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
Real abs Oriental handsome man selfie -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: [Real abs Oriental handsome man selfie -ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005806/0.png", "losevideos/005806/1.png", "losevideos/005806/2.png", "losevideos/005806/3.png", "losevideos/005806/4.png", "losevideos/005806/5.png", "losevideos/005806/6.png", "losevideos/005806/7.png", "winvideos/005806/0.png", "winvideos/005806/1.png", "winvideos/005806/2.png", "winvideos/005806/3.png", "winvideos/005806/4.png", "winvideos/005806/5.png", "winvideos/005806/6.png", "winvideos/005806/7.png" ]
a china town anime style Message: You look silly (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 china town anime style Message: You look silly (Font: MODERN).]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007572/0.png", "losevideos/007572/1.png", "losevideos/007572/2.png", "losevideos/007572/3.png", "losevideos/007572/4.png", "losevideos/007572/5.png", "losevideos/007572/6.png", "losevideos/007572/7.png", "winvideos/007572/0.png", "winvideos/007572/1.png", "winvideos/007572/2.png", "winvideos/007572/3.png", "winvideos/007572/4.png", "winvideos/007572/5.png", "winvideos/007572/6.png", "winvideos/007572/7.png" ]
moving hands through swampy water.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [moving hands through swampy water.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008766/0.png", "losevideos/008766/1.png", "losevideos/008766/2.png", "losevideos/008766/3.png", "losevideos/008766/4.png", "losevideos/008766/5.png", "losevideos/008766/6.png", "losevideos/008766/7.png", "winvideos/008766/0.png", "winvideos/008766/1.png", "winvideos/008766/2.png", "winvideos/008766/3.png", "winvideos/008766/4.png", "winvideos/008766/5.png", "winvideos/008766/6.png", "winvideos/008766/7.png" ]
Flames move.	[ { "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: [Flames move.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006183/0.png", "winvideos/006183/1.png", "winvideos/006183/2.png", "winvideos/006183/3.png", "winvideos/006183/4.png", "winvideos/006183/5.png", "winvideos/006183/6.png", "winvideos/006183/7.png", "losevideos/006183/0.png", "losevideos/006183/1.png", "losevideos/006183/2.png", "losevideos/006183/3.png", "losevideos/006183/4.png", "losevideos/006183/5.png", "losevideos/006183/6.png", "losevideos/006183/7.png" ]
quite angle shot, front shot, centered, a 25 year old adult man with yellow hair, wearing futuristic rubber clothing with details, is walking in a park around the futuristic eifel tower, about four characters walking, square grass, abstract futurism -neg " deform, distort, leg, light beam, light rays, reflection, smoke" -motion 1 -gs 12 -fps 24 -v6.0 -hide.	[ { "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: [quite angle shot, front shot, centered, a 25 year old adult man with yellow hair, wearing futuristic rubber clothing with details, is walking in a park around the futuristic eifel tower, about four characters walking, square grass, abstract futurism -neg " deform, distort, leg, light beam, light rays, reflection, smoke" -motion 1 -gs 12 -fps 24 -v6.0 -hide.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007207/0.png", "winvideos/007207/1.png", "winvideos/007207/2.png", "winvideos/007207/3.png", "winvideos/007207/4.png", "winvideos/007207/5.png", "winvideos/007207/6.png", "winvideos/007207/7.png", "losevideos/007207/0.png", "losevideos/007207/1.png", "losevideos/007207/2.png", "losevideos/007207/3.png", "losevideos/007207/4.png", "losevideos/007207/5.png", "losevideos/007207/6.png", "losevideos/007207/7.png" ]
young frog crawling toward an inset with moving wings.	[ { "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 frog crawling toward an inset with moving wings.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002916/0.png", "winvideos/002916/1.png", "winvideos/002916/2.png", "winvideos/002916/3.png", "winvideos/002916/4.png", "winvideos/002916/5.png", "winvideos/002916/6.png", "winvideos/002916/7.png", "losevideos/002916/0.png", "losevideos/002916/1.png", "losevideos/002916/2.png", "losevideos/002916/3.png", "losevideos/002916/4.png", "losevideos/002916/5.png", "losevideos/002916/6.png", "losevideos/002916/7.png" ]
