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 shooting dynamic movement of lemon fruits falling in clear water with splash, for advertising.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 shooting dynamic movement of lemon fruits falling in clear water with splash, for advertising.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002935/0.png", "winvideos/002935/1.png", "winvideos/002935/2.png", "winvideos/002935/3.png", "winvideos/002935/4.png", "winvideos/002935/5.png", "winvideos/002935/6.png", "winvideos/002935/7.png", "losevideos/002935/0.png", "losevideos/002935/1.png", "losevideos/002935/2.png", "losevideos/002935/3.png", "losevideos/002935/4.png", "losevideos/002935/5.png", "losevideos/002935/6.png", "losevideos/002935/7.png" ]
Teddy Bear: smiling, beautiful, wearing blue jean jacket, playing a chess game with Spider Man, sunrise storm as captured with a polarized canon 10-22mm lens on a Canon eos 5d mkii body, bright white patchy clouds, hazy chartreuse horizon, pucey blue in 3-point perspective fading into infinity, national geographic photo of the year, photography by David Attenborough, ross tran, Eugene de blaas, tom bagshaw as ruan jia, full body, high details, super realistic, 8K, cinematik, motion, style --ar 16:9 8k movie sequence.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Teddy Bear: smiling, beautiful, wearing blue jean jacket, playing a chess game with Spider Man, sunrise storm as captured with a polarized canon 10-22mm lens on a Canon eos 5d mkii body, bright white patchy clouds, hazy chartreuse horizon, pucey blue in 3-point perspective fading into infinity, national geographic photo of the year, photography by David Attenborough, ross tran, Eugene de blaas, tom bagshaw as ruan jia, full body, high details, super realistic, 8K, cinematik, motion, style --ar 16:9 8k movie sequence.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009886/0.png", "winvideos/009886/1.png", "winvideos/009886/2.png", "winvideos/009886/3.png", "winvideos/009886/4.png", "winvideos/009886/5.png", "winvideos/009886/6.png", "winvideos/009886/7.png", "losevideos/009886/0.png", "losevideos/009886/1.png", "losevideos/009886/2.png", "losevideos/009886/3.png", "losevideos/009886/4.png", "losevideos/009886/5.png", "losevideos/009886/6.png", "losevideos/009886/7.png" ]
a bottle of wine , putting wine in a glass of wine.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 bottle of wine , putting wine in a glass of wine.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006044/0.png", "losevideos/006044/1.png", "losevideos/006044/2.png", "losevideos/006044/3.png", "losevideos/006044/4.png", "losevideos/006044/5.png", "losevideos/006044/6.png", "losevideos/006044/7.png", "winvideos/006044/0.png", "winvideos/006044/1.png", "winvideos/006044/2.png", "winvideos/006044/3.png", "winvideos/006044/4.png", "winvideos/006044/5.png", "winvideos/006044/6.png", "winvideos/006044/7.png" ]
A classic red car, unpainted and dilapidated, driving along a road between a forest of dark fir trees, in the background we can see the classic American mountain town with a cloudy sky.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A classic red car, unpainted and dilapidated, driving along a road between a forest of dark fir trees, in the background we can see the classic American mountain town with a cloudy sky.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008431/0.png", "losevideos/008431/1.png", "losevideos/008431/2.png", "losevideos/008431/3.png", "losevideos/008431/4.png", "losevideos/008431/5.png", "losevideos/008431/6.png", "losevideos/008431/7.png", "winvideos/008431/0.png", "winvideos/008431/1.png", "winvideos/008431/2.png", "winvideos/008431/3.png", "winvideos/008431/4.png", "winvideos/008431/5.png", "winvideos/008431/6.png", "winvideos/008431/7.png" ]
An overweight Frenchman is sad about not being able to enjoy a sunny day in the park due to his sedentary lifestyle.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 overweight Frenchman is sad about not being able to enjoy a sunny day in the park due to his sedentary lifestyle.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002106/0.png", "losevideos/002106/1.png", "losevideos/002106/2.png", "losevideos/002106/3.png", "losevideos/002106/4.png", "losevideos/002106/5.png", "losevideos/002106/6.png", "losevideos/002106/7.png", "winvideos/002106/0.png", "winvideos/002106/1.png", "winvideos/002106/2.png", "winvideos/002106/3.png", "winvideos/002106/4.png", "winvideos/002106/5.png", "winvideos/002106/6.png", "winvideos/002106/7.png" ]
