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
tiger in the woods, huge snow, low light, by Rene Magritte, Salvador Dali, zdzislaw Beksinski.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [tiger in the woods, huge snow, low light, by Rene Magritte, Salvador Dali, zdzislaw Beksinski.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007841/0.png", "losevideos/007841/1.png", "losevideos/007841/2.png", "losevideos/007841/3.png", "losevideos/007841/4.png", "losevideos/007841/5.png", "losevideos/007841/6.png", "losevideos/007841/7.png", "winvideos/007841/0.png", "winvideos/007841/1.png", "winvideos/007841/2.png", "winvideos/007841/3.png", "winvideos/007841/4.png", "winvideos/007841/5.png", "winvideos/007841/6.png", "winvideos/007841/7.png" ]
Globe spinning slowly or an animated airplane flying across a map.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Globe spinning slowly or an animated airplane flying across a map.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005797/0.png", "losevideos/005797/1.png", "losevideos/005797/2.png", "losevideos/005797/3.png", "losevideos/005797/4.png", "losevideos/005797/5.png", "losevideos/005797/6.png", "losevideos/005797/7.png", "winvideos/005797/0.png", "winvideos/005797/1.png", "winvideos/005797/2.png", "winvideos/005797/3.png", "winvideos/005797/4.png", "winvideos/005797/5.png", "winvideos/005797/6.png", "winvideos/005797/7.png" ]
meditating and lights, alive cobra.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [meditating and lights, alive cobra.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006278/0.png", "losevideos/006278/1.png", "losevideos/006278/2.png", "losevideos/006278/3.png", "losevideos/006278/4.png", "losevideos/006278/5.png", "losevideos/006278/6.png", "losevideos/006278/7.png", "winvideos/006278/0.png", "winvideos/006278/1.png", "winvideos/006278/2.png", "winvideos/006278/3.png", "winvideos/006278/4.png", "winvideos/006278/5.png", "winvideos/006278/6.png", "winvideos/006278/7.png" ]
1. A cheerful meadow with vibrant flowers and a bright sun.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [1.\tA cheerful meadow with vibrant flowers and a bright sun.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003383/0.png", "winvideos/003383/1.png", "winvideos/003383/2.png", "winvideos/003383/3.png", "winvideos/003383/4.png", "winvideos/003383/5.png", "winvideos/003383/6.png", "winvideos/003383/7.png", "losevideos/003383/0.png", "losevideos/003383/1.png", "losevideos/003383/2.png", "losevideos/003383/3.png", "losevideos/003383/4.png", "losevideos/003383/5.png", "losevideos/003383/6.png", "losevideos/003383/7.png" ]
A girl is smiling and her hair is blowing with air.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A girl is smiling and her hair is blowing with air.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007613/0.png", "winvideos/007613/1.png", "winvideos/007613/2.png", "winvideos/007613/3.png", "winvideos/007613/4.png", "winvideos/007613/5.png", "winvideos/007613/6.png", "winvideos/007613/7.png", "losevideos/007613/0.png", "losevideos/007613/1.png", "losevideos/007613/2.png", "losevideos/007613/3.png", "losevideos/007613/4.png", "losevideos/007613/5.png", "losevideos/007613/6.png", "losevideos/007613/7.png" ]
cute cat dancing in rainny season.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cute cat dancing in rainny season.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008296/0.png", "losevideos/008296/1.png", "losevideos/008296/2.png", "losevideos/008296/3.png", "losevideos/008296/4.png", "losevideos/008296/5.png", "losevideos/008296/6.png", "losevideos/008296/7.png", "winvideos/008296/0.png", "winvideos/008296/1.png", "winvideos/008296/2.png", "winvideos/008296/3.png", "winvideos/008296/4.png", "winvideos/008296/5.png", "winvideos/008296/6.png", "winvideos/008296/7.png" ]
high end luxury fragrances and mens perfumes.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [high end luxury fragrances and mens perfumes.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000586/0.png", "winvideos/000586/1.png", "winvideos/000586/2.png", "winvideos/000586/3.png", "winvideos/000586/4.png", "winvideos/000586/5.png", "winvideos/000586/6.png", "winvideos/000586/7.png", "losevideos/000586/0.png", "losevideos/000586/1.png", "losevideos/000586/2.png", "losevideos/000586/3.png", "losevideos/000586/4.png", "losevideos/000586/5.png", "losevideos/000586/6.png", "losevideos/000586/7.png" ]
