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
female clown sitting in a chair on fire.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [female clown sitting in a chair on fire.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003130/0.png", "winvideos/003130/1.png", "winvideos/003130/2.png", "winvideos/003130/3.png", "winvideos/003130/4.png", "winvideos/003130/5.png", "winvideos/003130/6.png", "winvideos/003130/7.png", "losevideos/003130/0.png", "losevideos/003130/1.png", "losevideos/003130/2.png", "losevideos/003130/3.png", "losevideos/003130/4.png", "losevideos/003130/5.png", "losevideos/003130/6.png", "losevideos/003130/7.png" ]
geothermal reaction, cinematic, sunset -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: [geothermal reaction, cinematic, sunset -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004949/0.png", "winvideos/004949/1.png", "winvideos/004949/2.png", "winvideos/004949/3.png", "winvideos/004949/4.png", "winvideos/004949/5.png", "winvideos/004949/6.png", "winvideos/004949/7.png", "losevideos/004949/0.png", "losevideos/004949/1.png", "losevideos/004949/2.png", "losevideos/004949/3.png", "losevideos/004949/4.png", "losevideos/004949/5.png", "losevideos/004949/6.png", "losevideos/004949/7.png" ]
Cinematic medium shot fantasy film of a warrior standing on a hill overlooking a vast battlefield under a stormy sky -ar 16:9 -motion 3 -fps 24 -gs 2 -neg "modern buildings, cars, flying objects" -seed 12345 -camera pan up right.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Cinematic medium shot fantasy film of a warrior standing on a hill overlooking a vast battlefield under a stormy sky -ar 16:9 -motion 3 -fps 24 -gs 2 -neg "modern buildings, cars, flying objects" -seed 12345 -camera pan up right.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000578/0.png", "winvideos/000578/1.png", "winvideos/000578/2.png", "winvideos/000578/3.png", "winvideos/000578/4.png", "winvideos/000578/5.png", "winvideos/000578/6.png", "winvideos/000578/7.png", "losevideos/000578/0.png", "losevideos/000578/1.png", "losevideos/000578/2.png", "losevideos/000578/3.png", "losevideos/000578/4.png", "losevideos/000578/5.png", "losevideos/000578/6.png", "losevideos/000578/7.png" ]
A scene of an apocalyptic war, something powerful enough.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 scene of an apocalyptic war, something powerful enough.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004846/0.png", "winvideos/004846/1.png", "winvideos/004846/2.png", "winvideos/004846/3.png", "winvideos/004846/4.png", "winvideos/004846/5.png", "winvideos/004846/6.png", "winvideos/004846/7.png", "losevideos/004846/0.png", "losevideos/004846/1.png", "losevideos/004846/2.png", "losevideos/004846/3.png", "losevideos/004846/4.png", "losevideos/004846/5.png", "losevideos/004846/6.png", "losevideos/004846/7.png" ]
(Waterfall flowing, water flowing, trees growing on both sides, ink painting, naturalism, 4k resolution, outdoor environment, rich in details, clear and transparent, green vegetation, natural color tone.) -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: [(Waterfall flowing, water flowing, trees growing on both sides, ink painting, naturalism, 4k resolution, outdoor environment, rich in details, clear and transparent, green vegetation, natural color tone.) -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005815/0.png", "winvideos/005815/1.png", "winvideos/005815/2.png", "winvideos/005815/3.png", "winvideos/005815/4.png", "winvideos/005815/5.png", "winvideos/005815/6.png", "winvideos/005815/7.png", "losevideos/005815/0.png", "losevideos/005815/1.png", "losevideos/005815/2.png", "losevideos/005815/3.png", "losevideos/005815/4.png", "losevideos/005815/5.png", "losevideos/005815/6.png", "losevideos/005815/7.png" ]
naruto eats potato.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [naruto eats potato.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009224/0.png", "losevideos/009224/1.png", "losevideos/009224/2.png", "losevideos/009224/3.png", "losevideos/009224/4.png", "losevideos/009224/5.png", "losevideos/009224/6.png", "losevideos/009224/7.png", "winvideos/009224/0.png", "winvideos/009224/1.png", "winvideos/009224/2.png", "winvideos/009224/3.png", "winvideos/009224/4.png", "winvideos/009224/5.png", "winvideos/009224/6.png", "winvideos/009224/7.png" ]
