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
an alien driving a Car ,8K ,anamorphic,--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: [an alien driving a Car ,8K ,anamorphic,--ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007921/0.png", "losevideos/007921/1.png", "losevideos/007921/2.png", "losevideos/007921/3.png", "losevideos/007921/4.png", "losevideos/007921/5.png", "losevideos/007921/6.png", "losevideos/007921/7.png", "winvideos/007921/0.png", "winvideos/007921/1.png", "winvideos/007921/2.png", "winvideos/007921/3.png", "winvideos/007921/4.png", "winvideos/007921/5.png", "winvideos/007921/6.png", "winvideos/007921/7.png" ]
artificial intelligence, message in 3D, bold message,clear message,message growing larger,Gradient background,message continuously appear,Exquisite,detail,animation style is dynamic and energetic -w 2 -size 50 --gs 24 --ar 16:9 --seed 5678 -camera pan down -motion4 Message: CHEER (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: [artificial intelligence, message in 3D, bold message,clear message,message growing larger,Gradient background,message continuously appear,Exquisite,detail,animation style is dynamic and energetic -w 2 -size 50 --gs 24 --ar 16:9 --seed 5678 -camera pan down -motion4 Message: CHEER (Font: SANS SERIF).]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009966/0.png", "winvideos/009966/1.png", "winvideos/009966/2.png", "winvideos/009966/3.png", "winvideos/009966/4.png", "winvideos/009966/5.png", "winvideos/009966/6.png", "winvideos/009966/7.png", "losevideos/009966/0.png", "losevideos/009966/1.png", "losevideos/009966/2.png", "losevideos/009966/3.png", "losevideos/009966/4.png", "losevideos/009966/5.png", "losevideos/009966/6.png", "losevideos/009966/7.png" ]
real Runner in the rain crossing the finish line in a 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: [real Runner in the rain crossing the finish line in a race.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003302/0.png", "winvideos/003302/1.png", "winvideos/003302/2.png", "winvideos/003302/3.png", "winvideos/003302/4.png", "winvideos/003302/5.png", "winvideos/003302/6.png", "winvideos/003302/7.png", "losevideos/003302/0.png", "losevideos/003302/1.png", "losevideos/003302/2.png", "losevideos/003302/3.png", "losevideos/003302/4.png", "losevideos/003302/5.png", "losevideos/003302/6.png", "losevideos/003302/7.png" ]
Pooh and Piglet, Disney Mode.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Pooh and Piglet, Disney Mode.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001423/0.png", "winvideos/001423/1.png", "winvideos/001423/2.png", "winvideos/001423/3.png", "winvideos/001423/4.png", "winvideos/001423/5.png", "winvideos/001423/6.png", "winvideos/001423/7.png", "losevideos/001423/0.png", "losevideos/001423/1.png", "losevideos/001423/2.png", "losevideos/001423/3.png", "losevideos/001423/4.png", "losevideos/001423/5.png", "losevideos/001423/6.png", "losevideos/001423/7.png" ]
shocked emoji turning into laughing emoji.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [shocked emoji turning into laughing emoji.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008500/0.png", "winvideos/008500/1.png", "winvideos/008500/2.png", "winvideos/008500/3.png", "winvideos/008500/4.png", "winvideos/008500/5.png", "winvideos/008500/6.png", "winvideos/008500/7.png", "losevideos/008500/0.png", "losevideos/008500/1.png", "losevideos/008500/2.png", "losevideos/008500/3.png", "losevideos/008500/4.png", "losevideos/008500/5.png", "losevideos/008500/6.png", "losevideos/008500/7.png" ]
Descreva a primeira corrida clandestina em que Zippy e sua equipe participam, destacando a emoção e a adrenalina que sentem nas ruas da cidade.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Descreva a primeira corrida clandestina em que Zippy e sua equipe participam, destacando a emoção e a adrenalina que sentem nas ruas da cidade.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005151/0.png", "losevideos/005151/1.png", "losevideos/005151/2.png", "losevideos/005151/3.png", "losevideos/005151/4.png", "losevideos/005151/5.png", "losevideos/005151/6.png", "losevideos/005151/7.png", "winvideos/005151/0.png", "winvideos/005151/1.png", "winvideos/005151/2.png", "winvideos/005151/3.png", "winvideos/005151/4.png", "winvideos/005151/5.png", "winvideos/005151/6.png", "winvideos/005151/7.png" ]