hd 4k realistic farmer and his wife standing in front of barn watching war planes fly over -camera zoom in -ar 9:16 -fps 24 -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: [hd 4k realistic farmer and his wife standing in front of barn watching war planes fly over -camera zoom in -ar 9:16 -fps 24 -motion 2.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007919/0.png", "losevideos/007919/1.png", "losevideos/007919/2.png", "losevideos/007919/3.png", "losevideos/007919/4.png", "losevideos/007919/5.png", "losevideos/007919/6.png", "losevideos/007919/7.png", "winvideos/007919/0.png", "winvideos/007919/1.png", "winvideos/007919/2.png", "winvideos/007919/3.png", "winvideos/007919/4.png", "winvideos/007919/5.png", "winvideos/007919/6.png", "winvideos/007919/7.png" ]
3D. ultra realistic.movement. 8k quality. Siya Kolisi and Rachel Kolisi in South Africa.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [3D. ultra realistic.movement. 8k quality. Siya Kolisi and Rachel Kolisi in South Africa.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000658/0.png", "losevideos/000658/1.png", "losevideos/000658/2.png", "losevideos/000658/3.png", "losevideos/000658/4.png", "losevideos/000658/5.png", "losevideos/000658/6.png", "losevideos/000658/7.png", "winvideos/000658/0.png", "winvideos/000658/1.png", "winvideos/000658/2.png", "winvideos/000658/3.png", "winvideos/000658/4.png", "winvideos/000658/5.png", "winvideos/000658/6.png", "winvideos/000658/7.png" ]
Documentary film in 1918 I was showing soviet union Time Machine with a devil coming in hall and the people medical and the Smaug cinematic hyper realistic 8k.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Documentary film in 1918 I was showing soviet union Time Machine with a devil coming in hall and the people medical and the Smaug cinematic hyper realistic 8k.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003801/0.png", "losevideos/003801/1.png", "losevideos/003801/2.png", "losevideos/003801/3.png", "losevideos/003801/4.png", "losevideos/003801/5.png", "losevideos/003801/6.png", "losevideos/003801/7.png", "winvideos/003801/0.png", "winvideos/003801/1.png", "winvideos/003801/2.png", "winvideos/003801/3.png", "winvideos/003801/4.png", "winvideos/003801/5.png", "winvideos/003801/6.png", "winvideos/003801/7.png" ]
women rejuvenating, a heartful and curious expression, soft movement.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [women rejuvenating, a heartful and curious expression, soft movement.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002995/0.png", "winvideos/002995/1.png", "winvideos/002995/2.png", "winvideos/002995/3.png", "winvideos/002995/4.png", "winvideos/002995/5.png", "winvideos/002995/6.png", "winvideos/002995/7.png", "losevideos/002995/0.png", "losevideos/002995/1.png", "losevideos/002995/2.png", "losevideos/002995/3.png", "losevideos/002995/4.png", "losevideos/002995/5.png", "losevideos/002995/6.png", "losevideos/002995/7.png" ]
((MG animation, female with long black hair, wearing loose clothes, often feeling a sagging lower abdomen, frowning, and uncomfortable at home, with soft visuals and bright lighting)) -ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [((MG animation, female with long black hair, wearing loose clothes, often feeling a sagging lower abdomen, frowning, and uncomfortable at home, with soft visuals and bright lighting)) -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005807/0.png", "winvideos/005807/1.png", "winvideos/005807/2.png", "winvideos/005807/3.png", "winvideos/005807/4.png", "winvideos/005807/5.png", "winvideos/005807/6.png", "winvideos/005807/7.png", "losevideos/005807/0.png", "losevideos/005807/1.png", "losevideos/005807/2.png", "losevideos/005807/3.png", "losevideos/005807/4.png", "losevideos/005807/5.png", "losevideos/005807/6.png", "losevideos/005807/7.png" ]
A picture of Sonia looking at a photo frame containing a picture of Raj in uniform, capturing the longing and sadness in her eyes.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 picture of Sonia looking at a photo frame containing a picture of Raj in uniform, capturing the longing and sadness in her eyes.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000120/0.png", "winvideos/000120/1.png", "winvideos/000120/2.png", "winvideos/000120/3.png", "winvideos/000120/4.png", "winvideos/000120/5.png", "winvideos/000120/6.png", "winvideos/000120/7.png", "losevideos/000120/0.png", "losevideos/000120/1.png", "losevideos/000120/2.png", "losevideos/000120/3.png", "losevideos/000120/4.png", "losevideos/000120/5.png", "losevideos/000120/6.png", "losevideos/000120/7.png" ]