the man in coat, The icy river flowing through, the night street, mist, dim ominous lighting, cinematic, david fincher style, cinestill 800t, arri alexa, flash cut, high sharpness, highly detailed, in Real Photo style, hyper-realistic, high dynamic range, realistic textures, -motion 4 -gs 22 -fps 24 -ar 9:16 -neg "manga, 2D, no movement, random movements, deformed".	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 man in coat, The icy river flowing through, the night street, mist, dim ominous lighting, cinematic, david fincher style, cinestill 800t, arri alexa, flash cut, high sharpness, highly detailed, in Real Photo style, hyper-realistic, high dynamic range, realistic textures, -motion 4 -gs 22 -fps 24 -ar 9:16 -neg "manga, 2D, no movement, random movements, deformed".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004968/0.png", "losevideos/004968/1.png", "losevideos/004968/2.png", "losevideos/004968/3.png", "losevideos/004968/4.png", "losevideos/004968/5.png", "losevideos/004968/6.png", "losevideos/004968/7.png", "winvideos/004968/0.png", "winvideos/004968/1.png", "winvideos/004968/2.png", "winvideos/004968/3.png", "winvideos/004968/4.png", "winvideos/004968/5.png", "winvideos/004968/6.png", "winvideos/004968/7.png" ]
brown urban boy walking high-speed,motion 1 -gs 8 -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: [brown urban boy walking high-speed,motion 1 -gs 8 -camera zoom in.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005879/0.png", "losevideos/005879/1.png", "losevideos/005879/2.png", "losevideos/005879/3.png", "losevideos/005879/4.png", "losevideos/005879/5.png", "losevideos/005879/6.png", "losevideos/005879/7.png", "winvideos/005879/0.png", "winvideos/005879/1.png", "winvideos/005879/2.png", "winvideos/005879/3.png", "winvideos/005879/4.png", "winvideos/005879/5.png", "winvideos/005879/6.png", "winvideos/005879/7.png" ]
Birds flying.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Birds flying.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001125/0.png", "losevideos/001125/1.png", "losevideos/001125/2.png", "losevideos/001125/3.png", "losevideos/001125/4.png", "losevideos/001125/5.png", "losevideos/001125/6.png", "losevideos/001125/7.png", "winvideos/001125/0.png", "winvideos/001125/1.png", "winvideos/001125/2.png", "winvideos/001125/3.png", "winvideos/001125/4.png", "winvideos/001125/5.png", "winvideos/001125/6.png", "winvideos/001125/7.png" ]
Father, mother and child sitting at the dining table.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Father, mother and child sitting at the dining table.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009305/0.png", "winvideos/009305/1.png", "winvideos/009305/2.png", "winvideos/009305/3.png", "winvideos/009305/4.png", "winvideos/009305/5.png", "winvideos/009305/6.png", "winvideos/009305/7.png", "losevideos/009305/0.png", "losevideos/009305/1.png", "losevideos/009305/2.png", "losevideos/009305/3.png", "losevideos/009305/4.png", "losevideos/009305/5.png", "losevideos/009305/6.png", "losevideos/009305/7.png" ]
world map at global world war.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [world map at global world war.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006280/0.png", "losevideos/006280/1.png", "losevideos/006280/2.png", "losevideos/006280/3.png", "losevideos/006280/4.png", "losevideos/006280/5.png", "losevideos/006280/6.png", "losevideos/006280/7.png", "winvideos/006280/0.png", "winvideos/006280/1.png", "winvideos/006280/2.png", "winvideos/006280/3.png", "winvideos/006280/4.png", "winvideos/006280/5.png", "winvideos/006280/6.png", "winvideos/006280/7.png" ]
Three firefighters are using a hose to extinguish a burning car -ar 9:16 -motion 2.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Three firefighters are using a hose to extinguish a burning car -ar 9:16 -motion 2.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007157/0.png", "losevideos/007157/1.png", "losevideos/007157/2.png", "losevideos/007157/3.png", "losevideos/007157/4.png", "losevideos/007157/5.png", "losevideos/007157/6.png", "losevideos/007157/7.png", "winvideos/007157/0.png", "winvideos/007157/1.png", "winvideos/007157/2.png", "winvideos/007157/3.png", "winvideos/007157/4.png", "winvideos/007157/5.png", "winvideos/007157/6.png", "winvideos/007157/7.png" ]