an animation studio with several computers generating animations, and animators manning those computers.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 animation studio with several computers generating animations, and animators manning those computers.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008773/0.png", "losevideos/008773/1.png", "losevideos/008773/2.png", "losevideos/008773/3.png", "losevideos/008773/4.png", "losevideos/008773/5.png", "losevideos/008773/6.png", "losevideos/008773/7.png", "winvideos/008773/0.png", "winvideos/008773/1.png", "winvideos/008773/2.png", "winvideos/008773/3.png", "winvideos/008773/4.png", "winvideos/008773/5.png", "winvideos/008773/6.png", "winvideos/008773/7.png" ]
a young boys soccer team looking at a young girls soccer team and talking down on them telling them they are not good at soccer.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a young boys soccer team looking at a young girls soccer team and talking down on them telling them they are not good at soccer.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002324/0.png", "losevideos/002324/1.png", "losevideos/002324/2.png", "losevideos/002324/3.png", "losevideos/002324/4.png", "losevideos/002324/5.png", "losevideos/002324/6.png", "losevideos/002324/7.png", "winvideos/002324/0.png", "winvideos/002324/1.png", "winvideos/002324/2.png", "winvideos/002324/3.png", "winvideos/002324/4.png", "winvideos/002324/5.png", "winvideos/002324/6.png", "winvideos/002324/7.png" ]
A creature with the head of a rattlesnake and the body of a Buffalo.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 creature with the head of a rattlesnake and the body of a Buffalo.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004380/0.png", "winvideos/004380/1.png", "winvideos/004380/2.png", "winvideos/004380/3.png", "winvideos/004380/4.png", "winvideos/004380/5.png", "winvideos/004380/6.png", "winvideos/004380/7.png", "losevideos/004380/0.png", "losevideos/004380/1.png", "losevideos/004380/2.png", "losevideos/004380/3.png", "losevideos/004380/4.png", "losevideos/004380/5.png", "losevideos/004380/6.png", "losevideos/004380/7.png" ]
vehemently advocated for their eradication.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [vehemently advocated for their eradication.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004777/0.png", "winvideos/004777/1.png", "winvideos/004777/2.png", "winvideos/004777/3.png", "winvideos/004777/4.png", "winvideos/004777/5.png", "winvideos/004777/6.png", "winvideos/004777/7.png", "losevideos/004777/0.png", "losevideos/004777/1.png", "losevideos/004777/2.png", "losevideos/004777/3.png", "losevideos/004777/4.png", "losevideos/004777/5.png", "losevideos/004777/6.png", "losevideos/004777/7.png" ]
cinematic, detailed, dramatic, bright sun glowing , gold metallic lion with brilliant mane roars between two trees.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cinematic, detailed, dramatic, bright sun glowing , gold metallic lion with brilliant mane roars between two trees.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006605/0.png", "losevideos/006605/1.png", "losevideos/006605/2.png", "losevideos/006605/3.png", "losevideos/006605/4.png", "losevideos/006605/5.png", "losevideos/006605/6.png", "losevideos/006605/7.png", "winvideos/006605/0.png", "winvideos/006605/1.png", "winvideos/006605/2.png", "winvideos/006605/3.png", "winvideos/006605/4.png", "winvideos/006605/5.png", "winvideos/006605/6.png", "winvideos/006605/7.png" ]