x-ray fungus eating person.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [x-ray fungus eating person.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007422/0.png", "losevideos/007422/1.png", "losevideos/007422/2.png", "losevideos/007422/3.png", "losevideos/007422/4.png", "losevideos/007422/5.png", "losevideos/007422/6.png", "losevideos/007422/7.png", "winvideos/007422/0.png", "winvideos/007422/1.png", "winvideos/007422/2.png", "winvideos/007422/3.png", "winvideos/007422/4.png", "winvideos/007422/5.png", "winvideos/007422/6.png", "winvideos/007422/7.png" ]
anime video smart boy standing infront of tsunami.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [anime video smart boy standing infront of tsunami.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001038/0.png", "losevideos/001038/1.png", "losevideos/001038/2.png", "losevideos/001038/3.png", "losevideos/001038/4.png", "losevideos/001038/5.png", "losevideos/001038/6.png", "losevideos/001038/7.png", "winvideos/001038/0.png", "winvideos/001038/1.png", "winvideos/001038/2.png", "winvideos/001038/3.png", "winvideos/001038/4.png", "winvideos/001038/5.png", "winvideos/001038/6.png", "winvideos/001038/7.png" ]
A balloon exploded in the dog's mouth -ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A balloon exploded in the dog's mouth -ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002735/0.png", "losevideos/002735/1.png", "losevideos/002735/2.png", "losevideos/002735/3.png", "losevideos/002735/4.png", "losevideos/002735/5.png", "losevideos/002735/6.png", "losevideos/002735/7.png", "winvideos/002735/0.png", "winvideos/002735/1.png", "winvideos/002735/2.png", "winvideos/002735/3.png", "winvideos/002735/4.png", "winvideos/002735/5.png", "winvideos/002735/6.png", "winvideos/002735/7.png" ]
a dancing craftsman.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a dancing craftsman.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007255/0.png", "winvideos/007255/1.png", "winvideos/007255/2.png", "winvideos/007255/3.png", "winvideos/007255/4.png", "winvideos/007255/5.png", "winvideos/007255/6.png", "winvideos/007255/7.png", "losevideos/007255/0.png", "losevideos/007255/1.png", "losevideos/007255/2.png", "losevideos/007255/3.png", "losevideos/007255/4.png", "losevideos/007255/5.png", "losevideos/007255/6.png", "losevideos/007255/7.png" ]
aliens and big human's brain on The Moon, 16 mm, black and white, realism.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [aliens and big human's brain on The Moon, 16 mm, black and white, realism.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001357/0.png", "winvideos/001357/1.png", "winvideos/001357/2.png", "winvideos/001357/3.png", "winvideos/001357/4.png", "winvideos/001357/5.png", "winvideos/001357/6.png", "winvideos/001357/7.png", "losevideos/001357/0.png", "losevideos/001357/1.png", "losevideos/001357/2.png", "losevideos/001357/3.png", "losevideos/001357/4.png", "losevideos/001357/5.png", "losevideos/001357/6.png", "losevideos/001357/7.png" ]
zooming out from an escalator in a dead mall, full moon visible through the skylight, dark -ar 5:4 -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: [zooming out from an escalator in a dead mall, full moon visible through the skylight, dark -ar 5:4 -motion 2.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007238/0.png", "losevideos/007238/1.png", "losevideos/007238/2.png", "losevideos/007238/3.png", "losevideos/007238/4.png", "losevideos/007238/5.png", "losevideos/007238/6.png", "losevideos/007238/7.png", "winvideos/007238/0.png", "winvideos/007238/1.png", "winvideos/007238/2.png", "winvideos/007238/3.png", "winvideos/007238/4.png", "winvideos/007238/5.png", "winvideos/007238/6.png", "winvideos/007238/7.png" ]
Two man young white argue and fighting and envy and jealousy, rip off the shirts. they scream. discovers betrayal by a woman in clothes. In room. 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: [Two man young white argue and fighting and envy and jealousy, rip off the shirts. they scream. discovers betrayal by a woman in clothes. In room. 4K.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003306/0.png", "winvideos/003306/1.png", "winvideos/003306/2.png", "winvideos/003306/3.png", "winvideos/003306/4.png", "winvideos/003306/5.png", "winvideos/003306/6.png", "winvideos/003306/7.png", "losevideos/003306/0.png", "losevideos/003306/1.png", "losevideos/003306/2.png", "losevideos/003306/3.png", "losevideos/003306/4.png", "losevideos/003306/5.png", "losevideos/003306/6.png", "losevideos/003306/7.png" ]