Create an image zoomed in on intense eyes reflecting a tumultuous, darkened sky, symbolizing the depth of conflicting thoughts.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Create an image zoomed in on intense eyes reflecting a tumultuous, darkened sky, symbolizing the depth of conflicting thoughts.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002372/0.png", "winvideos/002372/1.png", "winvideos/002372/2.png", "winvideos/002372/3.png", "winvideos/002372/4.png", "winvideos/002372/5.png", "winvideos/002372/6.png", "winvideos/002372/7.png", "losevideos/002372/0.png", "losevideos/002372/1.png", "losevideos/002372/2.png", "losevideos/002372/3.png", "losevideos/002372/4.png", "losevideos/002372/5.png", "losevideos/002372/6.png", "losevideos/002372/7.png" ]
making memories. Sunnyville was forever filled with the laughter of friends, thanks to Benny and.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [making memories. Sunnyville was forever filled with the laughter of friends, thanks to Benny and.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001201/0.png", "winvideos/001201/1.png", "winvideos/001201/2.png", "winvideos/001201/3.png", "winvideos/001201/4.png", "winvideos/001201/5.png", "winvideos/001201/6.png", "winvideos/001201/7.png", "losevideos/001201/0.png", "losevideos/001201/1.png", "losevideos/001201/2.png", "losevideos/001201/3.png", "losevideos/001201/4.png", "losevideos/001201/5.png", "losevideos/001201/6.png", "losevideos/001201/7.png" ]
cartoon showing different layers of the atmosphere.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cartoon showing different layers of the atmosphere.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000935/0.png", "winvideos/000935/1.png", "winvideos/000935/2.png", "winvideos/000935/3.png", "winvideos/000935/4.png", "winvideos/000935/5.png", "winvideos/000935/6.png", "winvideos/000935/7.png", "losevideos/000935/0.png", "losevideos/000935/1.png", "losevideos/000935/2.png", "losevideos/000935/3.png", "losevideos/000935/4.png", "losevideos/000935/5.png", "losevideos/000935/6.png", "losevideos/000935/7.png" ]
A person is taking deep breaths.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 person is taking deep breaths.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003508/0.png", "losevideos/003508/1.png", "losevideos/003508/2.png", "losevideos/003508/3.png", "losevideos/003508/4.png", "losevideos/003508/5.png", "losevideos/003508/6.png", "losevideos/003508/7.png", "winvideos/003508/0.png", "winvideos/003508/1.png", "winvideos/003508/2.png", "winvideos/003508/3.png", "winvideos/003508/4.png", "winvideos/003508/5.png", "winvideos/003508/6.png", "winvideos/003508/7.png" ]
5 Humans disregarding nature.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [5 Humans disregarding nature.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004524/0.png", "winvideos/004524/1.png", "winvideos/004524/2.png", "winvideos/004524/3.png", "winvideos/004524/4.png", "winvideos/004524/5.png", "winvideos/004524/6.png", "winvideos/004524/7.png", "losevideos/004524/0.png", "losevideos/004524/1.png", "losevideos/004524/2.png", "losevideos/004524/3.png", "losevideos/004524/4.png", "losevideos/004524/5.png", "losevideos/004524/6.png", "losevideos/004524/7.png" ]
Ein schweizer der mit Käse rumschiest und ein Sackmesser hat.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Ein schweizer der mit Käse rumschiest und ein Sackmesser hat.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007262/0.png", "losevideos/007262/1.png", "losevideos/007262/2.png", "losevideos/007262/3.png", "losevideos/007262/4.png", "losevideos/007262/5.png", "losevideos/007262/6.png", "losevideos/007262/7.png", "winvideos/007262/0.png", "winvideos/007262/1.png", "winvideos/007262/2.png", "winvideos/007262/3.png", "winvideos/007262/4.png", "winvideos/007262/5.png", "winvideos/007262/6.png", "winvideos/007262/7.png" ]
