Datasets:

CodeGoat24
/

VideoDPO

Dataset card Data Studio Files Files and versions Community

Split (1)

train · 10k rows

Subsets and Splits

No community queries yet

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

prompt stringlengths 4 8.37k	conversations listlengths 2 2	images sequencelengths 16 16
a dancing christmas tree with two wooden legs.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 dancing christmas tree with two wooden legs.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009640/0.png", "winvideos/009640/1.png", "winvideos/009640/2.png", "winvideos/009640/3.png", "winvideos/009640/4.png", "winvideos/009640/5.png", "winvideos/009640/6.png", "winvideos/009640/7.png", "losevideos/009640/0.png", "losevideos/009640/1.png", "losevideos/009640/2.png", "losevideos/009640/3.png", "losevideos/009640/4.png", "losevideos/009640/5.png", "losevideos/009640/6.png", "losevideos/009640/7.png" ]
globe in the smoke.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [globe in the smoke.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005941/0.png", "losevideos/005941/1.png", "losevideos/005941/2.png", "losevideos/005941/3.png", "losevideos/005941/4.png", "losevideos/005941/5.png", "losevideos/005941/6.png", "losevideos/005941/7.png", "winvideos/005941/0.png", "winvideos/005941/1.png", "winvideos/005941/2.png", "winvideos/005941/3.png", "winvideos/005941/4.png", "winvideos/005941/5.png", "winvideos/005941/6.png", "winvideos/005941/7.png" ]
Begin with an underwater scene, showcasing the colorful and lively underwater world.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Begin with an underwater scene, showcasing the colorful and lively underwater world.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001628/0.png", "losevideos/001628/1.png", "losevideos/001628/2.png", "losevideos/001628/3.png", "losevideos/001628/4.png", "losevideos/001628/5.png", "losevideos/001628/6.png", "losevideos/001628/7.png", "winvideos/001628/0.png", "winvideos/001628/1.png", "winvideos/001628/2.png", "winvideos/001628/3.png", "winvideos/001628/4.png", "winvideos/001628/5.png", "winvideos/001628/6.png", "winvideos/001628/7.png" ]
The cat climbed the tree.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The cat climbed the tree.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008147/0.png", "losevideos/008147/1.png", "losevideos/008147/2.png", "losevideos/008147/3.png", "losevideos/008147/4.png", "losevideos/008147/5.png", "losevideos/008147/6.png", "losevideos/008147/7.png", "winvideos/008147/0.png", "winvideos/008147/1.png", "winvideos/008147/2.png", "winvideos/008147/3.png", "winvideos/008147/4.png", "winvideos/008147/5.png", "winvideos/008147/6.png", "winvideos/008147/7.png" ]
man in beautiful camelhair coat collides with young white woman wearing jeans in foyer of un building in New York -cinematic -fps24.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 in beautiful camelhair coat collides with young white woman wearing jeans in foyer of un building in New York -cinematic -fps24.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003521/0.png", "losevideos/003521/1.png", "losevideos/003521/2.png", "losevideos/003521/3.png", "losevideos/003521/4.png", "losevideos/003521/5.png", "losevideos/003521/6.png", "losevideos/003521/7.png", "winvideos/003521/0.png", "winvideos/003521/1.png", "winvideos/003521/2.png", "winvideos/003521/3.png", "winvideos/003521/4.png", "winvideos/003521/5.png", "winvideos/003521/6.png", "winvideos/003521/7.png" ]
virus in the bloodstream.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [virus in the bloodstream.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004310/0.png", "losevideos/004310/1.png", "losevideos/004310/2.png", "losevideos/004310/3.png", "losevideos/004310/4.png", "losevideos/004310/5.png", "losevideos/004310/6.png", "losevideos/004310/7.png", "winvideos/004310/0.png", "winvideos/004310/1.png", "winvideos/004310/2.png", "winvideos/004310/3.png", "winvideos/004310/4.png", "winvideos/004310/5.png", "winvideos/004310/6.png", "winvideos/004310/7.png" ]
school of fish swimming. 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: [school of fish swimming. ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001983/0.png", "winvideos/001983/1.png", "winvideos/001983/2.png", "winvideos/001983/3.png", "winvideos/001983/4.png", "winvideos/001983/5.png", "winvideos/001983/6.png", "winvideos/001983/7.png", "losevideos/001983/0.png", "losevideos/001983/1.png", "losevideos/001983/2.png", "losevideos/001983/3.png", "losevideos/001983/4.png", "losevideos/001983/5.png", "losevideos/001983/6.png", "losevideos/001983/7.png" ]