create me a video with a zoom lens of a house.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 me a video with a zoom lens of a house.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003779/0.png", "losevideos/003779/1.png", "losevideos/003779/2.png", "losevideos/003779/3.png", "losevideos/003779/4.png", "losevideos/003779/5.png", "losevideos/003779/6.png", "losevideos/003779/7.png", "winvideos/003779/0.png", "winvideos/003779/1.png", "winvideos/003779/2.png", "winvideos/003779/3.png", "winvideos/003779/4.png", "winvideos/003779/5.png", "winvideos/003779/6.png", "winvideos/003779/7.png" ]
"Generate a comical cartoon panel depicting the monkeys rushing into a nearby cave, seeking refuge from the cold.""hyper realistic, 8k, ultra hd, pixar style,disney style, cinema 4d, --ar 3:2.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: ["Generate a comical cartoon panel depicting the monkeys rushing into a nearby cave, seeking refuge from the cold.""hyper realistic, 8k, ultra hd, pixar style,disney style, cinema 4d, --ar 3:2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009623/0.png", "winvideos/009623/1.png", "winvideos/009623/2.png", "winvideos/009623/3.png", "winvideos/009623/4.png", "winvideos/009623/5.png", "winvideos/009623/6.png", "winvideos/009623/7.png", "losevideos/009623/0.png", "losevideos/009623/1.png", "losevideos/009623/2.png", "losevideos/009623/3.png", "losevideos/009623/4.png", "losevideos/009623/5.png", "losevideos/009623/6.png", "losevideos/009623/7.png" ]
a cat in coat and tails dancing with a fish.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 cat in coat and tails dancing with a fish.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000241/0.png", "winvideos/000241/1.png", "winvideos/000241/2.png", "winvideos/000241/3.png", "winvideos/000241/4.png", "winvideos/000241/5.png", "winvideos/000241/6.png", "winvideos/000241/7.png", "losevideos/000241/0.png", "losevideos/000241/1.png", "losevideos/000241/2.png", "losevideos/000241/3.png", "losevideos/000241/4.png", "losevideos/000241/5.png", "losevideos/000241/6.png", "losevideos/000241/7.png" ]
cat on the sofa playing, c4d 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: [cat on the sofa playing, c4d style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006274/0.png", "winvideos/006274/1.png", "winvideos/006274/2.png", "winvideos/006274/3.png", "winvideos/006274/4.png", "winvideos/006274/5.png", "winvideos/006274/6.png", "winvideos/006274/7.png", "losevideos/006274/0.png", "losevideos/006274/1.png", "losevideos/006274/2.png", "losevideos/006274/3.png", "losevideos/006274/4.png", "losevideos/006274/5.png", "losevideos/006274/6.png", "losevideos/006274/7.png" ]
children top down shot doing bycicle , manga style, creepy mood, god's rays, foggy, neon, moody, manga, watercolor, cinematic, sharp, chromatic aberration, light flares, film halation, drawing, detailed -camera zoom out -ar 9:16 -motion 4 -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: [children top down shot doing bycicle , manga style, creepy mood, god's rays, foggy, neon, moody, manga, watercolor, cinematic, sharp, chromatic aberration, light flares, film halation, drawing, detailed -camera zoom out -ar 9:16 -motion 4 -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/003740/0.png", "losevideos/003740/1.png", "losevideos/003740/2.png", "losevideos/003740/3.png", "losevideos/003740/4.png", "losevideos/003740/5.png", "losevideos/003740/6.png", "losevideos/003740/7.png", "winvideos/003740/0.png", "winvideos/003740/1.png", "winvideos/003740/2.png", "winvideos/003740/3.png", "winvideos/003740/4.png", "winvideos/003740/5.png", "winvideos/003740/6.png", "winvideos/003740/7.png" ]
King wearing a crown and on his throne, laughing.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [King wearing a crown and on his throne, laughing.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002055/0.png", "losevideos/002055/1.png", "losevideos/002055/2.png", "losevideos/002055/3.png", "losevideos/002055/4.png", "losevideos/002055/5.png", "losevideos/002055/6.png", "losevideos/002055/7.png", "winvideos/002055/0.png", "winvideos/002055/1.png", "winvideos/002055/2.png", "winvideos/002055/3.png", "winvideos/002055/4.png", "winvideos/002055/5.png", "winvideos/002055/6.png", "winvideos/002055/7.png" ]