Ron jermy at the whitehouse.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Ron jermy at the whitehouse.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005308/0.png", "losevideos/005308/1.png", "losevideos/005308/2.png", "losevideos/005308/3.png", "losevideos/005308/4.png", "losevideos/005308/5.png", "losevideos/005308/6.png", "losevideos/005308/7.png", "winvideos/005308/0.png", "winvideos/005308/1.png", "winvideos/005308/2.png", "winvideos/005308/3.png", "winvideos/005308/4.png", "winvideos/005308/5.png", "winvideos/005308/6.png", "winvideos/005308/7.png" ]
realistic fantasy.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [realistic fantasy.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000837/0.png", "winvideos/000837/1.png", "winvideos/000837/2.png", "winvideos/000837/3.png", "winvideos/000837/4.png", "winvideos/000837/5.png", "winvideos/000837/6.png", "winvideos/000837/7.png", "losevideos/000837/0.png", "losevideos/000837/1.png", "losevideos/000837/2.png", "losevideos/000837/3.png", "losevideos/000837/4.png", "losevideos/000837/5.png", "losevideos/000837/6.png", "losevideos/000837/7.png" ]
The angel swung his sickle on the earth, gathered its grapes and threw them into the great winepress of God’s wrath.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 angel swung his sickle on the earth, gathered its grapes and threw them into the great winepress of God’s wrath.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008851/0.png", "winvideos/008851/1.png", "winvideos/008851/2.png", "winvideos/008851/3.png", "winvideos/008851/4.png", "winvideos/008851/5.png", "winvideos/008851/6.png", "winvideos/008851/7.png", "losevideos/008851/0.png", "losevideos/008851/1.png", "losevideos/008851/2.png", "losevideos/008851/3.png", "losevideos/008851/4.png", "losevideos/008851/5.png", "losevideos/008851/6.png", "losevideos/008851/7.png" ]
wind, light smile, sunlight.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [wind, light smile, sunlight.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003491/0.png", "losevideos/003491/1.png", "losevideos/003491/2.png", "losevideos/003491/3.png", "losevideos/003491/4.png", "losevideos/003491/5.png", "losevideos/003491/6.png", "losevideos/003491/7.png", "winvideos/003491/0.png", "winvideos/003491/1.png", "winvideos/003491/2.png", "winvideos/003491/3.png", "winvideos/003491/4.png", "winvideos/003491/5.png", "winvideos/003491/6.png", "winvideos/003491/7.png" ]
beautiful and young Arab women in love lesbian love romance.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [beautiful and young Arab women in love lesbian love romance.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005833/0.png", "losevideos/005833/1.png", "losevideos/005833/2.png", "losevideos/005833/3.png", "losevideos/005833/4.png", "losevideos/005833/5.png", "losevideos/005833/6.png", "losevideos/005833/7.png", "winvideos/005833/0.png", "winvideos/005833/1.png", "winvideos/005833/2.png", "winvideos/005833/3.png", "winvideos/005833/4.png", "winvideos/005833/5.png", "winvideos/005833/6.png", "winvideos/005833/7.png" ]
yasser arafat nobel prize, 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: [yasser arafat nobel prize, talking.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003220/0.png", "losevideos/003220/1.png", "losevideos/003220/2.png", "losevideos/003220/3.png", "losevideos/003220/4.png", "losevideos/003220/5.png", "losevideos/003220/6.png", "losevideos/003220/7.png", "winvideos/003220/0.png", "winvideos/003220/1.png", "winvideos/003220/2.png", "winvideos/003220/3.png", "winvideos/003220/4.png", "winvideos/003220/5.png", "winvideos/003220/6.png", "winvideos/003220/7.png" ]
5 kids engaged in activities like jumping, stretching and balancing . Style: Real footage blended with playful, space-themed graphics, with galaxy and space in background.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [5 kids engaged in activities like jumping, stretching and balancing . Style: Real footage blended with playful, space-themed graphics, with galaxy and space in background.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003221/0.png", "losevideos/003221/1.png", "losevideos/003221/2.png", "losevideos/003221/3.png", "losevideos/003221/4.png", "losevideos/003221/5.png", "losevideos/003221/6.png", "losevideos/003221/7.png", "winvideos/003221/0.png", "winvideos/003221/1.png", "winvideos/003221/2.png", "winvideos/003221/3.png", "winvideos/003221/4.png", "winvideos/003221/5.png", "winvideos/003221/6.png", "winvideos/003221/7.png" ]