MEDIUM: 3D animation, 2D animation, Cinematic Film, Animation, Cartoon, STYLE: Pixar, Dreamworks, Animation, anime, Spiderverse, Incredibles, Murakami SCENE: A space themed open aired food stand on a it’s own meteorite, a galactic sushi bar and ramen stand, kooky, fun, colorful ACTION: Spaceships flying in the background, twinkling stars, moving milkyways MODULATE: Shooting stars, space ship boosters, colorful milkyways PARAMETERS: Details to follow 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: [MEDIUM: 3D animation, 2D animation, Cinematic Film, Animation, Cartoon, STYLE: Pixar, Dreamworks, Animation, anime, Spiderverse, Incredibles, Murakami SCENE: A space themed open aired food stand on a it’s own meteorite, a galactic sushi bar and ramen stand, kooky, fun, colorful ACTION: Spaceships flying in the background, twinkling stars, moving milkyways MODULATE: Shooting stars, space ship boosters, colorful milkyways PARAMETERS: Details to follow Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000018/0.png", "winvideos/000018/1.png", "winvideos/000018/2.png", "winvideos/000018/3.png", "winvideos/000018/4.png", "winvideos/000018/5.png", "winvideos/000018/6.png", "winvideos/000018/7.png", "losevideos/000018/0.png", "losevideos/000018/1.png", "losevideos/000018/2.png", "losevideos/000018/3.png", "losevideos/000018/4.png", "losevideos/000018/5.png", "losevideos/000018/6.png", "losevideos/000018/7.png" ]
Retratar a beleza e a alegria da vida através de personagens animados em aquarela, celebrando momentos preciosos juntos. <strong>Formato:</strong> Animação em estilo aquarela. <strong>Cenário:</strong> Um parque urbano amplo com árvores, bancos, um lago e crianças brincando. As cores são vibrantes e fluidas, com bordas suaves e tons que se misturam organicamente. cinematic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Retratar a beleza e a alegria da vida através de personagens animados em aquarela, celebrando momentos preciosos juntos. <strong>Formato:</strong> Animação em estilo aquarela. <strong>Cenário:</strong> Um parque urbano amplo com árvores, bancos, um lago e crianças brincando. As cores são vibrantes e fluidas, com bordas suaves e tons que se misturam organicamente. cinematic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008335/0.png", "losevideos/008335/1.png", "losevideos/008335/2.png", "losevideos/008335/3.png", "losevideos/008335/4.png", "losevideos/008335/5.png", "losevideos/008335/6.png", "losevideos/008335/7.png", "winvideos/008335/0.png", "winvideos/008335/1.png", "winvideos/008335/2.png", "winvideos/008335/3.png", "winvideos/008335/4.png", "winvideos/008335/5.png", "winvideos/008335/6.png", "winvideos/008335/7.png" ]
a photorealistic,cinematic scene of a virtual reality show at a convention center.-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: [a photorealistic,cinematic scene of a virtual reality show at a convention center.-motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005285/0.png", "losevideos/005285/1.png", "losevideos/005285/2.png", "losevideos/005285/3.png", "losevideos/005285/4.png", "losevideos/005285/5.png", "losevideos/005285/6.png", "losevideos/005285/7.png", "winvideos/005285/0.png", "winvideos/005285/1.png", "winvideos/005285/2.png", "winvideos/005285/3.png", "winvideos/005285/4.png", "winvideos/005285/5.png", "winvideos/005285/6.png", "winvideos/005285/7.png" ]
travelling cam: side long shot of man walking through the streets of a city with architectural buildings in Brooklyn, award-winning photography for Moma Art, black and white, cinematic, filmandarts.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [travelling cam: side long shot of man walking through the streets of a city with architectural buildings in Brooklyn, award-winning photography for Moma Art, black and white, cinematic, filmandarts.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003555/0.png", "losevideos/003555/1.png", "losevideos/003555/2.png", "losevideos/003555/3.png", "losevideos/003555/4.png", "losevideos/003555/5.png", "losevideos/003555/6.png", "losevideos/003555/7.png", "winvideos/003555/0.png", "winvideos/003555/1.png", "winvideos/003555/2.png", "winvideos/003555/3.png", "winvideos/003555/4.png", "winvideos/003555/5.png", "winvideos/003555/6.png", "winvideos/003555/7.png" ]