Opening Shot of the Eiffel Tower].	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Opening Shot of the Eiffel Tower].]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003837/0.png", "winvideos/003837/1.png", "winvideos/003837/2.png", "winvideos/003837/3.png", "winvideos/003837/4.png", "winvideos/003837/5.png", "winvideos/003837/6.png", "winvideos/003837/7.png", "losevideos/003837/0.png", "losevideos/003837/1.png", "losevideos/003837/2.png", "losevideos/003837/3.png", "losevideos/003837/4.png", "losevideos/003837/5.png", "losevideos/003837/6.png", "losevideos/003837/7.png" ]
"Trading Creativity: Your Ideas, Our Neural Network.".	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: ["Trading Creativity: Your Ideas, Our Neural Network.".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006079/0.png", "losevideos/006079/1.png", "losevideos/006079/2.png", "losevideos/006079/3.png", "losevideos/006079/4.png", "losevideos/006079/5.png", "losevideos/006079/6.png", "losevideos/006079/7.png", "winvideos/006079/0.png", "winvideos/006079/1.png", "winvideos/006079/2.png", "winvideos/006079/3.png", "winvideos/006079/4.png", "winvideos/006079/5.png", "winvideos/006079/6.png", "winvideos/006079/7.png" ]
The Laughing Forest in all its glory, trees, flowers, and animals laughing heartily, creating a vibrant and cheerful 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: [The Laughing Forest in all its glory, trees, flowers, and animals laughing heartily, creating a vibrant and cheerful atmosphere.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003588/0.png", "losevideos/003588/1.png", "losevideos/003588/2.png", "losevideos/003588/3.png", "losevideos/003588/4.png", "losevideos/003588/5.png", "losevideos/003588/6.png", "losevideos/003588/7.png", "winvideos/003588/0.png", "winvideos/003588/1.png", "winvideos/003588/2.png", "winvideos/003588/3.png", "winvideos/003588/4.png", "winvideos/003588/5.png", "winvideos/003588/6.png", "winvideos/003588/7.png" ]
A running cyberpunk rhinoceros with Tokyo city streets in the 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: [A running cyberpunk rhinoceros with Tokyo city streets in the background.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005780/0.png", "winvideos/005780/1.png", "winvideos/005780/2.png", "winvideos/005780/3.png", "winvideos/005780/4.png", "winvideos/005780/5.png", "winvideos/005780/6.png", "winvideos/005780/7.png", "losevideos/005780/0.png", "losevideos/005780/1.png", "losevideos/005780/2.png", "losevideos/005780/3.png", "losevideos/005780/4.png", "losevideos/005780/5.png", "losevideos/005780/6.png", "losevideos/005780/7.png" ]
shaking your hair anime style Message: 1 Attachment.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [shaking your hair anime style Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009867/0.png", "losevideos/009867/1.png", "losevideos/009867/2.png", "losevideos/009867/3.png", "losevideos/009867/4.png", "losevideos/009867/5.png", "losevideos/009867/6.png", "losevideos/009867/7.png", "winvideos/009867/0.png", "winvideos/009867/1.png", "winvideos/009867/2.png", "winvideos/009867/3.png", "winvideos/009867/4.png", "winvideos/009867/5.png", "winvideos/009867/6.png", "winvideos/009867/7.png" ]
dog with chains and torn mouth dota 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: [dog with chains and torn mouth dota 2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004619/0.png", "winvideos/004619/1.png", "winvideos/004619/2.png", "winvideos/004619/3.png", "winvideos/004619/4.png", "winvideos/004619/5.png", "winvideos/004619/6.png", "winvideos/004619/7.png", "losevideos/004619/0.png", "losevideos/004619/1.png", "losevideos/004619/2.png", "losevideos/004619/3.png", "losevideos/004619/4.png", "losevideos/004619/5.png", "losevideos/004619/6.png", "losevideos/004619/7.png" ]
Druids in Gas-masks sell massive insects at alien wet market in the desert Alfred Stieglitz black and white 1900s.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Druids in Gas-masks sell massive insects at alien wet market in the desert Alfred Stieglitz black and white 1900s.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002457/0.png", "winvideos/002457/1.png", "winvideos/002457/2.png", "winvideos/002457/3.png", "winvideos/002457/4.png", "winvideos/002457/5.png", "winvideos/002457/6.png", "winvideos/002457/7.png", "losevideos/002457/0.png", "losevideos/002457/1.png", "losevideos/002457/2.png", "losevideos/002457/3.png", "losevideos/002457/4.png", "losevideos/002457/5.png", "losevideos/002457/6.png", "losevideos/002457/7.png" ]