dj spining records in room filled with records.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [dj spining records in room filled with records.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008626/0.png", "losevideos/008626/1.png", "losevideos/008626/2.png", "losevideos/008626/3.png", "losevideos/008626/4.png", "losevideos/008626/5.png", "losevideos/008626/6.png", "losevideos/008626/7.png", "winvideos/008626/0.png", "winvideos/008626/1.png", "winvideos/008626/2.png", "winvideos/008626/3.png", "winvideos/008626/4.png", "winvideos/008626/5.png", "winvideos/008626/6.png", "winvideos/008626/7.png" ]
a beautiful pink haired female model sitting in front of a fan, fan blowing air, floral bikini, dancing, ultra realistic, 4k video, wide angle shot, studio lighting, Guillermo del Toro, 4K -gs 12 -neg "ugly, blurry, cartoon, drawing, unrealistic, bad anatomy" -ar 4:3 -motion 2 --upbeta.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 pink haired female model sitting in front of a fan, fan blowing air, floral bikini, dancing, ultra realistic, 4k video, wide angle shot, studio lighting, Guillermo del Toro, 4K -gs 12 -neg "ugly, blurry, cartoon, drawing, unrealistic, bad anatomy" -ar 4:3 -motion 2 --upbeta.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008584/0.png", "winvideos/008584/1.png", "winvideos/008584/2.png", "winvideos/008584/3.png", "winvideos/008584/4.png", "winvideos/008584/5.png", "winvideos/008584/6.png", "winvideos/008584/7.png", "losevideos/008584/0.png", "losevideos/008584/1.png", "losevideos/008584/2.png", "losevideos/008584/3.png", "losevideos/008584/4.png", "losevideos/008584/5.png", "losevideos/008584/6.png", "losevideos/008584/7.png" ]
little turtle swing slowly, water wave, fishes swimming,coral move , -motion3 --ar16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [little turtle swing slowly, water wave, fishes swimming,coral move , -motion3 --ar16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002351/0.png", "losevideos/002351/1.png", "losevideos/002351/2.png", "losevideos/002351/3.png", "losevideos/002351/4.png", "losevideos/002351/5.png", "losevideos/002351/6.png", "losevideos/002351/7.png", "winvideos/002351/0.png", "winvideos/002351/1.png", "winvideos/002351/2.png", "winvideos/002351/3.png", "winvideos/002351/4.png", "winvideos/002351/5.png", "winvideos/002351/6.png", "winvideos/002351/7.png" ]
use "subscribe" and "like" English words in the center, use cute laddy laughing to invite and encourage and atract viewers, uses warm color -ar 9:16 4k ultera HD.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [use "subscribe" and "like" English words in the center, use cute laddy laughing to invite and encourage and atract viewers, uses warm color -ar 9:16 4k ultera HD.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003082/0.png", "losevideos/003082/1.png", "losevideos/003082/2.png", "losevideos/003082/3.png", "losevideos/003082/4.png", "losevideos/003082/5.png", "losevideos/003082/6.png", "losevideos/003082/7.png", "winvideos/003082/0.png", "winvideos/003082/1.png", "winvideos/003082/2.png", "winvideos/003082/3.png", "winvideos/003082/4.png", "winvideos/003082/5.png", "winvideos/003082/6.png", "winvideos/003082/7.png" ]
A group of humans in the city of Persepolis in the years 559-530 BC. High definition, cinematic, hyper realistic -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 group of humans in the city of Persepolis in the years 559-530 BC. High definition, cinematic, hyper realistic -16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008769/0.png", "losevideos/008769/1.png", "losevideos/008769/2.png", "losevideos/008769/3.png", "losevideos/008769/4.png", "losevideos/008769/5.png", "losevideos/008769/6.png", "losevideos/008769/7.png", "winvideos/008769/0.png", "winvideos/008769/1.png", "winvideos/008769/2.png", "winvideos/008769/3.png", "winvideos/008769/4.png", "winvideos/008769/5.png", "winvideos/008769/6.png", "winvideos/008769/7.png" ]
The Andy Griffith Show Barney finds a Nuclear Device.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 Andy Griffith Show Barney finds a Nuclear Device.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000713/0.png", "winvideos/000713/1.png", "winvideos/000713/2.png", "winvideos/000713/3.png", "winvideos/000713/4.png", "winvideos/000713/5.png", "winvideos/000713/6.png", "winvideos/000713/7.png", "losevideos/000713/0.png", "losevideos/000713/1.png", "losevideos/000713/2.png", "losevideos/000713/3.png", "losevideos/000713/4.png", "losevideos/000713/5.png", "losevideos/000713/6.png", "losevideos/000713/7.png" ]