mattel's barbie dreamnuclear bomb toy.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [mattel's barbie dreamnuclear bomb toy.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004790/0.png", "winvideos/004790/1.png", "winvideos/004790/2.png", "winvideos/004790/3.png", "winvideos/004790/4.png", "winvideos/004790/5.png", "winvideos/004790/6.png", "winvideos/004790/7.png", "losevideos/004790/0.png", "losevideos/004790/1.png", "losevideos/004790/2.png", "losevideos/004790/3.png", "losevideos/004790/4.png", "losevideos/004790/5.png", "losevideos/004790/6.png", "losevideos/004790/7.png" ]
child eating vitamine.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [child eating vitamine.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006639/0.png", "losevideos/006639/1.png", "losevideos/006639/2.png", "losevideos/006639/3.png", "losevideos/006639/4.png", "losevideos/006639/5.png", "losevideos/006639/6.png", "losevideos/006639/7.png", "winvideos/006639/0.png", "winvideos/006639/1.png", "winvideos/006639/2.png", "winvideos/006639/3.png", "winvideos/006639/4.png", "winvideos/006639/5.png", "winvideos/006639/6.png", "winvideos/006639/7.png" ]
drawing of lonestar in sky animated.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [drawing of lonestar in sky animated.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005249/0.png", "winvideos/005249/1.png", "winvideos/005249/2.png", "winvideos/005249/3.png", "winvideos/005249/4.png", "winvideos/005249/5.png", "winvideos/005249/6.png", "winvideos/005249/7.png", "losevideos/005249/0.png", "losevideos/005249/1.png", "losevideos/005249/2.png", "losevideos/005249/3.png", "losevideos/005249/4.png", "losevideos/005249/5.png", "losevideos/005249/6.png", "losevideos/005249/7.png" ]
A human with the features of a devil, two horns, and a red color.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A human with the features of a devil, two horns, and a red color.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006385/0.png", "losevideos/006385/1.png", "losevideos/006385/2.png", "losevideos/006385/3.png", "losevideos/006385/4.png", "losevideos/006385/5.png", "losevideos/006385/6.png", "losevideos/006385/7.png", "winvideos/006385/0.png", "winvideos/006385/1.png", "winvideos/006385/2.png", "winvideos/006385/3.png", "winvideos/006385/4.png", "winvideos/006385/5.png", "winvideos/006385/6.png", "winvideos/006385/7.png" ]
viking driving a bus.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [viking driving a bus.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000521/0.png", "winvideos/000521/1.png", "winvideos/000521/2.png", "winvideos/000521/3.png", "winvideos/000521/4.png", "winvideos/000521/5.png", "winvideos/000521/6.png", "winvideos/000521/7.png", "losevideos/000521/0.png", "losevideos/000521/1.png", "losevideos/000521/2.png", "losevideos/000521/3.png", "losevideos/000521/4.png", "losevideos/000521/5.png", "losevideos/000521/6.png", "losevideos/000521/7.png" ]
nani teri morni ko mor lay gaye.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [nani teri morni ko mor lay gaye.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003934/0.png", "losevideos/003934/1.png", "losevideos/003934/2.png", "losevideos/003934/3.png", "losevideos/003934/4.png", "losevideos/003934/5.png", "losevideos/003934/6.png", "losevideos/003934/7.png", "winvideos/003934/0.png", "winvideos/003934/1.png", "winvideos/003934/2.png", "winvideos/003934/3.png", "winvideos/003934/4.png", "winvideos/003934/5.png", "winvideos/003934/6.png", "winvideos/003934/7.png" ]
cartoon ant.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 ant.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009302/0.png", "winvideos/009302/1.png", "winvideos/009302/2.png", "winvideos/009302/3.png", "winvideos/009302/4.png", "winvideos/009302/5.png", "winvideos/009302/6.png", "winvideos/009302/7.png", "losevideos/009302/0.png", "losevideos/009302/1.png", "losevideos/009302/2.png", "losevideos/009302/3.png", "losevideos/009302/4.png", "losevideos/009302/5.png", "losevideos/009302/6.png", "losevideos/009302/7.png" ]