Aliens are coming.	[ { "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 are coming.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007650/0.png", "losevideos/007650/1.png", "losevideos/007650/2.png", "losevideos/007650/3.png", "losevideos/007650/4.png", "losevideos/007650/5.png", "losevideos/007650/6.png", "losevideos/007650/7.png", "winvideos/007650/0.png", "winvideos/007650/1.png", "winvideos/007650/2.png", "winvideos/007650/3.png", "winvideos/007650/4.png", "winvideos/007650/5.png", "winvideos/007650/6.png", "winvideos/007650/7.png" ]
a rat eating laduu with hands. realistic 3d animation.	[ { "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 rat eating laduu with hands. realistic 3d animation.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005977/0.png", "winvideos/005977/1.png", "winvideos/005977/2.png", "winvideos/005977/3.png", "winvideos/005977/4.png", "winvideos/005977/5.png", "winvideos/005977/6.png", "winvideos/005977/7.png", "losevideos/005977/0.png", "losevideos/005977/1.png", "losevideos/005977/2.png", "losevideos/005977/3.png", "losevideos/005977/4.png", "losevideos/005977/5.png", "losevideos/005977/6.png", "losevideos/005977/7.png" ]
frontal coche fantástico kitt con luces de neón rojos iluminando derrapando y zoom.	[ { "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: [frontal coche fantástico kitt con luces de neón rojos iluminando derrapando y zoom.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007945/0.png", "winvideos/007945/1.png", "winvideos/007945/2.png", "winvideos/007945/3.png", "winvideos/007945/4.png", "winvideos/007945/5.png", "winvideos/007945/6.png", "winvideos/007945/7.png", "losevideos/007945/0.png", "losevideos/007945/1.png", "losevideos/007945/2.png", "losevideos/007945/3.png", "losevideos/007945/4.png", "losevideos/007945/5.png", "losevideos/007945/6.png", "losevideos/007945/7.png" ]
Brown Package on Doorstep: "A low-angle shot captures the weathered, plain brown package sitting ominously on a doorstep, surrounded by swirling mist and dead, skeletal branches reaching out like grasping fingers. The lighting is dim, with a soft backlight highlighting the mist, and a subtle vignette effect adds to the eerie atmosphere. (Blurry, black and white, with added vignette effect for heightened tension) [Shorts dimensions: 1080 x 1920 pixels, with an aspect ratio of 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: [Brown Package on Doorstep: "A low-angle shot captures the weathered, plain brown package sitting ominously on a doorstep, surrounded by swirling mist and dead, skeletal branches reaching out like grasping fingers. The lighting is dim, with a soft backlight highlighting the mist, and a subtle vignette effect adds to the eerie atmosphere. (Blurry, black and white, with added vignette effect for heightened tension) [Shorts dimensions: 1080 x 1920 pixels, with an aspect ratio of 9:16]".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005769/0.png", "losevideos/005769/1.png", "losevideos/005769/2.png", "losevideos/005769/3.png", "losevideos/005769/4.png", "losevideos/005769/5.png", "losevideos/005769/6.png", "losevideos/005769/7.png", "winvideos/005769/0.png", "winvideos/005769/1.png", "winvideos/005769/2.png", "winvideos/005769/3.png", "winvideos/005769/4.png", "winvideos/005769/5.png", "winvideos/005769/6.png", "winvideos/005769/7.png" ]
"Create a vivid description of a group of girls dancing gracefully in a moonlit garden, capturing the beauty and joy of the moment.".	[ { "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 a vivid description of a group of girls dancing gracefully in a moonlit garden, capturing the beauty and joy of the moment.".]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000871/0.png", "winvideos/000871/1.png", "winvideos/000871/2.png", "winvideos/000871/3.png", "winvideos/000871/4.png", "winvideos/000871/5.png", "winvideos/000871/6.png", "winvideos/000871/7.png", "losevideos/000871/0.png", "losevideos/000871/1.png", "losevideos/000871/2.png", "losevideos/000871/3.png", "losevideos/000871/4.png", "losevideos/000871/5.png", "losevideos/000871/6.png", "losevideos/000871/7.png" ]
root chakra with 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: [root chakra with movement.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005269/0.png", "losevideos/005269/1.png", "losevideos/005269/2.png", "losevideos/005269/3.png", "losevideos/005269/4.png", "losevideos/005269/5.png", "losevideos/005269/6.png", "losevideos/005269/7.png", "winvideos/005269/0.png", "winvideos/005269/1.png", "winvideos/005269/2.png", "winvideos/005269/3.png", "winvideos/005269/4.png", "winvideos/005269/5.png", "winvideos/005269/6.png", "winvideos/005269/7.png" ]
