescent greens and purples for the mermaid's tail, and a rainbow of colors for the coral and fish.\nComposition: Shot on a Fujifilm GFX 100S, GF 32-64mm f/4 R LM WR lens, Resolution 102 megapixels, ISO sensitivity: 12,800, Shutter speed 1/4000 second.\n--ar 16:9 --v 5.1 --style raw --q 2 --s 750.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/005865/0.png",
"winvideos/005865/1.png",
"winvideos/005865/2.png",
"winvideos/005865/3.png",
"winvideos/005865/4.png",
"winvideos/005865/5.png",
"winvideos/005865/6.png",
"winvideos/005865/7.png",
"losevideos/005865/0.png",
"losevideos/005865/1.png",
"losevideos/005865/2.png",
"losevideos/005865/3.png",
"losevideos/005865/4.png",
"losevideos/005865/5.png",
"losevideos/005865/6.png",
"losevideos/005865/7.png"
] |
man walking slowly inside a coliseum full of blood. leaving behind bodies of their defeated enemies. dark and cloudy environment. Far 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: [man walking slowly inside a coliseum full of blood. leaving behind bodies of their defeated enemies. dark and cloudy environment. Far front view.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/003071/0.png",
"winvideos/003071/1.png",
"winvideos/003071/2.png",
"winvideos/003071/3.png",
"winvideos/003071/4.png",
"winvideos/003071/5.png",
"winvideos/003071/6.png",
"winvideos/003071/7.png",
"losevideos/003071/0.png",
"losevideos/003071/1.png",
"losevideos/003071/2.png",
"losevideos/003071/3.png",
"losevideos/003071/4.png",
"losevideos/003071/5.png",
"losevideos/003071/6.png",
"losevideos/003071/7.png"
] |
lotus flower, van gogh.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [lotus flower, van gogh.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/005486/0.png",
"losevideos/005486/1.png",
"losevideos/005486/2.png",
"losevideos/005486/3.png",
"losevideos/005486/4.png",
"losevideos/005486/5.png",
"losevideos/005486/6.png",
"losevideos/005486/7.png",
"winvideos/005486/0.png",
"winvideos/005486/1.png",
"winvideos/005486/2.png",
"winvideos/005486/3.png",
"winvideos/005486/4.png",
"winvideos/005486/5.png",
"winvideos/005486/6.png",
"winvideos/005486/7.png"
] |
The little monk has round and bright eyes. He wears a golden cassock and has Buddhist beads hanging around his neck. The background is the universe. His skin is white and crystal clear. He smiles. HYPER REAL.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: [The little monk has round and bright eyes. He wears a golden cassock and has Buddhist beads hanging around his neck. The background is the universe. His skin is white and crystal clear. He smiles. HYPER REAL.4K.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/003101/0.png",
"losevideos/003101/1.png",
"losevideos/003101/2.png",
"losevideos/003101/3.png",
"losevideos/003101/4.png",
"losevideos/003101/5.png",
"losevideos/003101/6.png",
"losevideos/003101/7.png",
"winvideos/003101/0.png",
"winvideos/003101/1.png",
"winvideos/003101/2.png",
"winvideos/003101/3.png",
"winvideos/003101/4.png",
"winvideos/003101/5.png",
"winvideos/003101/6.png",
"winvideos/003101/7.png"
] |
Imagine a colossal, bioluminescent jellyfish floating gracefully in the depths of an alien ocean. Its translucent, iridescent body shimmers with a mesmerizing array of colors, while long, tendrillike appendages trail behind it, catching the faint glow of phosphorescent organisms that illuminate the eerie, otherworldly aquatic environment. The jellyfish pulses with a gentle, hypnotic rhythm, casting an ethereal glow that bathes the surrounding marine life in a surreal, dreamlike ambiance.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Imagine a colossal, bioluminescent jellyfish floating gracefully in the depths of an alien ocean. Its translucent, iridescent body shimmers with a mesmerizing array of colors, while long, tendrillike appendages trail behind it, catching the faint glow of phosphorescent organisms that illuminate the eerie, otherworldly aquatic environment. The jellyfish pulses with a gentle, hypnotic rhythm, casting an ethereal glow that bathes the surrounding marine life in a surreal, dreamlike ambiance.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/009956/0.png",