a standing staff find in the forest -ar 16:9 -motion 1.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a standing staff find in the forest -ar 16:9 -motion 1.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004740/0.png", "losevideos/004740/1.png", "losevideos/004740/2.png", "losevideos/004740/3.png", "losevideos/004740/4.png", "losevideos/004740/5.png", "losevideos/004740/6.png", "losevideos/004740/7.png", "winvideos/004740/0.png", "winvideos/004740/1.png", "winvideos/004740/2.png", "winvideos/004740/3.png", "winvideos/004740/4.png", "winvideos/004740/5.png", "winvideos/004740/6.png", "winvideos/004740/7.png" ]
Monkey D. Dragon.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Monkey D. Dragon.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004106/0.png", "losevideos/004106/1.png", "losevideos/004106/2.png", "losevideos/004106/3.png", "losevideos/004106/4.png", "losevideos/004106/5.png", "losevideos/004106/6.png", "losevideos/004106/7.png", "winvideos/004106/0.png", "winvideos/004106/1.png", "winvideos/004106/2.png", "winvideos/004106/3.png", "winvideos/004106/4.png", "winvideos/004106/5.png", "winvideos/004106/6.png", "winvideos/004106/7.png" ]
Renaissance only meat body marble statue, details not MEAT, Alberto Seveso's art. the perfect natural highly detailed god man Shaman femenine with MEAT skin Wearing long HAWAIAN traditional , vector design. ethereal random color Power Rage, Celestial beautiful Surrounding Goddess "AFRODITA" in Rage Electricity Fire in the Whole Universe in style of artists like Russ Mills, Martina Joanna, Willem Haenraets, Audrey Kawasaki. standing pose, cosmic, outer space, and fire colors Artwork styles, highly detailed, Luminous Studio graphics engine, highly detailed symmetric beautiful hazel eyes, highly detailed gorgeous face, dynamic pose, ethereal, mystical, ultra detailed artistic photography. Ink Dropped in water, splatter drippings, paper texture, and perfect shading, with dramatic lighting. artwork should be centered, stylized, and elaborate. rendered in 8K resolution for high-quality detail, artstation,illustration, highly detailed, soft natural volumetric cinematic perfect 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: [Renaissance only meat body marble statue, details not MEAT, Alberto Seveso's art. the perfect natural highly detailed god man Shaman femenine with MEAT skin Wearing long HAWAIAN traditional , vector design. ethereal random color Power Rage, Celestial beautiful Surrounding Goddess "AFRODITA" in Rage Electricity Fire in the Whole Universe in style of artists like Russ Mills, Martina Joanna, Willem Haenraets, Audrey Kawasaki. standing pose, cosmic, outer space, and fire colors Artwork styles, highly detailed, Luminous Studio graphics engine, highly detailed symmetric beautiful hazel eyes, highly detailed gorgeous face, dynamic pose, ethereal, mystical, ultra detailed artistic photography. Ink Dropped in water, splatter drippings, paper texture, and perfect shading, with dramatic lighting. artwork should be centered, stylized, and elaborate. rendered in 8K resolution for high-quality detail, artstation,illustration, highly detailed, soft natural volumetric cinematic perfect light,.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005881/0.png", "losevideos/005881/1.png", "losevideos/005881/2.png", "losevideos/005881/3.png", "losevideos/005881/4.png", "losevideos/005881/5.png", "losevideos/005881/6.png", "losevideos/005881/7.png", "winvideos/005881/0.png", "winvideos/005881/1.png", "winvideos/005881/2.png", "winvideos/005881/3.png", "winvideos/005881/4.png", "winvideos/005881/5.png", "winvideos/005881/6.png", "winvideos/005881/7.png" ]
a tiger bie a 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 tiger bie a man.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005392/0.png", "losevideos/005392/1.png", "losevideos/005392/2.png", "losevideos/005392/3.png", "losevideos/005392/4.png", "losevideos/005392/5.png", "losevideos/005392/6.png", "losevideos/005392/7.png", "winvideos/005392/0.png", "winvideos/005392/1.png", "winvideos/005392/2.png", "winvideos/005392/3.png", "winvideos/005392/4.png", "winvideos/005392/5.png", "winvideos/005392/6.png", "winvideos/005392/7.png" ]