modern style living room with ceiling window.	[ { "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: [modern style living room with ceiling window.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002581/0.png", "losevideos/002581/1.png", "losevideos/002581/2.png", "losevideos/002581/3.png", "losevideos/002581/4.png", "losevideos/002581/5.png", "losevideos/002581/6.png", "losevideos/002581/7.png", "winvideos/002581/0.png", "winvideos/002581/1.png", "winvideos/002581/2.png", "winvideos/002581/3.png", "winvideos/002581/4.png", "winvideos/002581/5.png", "winvideos/002581/6.png", "winvideos/002581/7.png" ]
"Explore the fascinating world of exoplanets and their parent stars. Investigate the diverse range of star types, including G-type stars like our Sun, K dwarfs, and M dwarfs. Delve into the concept of habitable zones and how they relate to star characteristics. Examine the potential challenges and advantages for exoplanets orbiting different types of stars, considering factors such as radiation levels and star longevity. Speculate on the prospects for life evolving on exoplanets around various stars. Your task is to provide a concise, informative paragraph that encapsulates the intriguing relationship between stars and exoplanets in our galaxy.".	[ { "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: ["Explore the fascinating world of exoplanets and their parent stars. Investigate the diverse range of star types, including G-type stars like our Sun, K dwarfs, and M dwarfs. Delve into the concept of habitable zones and how they relate to star characteristics. Examine the potential challenges and advantages for exoplanets orbiting different types of stars, considering factors such as radiation levels and star longevity. Speculate on the prospects for life evolving on exoplanets around various stars. Your task is to provide a concise, informative paragraph that encapsulates the intriguing relationship between stars and exoplanets in our galaxy.".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004640/0.png", "losevideos/004640/1.png", "losevideos/004640/2.png", "losevideos/004640/3.png", "losevideos/004640/4.png", "losevideos/004640/5.png", "losevideos/004640/6.png", "losevideos/004640/7.png", "winvideos/004640/0.png", "winvideos/004640/1.png", "winvideos/004640/2.png", "winvideos/004640/3.png", "winvideos/004640/4.png", "winvideos/004640/5.png", "winvideos/004640/6.png", "winvideos/004640/7.png" ]
1961 footage, using VR, zoom out slow shot --ar 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [1961 footage, using VR, zoom out slow shot --ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009801/0.png", "winvideos/009801/1.png", "winvideos/009801/2.png", "winvideos/009801/3.png", "winvideos/009801/4.png", "winvideos/009801/5.png", "winvideos/009801/6.png", "winvideos/009801/7.png", "losevideos/009801/0.png", "losevideos/009801/1.png", "losevideos/009801/2.png", "losevideos/009801/3.png", "losevideos/009801/4.png", "losevideos/009801/5.png", "losevideos/009801/6.png", "losevideos/009801/7.png" ]
a we see a zoom in drone shot of (EffGey) meditating high above an erupting volcano,he sits in indian style wearing Black and red snake print pants.one eye is red the other eye is green, futuristic, Cyberpunk style, neon colors. Retro video effects but with great detail and realistic -neg “BLURRY, DEFORMED, MULTIPLE LIMBS, PIXELATED, STATIC, UNCLEAR, DISTORTED, ERROR, STILL, LOW RESOLUTION, OVERSATURATED, BLUR, robot transformation”.	[ { "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 we see a zoom in drone shot of (EffGey) meditating high above an erupting volcano,he sits in indian style wearing Black and red snake print pants.one eye is red the other eye is green, futuristic, Cyberpunk style, neon colors. Retro video effects but with great detail and realistic -neg “BLURRY, DEFORMED, MULTIPLE LIMBS, PIXELATED, STATIC, UNCLEAR, DISTORTED, ERROR, STILL, LOW RESOLUTION, OVERSATURATED, BLUR, robot transformation”.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004126/0.png", "winvideos/004126/1.png", "winvideos/004126/2.png", "winvideos/004126/3.png", "winvideos/004126/4.png", "winvideos/004126/5.png", "winvideos/004126/6.png", "winvideos/004126/7.png", "losevideos/004126/0.png", "losevideos/004126/1.png", "losevideos/004126/2.png", "losevideos/004126/3.png", "losevideos/004126/4.png", "losevideos/004126/5.png", "losevideos/004126/6.png", "losevideos/004126/7.png" ]