snow chair.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [snow chair.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007502/0.png", "winvideos/007502/1.png", "winvideos/007502/2.png", "winvideos/007502/3.png", "winvideos/007502/4.png", "winvideos/007502/5.png", "winvideos/007502/6.png", "winvideos/007502/7.png", "losevideos/007502/0.png", "losevideos/007502/1.png", "losevideos/007502/2.png", "losevideos/007502/3.png", "losevideos/007502/4.png", "losevideos/007502/5.png", "losevideos/007502/6.png", "losevideos/007502/7.png" ]
Thinking of you, the clothing corner gently swaying in the lotus-scented breeze of that year.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Thinking of you, the clothing corner gently swaying in the lotus-scented breeze of that year.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007622/0.png", "winvideos/007622/1.png", "winvideos/007622/2.png", "winvideos/007622/3.png", "winvideos/007622/4.png", "winvideos/007622/5.png", "winvideos/007622/6.png", "winvideos/007622/7.png", "losevideos/007622/0.png", "losevideos/007622/1.png", "losevideos/007622/2.png", "losevideos/007622/3.png", "losevideos/007622/4.png", "losevideos/007622/5.png", "losevideos/007622/6.png", "losevideos/007622/7.png" ]
friendship and love story.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [friendship and love story.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004088/0.png", "losevideos/004088/1.png", "losevideos/004088/2.png", "losevideos/004088/3.png", "losevideos/004088/4.png", "losevideos/004088/5.png", "losevideos/004088/6.png", "losevideos/004088/7.png", "winvideos/004088/0.png", "winvideos/004088/1.png", "winvideos/004088/2.png", "winvideos/004088/3.png", "winvideos/004088/4.png", "winvideos/004088/5.png", "winvideos/004088/6.png", "winvideos/004088/7.png" ]
young romanian guy eating burgers and parachuting.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 romanian guy eating burgers and parachuting.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001925/0.png", "winvideos/001925/1.png", "winvideos/001925/2.png", "winvideos/001925/3.png", "winvideos/001925/4.png", "winvideos/001925/5.png", "winvideos/001925/6.png", "winvideos/001925/7.png", "losevideos/001925/0.png", "losevideos/001925/1.png", "losevideos/001925/2.png", "losevideos/001925/3.png", "losevideos/001925/4.png", "losevideos/001925/5.png", "losevideos/001925/6.png", "losevideos/001925/7.png" ]
A vibrant and lively town with colorful houses, bustling streets, and people going about their daily activities.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 vibrant and lively town with colorful houses, bustling streets, and people going about their daily activities.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005891/0.png", "winvideos/005891/1.png", "winvideos/005891/2.png", "winvideos/005891/3.png", "winvideos/005891/4.png", "winvideos/005891/5.png", "winvideos/005891/6.png", "winvideos/005891/7.png", "losevideos/005891/0.png", "losevideos/005891/1.png", "losevideos/005891/2.png", "losevideos/005891/3.png", "losevideos/005891/4.png", "losevideos/005891/5.png", "losevideos/005891/6.png", "losevideos/005891/7.png" ]
Show a thief stealing the antique vase inside the temple at midnight with moonlight. ultra hd, cinematic, dynamic 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: [Show a thief stealing the antique vase inside the temple at midnight with moonlight. ultra hd, cinematic, dynamic movement.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004020/0.png", "winvideos/004020/1.png", "winvideos/004020/2.png", "winvideos/004020/3.png", "winvideos/004020/4.png", "winvideos/004020/5.png", "winvideos/004020/6.png", "winvideos/004020/7.png", "losevideos/004020/0.png", "losevideos/004020/1.png", "losevideos/004020/2.png", "losevideos/004020/3.png", "losevideos/004020/4.png", "losevideos/004020/5.png", "losevideos/004020/6.png", "losevideos/004020/7.png" ]
a girl with low rise jeans doing belly dance in a room.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 with low rise jeans doing belly dance in a room.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002746/0.png", "winvideos/002746/1.png", "winvideos/002746/2.png", "winvideos/002746/3.png", "winvideos/002746/4.png", "winvideos/002746/5.png", "winvideos/002746/6.png", "winvideos/002746/7.png", "losevideos/002746/0.png", "losevideos/002746/1.png", "losevideos/002746/2.png", "losevideos/002746/3.png", "losevideos/002746/4.png", "losevideos/002746/5.png", "losevideos/002746/6.png", "losevideos/002746/7.png" ]