an emoji talking bulb.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 emoji talking bulb.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006023/0.png", "losevideos/006023/1.png", "losevideos/006023/2.png", "losevideos/006023/3.png", "losevideos/006023/4.png", "losevideos/006023/5.png", "losevideos/006023/6.png", "losevideos/006023/7.png", "winvideos/006023/0.png", "winvideos/006023/1.png", "winvideos/006023/2.png", "winvideos/006023/3.png", "winvideos/006023/4.png", "winvideos/006023/5.png", "winvideos/006023/6.png", "winvideos/006023/7.png" ]
bunny sleeping under the tree.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [bunny sleeping under the tree.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003593/0.png", "winvideos/003593/1.png", "winvideos/003593/2.png", "winvideos/003593/3.png", "winvideos/003593/4.png", "winvideos/003593/5.png", "winvideos/003593/6.png", "winvideos/003593/7.png", "losevideos/003593/0.png", "losevideos/003593/1.png", "losevideos/003593/2.png", "losevideos/003593/3.png", "losevideos/003593/4.png", "losevideos/003593/5.png", "losevideos/003593/6.png", "losevideos/003593/7.png" ]
Create an image Shree ram standing with his dhanush and baan, bow and arrow.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 Shree ram standing with his dhanush and baan, bow and arrow.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003953/0.png", "losevideos/003953/1.png", "losevideos/003953/2.png", "losevideos/003953/3.png", "losevideos/003953/4.png", "losevideos/003953/5.png", "losevideos/003953/6.png", "losevideos/003953/7.png", "winvideos/003953/0.png", "winvideos/003953/1.png", "winvideos/003953/2.png", "winvideos/003953/3.png", "winvideos/003953/4.png", "winvideos/003953/5.png", "winvideos/003953/6.png", "winvideos/003953/7.png" ]
goku in his base form transforming into super saiyan.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [goku in his base form transforming into super saiyan.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008556/0.png", "losevideos/008556/1.png", "losevideos/008556/2.png", "losevideos/008556/3.png", "losevideos/008556/4.png", "losevideos/008556/5.png", "losevideos/008556/6.png", "losevideos/008556/7.png", "winvideos/008556/0.png", "winvideos/008556/1.png", "winvideos/008556/2.png", "winvideos/008556/3.png", "winvideos/008556/4.png", "winvideos/008556/5.png", "winvideos/008556/6.png", "winvideos/008556/7.png" ]
2d animation explainer video business video creator.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [2d animation explainer video business video creator.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006817/0.png", "losevideos/006817/1.png", "losevideos/006817/2.png", "losevideos/006817/3.png", "losevideos/006817/4.png", "losevideos/006817/5.png", "losevideos/006817/6.png", "losevideos/006817/7.png", "winvideos/006817/0.png", "winvideos/006817/1.png", "winvideos/006817/2.png", "winvideos/006817/3.png", "winvideos/006817/4.png", "winvideos/006817/5.png", "winvideos/006817/6.png", "winvideos/006817/7.png" ]
grinning cunning street performer.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [grinning cunning street performer.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002362/0.png", "losevideos/002362/1.png", "losevideos/002362/2.png", "losevideos/002362/3.png", "losevideos/002362/4.png", "losevideos/002362/5.png", "losevideos/002362/6.png", "losevideos/002362/7.png", "winvideos/002362/0.png", "winvideos/002362/1.png", "winvideos/002362/2.png", "winvideos/002362/3.png", "winvideos/002362/4.png", "winvideos/002362/5.png", "winvideos/002362/6.png", "winvideos/002362/7.png" ]
dark spooky night forest, foggy trail.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [dark spooky night forest, foggy trail.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004963/0.png", "losevideos/004963/1.png", "losevideos/004963/2.png", "losevideos/004963/3.png", "losevideos/004963/4.png", "losevideos/004963/5.png", "losevideos/004963/6.png", "losevideos/004963/7.png", "winvideos/004963/0.png", "winvideos/004963/1.png", "winvideos/004963/2.png", "winvideos/004963/3.png", "winvideos/004963/4.png", "winvideos/004963/5.png", "winvideos/004963/6.png", "winvideos/004963/7.png" ]