big ugly mouth smiling, old horror cinema, grainy, black and white, black contrast, bizarre, scary, creepy.	[ { "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: [big ugly mouth smiling, old horror cinema, grainy, black and white, black contrast, bizarre, scary, creepy.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000701/0.png", "winvideos/000701/1.png", "winvideos/000701/2.png", "winvideos/000701/3.png", "winvideos/000701/4.png", "winvideos/000701/5.png", "winvideos/000701/6.png", "winvideos/000701/7.png", "losevideos/000701/0.png", "losevideos/000701/1.png", "losevideos/000701/2.png", "losevideos/000701/3.png", "losevideos/000701/4.png", "losevideos/000701/5.png", "losevideos/000701/6.png", "losevideos/000701/7.png" ]
scary dog.	[ { "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: [scary dog.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006384/0.png", "losevideos/006384/1.png", "losevideos/006384/2.png", "losevideos/006384/3.png", "losevideos/006384/4.png", "losevideos/006384/5.png", "losevideos/006384/6.png", "losevideos/006384/7.png", "winvideos/006384/0.png", "winvideos/006384/1.png", "winvideos/006384/2.png", "winvideos/006384/3.png", "winvideos/006384/4.png", "winvideos/006384/5.png", "winvideos/006384/6.png", "winvideos/006384/7.png" ]
UNA MUJER CORRIENDO CON UNA CIUDAD EN LLAMAS DETRAS ESTILO FUTIRISTA COLORES ROJO Y NEGRO.	[ { "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: [UNA MUJER CORRIENDO CON UNA CIUDAD EN LLAMAS DETRAS ESTILO FUTIRISTA COLORES ROJO Y NEGRO.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008290/0.png", "losevideos/008290/1.png", "losevideos/008290/2.png", "losevideos/008290/3.png", "losevideos/008290/4.png", "losevideos/008290/5.png", "losevideos/008290/6.png", "losevideos/008290/7.png", "winvideos/008290/0.png", "winvideos/008290/1.png", "winvideos/008290/2.png", "winvideos/008290/3.png", "winvideos/008290/4.png", "winvideos/008290/5.png", "winvideos/008290/6.png", "winvideos/008290/7.png" ]
Middle-class families can make smart money moves to foster financial growthgrowth, show someone saving money.	[ { "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: [Middle-class families can make smart money moves to foster financial growthgrowth, show someone saving money.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009413/0.png", "winvideos/009413/1.png", "winvideos/009413/2.png", "winvideos/009413/3.png", "winvideos/009413/4.png", "winvideos/009413/5.png", "winvideos/009413/6.png", "winvideos/009413/7.png", "losevideos/009413/0.png", "losevideos/009413/1.png", "losevideos/009413/2.png", "losevideos/009413/3.png", "losevideos/009413/4.png", "losevideos/009413/5.png", "losevideos/009413/6.png", "losevideos/009413/7.png" ]
angry blonde teacher shouting at classroom.	[ { "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: [angry blonde teacher shouting at classroom.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003594/0.png", "losevideos/003594/1.png", "losevideos/003594/2.png", "losevideos/003594/3.png", "losevideos/003594/4.png", "losevideos/003594/5.png", "losevideos/003594/6.png", "losevideos/003594/7.png", "winvideos/003594/0.png", "winvideos/003594/1.png", "winvideos/003594/2.png", "winvideos/003594/3.png", "winvideos/003594/4.png", "winvideos/003594/5.png", "winvideos/003594/6.png", "winvideos/003594/7.png" ]
excited, bouncing, jumping up and down, conservative and modest swimsuit, a beautiful feminist punk chick with dyed hair celebrates diversity in the mall,respectful overhead view -neg boy -ar 1:1.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [excited, bouncing, jumping up and down, conservative and modest swimsuit, a beautiful feminist punk chick with dyed hair celebrates diversity in the mall,respectful overhead view -neg boy -ar 1:1.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002469/0.png", "winvideos/002469/1.png", "winvideos/002469/2.png", "winvideos/002469/3.png", "winvideos/002469/4.png", "winvideos/002469/5.png", "winvideos/002469/6.png", "winvideos/002469/7.png", "losevideos/002469/0.png", "losevideos/002469/1.png", "losevideos/002469/2.png", "losevideos/002469/3.png", "losevideos/002469/4.png", "losevideos/002469/5.png", "losevideos/002469/6.png", "losevideos/002469/7.png" ]