rooster superhero.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [rooster superhero.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002717/0.png", "losevideos/002717/1.png", "losevideos/002717/2.png", "losevideos/002717/3.png", "losevideos/002717/4.png", "losevideos/002717/5.png", "losevideos/002717/6.png", "losevideos/002717/7.png", "winvideos/002717/0.png", "winvideos/002717/1.png", "winvideos/002717/2.png", "winvideos/002717/3.png", "winvideos/002717/4.png", "winvideos/002717/5.png", "winvideos/002717/6.png", "winvideos/002717/7.png" ]
a busy airport terminal.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 busy airport terminal.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006845/0.png", "losevideos/006845/1.png", "losevideos/006845/2.png", "losevideos/006845/3.png", "losevideos/006845/4.png", "losevideos/006845/5.png", "losevideos/006845/6.png", "losevideos/006845/7.png", "winvideos/006845/0.png", "winvideos/006845/1.png", "winvideos/006845/2.png", "winvideos/006845/3.png", "winvideos/006845/4.png", "winvideos/006845/5.png", "winvideos/006845/6.png", "winvideos/006845/7.png" ]
Cinematic, Armenian women in a forest, beautiful lighting, 3d animation, 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Cinematic, Armenian women in a forest, beautiful lighting, 3d animation, 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009476/0.png", "losevideos/009476/1.png", "losevideos/009476/2.png", "losevideos/009476/3.png", "losevideos/009476/4.png", "losevideos/009476/5.png", "losevideos/009476/6.png", "losevideos/009476/7.png", "winvideos/009476/0.png", "winvideos/009476/1.png", "winvideos/009476/2.png", "winvideos/009476/3.png", "winvideos/009476/4.png", "winvideos/009476/5.png", "winvideos/009476/6.png", "winvideos/009476/7.png" ]
the girl in the pink dress. She's opening the door to the attic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [the girl in the pink dress. She's opening the door to the attic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002514/0.png", "losevideos/002514/1.png", "losevideos/002514/2.png", "losevideos/002514/3.png", "losevideos/002514/4.png", "losevideos/002514/5.png", "losevideos/002514/6.png", "losevideos/002514/7.png", "winvideos/002514/0.png", "winvideos/002514/1.png", "winvideos/002514/2.png", "winvideos/002514/3.png", "winvideos/002514/4.png", "winvideos/002514/5.png", "winvideos/002514/6.png", "winvideos/002514/7.png" ]
a montage of drone footage made as a YouTube intro.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 montage of drone footage made as a YouTube intro.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002327/0.png", "losevideos/002327/1.png", "losevideos/002327/2.png", "losevideos/002327/3.png", "losevideos/002327/4.png", "losevideos/002327/5.png", "losevideos/002327/6.png", "losevideos/002327/7.png", "winvideos/002327/0.png", "winvideos/002327/1.png", "winvideos/002327/2.png", "winvideos/002327/3.png", "winvideos/002327/4.png", "winvideos/002327/5.png", "winvideos/002327/6.png", "winvideos/002327/7.png" ]
a cat run.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 cat run.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004899/0.png", "winvideos/004899/1.png", "winvideos/004899/2.png", "winvideos/004899/3.png", "winvideos/004899/4.png", "winvideos/004899/5.png", "winvideos/004899/6.png", "winvideos/004899/7.png", "losevideos/004899/0.png", "losevideos/004899/1.png", "losevideos/004899/2.png", "losevideos/004899/3.png", "losevideos/004899/4.png", "losevideos/004899/5.png", "losevideos/004899/6.png", "losevideos/004899/7.png" ]
an orange car -seed 2240132.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 orange car -seed 2240132.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004874/0.png", "losevideos/004874/1.png", "losevideos/004874/2.png", "losevideos/004874/3.png", "losevideos/004874/4.png", "losevideos/004874/5.png", "losevideos/004874/6.png", "losevideos/004874/7.png", "winvideos/004874/0.png", "winvideos/004874/1.png", "winvideos/004874/2.png", "winvideos/004874/3.png", "winvideos/004874/4.png", "winvideos/004874/5.png", "winvideos/004874/6.png", "winvideos/004874/7.png" ]