Caterpillar and Cricket • Caterpillar having a conversation with Cricket under the shade of a large leaf. • Cricket, a wise old insect, sharing his knowledge with Caterpillar.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Caterpillar and Cricket\n • Caterpillar having a conversation with Cricket under the shade of a large leaf.\n • Cricket, a wise old insect, sharing his knowledge with Caterpillar.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004651/0.png", "winvideos/004651/1.png", "winvideos/004651/2.png", "winvideos/004651/3.png", "winvideos/004651/4.png", "winvideos/004651/5.png", "winvideos/004651/6.png", "winvideos/004651/7.png", "losevideos/004651/0.png", "losevideos/004651/1.png", "losevideos/004651/2.png", "losevideos/004651/3.png", "losevideos/004651/4.png", "losevideos/004651/5.png", "losevideos/004651/6.png", "losevideos/004651/7.png" ]
The now sixty Elves dwelt by the rivers, and they invented poetry and music in Middle-earth. lotr movie style.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The now sixty Elves dwelt by the rivers, and they invented poetry and music in Middle-earth. lotr movie style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003141/0.png", "winvideos/003141/1.png", "winvideos/003141/2.png", "winvideos/003141/3.png", "winvideos/003141/4.png", "winvideos/003141/5.png", "winvideos/003141/6.png", "winvideos/003141/7.png", "losevideos/003141/0.png", "losevideos/003141/1.png", "losevideos/003141/2.png", "losevideos/003141/3.png", "losevideos/003141/4.png", "losevideos/003141/5.png", "losevideos/003141/6.png", "losevideos/003141/7.png" ]
fantasy council members 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: [fantasy council members talking.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007449/0.png", "winvideos/007449/1.png", "winvideos/007449/2.png", "winvideos/007449/3.png", "winvideos/007449/4.png", "winvideos/007449/5.png", "winvideos/007449/6.png", "winvideos/007449/7.png", "losevideos/007449/0.png", "losevideos/007449/1.png", "losevideos/007449/2.png", "losevideos/007449/3.png", "losevideos/007449/4.png", "losevideos/007449/5.png", "losevideos/007449/6.png", "losevideos/007449/7.png" ]
crow drinking water.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [crow drinking water.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007832/0.png", "winvideos/007832/1.png", "winvideos/007832/2.png", "winvideos/007832/3.png", "winvideos/007832/4.png", "winvideos/007832/5.png", "winvideos/007832/6.png", "winvideos/007832/7.png", "losevideos/007832/0.png", "losevideos/007832/1.png", "losevideos/007832/2.png", "losevideos/007832/3.png", "losevideos/007832/4.png", "losevideos/007832/5.png", "losevideos/007832/6.png", "losevideos/007832/7.png" ]
A video opens with a dark, atmospheric shot. mysterious light gradually illuminates the scene.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A video opens with a dark, atmospheric shot. mysterious light gradually illuminates the scene.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007612/0.png", "winvideos/007612/1.png", "winvideos/007612/2.png", "winvideos/007612/3.png", "winvideos/007612/4.png", "winvideos/007612/5.png", "winvideos/007612/6.png", "winvideos/007612/7.png", "losevideos/007612/0.png", "losevideos/007612/1.png", "losevideos/007612/2.png", "losevideos/007612/3.png", "losevideos/007612/4.png", "losevideos/007612/5.png", "losevideos/007612/6.png", "losevideos/007612/7.png" ]
wind freez,man sad in court with his wife.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [wind freez,man sad in court with his wife.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004351/0.png", "losevideos/004351/1.png", "losevideos/004351/2.png", "losevideos/004351/3.png", "losevideos/004351/4.png", "losevideos/004351/5.png", "losevideos/004351/6.png", "losevideos/004351/7.png", "winvideos/004351/0.png", "winvideos/004351/1.png", "winvideos/004351/2.png", "winvideos/004351/3.png", "winvideos/004351/4.png", "winvideos/004351/5.png", "winvideos/004351/6.png", "winvideos/004351/7.png" ]