In 'Forest Haven,' the haunting is your own, the fear, your own creation. As you tremble, remember, the most terrifying ghost is the one within.".	[ { "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: [In 'Forest Haven,' the haunting is your own, the fear, your own creation. As you tremble, remember, the most terrifying ghost is the one within.".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004246/0.png", "losevideos/004246/1.png", "losevideos/004246/2.png", "losevideos/004246/3.png", "losevideos/004246/4.png", "losevideos/004246/5.png", "losevideos/004246/6.png", "losevideos/004246/7.png", "winvideos/004246/0.png", "winvideos/004246/1.png", "winvideos/004246/2.png", "winvideos/004246/3.png", "winvideos/004246/4.png", "winvideos/004246/5.png", "winvideos/004246/6.png", "winvideos/004246/7.png" ]
bright white light flows like threads of landscape.	[ { "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: [bright white light flows like threads of landscape.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000415/0.png", "winvideos/000415/1.png", "winvideos/000415/2.png", "winvideos/000415/3.png", "winvideos/000415/4.png", "winvideos/000415/5.png", "winvideos/000415/6.png", "winvideos/000415/7.png", "losevideos/000415/0.png", "losevideos/000415/1.png", "losevideos/000415/2.png", "losevideos/000415/3.png", "losevideos/000415/4.png", "losevideos/000415/5.png", "losevideos/000415/6.png", "losevideos/000415/7.png" ]
lighting, movement, subtle wind.	[ { "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: [lighting, movement, subtle wind.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003267/0.png", "losevideos/003267/1.png", "losevideos/003267/2.png", "losevideos/003267/3.png", "losevideos/003267/4.png", "losevideos/003267/5.png", "losevideos/003267/6.png", "losevideos/003267/7.png", "winvideos/003267/0.png", "winvideos/003267/1.png", "winvideos/003267/2.png", "winvideos/003267/3.png", "winvideos/003267/4.png", "winvideos/003267/5.png", "winvideos/003267/6.png", "winvideos/003267/7.png" ]
a girl with wind, <a href="https://cdn.discordapp.com/attachments/1123665843365093487/1129699671661613156/11001_LOOKBOOK_RINGS.png">https://cdn.discordapp.com/attachments/1123665843365093487/1129699671661613156/11001_LOOKBOOK_RINGS.png</a>.	[ { "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 wind, <a href=\"https://cdn.discordapp.com/attachments/1123665843365093487/1129699671661613156/11001_LOOKBOOK_RINGS.png\">https://cdn.discordapp.com/attachments/1123665843365093487/1129699671661613156/11001_LOOKBOOK_RINGS.png</a>.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005998/0.png", "losevideos/005998/1.png", "losevideos/005998/2.png", "losevideos/005998/3.png", "losevideos/005998/4.png", "losevideos/005998/5.png", "losevideos/005998/6.png", "losevideos/005998/7.png", "winvideos/005998/0.png", "winvideos/005998/1.png", "winvideos/005998/2.png", "winvideos/005998/3.png", "winvideos/005998/4.png", "winvideos/005998/5.png", "winvideos/005998/6.png", "winvideos/005998/7.png" ]
image of seed.	[ { "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: [image of seed.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002624/0.png", "winvideos/002624/1.png", "winvideos/002624/2.png", "winvideos/002624/3.png", "winvideos/002624/4.png", "winvideos/002624/5.png", "winvideos/002624/6.png", "winvideos/002624/7.png", "losevideos/002624/0.png", "losevideos/002624/1.png", "losevideos/002624/2.png", "losevideos/002624/3.png", "losevideos/002624/4.png", "losevideos/002624/5.png", "losevideos/002624/6.png", "losevideos/002624/7.png" ]
fierce fast action and destruction at the literal insane monster truck tires are crushing piles of dirty plaster skulls in a giant stadium full of angry screaming crowd a monter truck is crushing a plaster statue head it crumbles into rubble. -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: [fierce fast action and destruction at the literal insane monster truck tires are crushing piles of dirty plaster skulls in a giant stadium full of angry screaming crowd \na monter truck is crushing a plaster statue head it crumbles into rubble. -ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000553/0.png", "losevideos/000553/1.png", "losevideos/000553/2.png", "losevideos/000553/3.png", "losevideos/000553/4.png", "losevideos/000553/5.png", "losevideos/000553/6.png", "losevideos/000553/7.png", "winvideos/000553/0.png", "winvideos/000553/1.png", "winvideos/000553/2.png", "winvideos/000553/3.png", "winvideos/000553/4.png", "winvideos/000553/5.png", "winvideos/000553/6.png", "winvideos/000553/7.png" ]