timelapse rainbow mushroom psychedelic camera 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: [timelapse rainbow mushroom psychedelic camera flying.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007121/0.png", "winvideos/007121/1.png", "winvideos/007121/2.png", "winvideos/007121/3.png", "winvideos/007121/4.png", "winvideos/007121/5.png", "winvideos/007121/6.png", "winvideos/007121/7.png", "losevideos/007121/0.png", "losevideos/007121/1.png", "losevideos/007121/2.png", "losevideos/007121/3.png", "losevideos/007121/4.png", "losevideos/007121/5.png", "losevideos/007121/6.png", "losevideos/007121/7.png" ]
woman being harassed by a man in an alley middle ages 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: [woman being harassed by a man in an alley middle ages style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007370/0.png", "winvideos/007370/1.png", "winvideos/007370/2.png", "winvideos/007370/3.png", "winvideos/007370/4.png", "winvideos/007370/5.png", "winvideos/007370/6.png", "winvideos/007370/7.png", "losevideos/007370/0.png", "losevideos/007370/1.png", "losevideos/007370/2.png", "losevideos/007370/3.png", "losevideos/007370/4.png", "losevideos/007370/5.png", "losevideos/007370/6.png", "losevideos/007370/7.png" ]
a bunch of wine bottles on display Message: mhanz (Font: MODERN).	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a bunch of wine bottles on display Message: mhanz (Font: MODERN).]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002821/0.png", "winvideos/002821/1.png", "winvideos/002821/2.png", "winvideos/002821/3.png", "winvideos/002821/4.png", "winvideos/002821/5.png", "winvideos/002821/6.png", "winvideos/002821/7.png", "losevideos/002821/0.png", "losevideos/002821/1.png", "losevideos/002821/2.png", "losevideos/002821/3.png", "losevideos/002821/4.png", "losevideos/002821/5.png", "losevideos/002821/6.png", "losevideos/002821/7.png" ]
trees moving 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: [trees moving in background.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003964/0.png", "winvideos/003964/1.png", "winvideos/003964/2.png", "winvideos/003964/3.png", "winvideos/003964/4.png", "winvideos/003964/5.png", "winvideos/003964/6.png", "winvideos/003964/7.png", "losevideos/003964/0.png", "losevideos/003964/1.png", "losevideos/003964/2.png", "losevideos/003964/3.png", "losevideos/003964/4.png", "losevideos/003964/5.png", "losevideos/003964/6.png", "losevideos/003964/7.png" ]
A sexy chinese girl wearing jeans standing on top of a tall building, looking down at the road below with a very frightened expression -ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A sexy chinese girl wearing jeans standing on top of a tall building, looking down at the road below with a very frightened expression -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000427/0.png", "winvideos/000427/1.png", "winvideos/000427/2.png", "winvideos/000427/3.png", "winvideos/000427/4.png", "winvideos/000427/5.png", "winvideos/000427/6.png", "winvideos/000427/7.png", "losevideos/000427/0.png", "losevideos/000427/1.png", "losevideos/000427/2.png", "losevideos/000427/3.png", "losevideos/000427/4.png", "losevideos/000427/5.png", "losevideos/000427/6.png", "losevideos/000427/7.png" ]
scientific research records.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [scientific research records.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000373/0.png", "losevideos/000373/1.png", "losevideos/000373/2.png", "losevideos/000373/3.png", "losevideos/000373/4.png", "losevideos/000373/5.png", "losevideos/000373/6.png", "losevideos/000373/7.png", "winvideos/000373/0.png", "winvideos/000373/1.png", "winvideos/000373/2.png", "winvideos/000373/3.png", "winvideos/000373/4.png", "winvideos/000373/5.png", "winvideos/000373/6.png", "winvideos/000373/7.png" ]
Young couple kiss, flowers and trees, 1950s advertisement black and white.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Young couple kiss, flowers and trees, 1950s advertisement black and white.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006451/0.png", "losevideos/006451/1.png", "losevideos/006451/2.png", "losevideos/006451/3.png", "losevideos/006451/4.png", "losevideos/006451/5.png", "losevideos/006451/6.png", "losevideos/006451/7.png", "winvideos/006451/0.png", "winvideos/006451/1.png", "winvideos/006451/2.png", "winvideos/006451/3.png", "winvideos/006451/4.png", "winvideos/006451/5.png", "winvideos/006451/6.png", "winvideos/006451/7.png" ]