a airplane takes off.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 airplane takes off.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001279/0.png", "winvideos/001279/1.png", "winvideos/001279/2.png", "winvideos/001279/3.png", "winvideos/001279/4.png", "winvideos/001279/5.png", "winvideos/001279/6.png", "winvideos/001279/7.png", "losevideos/001279/0.png", "losevideos/001279/1.png", "losevideos/001279/2.png", "losevideos/001279/3.png", "losevideos/001279/4.png", "losevideos/001279/5.png", "losevideos/001279/6.png", "losevideos/001279/7.png" ]
avant garde ultra realistic fashion beauty photo editorial, wearing shiny black fabric suit in a studio,.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [avant garde ultra realistic fashion beauty photo editorial, wearing shiny black fabric suit in a studio,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000059/0.png", "winvideos/000059/1.png", "winvideos/000059/2.png", "winvideos/000059/3.png", "winvideos/000059/4.png", "winvideos/000059/5.png", "winvideos/000059/6.png", "winvideos/000059/7.png", "losevideos/000059/0.png", "losevideos/000059/1.png", "losevideos/000059/2.png", "losevideos/000059/3.png", "losevideos/000059/4.png", "losevideos/000059/5.png", "losevideos/000059/6.png", "losevideos/000059/7.png" ]
move,image.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [move,image.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008602/0.png", "losevideos/008602/1.png", "losevideos/008602/2.png", "losevideos/008602/3.png", "losevideos/008602/4.png", "losevideos/008602/5.png", "losevideos/008602/6.png", "losevideos/008602/7.png", "winvideos/008602/0.png", "winvideos/008602/1.png", "winvideos/008602/2.png", "winvideos/008602/3.png", "winvideos/008602/4.png", "winvideos/008602/5.png", "winvideos/008602/6.png", "winvideos/008602/7.png" ]
Nature Peony Garden Japan.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Nature Peony Garden Japan.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000681/0.png", "losevideos/000681/1.png", "losevideos/000681/2.png", "losevideos/000681/3.png", "losevideos/000681/4.png", "losevideos/000681/5.png", "losevideos/000681/6.png", "losevideos/000681/7.png", "winvideos/000681/0.png", "winvideos/000681/1.png", "winvideos/000681/2.png", "winvideos/000681/3.png", "winvideos/000681/4.png", "winvideos/000681/5.png", "winvideos/000681/6.png", "winvideos/000681/7.png" ]
a man is standing under a waterfall -fps 24 -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 man is standing under a waterfall -fps 24 -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003545/0.png", "winvideos/003545/1.png", "winvideos/003545/2.png", "winvideos/003545/3.png", "winvideos/003545/4.png", "winvideos/003545/5.png", "winvideos/003545/6.png", "winvideos/003545/7.png", "losevideos/003545/0.png", "losevideos/003545/1.png", "losevideos/003545/2.png", "losevideos/003545/3.png", "losevideos/003545/4.png", "losevideos/003545/5.png", "losevideos/003545/6.png", "losevideos/003545/7.png" ]
Spilling gouache pattern Yellow-red, - cover the earth.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Spilling gouache pattern\nYellow-red, - cover the earth.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003966/0.png", "winvideos/003966/1.png", "winvideos/003966/2.png", "winvideos/003966/3.png", "winvideos/003966/4.png", "winvideos/003966/5.png", "winvideos/003966/6.png", "winvideos/003966/7.png", "losevideos/003966/0.png", "losevideos/003966/1.png", "losevideos/003966/2.png", "losevideos/003966/3.png", "losevideos/003966/4.png", "losevideos/003966/5.png", "losevideos/003966/6.png", "losevideos/003966/7.png" ]
Hulk playing tennis the best action.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Hulk playing tennis the best action.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005930/0.png", "losevideos/005930/1.png", "losevideos/005930/2.png", "losevideos/005930/3.png", "losevideos/005930/4.png", "losevideos/005930/5.png", "losevideos/005930/6.png", "losevideos/005930/7.png", "winvideos/005930/0.png", "winvideos/005930/1.png", "winvideos/005930/2.png", "winvideos/005930/3.png", "winvideos/005930/4.png", "winvideos/005930/5.png", "winvideos/005930/6.png", "winvideos/005930/7.png" ]