4k video on dating, -camera pan right -fps 24 -motion 3 -gs 16 -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: [4k video on dating, -camera pan right -fps 24 -motion 3 -gs 16 -ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006357/0.png", "losevideos/006357/1.png", "losevideos/006357/2.png", "losevideos/006357/3.png", "losevideos/006357/4.png", "losevideos/006357/5.png", "losevideos/006357/6.png", "losevideos/006357/7.png", "winvideos/006357/0.png", "winvideos/006357/1.png", "winvideos/006357/2.png", "winvideos/006357/3.png", "winvideos/006357/4.png", "winvideos/006357/5.png", "winvideos/006357/6.png", "winvideos/006357/7.png" ]
[monkey turning into robot from hell, 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: [[monkey turning into robot from hell, 4k ].]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001199/0.png", "winvideos/001199/1.png", "winvideos/001199/2.png", "winvideos/001199/3.png", "winvideos/001199/4.png", "winvideos/001199/5.png", "winvideos/001199/6.png", "winvideos/001199/7.png", "losevideos/001199/0.png", "losevideos/001199/1.png", "losevideos/001199/2.png", "losevideos/001199/3.png", "losevideos/001199/4.png", "losevideos/001199/5.png", "losevideos/001199/6.png", "losevideos/001199/7.png" ]
action shot of Indiana Jones running from collapsing ruins evading spikes in walls, within an underground cave, cinematic, directed by Steven Spielberg, cinematic -ar 21:9 -neg slow moving camera, slow moving.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [action shot of Indiana Jones running from collapsing ruins evading spikes in walls, within an underground cave, cinematic, directed by Steven Spielberg, cinematic -ar 21:9 -neg slow moving camera, slow moving.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001926/0.png", "winvideos/001926/1.png", "winvideos/001926/2.png", "winvideos/001926/3.png", "winvideos/001926/4.png", "winvideos/001926/5.png", "winvideos/001926/6.png", "winvideos/001926/7.png", "losevideos/001926/0.png", "losevideos/001926/1.png", "losevideos/001926/2.png", "losevideos/001926/3.png", "losevideos/001926/4.png", "losevideos/001926/5.png", "losevideos/001926/6.png", "losevideos/001926/7.png" ]
silver surfer flying over new york city, hyperrealistic video in 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: [silver surfer flying over new york city, hyperrealistic video in 4k.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004848/0.png", "winvideos/004848/1.png", "winvideos/004848/2.png", "winvideos/004848/3.png", "winvideos/004848/4.png", "winvideos/004848/5.png", "winvideos/004848/6.png", "winvideos/004848/7.png", "losevideos/004848/0.png", "losevideos/004848/1.png", "losevideos/004848/2.png", "losevideos/004848/3.png", "losevideos/004848/4.png", "losevideos/004848/5.png", "losevideos/004848/6.png", "losevideos/004848/7.png" ]
group of diverse people standing on the street 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: [group of diverse people standing on the street at night.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006945/0.png", "winvideos/006945/1.png", "winvideos/006945/2.png", "winvideos/006945/3.png", "winvideos/006945/4.png", "winvideos/006945/5.png", "winvideos/006945/6.png", "winvideos/006945/7.png", "losevideos/006945/0.png", "losevideos/006945/1.png", "losevideos/006945/2.png", "losevideos/006945/3.png", "losevideos/006945/4.png", "losevideos/006945/5.png", "losevideos/006945/6.png", "losevideos/006945/7.png" ]
a wood, nigth, a moon, and snow fall dawn.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 wood, nigth, a moon, and snow fall dawn.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007380/0.png", "losevideos/007380/1.png", "losevideos/007380/2.png", "losevideos/007380/3.png", "losevideos/007380/4.png", "losevideos/007380/5.png", "losevideos/007380/6.png", "losevideos/007380/7.png", "winvideos/007380/0.png", "winvideos/007380/1.png", "winvideos/007380/2.png", "winvideos/007380/3.png", "winvideos/007380/4.png", "winvideos/007380/5.png", "winvideos/007380/6.png", "winvideos/007380/7.png" ]