template for the game "just dance" with people from east timor dancing.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [template for the game "just dance" with people from east timor dancing.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009935/0.png", "winvideos/009935/1.png", "winvideos/009935/2.png", "winvideos/009935/3.png", "winvideos/009935/4.png", "winvideos/009935/5.png", "winvideos/009935/6.png", "winvideos/009935/7.png", "losevideos/009935/0.png", "losevideos/009935/1.png", "losevideos/009935/2.png", "losevideos/009935/3.png", "losevideos/009935/4.png", "losevideos/009935/5.png", "losevideos/009935/6.png", "losevideos/009935/7.png" ]
occult temple where a priest holds a dish with red jelly.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [occult temple where a priest holds a dish with red jelly.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002045/0.png", "losevideos/002045/1.png", "losevideos/002045/2.png", "losevideos/002045/3.png", "losevideos/002045/4.png", "losevideos/002045/5.png", "losevideos/002045/6.png", "losevideos/002045/7.png", "winvideos/002045/0.png", "winvideos/002045/1.png", "winvideos/002045/2.png", "winvideos/002045/3.png", "winvideos/002045/4.png", "winvideos/002045/5.png", "winvideos/002045/6.png", "winvideos/002045/7.png" ]
sad clown bringing a revolver up to point at his head.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [sad clown bringing a revolver up to point at his head.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007429/0.png", "losevideos/007429/1.png", "losevideos/007429/2.png", "losevideos/007429/3.png", "losevideos/007429/4.png", "losevideos/007429/5.png", "losevideos/007429/6.png", "losevideos/007429/7.png", "winvideos/007429/0.png", "winvideos/007429/1.png", "winvideos/007429/2.png", "winvideos/007429/3.png", "winvideos/007429/4.png", "winvideos/007429/5.png", "winvideos/007429/6.png", "winvideos/007429/7.png" ]
<a href="https://cdn.discordapp.com/attachments/1129173449592553564/1134073334540283924/mmexport1688648069196.webp">https://cdn.discordapp.com/attachments/1129173449592553564/1134073334540283924/mmexport1688648069196.webp</a> Cleopatra, smiling sideways.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [<a href=\"https://cdn.discordapp.com/attachments/1129173449592553564/1134073334540283924/mmexport1688648069196.webp\">https://cdn.discordapp.com/attachments/1129173449592553564/1134073334540283924/mmexport1688648069196.webp</a> Cleopatra, smiling sideways.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005116/0.png", "losevideos/005116/1.png", "losevideos/005116/2.png", "losevideos/005116/3.png", "losevideos/005116/4.png", "losevideos/005116/5.png", "losevideos/005116/6.png", "losevideos/005116/7.png", "winvideos/005116/0.png", "winvideos/005116/1.png", "winvideos/005116/2.png", "winvideos/005116/3.png", "winvideos/005116/4.png", "winvideos/005116/5.png", "winvideos/005116/6.png", "winvideos/005116/7.png" ]
/imagine prompt: 3D Animation, personality: [Outdoors in the dusty football field, Johnny and his friends, Tom, Peter, and David, kick a ball around. They are engrossed in laughter and playful banter, their genuine happiness is evident in their expressions. The dusty field and the vibrant colors of their clothes create a lively atmosphere]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 Animation, personality: [Outdoors in the dusty football field, Johnny and his friends, Tom, Peter, and David, kick a ball around. They are engrossed in laughter and playful banter, their genuine happiness is evident in their expressions. The dusty field and the vibrant colors of their clothes create a lively atmosphere]unreal engine, hyper real --q 2 --v 5.2 --ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000348/0.png", "losevideos/000348/1.png", "losevideos/000348/2.png", "losevideos/000348/3.png", "losevideos/000348/4.png", "losevideos/000348/5.png", "losevideos/000348/6.png", "losevideos/000348/7.png", "winvideos/000348/0.png", "winvideos/000348/1.png", "winvideos/000348/2.png", "winvideos/000348/3.png", "winvideos/000348/4.png", "winvideos/000348/5.png", "winvideos/000348/6.png", "winvideos/000348/7.png" ]
screen showing someone using gpt chat.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [screen showing someone using gpt chat.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005722/0.png", "winvideos/005722/1.png", "winvideos/005722/2.png", "winvideos/005722/3.png", "winvideos/005722/4.png", "winvideos/005722/5.png", "winvideos/005722/6.png", "winvideos/005722/7.png", "losevideos/005722/0.png", "losevideos/005722/1.png", "losevideos/005722/2.png", "losevideos/005722/3.png", "losevideos/005722/4.png", "losevideos/005722/5.png", "losevideos/005722/6.png", "losevideos/005722/7.png" ]