mind of the universe, creator, human head silhouette, high energy, lighting, dark space, 8k, cinematic, -gs50 -ar16:9 -neg "planets".	[ { "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: [mind of the universe, creator, human head silhouette, high energy, lighting, dark space, 8k, cinematic, -gs50 -ar16:9 -neg "planets".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007360/0.png", "losevideos/007360/1.png", "losevideos/007360/2.png", "losevideos/007360/3.png", "losevideos/007360/4.png", "losevideos/007360/5.png", "losevideos/007360/6.png", "losevideos/007360/7.png", "winvideos/007360/0.png", "winvideos/007360/1.png", "winvideos/007360/2.png", "winvideos/007360/3.png", "winvideos/007360/4.png", "winvideos/007360/5.png", "winvideos/007360/6.png", "winvideos/007360/7.png" ]
architectural render.	[ { "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: [architectural render.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004793/0.png", "winvideos/004793/1.png", "winvideos/004793/2.png", "winvideos/004793/3.png", "winvideos/004793/4.png", "winvideos/004793/5.png", "winvideos/004793/6.png", "winvideos/004793/7.png", "losevideos/004793/0.png", "losevideos/004793/1.png", "losevideos/004793/2.png", "losevideos/004793/3.png", "losevideos/004793/4.png", "losevideos/004793/5.png", "losevideos/004793/6.png", "losevideos/004793/7.png" ]
image of lal bahadur sashtari giving speach to crowd.	[ { "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: [image of lal bahadur sashtari giving speach to crowd.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009414/0.png", "winvideos/009414/1.png", "winvideos/009414/2.png", "winvideos/009414/3.png", "winvideos/009414/4.png", "winvideos/009414/5.png", "winvideos/009414/6.png", "winvideos/009414/7.png", "losevideos/009414/0.png", "losevideos/009414/1.png", "losevideos/009414/2.png", "losevideos/009414/3.png", "losevideos/009414/4.png", "losevideos/009414/5.png", "losevideos/009414/6.png", "losevideos/009414/7.png" ]
image barbarians attack timwn.	[ { "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: [image barbarians attack timwn.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001719/0.png", "winvideos/001719/1.png", "winvideos/001719/2.png", "winvideos/001719/3.png", "winvideos/001719/4.png", "winvideos/001719/5.png", "winvideos/001719/6.png", "winvideos/001719/7.png", "losevideos/001719/0.png", "losevideos/001719/1.png", "losevideos/001719/2.png", "losevideos/001719/3.png", "losevideos/001719/4.png", "losevideos/001719/5.png", "losevideos/001719/6.png", "losevideos/001719/7.png" ]
our continent and fly through it to get closer to our training center. The landscape has mountains, rivers, lakes, and a base for training the first units. The image is in blue-green tones, with color additions. The training center looks like a complex of buildings in a futuristic 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: [our continent and fly through it to get closer to our training center. The landscape has mountains, rivers, lakes, and a base for training the first units. The image is in blue-green tones, with color additions. The training center looks like a complex of buildings in a futuristic style.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001098/0.png", "losevideos/001098/1.png", "losevideos/001098/2.png", "losevideos/001098/3.png", "losevideos/001098/4.png", "losevideos/001098/5.png", "losevideos/001098/6.png", "losevideos/001098/7.png", "winvideos/001098/0.png", "winvideos/001098/1.png", "winvideos/001098/2.png", "winvideos/001098/3.png", "winvideos/001098/4.png", "winvideos/001098/5.png", "winvideos/001098/6.png", "winvideos/001098/7.png" ]