"losevideos/009956/1.png",
"losevideos/009956/2.png",
"losevideos/009956/3.png",
"losevideos/009956/4.png",
"losevideos/009956/5.png",
"losevideos/009956/6.png",
"losevideos/009956/7.png",
"winvideos/009956/0.png",
"winvideos/009956/1.png",
"winvideos/009956/2.png",
"winvideos/009956/3.png",
"winvideos/009956/4.png",
"winvideos/009956/5.png",
"winvideos/009956/6.png",
"winvideos/009956/7.png"
] |
astronaut riding a horse.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [astronaut riding a horse.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/003455/0.png",
"winvideos/003455/1.png",
"winvideos/003455/2.png",
"winvideos/003455/3.png",
"winvideos/003455/4.png",
"winvideos/003455/5.png",
"winvideos/003455/6.png",
"winvideos/003455/7.png",
"losevideos/003455/0.png",
"losevideos/003455/1.png",
"losevideos/003455/2.png",
"losevideos/003455/3.png",
"losevideos/003455/4.png",
"losevideos/003455/5.png",
"losevideos/003455/6.png",
"losevideos/003455/7.png"
] |
frontal photo Upshot foot shot, frontal shot, centered, daytime, a turtle-headed alien wearing alien armor, walking in a futuristic alien metropolis, open location, primary tones, cinematic -neg "deformation, distortion, light rays, light beam, 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: [frontal photo Upshot foot shot, frontal shot, centered, daytime, a turtle-headed alien wearing alien armor, walking in a futuristic alien metropolis, open location, primary tones, cinematic -neg "deformation, distortion, light rays, light beam, 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/005943/0.png",
"winvideos/005943/1.png",
"winvideos/005943/2.png",
"winvideos/005943/3.png",
"winvideos/005943/4.png",
"winvideos/005943/5.png",
"winvideos/005943/6.png",
"winvideos/005943/7.png",
"losevideos/005943/0.png",
"losevideos/005943/1.png",
"losevideos/005943/2.png",
"losevideos/005943/3.png",
"losevideos/005943/4.png",
"losevideos/005943/5.png",
"losevideos/005943/6.png",
"losevideos/005943/7.png"
] |
An antique vintage photograph featuring a lake, shrouded in a dark atmosphere, creating a mysterious ambiance; shot in 4K resolution with HDR and UHDR effects, emphasize the moody lighting, subtle details, and the overall eerie feeling, Photography, Canon EOS R5, 24-70mm lens, f/2.8,.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 antique vintage photograph featuring a lake, shrouded in a dark atmosphere, creating a mysterious ambiance; shot in 4K resolution with HDR and UHDR effects, emphasize the moody lighting, subtle details, and the overall eerie feeling, Photography, Canon EOS R5, 24-70mm lens, f/2.8,.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/008629/0.png",
"losevideos/008629/1.png",
"losevideos/008629/2.png",
"losevideos/008629/3.png",
"losevideos/008629/4.png",
"losevideos/008629/5.png",
"losevideos/008629/6.png",
"losevideos/008629/7.png",
"winvideos/008629/0.png",
"winvideos/008629/1.png",
"winvideos/008629/2.png",
"winvideos/008629/3.png",
"winvideos/008629/4.png",
"winvideos/008629/5.png",
"winvideos/008629/6.png",
"winvideos/008629/7.png"
] |
animate a scene where a real man has a real snake head and the atmosphere is like he is in a huge cave like 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: [animate a scene where a real man has a real snake head and the atmosphere is like he is in a huge cave like space.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/004137/0.png",
"losevideos/004137/1.png",
"losevideos/004137/2.png",
"losevideos/004137/3.png",
"losevideos/004137/4.png",
"losevideos/004137/5.png",
"losevideos/004137/6.png",
"losevideos/004137/7.png",
"winvideos/004137/0.png",
"winvideos/004137/1.png",
"winvideos/004137/2.png",
"winvideos/004137/3.png",
"winvideos/004137/4.png",
"winvideos/004137/5.png",
"winvideos/004137/6.png",
"winvideos/004137/7.png"
] |
bus moving right.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [bus moving right.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/002827/0.png",
"losevideos/002827/1.png",
"losevideos/002827/2.png",
"losevideos/002827/3.png",
"losevideos/002827/4.png",
"losevideos/002827/5.png",