titanic ship in the bottom of the ocean.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [titanic ship in the bottom of the ocean.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007414/0.png", "winvideos/007414/1.png", "winvideos/007414/2.png", "winvideos/007414/3.png", "winvideos/007414/4.png", "winvideos/007414/5.png", "winvideos/007414/6.png", "winvideos/007414/7.png", "losevideos/007414/0.png", "losevideos/007414/1.png", "losevideos/007414/2.png", "losevideos/007414/3.png", "losevideos/007414/4.png", "losevideos/007414/5.png", "losevideos/007414/6.png", "losevideos/007414/7.png" ]
sunrise between two mountains.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [sunrise between two mountains.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008320/0.png", "losevideos/008320/1.png", "losevideos/008320/2.png", "losevideos/008320/3.png", "losevideos/008320/4.png", "losevideos/008320/5.png", "losevideos/008320/6.png", "losevideos/008320/7.png", "winvideos/008320/0.png", "winvideos/008320/1.png", "winvideos/008320/2.png", "winvideos/008320/3.png", "winvideos/008320/4.png", "winvideos/008320/5.png", "winvideos/008320/6.png", "winvideos/008320/7.png" ]
without head, in the cirque du soleil.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [without head, in the cirque du soleil.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004741/0.png", "losevideos/004741/1.png", "losevideos/004741/2.png", "losevideos/004741/3.png", "losevideos/004741/4.png", "losevideos/004741/5.png", "losevideos/004741/6.png", "losevideos/004741/7.png", "winvideos/004741/0.png", "winvideos/004741/1.png", "winvideos/004741/2.png", "winvideos/004741/3.png", "winvideos/004741/4.png", "winvideos/004741/5.png", "winvideos/004741/6.png", "winvideos/004741/7.png" ]
one man in hoodie, inside a house bludgeoning a guy in white t shirt with a machete , making him bleed, blood slplattering.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [one man in hoodie, inside a house bludgeoning a guy in white t shirt with a machete , making him bleed, blood slplattering.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002982/0.png", "losevideos/002982/1.png", "losevideos/002982/2.png", "losevideos/002982/3.png", "losevideos/002982/4.png", "losevideos/002982/5.png", "losevideos/002982/6.png", "losevideos/002982/7.png", "winvideos/002982/0.png", "winvideos/002982/1.png", "winvideos/002982/2.png", "winvideos/002982/3.png", "winvideos/002982/4.png", "winvideos/002982/5.png", "winvideos/002982/6.png", "winvideos/002982/7.png" ]
A serene view of Jupiter and its four Galilean moons. High movement. Hyperrealistic. --ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A serene view of Jupiter and its four Galilean moons. High movement. Hyperrealistic. --ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005932/0.png", "losevideos/005932/1.png", "losevideos/005932/2.png", "losevideos/005932/3.png", "losevideos/005932/4.png", "losevideos/005932/5.png", "losevideos/005932/6.png", "losevideos/005932/7.png", "winvideos/005932/0.png", "winvideos/005932/1.png", "winvideos/005932/2.png", "winvideos/005932/3.png", "winvideos/005932/4.png", "winvideos/005932/5.png", "winvideos/005932/6.png", "winvideos/005932/7.png" ]
onam celebration trailer.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [onam celebration trailer.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004464/0.png", "winvideos/004464/1.png", "winvideos/004464/2.png", "winvideos/004464/3.png", "winvideos/004464/4.png", "winvideos/004464/5.png", "winvideos/004464/6.png", "winvideos/004464/7.png", "losevideos/004464/0.png", "losevideos/004464/1.png", "losevideos/004464/2.png", "losevideos/004464/3.png", "losevideos/004464/4.png", "losevideos/004464/5.png", "losevideos/004464/6.png", "losevideos/004464/7.png" ]
Twinkle Twinkle Little Star.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Twinkle Twinkle Little Star.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002869/0.png", "winvideos/002869/1.png", "winvideos/002869/2.png", "winvideos/002869/3.png", "winvideos/002869/4.png", "winvideos/002869/5.png", "winvideos/002869/6.png", "winvideos/002869/7.png", "losevideos/002869/0.png", "losevideos/002869/1.png", "losevideos/002869/2.png", "losevideos/002869/3.png", "losevideos/002869/4.png", "losevideos/002869/5.png", "losevideos/002869/6.png", "losevideos/002869/7.png" ]