a still from a 2013 sci - fi film, Ad Astra, a woman, Cinestill 50D -motion 1 -neg “blur” -ar 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a still from a 2013 sci - fi film, Ad Astra, a woman, Cinestill 50D -motion 1 -neg “blur” -ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002824/0.png", "losevideos/002824/1.png", "losevideos/002824/2.png", "losevideos/002824/3.png", "losevideos/002824/4.png", "losevideos/002824/5.png", "losevideos/002824/6.png", "losevideos/002824/7.png", "winvideos/002824/0.png", "winvideos/002824/1.png", "winvideos/002824/2.png", "winvideos/002824/3.png", "winvideos/002824/4.png", "winvideos/002824/5.png", "winvideos/002824/6.png", "winvideos/002824/7.png" ]
a man with girl friend riding bike in the spach, 8k, hyper realistic, 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 man with girl friend riding bike in the spach, 8k, hyper realistic, 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007490/0.png", "losevideos/007490/1.png", "losevideos/007490/2.png", "losevideos/007490/3.png", "losevideos/007490/4.png", "losevideos/007490/5.png", "losevideos/007490/6.png", "losevideos/007490/7.png", "winvideos/007490/0.png", "winvideos/007490/1.png", "winvideos/007490/2.png", "winvideos/007490/3.png", "winvideos/007490/4.png", "winvideos/007490/5.png", "winvideos/007490/6.png", "winvideos/007490/7.png" ]
1984 video, supermodel aliens coming down from a space ship over the palace of versailles. 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: [1984 video, supermodel aliens coming down from a space ship over the palace of versailles. AR 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005440/0.png", "losevideos/005440/1.png", "losevideos/005440/2.png", "losevideos/005440/3.png", "losevideos/005440/4.png", "losevideos/005440/5.png", "losevideos/005440/6.png", "losevideos/005440/7.png", "winvideos/005440/0.png", "winvideos/005440/1.png", "winvideos/005440/2.png", "winvideos/005440/3.png", "winvideos/005440/4.png", "winvideos/005440/5.png", "winvideos/005440/6.png", "winvideos/005440/7.png" ]
Amnesia inspired, DEEP DREAM aesthetic, Nam June Paik inspired, Found footage inspired, Hyper resolution, POV you are in an aerial zen garden in the clouds with sky monks. Visual focal point. They emit web of lightning when they speak and high winds when they look. Spectactular multi branched lightning strikes light up the sky. You carry out a SHAMANIC ritual with your tribe of twelve in the clouds. Each being represents a point in the Zodiac. Mirrored lighting: Tornado, Hurricane, Wind, Super storm, Pharoah, kaliedoscope, Arachnid, Octagon, Time Web, Alien spacecraft, Neural network, Quantum Computer, Tomb, Eclipse, Quantum jumping, Cosmic cycle, Ancient past, Far future, Wormhole, high beauty, super summetry, luminous sfumato, kodak tmax p3200, Surreal -pos "high contrast, cloud city"-neg "dark, poorly drawn, glitch, blurry" --ar 16:9 -tile fractal, reflective -gs5 -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: [Amnesia inspired, DEEP DREAM aesthetic, Nam June Paik inspired, Found footage inspired, Hyper resolution, POV you are in an aerial zen garden in the clouds with sky monks. Visual focal point. They emit web of lightning when they speak and high winds when they look. Spectactular multi branched lightning strikes light up the sky. You carry out a SHAMANIC ritual with your tribe of twelve in the clouds. Each being represents a point in the Zodiac. Mirrored lighting: Tornado, Hurricane, Wind, Super storm, Pharoah, kaliedoscope, Arachnid, Octagon, Time Web, Alien spacecraft, Neural network, Quantum Computer, Tomb, Eclipse, Quantum jumping, Cosmic cycle, Ancient past, Far future, Wormhole, high beauty, super summetry, luminous sfumato, kodak tmax p3200, Surreal -pos "high contrast, cloud city"-neg "dark, poorly drawn, glitch, blurry" --ar 16:9 -tile fractal, reflective -gs5 -motion 4 -camera zoom in.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004857/0.png", "winvideos/004857/1.png", "winvideos/004857/2.png", "winvideos/004857/3.png", "winvideos/004857/4.png", "winvideos/004857/5.png", "winvideos/004857/6.png", "winvideos/004857/7.png", "losevideos/004857/0.png", "losevideos/004857/1.png", "losevideos/004857/2.png", "losevideos/004857/3.png", "losevideos/004857/4.png", "losevideos/004857/5.png", "losevideos/004857/6.png", "losevideos/004857/7.png" ]