Raja's compassion and sense of justice made him a revered figure in the jungle. His cave became a symbol of safety and good fortune for all the animals in the jungle.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Raja's compassion and sense of justice made him a revered figure in the jungle. His cave became a symbol of safety and good fortune for all the animals in the jungle.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006652/0.png", "winvideos/006652/1.png", "winvideos/006652/2.png", "winvideos/006652/3.png", "winvideos/006652/4.png", "winvideos/006652/5.png", "winvideos/006652/6.png", "winvideos/006652/7.png", "losevideos/006652/0.png", "losevideos/006652/1.png", "losevideos/006652/2.png", "losevideos/006652/3.png", "losevideos/006652/4.png", "losevideos/006652/5.png", "losevideos/006652/6.png", "losevideos/006652/7.png" ]
psychedelic spiral, Alex Grey style, rainbow color palette -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: [psychedelic spiral, Alex Grey style, rainbow color palette -ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007761/0.png", "winvideos/007761/1.png", "winvideos/007761/2.png", "winvideos/007761/3.png", "winvideos/007761/4.png", "winvideos/007761/5.png", "winvideos/007761/6.png", "winvideos/007761/7.png", "losevideos/007761/0.png", "losevideos/007761/1.png", "losevideos/007761/2.png", "losevideos/007761/3.png", "losevideos/007761/4.png", "losevideos/007761/5.png", "losevideos/007761/6.png", "losevideos/007761/7.png" ]
harpers book in laboratory.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [harpers book in laboratory.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004381/0.png", "losevideos/004381/1.png", "losevideos/004381/2.png", "losevideos/004381/3.png", "losevideos/004381/4.png", "losevideos/004381/5.png", "losevideos/004381/6.png", "losevideos/004381/7.png", "winvideos/004381/0.png", "winvideos/004381/1.png", "winvideos/004381/2.png", "winvideos/004381/3.png", "winvideos/004381/4.png", "winvideos/004381/5.png", "winvideos/004381/6.png", "winvideos/004381/7.png" ]
wave pushing. Strongman 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: [wave pushing. Strongman view.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002616/0.png", "losevideos/002616/1.png", "losevideos/002616/2.png", "losevideos/002616/3.png", "losevideos/002616/4.png", "losevideos/002616/5.png", "losevideos/002616/6.png", "losevideos/002616/7.png", "winvideos/002616/0.png", "winvideos/002616/1.png", "winvideos/002616/2.png", "winvideos/002616/3.png", "winvideos/002616/4.png", "winvideos/002616/5.png", "winvideos/002616/6.png", "winvideos/002616/7.png" ]
professional baby ufc fight.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [professional baby ufc fight.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008707/0.png", "losevideos/008707/1.png", "losevideos/008707/2.png", "losevideos/008707/3.png", "losevideos/008707/4.png", "losevideos/008707/5.png", "losevideos/008707/6.png", "losevideos/008707/7.png", "winvideos/008707/0.png", "winvideos/008707/1.png", "winvideos/008707/2.png", "winvideos/008707/3.png", "winvideos/008707/4.png", "winvideos/008707/5.png", "winvideos/008707/6.png", "winvideos/008707/7.png" ]
food digestion.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [food digestion.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005829/0.png", "winvideos/005829/1.png", "winvideos/005829/2.png", "winvideos/005829/3.png", "winvideos/005829/4.png", "winvideos/005829/5.png", "winvideos/005829/6.png", "winvideos/005829/7.png", "losevideos/005829/0.png", "losevideos/005829/1.png", "losevideos/005829/2.png", "losevideos/005829/3.png", "losevideos/005829/4.png", "losevideos/005829/5.png", "losevideos/005829/6.png", "losevideos/005829/7.png" ]