REM Sleep inspired, Rembrandt inspired, Aboriginal Dot painting inspired, Hyper resolution, Apostlets of the Black Sun terraform the Earth to make way for the dawn of the African Man. POV you spawn in a world in which a massive locust storm is occuring. The locusts are bioluminescent creating a light tornado. You are birthed from the rings of Saturn and embark on an interplanetary voyage to Earth. A coucil of cosmic elders, magicians, and sages take you through a SHAMANIC ritual. You see spiraling galaxies and illumiating star seeds. You percieve vibrations up to the eighth dimension. The Black Sun is Saturn. Its rings are made of crystals. These crystals radiate pure energy onto the Earth. You see these vibrations flowing in vibrant synesthesia. Visual focal point. Cinematic lighting: Vivid, vibrant, live flame, jarring, Annunaki, Eclipse, Star Wars, Obi Wan, Quantum jumping, Realm hopping, supernatural currency, Time wave current, Crystal reflection, destiny, Ancient past, Far future, Wormhole, quantum entaglement, high beauty, super summetry -pos "high contrast, complex, starry sky"-neg "dark, poorly drawn, black space" --ar 16:9 -tile fractal, reflective -motion 4 -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: [REM Sleep inspired, Rembrandt inspired, Aboriginal Dot painting inspired, Hyper resolution, Apostlets of the Black Sun terraform the Earth to make way for the dawn of the African Man. POV you spawn in a world in which a massive locust storm is occuring. The locusts are bioluminescent creating a light tornado. You are birthed from the rings of Saturn and embark on an interplanetary voyage to Earth. A coucil of cosmic elders, magicians, and sages take you through a SHAMANIC ritual. You see spiraling galaxies and illumiating star seeds. You percieve vibrations up to the eighth dimension. The Black Sun is Saturn. Its rings are made of crystals. These crystals radiate pure energy onto the Earth. You see these vibrations flowing in vibrant synesthesia. Visual focal point. Cinematic lighting: Vivid, vibrant, live flame, jarring, Annunaki, Eclipse, Star Wars, Obi Wan, Quantum jumping, Realm hopping, supernatural currency, Time wave current, Crystal reflection, destiny, Ancient past, Far future, Wormhole, quantum entaglement, high beauty, super summetry -pos "high contrast, complex, starry sky"-neg "dark, poorly drawn, black space" --ar 16:9 -tile fractal, reflective -motion 4 -camera zoom in.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004986/0.png", "losevideos/004986/1.png", "losevideos/004986/2.png", "losevideos/004986/3.png", "losevideos/004986/4.png", "losevideos/004986/5.png", "losevideos/004986/6.png", "losevideos/004986/7.png", "winvideos/004986/0.png", "winvideos/004986/1.png", "winvideos/004986/2.png", "winvideos/004986/3.png", "winvideos/004986/4.png", "winvideos/004986/5.png", "winvideos/004986/6.png", "winvideos/004986/7.png" ]
3D satisfying animation of a glass wrecking ball hitting a tower of thausends bricks, rendered, soft colors and soft light.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [3D satisfying animation of a glass wrecking ball hitting a tower of thausends bricks, rendered, soft colors and soft light.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008690/0.png", "winvideos/008690/1.png", "winvideos/008690/2.png", "winvideos/008690/3.png", "winvideos/008690/4.png", "winvideos/008690/5.png", "winvideos/008690/6.png", "winvideos/008690/7.png", "losevideos/008690/0.png", "losevideos/008690/1.png", "losevideos/008690/2.png", "losevideos/008690/3.png", "losevideos/008690/4.png", "losevideos/008690/5.png", "losevideos/008690/6.png", "losevideos/008690/7.png" ]
Mother wolf is talking.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Mother wolf is talking.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001333/0.png", "losevideos/001333/1.png", "losevideos/001333/2.png", "losevideos/001333/3.png", "losevideos/001333/4.png", "losevideos/001333/5.png", "losevideos/001333/6.png", "losevideos/001333/7.png", "winvideos/001333/0.png", "winvideos/001333/1.png", "winvideos/001333/2.png", "winvideos/001333/3.png", "winvideos/001333/4.png", "winvideos/001333/5.png", "winvideos/001333/6.png", "winvideos/001333/7.png" ]