pickachu danching with his friends.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [pickachu danching with his friends.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002323/0.png", "losevideos/002323/1.png", "losevideos/002323/2.png", "losevideos/002323/3.png", "losevideos/002323/4.png", "losevideos/002323/5.png", "losevideos/002323/6.png", "losevideos/002323/7.png", "winvideos/002323/0.png", "winvideos/002323/1.png", "winvideos/002323/2.png", "winvideos/002323/3.png", "winvideos/002323/4.png", "winvideos/002323/5.png", "winvideos/002323/6.png", "winvideos/002323/7.png" ]
a beautiful nebula and galaxy in space, HD astrophotography capture, detailed stacked photo.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a beautiful nebula and galaxy in space, HD astrophotography capture, detailed stacked photo.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006571/0.png", "winvideos/006571/1.png", "winvideos/006571/2.png", "winvideos/006571/3.png", "winvideos/006571/4.png", "winvideos/006571/5.png", "winvideos/006571/6.png", "winvideos/006571/7.png", "losevideos/006571/0.png", "losevideos/006571/1.png", "losevideos/006571/2.png", "losevideos/006571/3.png", "losevideos/006571/4.png", "losevideos/006571/5.png", "losevideos/006571/6.png", "losevideos/006571/7.png" ]
looking around, zooming out, a lone black cub wolf left in the woods.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [looking around, zooming out, a lone black cub wolf left in the woods.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005176/0.png", "losevideos/005176/1.png", "losevideos/005176/2.png", "losevideos/005176/3.png", "losevideos/005176/4.png", "losevideos/005176/5.png", "losevideos/005176/6.png", "losevideos/005176/7.png", "winvideos/005176/0.png", "winvideos/005176/1.png", "winvideos/005176/2.png", "winvideos/005176/3.png", "winvideos/005176/4.png", "winvideos/005176/5.png", "winvideos/005176/6.png", "winvideos/005176/7.png" ]
timelapse of a dramatic night sky.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [timelapse of a dramatic night sky.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004859/0.png", "winvideos/004859/1.png", "winvideos/004859/2.png", "winvideos/004859/3.png", "winvideos/004859/4.png", "winvideos/004859/5.png", "winvideos/004859/6.png", "winvideos/004859/7.png", "losevideos/004859/0.png", "losevideos/004859/1.png", "losevideos/004859/2.png", "losevideos/004859/3.png", "losevideos/004859/4.png", "losevideos/004859/5.png", "losevideos/004859/6.png", "losevideos/004859/7.png" ]
wide angle low level cinematic steampunk robot wearing tattered overseeing the construction of the pyramids, dark red, purple, black color palette, In the artistic style of H.R. Giger -gs 19 -motion 4 -camera zoom out.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [wide angle low level cinematic steampunk robot wearing tattered overseeing the construction of the pyramids, dark red, purple, black color palette, In the artistic style of H.R. Giger -gs 19 -motion 4 -camera zoom out.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006154/0.png", "losevideos/006154/1.png", "losevideos/006154/2.png", "losevideos/006154/3.png", "losevideos/006154/4.png", "losevideos/006154/5.png", "losevideos/006154/6.png", "losevideos/006154/7.png", "winvideos/006154/0.png", "winvideos/006154/1.png", "winvideos/006154/2.png", "winvideos/006154/3.png", "winvideos/006154/4.png", "winvideos/006154/5.png", "winvideos/006154/6.png", "winvideos/006154/7.png" ]
a dark room, glimmer light from outside through the winow, a clock on the wall, the clock tick is 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: [a dark room, glimmer light from outside through the winow, a clock on the wall, the clock tick is moving.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007958/0.png", "winvideos/007958/1.png", "winvideos/007958/2.png", "winvideos/007958/3.png", "winvideos/007958/4.png", "winvideos/007958/5.png", "winvideos/007958/6.png", "winvideos/007958/7.png", "losevideos/007958/0.png", "losevideos/007958/1.png", "losevideos/007958/2.png", "losevideos/007958/3.png", "losevideos/007958/4.png", "losevideos/007958/5.png", "losevideos/007958/6.png", "losevideos/007958/7.png" ]