switzerland, hyper lapse, Rajkumar hirani style, well lit ,extreme wide shot, drone shot, hyper track in camera movement, cloudy, 60%fog, hyper realistic, high detail, high octane render, high texture,.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [switzerland, hyper lapse, Rajkumar hirani style, well lit ,extreme wide shot, drone shot, hyper track in camera movement, cloudy, 60%fog, hyper realistic, high detail, high octane render, high texture,.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007812/0.png", "losevideos/007812/1.png", "losevideos/007812/2.png", "losevideos/007812/3.png", "losevideos/007812/4.png", "losevideos/007812/5.png", "losevideos/007812/6.png", "losevideos/007812/7.png", "winvideos/007812/0.png", "winvideos/007812/1.png", "winvideos/007812/2.png", "winvideos/007812/3.png", "winvideos/007812/4.png", "winvideos/007812/5.png", "winvideos/007812/6.png", "winvideos/007812/7.png" ]
creatan epic 3d monster moving head around angry.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [creatan epic 3d monster moving head around angry.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006816/0.png", "losevideos/006816/1.png", "losevideos/006816/2.png", "losevideos/006816/3.png", "losevideos/006816/4.png", "losevideos/006816/5.png", "losevideos/006816/6.png", "losevideos/006816/7.png", "winvideos/006816/0.png", "winvideos/006816/1.png", "winvideos/006816/2.png", "winvideos/006816/3.png", "winvideos/006816/4.png", "winvideos/006816/5.png", "winvideos/006816/6.png", "winvideos/006816/7.png" ]
We see an imposing figure of a Minotaur standing at the center of a large chamber. Its muscular frame is covered with matted fur, and its snarling face is crowned with enormous bull horns. The camera zooms in to reveal the Minotaur’s deep crimson eyes, blazing with fury and defiance.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [We see an imposing figure of a Minotaur standing at the center of a large chamber. Its muscular frame is covered with matted fur, and its snarling face is crowned with enormous bull horns. The camera zooms in to reveal the Minotaur’s deep crimson eyes, blazing with fury and defiance.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005257/0.png", "losevideos/005257/1.png", "losevideos/005257/2.png", "losevideos/005257/3.png", "losevideos/005257/4.png", "losevideos/005257/5.png", "losevideos/005257/6.png", "losevideos/005257/7.png", "winvideos/005257/0.png", "winvideos/005257/1.png", "winvideos/005257/2.png", "winvideos/005257/3.png", "winvideos/005257/4.png", "winvideos/005257/5.png", "winvideos/005257/6.png", "winvideos/005257/7.png" ]
most beautiful woman full body.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [most beautiful woman full body.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009308/0.png", "losevideos/009308/1.png", "losevideos/009308/2.png", "losevideos/009308/3.png", "losevideos/009308/4.png", "losevideos/009308/5.png", "losevideos/009308/6.png", "losevideos/009308/7.png", "winvideos/009308/0.png", "winvideos/009308/1.png", "winvideos/009308/2.png", "winvideos/009308/3.png", "winvideos/009308/4.png", "winvideos/009308/5.png", "winvideos/009308/6.png", "winvideos/009308/7.png" ]
prompt:cute cat baby.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [prompt:cute cat baby.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000326/0.png", "winvideos/000326/1.png", "winvideos/000326/2.png", "winvideos/000326/3.png", "winvideos/000326/4.png", "winvideos/000326/5.png", "winvideos/000326/6.png", "winvideos/000326/7.png", "losevideos/000326/0.png", "losevideos/000326/1.png", "losevideos/000326/2.png", "losevideos/000326/3.png", "losevideos/000326/4.png", "losevideos/000326/5.png", "losevideos/000326/6.png", "losevideos/000326/7.png" ]
Exterior of Scott's Jazz Club in London 1974.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Exterior of Scott's Jazz Club in London 1974.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004730/0.png", "losevideos/004730/1.png", "losevideos/004730/2.png", "losevideos/004730/3.png", "losevideos/004730/4.png", "losevideos/004730/5.png", "losevideos/004730/6.png", "losevideos/004730/7.png", "winvideos/004730/0.png", "winvideos/004730/1.png", "winvideos/004730/2.png", "winvideos/004730/3.png", "winvideos/004730/4.png", "winvideos/004730/5.png", "winvideos/004730/6.png", "winvideos/004730/7.png" ]
explosion of rain splashing and splattering.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [explosion of rain splashing and splattering.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000591/0.png", "winvideos/000591/1.png", "winvideos/000591/2.png", "winvideos/000591/3.png", "winvideos/000591/4.png", "winvideos/000591/5.png", "winvideos/000591/6.png", "winvideos/000591/7.png", "losevideos/000591/0.png", "losevideos/000591/1.png", "losevideos/000591/2.png", "losevideos/000591/3.png", "losevideos/000591/4.png", "losevideos/000591/5.png", "losevideos/000591/6.png", "losevideos/000591/7.png" ]