Transformers g1 optimus prime asleep in bed . Cartoon 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: [Transformers g1 optimus prime asleep in bed . Cartoon style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003895/0.png", "winvideos/003895/1.png", "winvideos/003895/2.png", "winvideos/003895/3.png", "winvideos/003895/4.png", "winvideos/003895/5.png", "winvideos/003895/6.png", "winvideos/003895/7.png", "losevideos/003895/0.png", "losevideos/003895/1.png", "losevideos/003895/2.png", "losevideos/003895/3.png", "losevideos/003895/4.png", "losevideos/003895/5.png", "losevideos/003895/6.png", "losevideos/003895/7.png" ]
3d style animation crow pick small stone with its beak then flying horizontally close 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: [3d style animation crow pick small stone with its beak then flying horizontally close view.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002878/0.png", "losevideos/002878/1.png", "losevideos/002878/2.png", "losevideos/002878/3.png", "losevideos/002878/4.png", "losevideos/002878/5.png", "losevideos/002878/6.png", "losevideos/002878/7.png", "winvideos/002878/0.png", "winvideos/002878/1.png", "winvideos/002878/2.png", "winvideos/002878/3.png", "winvideos/002878/4.png", "winvideos/002878/5.png", "winvideos/002878/6.png", "winvideos/002878/7.png" ]
a dark anime neo tokyo hip hop style video with laser effects and neon light fractals for the phrase "my eyes not used to the brightness were widened" .......include anime eyes and a reflection in them.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a dark anime neo tokyo hip hop style video with laser effects and neon light fractals for the phrase "my eyes not used to the brightness were widened" .......include anime eyes and a reflection in them.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008616/0.png", "winvideos/008616/1.png", "winvideos/008616/2.png", "winvideos/008616/3.png", "winvideos/008616/4.png", "winvideos/008616/5.png", "winvideos/008616/6.png", "winvideos/008616/7.png", "losevideos/008616/0.png", "losevideos/008616/1.png", "losevideos/008616/2.png", "losevideos/008616/3.png", "losevideos/008616/4.png", "losevideos/008616/5.png", "losevideos/008616/6.png", "losevideos/008616/7.png" ]
epic night nature scene full of stars 32k resolution --ar 9:16 --motion 10.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [epic night nature scene full of stars 32k resolution --ar 9:16 --motion 10.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009189/0.png", "winvideos/009189/1.png", "winvideos/009189/2.png", "winvideos/009189/3.png", "winvideos/009189/4.png", "winvideos/009189/5.png", "winvideos/009189/6.png", "winvideos/009189/7.png", "losevideos/009189/0.png", "losevideos/009189/1.png", "losevideos/009189/2.png", "losevideos/009189/3.png", "losevideos/009189/4.png", "losevideos/009189/5.png", "losevideos/009189/6.png", "losevideos/009189/7.png" ]
Squeaky leading them through a series of magical glades, with glimpses of other creatures in the background. cartoon 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: [Squeaky leading them through a series of magical glades, with glimpses of other creatures in the background. cartoon style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004471/0.png", "winvideos/004471/1.png", "winvideos/004471/2.png", "winvideos/004471/3.png", "winvideos/004471/4.png", "winvideos/004471/5.png", "winvideos/004471/6.png", "winvideos/004471/7.png", "losevideos/004471/0.png", "losevideos/004471/1.png", "losevideos/004471/2.png", "losevideos/004471/3.png", "losevideos/004471/4.png", "losevideos/004471/5.png", "losevideos/004471/6.png", "losevideos/004471/7.png" ]
boys and girls reading book with many little monsters in a creepy place, Tim Burton 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: [boys and girls reading book with many little monsters in a creepy place, Tim Burton style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005562/0.png", "winvideos/005562/1.png", "winvideos/005562/2.png", "winvideos/005562/3.png", "winvideos/005562/4.png", "winvideos/005562/5.png", "winvideos/005562/6.png", "winvideos/005562/7.png", "losevideos/005562/0.png", "losevideos/005562/1.png", "losevideos/005562/2.png", "losevideos/005562/3.png", "losevideos/005562/4.png", "losevideos/005562/5.png", "losevideos/005562/6.png", "losevideos/005562/7.png" ]