"losevideos/002827/6.png",
"losevideos/002827/7.png",
"winvideos/002827/0.png",
"winvideos/002827/1.png",
"winvideos/002827/2.png",
"winvideos/002827/3.png",
"winvideos/002827/4.png",
"winvideos/002827/5.png",
"winvideos/002827/6.png",
"winvideos/002827/7.png"
] |
/imagine prompt: 3d, personality: [The music builds up to a heroic crescendo as quick cuts of Lord Shiva demonstrate his strength and determination in the midst of the battle. His expressions are focused and resolute, showcasing his unwavering resolve to defeat the darkness.] unreal engine, hyper real --q 2 --v 5.2 --ar 16:9.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [/imagine prompt: 3d, personality: [The music builds up to a heroic crescendo as quick cuts of Lord Shiva demonstrate his strength and determination in the midst of the battle. His expressions are focused and resolute, showcasing his unwavering resolve to defeat the darkness.] unreal engine, hyper real --q 2 --v 5.2 --ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/002675/0.png",
"losevideos/002675/1.png",
"losevideos/002675/2.png",
"losevideos/002675/3.png",
"losevideos/002675/4.png",
"losevideos/002675/5.png",
"losevideos/002675/6.png",
"losevideos/002675/7.png",
"winvideos/002675/0.png",
"winvideos/002675/1.png",
"winvideos/002675/2.png",
"winvideos/002675/3.png",
"winvideos/002675/4.png",
"winvideos/002675/5.png",
"winvideos/002675/6.png",
"winvideos/002675/7.png"
] |
Full frame the exoplanet with Earth-like atmosphere and landscapes, beautiful and coloful. deep space -fps 24 -motion 4 -ar16:9.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Full frame the exoplanet with Earth-like atmosphere and landscapes, beautiful and coloful. deep space -fps 24 -motion 4 -ar16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/009563/0.png",
"winvideos/009563/1.png",
"winvideos/009563/2.png",
"winvideos/009563/3.png",
"winvideos/009563/4.png",
"winvideos/009563/5.png",
"winvideos/009563/6.png",
"winvideos/009563/7.png",
"losevideos/009563/0.png",
"losevideos/009563/1.png",
"losevideos/009563/2.png",
"losevideos/009563/3.png",
"losevideos/009563/4.png",
"losevideos/009563/5.png",
"losevideos/009563/6.png",
"losevideos/009563/7.png"
] |
a sheep with hair made of cash bills.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 sheep with hair made of cash bills.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
] |
[
"winvideos/004659/0.png",
"winvideos/004659/1.png",
"winvideos/004659/2.png",
"winvideos/004659/3.png",
"winvideos/004659/4.png",
"winvideos/004659/5.png",
"winvideos/004659/6.png",
"winvideos/004659/7.png",
"losevideos/004659/0.png",
"losevideos/004659/1.png",
"losevideos/004659/2.png",
"losevideos/004659/3.png",
"losevideos/004659/4.png",
"losevideos/004659/5.png",
"losevideos/004659/6.png",
"losevideos/004659/7.png"
] |
Cat on a kickboard running at super-light speed.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Cat on a kickboard running at super-light speed.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/006417/0.png",
"losevideos/006417/1.png",
"losevideos/006417/2.png",
"losevideos/006417/3.png",
"losevideos/006417/4.png",
"losevideos/006417/5.png",
"losevideos/006417/6.png",
"losevideos/006417/7.png",
"winvideos/006417/0.png",
"winvideos/006417/1.png",
"winvideos/006417/2.png",
"winvideos/006417/3.png",
"winvideos/006417/4.png",
"winvideos/006417/5.png",
"winvideos/006417/6.png",
"winvideos/006417/7.png"
] |
Beautiful woman's eyes emerging from the ocean at sunrise.
|
[
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Beautiful woman's eyes emerging from the ocean at sunrise.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
] |
[
"losevideos/003329/0.png",
"losevideos/003329/1.png",
"losevideos/003329/2.png",
"losevideos/003329/3.png",
"losevideos/003329/4.png",
"losevideos/003329/5.png",
"losevideos/003329/6.png",
"losevideos/003329/7.png",
"winvideos/003329/0.png",
"winvideos/003329/1.png",
"winvideos/003329/2.png",
"winvideos/003329/3.png",
"winvideos/003329/4.png",
"winvideos/003329/5.png",
"winvideos/003329/6.png",
"winvideos/003329/7.png"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.