the mythical forest burns as if in a dream.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better 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 mythical forest burns as if in a dream.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003847/0.png", "winvideos/003847/1.png", "winvideos/003847/2.png", "winvideos/003847/3.png", "winvideos/003847/4.png", "winvideos/003847/5.png", "winvideos/003847/6.png", "winvideos/003847/7.png", "losevideos/003847/0.png", "losevideos/003847/1.png", "losevideos/003847/2.png", "losevideos/003847/3.png", "losevideos/003847/4.png", "losevideos/003847/5.png", "losevideos/003847/6.png", "losevideos/003847/7.png" ]
golden gate bridge collapses with too many cars on it, ultra wide shot, intricate details.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [golden gate bridge collapses with too many cars on it, ultra wide shot, intricate details.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006810/0.png", "winvideos/006810/1.png", "winvideos/006810/2.png", "winvideos/006810/3.png", "winvideos/006810/4.png", "winvideos/006810/5.png", "winvideos/006810/6.png", "winvideos/006810/7.png", "losevideos/006810/0.png", "losevideos/006810/1.png", "losevideos/006810/2.png", "losevideos/006810/3.png", "losevideos/006810/4.png", "losevideos/006810/5.png", "losevideos/006810/6.png", "losevideos/006810/7.png" ]
A colonist on his ship, ships in background, Full shot, erratic fluctuation in motion, noisy, high production value, intricate details, high resolution --ar 21:9.	[ { "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 colonist on his ship, ships in background, Full shot, erratic fluctuation in motion, noisy, high production value, intricate details, high resolution --ar 21:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000324/0.png", "losevideos/000324/1.png", "losevideos/000324/2.png", "losevideos/000324/3.png", "losevideos/000324/4.png", "losevideos/000324/5.png", "losevideos/000324/6.png", "losevideos/000324/7.png", "winvideos/000324/0.png", "winvideos/000324/1.png", "winvideos/000324/2.png", "winvideos/000324/3.png", "winvideos/000324/4.png", "winvideos/000324/5.png", "winvideos/000324/6.png", "winvideos/000324/7.png" ]
leaves falling, slowly blinking, gently turning the pages, a girl is sitting under a tree with a book in her hands and reading it, gentle wind, anime 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: [leaves falling, slowly blinking, gently turning the pages, a girl is sitting under a tree with a book in her hands and reading it, gentle wind, anime style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000066/0.png", "winvideos/000066/1.png", "winvideos/000066/2.png", "winvideos/000066/3.png", "winvideos/000066/4.png", "winvideos/000066/5.png", "winvideos/000066/6.png", "winvideos/000066/7.png", "losevideos/000066/0.png", "losevideos/000066/1.png", "losevideos/000066/2.png", "losevideos/000066/3.png", "losevideos/000066/4.png", "losevideos/000066/5.png", "losevideos/000066/6.png", "losevideos/000066/7.png" ]
the love.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [the love.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006069/0.png", "winvideos/006069/1.png", "winvideos/006069/2.png", "winvideos/006069/3.png", "winvideos/006069/4.png", "winvideos/006069/5.png", "winvideos/006069/6.png", "winvideos/006069/7.png", "losevideos/006069/0.png", "losevideos/006069/1.png", "losevideos/006069/2.png", "losevideos/006069/3.png", "losevideos/006069/4.png", "losevideos/006069/5.png", "losevideos/006069/6.png", "losevideos/006069/7.png" ]
The grandmother is holding an umbrella in the blue rain.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The grandmother is holding an umbrella in the blue rain.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004155/0.png", "winvideos/004155/1.png", "winvideos/004155/2.png", "winvideos/004155/3.png", "winvideos/004155/4.png", "winvideos/004155/5.png", "winvideos/004155/6.png", "winvideos/004155/7.png", "losevideos/004155/0.png", "losevideos/004155/1.png", "losevideos/004155/2.png", "losevideos/004155/3.png", "losevideos/004155/4.png", "losevideos/004155/5.png", "losevideos/004155/6.png", "losevideos/004155/7.png" ]