space cyberpunk neon cityscape futuristic design.	[ { "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: [space cyberpunk neon cityscape futuristic design.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002742/0.png", "losevideos/002742/1.png", "losevideos/002742/2.png", "losevideos/002742/3.png", "losevideos/002742/4.png", "losevideos/002742/5.png", "losevideos/002742/6.png", "losevideos/002742/7.png", "winvideos/002742/0.png", "winvideos/002742/1.png", "winvideos/002742/2.png", "winvideos/002742/3.png", "winvideos/002742/4.png", "winvideos/002742/5.png", "winvideos/002742/6.png", "winvideos/002742/7.png" ]
Imran Khan won the election celebration.	[ { "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: [Imran Khan won the election celebration.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000327/0.png", "winvideos/000327/1.png", "winvideos/000327/2.png", "winvideos/000327/3.png", "winvideos/000327/4.png", "winvideos/000327/5.png", "winvideos/000327/6.png", "winvideos/000327/7.png", "losevideos/000327/0.png", "losevideos/000327/1.png", "losevideos/000327/2.png", "losevideos/000327/3.png", "losevideos/000327/4.png", "losevideos/000327/5.png", "losevideos/000327/6.png", "losevideos/000327/7.png" ]
A dolphin with human running in garden -ar 16:9 -motion 3.	[ { "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 dolphin with human running in garden -ar 16:9 -motion 3.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003170/0.png", "losevideos/003170/1.png", "losevideos/003170/2.png", "losevideos/003170/3.png", "losevideos/003170/4.png", "losevideos/003170/5.png", "losevideos/003170/6.png", "losevideos/003170/7.png", "winvideos/003170/0.png", "winvideos/003170/1.png", "winvideos/003170/2.png", "winvideos/003170/3.png", "winvideos/003170/4.png", "winvideos/003170/5.png", "winvideos/003170/6.png", "winvideos/003170/7.png" ]
a living pineapple character fights a living carrot character.	[ { "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 living pineapple character fights a living carrot character.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003074/0.png", "losevideos/003074/1.png", "losevideos/003074/2.png", "losevideos/003074/3.png", "losevideos/003074/4.png", "losevideos/003074/5.png", "losevideos/003074/6.png", "losevideos/003074/7.png", "winvideos/003074/0.png", "winvideos/003074/1.png", "winvideos/003074/2.png", "winvideos/003074/3.png", "winvideos/003074/4.png", "winvideos/003074/5.png", "winvideos/003074/6.png", "winvideos/003074/7.png" ]
a girl doing the slickback dance.	[ { "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 doing the slickback dance.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003542/0.png", "winvideos/003542/1.png", "winvideos/003542/2.png", "winvideos/003542/3.png", "winvideos/003542/4.png", "winvideos/003542/5.png", "winvideos/003542/6.png", "winvideos/003542/7.png", "losevideos/003542/0.png", "losevideos/003542/1.png", "losevideos/003542/2.png", "losevideos/003542/3.png", "losevideos/003542/4.png", "losevideos/003542/5.png", "losevideos/003542/6.png", "losevideos/003542/7.png" ]
padded cell with tvs covering the walls hd epic horror 4 k surreal enviroment timelapse cinematic more like this uneven light dungeon -ar 16:9 -motion 4.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [padded cell with tvs covering the walls hd epic horror 4 k surreal enviroment timelapse cinematic more like this uneven light dungeon -ar 16:9 -motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007171/0.png", "losevideos/007171/1.png", "losevideos/007171/2.png", "losevideos/007171/3.png", "losevideos/007171/4.png", "losevideos/007171/5.png", "losevideos/007171/6.png", "losevideos/007171/7.png", "winvideos/007171/0.png", "winvideos/007171/1.png", "winvideos/007171/2.png", "winvideos/007171/3.png", "winvideos/007171/4.png", "winvideos/007171/5.png", "winvideos/007171/6.png", "winvideos/007171/7.png" ]
roblox spiderman rides a clown buggy from one piece.	[ { "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: [roblox spiderman rides a clown buggy from one piece.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001281/0.png", "winvideos/001281/1.png", "winvideos/001281/2.png", "winvideos/001281/3.png", "winvideos/001281/4.png", "winvideos/001281/5.png", "winvideos/001281/6.png", "winvideos/001281/7.png", "losevideos/001281/0.png", "losevideos/001281/1.png", "losevideos/001281/2.png", "losevideos/001281/3.png", "losevideos/001281/4.png", "losevideos/001281/5.png", "losevideos/001281/6.png", "losevideos/001281/7.png" ]