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
Craft a high-energy video that captures Iemanjá's relentless determination in a battle against a powerful storm lord. Begin with an escalating tempest that threatens to devastate the seas and coastal areas. Showcase Iemanjá's unwavering resolve as she confronts the storm lord head-on, using her mastery over water to shield against lightning strikes and colossal waves. Employ dynamic camera angles and fast-paced editing to emphasize the intensity of their clash. Highlight Iemanjá's growth throughout the battle, culminating in a climactic moment where she harnesses the storm's energy and transforms it into a force for good, quelling the tempest and asserting her status as a true siren of strength.	[ { "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: [Craft a high-energy video that captures Iemanjá's relentless determination in a battle against a powerful storm lord. Begin with an escalating tempest that threatens to devastate the seas and coastal areas. Showcase Iemanjá's unwavering resolve as she confronts the storm lord head-on, using her mastery over water to shield against lightning strikes and colossal waves. Employ dynamic camera angles and fast-paced editing to emphasize the intensity of their clash. Highlight Iemanjá's growth throughout the battle, culminating in a climactic moment where she harnesses the storm's energy and transforms it into a force for good, quelling the tempest and asserting her status as a true siren of strength.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007047/0.png", "winvideos/007047/1.png", "winvideos/007047/2.png", "winvideos/007047/3.png", "winvideos/007047/4.png", "winvideos/007047/5.png", "winvideos/007047/6.png", "winvideos/007047/7.png", "losevideos/007047/0.png", "losevideos/007047/1.png", "losevideos/007047/2.png", "losevideos/007047/3.png", "losevideos/007047/4.png", "losevideos/007047/5.png", "losevideos/007047/6.png", "losevideos/007047/7.png" ]
give me awesome logo black background and st letter.	[ { "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: [give me awesome logo black background and st letter.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007935/0.png", "winvideos/007935/1.png", "winvideos/007935/2.png", "winvideos/007935/3.png", "winvideos/007935/4.png", "winvideos/007935/5.png", "winvideos/007935/6.png", "winvideos/007935/7.png", "losevideos/007935/0.png", "losevideos/007935/1.png", "losevideos/007935/2.png", "losevideos/007935/3.png", "losevideos/007935/4.png", "losevideos/007935/5.png", "losevideos/007935/6.png", "losevideos/007935/7.png" ]
warhammer inquisitor enters hall.	[ { "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: [warhammer inquisitor enters hall.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000621/0.png", "winvideos/000621/1.png", "winvideos/000621/2.png", "winvideos/000621/3.png", "winvideos/000621/4.png", "winvideos/000621/5.png", "winvideos/000621/6.png", "winvideos/000621/7.png", "losevideos/000621/0.png", "losevideos/000621/1.png", "losevideos/000621/2.png", "losevideos/000621/3.png", "losevideos/000621/4.png", "losevideos/000621/5.png", "losevideos/000621/6.png", "losevideos/000621/7.png" ]
Elaborately costumed performers engage in a courtly dance amidst the canals and architecture of Venice during carnival.	[ { "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: [Elaborately costumed performers engage in a courtly dance amidst the canals and architecture of Venice during carnival.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002972/0.png", "winvideos/002972/1.png", "winvideos/002972/2.png", "winvideos/002972/3.png", "winvideos/002972/4.png", "winvideos/002972/5.png", "winvideos/002972/6.png", "winvideos/002972/7.png", "losevideos/002972/0.png", "losevideos/002972/1.png", "losevideos/002972/2.png", "losevideos/002972/3.png", "losevideos/002972/4.png", "losevideos/002972/5.png", "losevideos/002972/6.png", "losevideos/002972/7.png" ]
a gril in parchuite her hair blwing by air she is smiling.	[ { "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 gril in parchuite her hair blwing by air she is smiling.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000670/0.png", "winvideos/000670/1.png", "winvideos/000670/2.png", "winvideos/000670/3.png", "winvideos/000670/4.png", "winvideos/000670/5.png", "winvideos/000670/6.png", "winvideos/000670/7.png", "losevideos/000670/0.png", "losevideos/000670/1.png", "losevideos/000670/2.png", "losevideos/000670/3.png", "losevideos/000670/4.png", "losevideos/000670/5.png", "losevideos/000670/6.png", "losevideos/000670/7.png" ]
an expansive view, ancient Chinese building are lined up on both sides of the wide street. There are white fireworks in the sky, and there are falling fireworks like falling stars, huge moon in the night sky,Trending on artstation, mysterious assassins, with a realistic fantasy art style, neogeo, rich and detailed genre paintings, dark gold and black,chinese punk, graphic design,original art, game, detailed character illustrations, super detail, cinematic lighting, volumetric lighting --ar 20:9 --q 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: [an expansive view, ancient Chinese building are lined up on both sides of the wide street. There are white fireworks in the sky, and there are falling fireworks like falling stars, huge moon in the night sky,Trending on artstation, mysterious assassins, with a realistic fantasy art style, neogeo, rich and detailed genre paintings, dark gold and black,chinese punk, graphic design,original art, game, detailed character illustrations, super detail, cinematic lighting, volumetric lighting --ar 20:9 --q 2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006938/0.png", "winvideos/006938/1.png", "winvideos/006938/2.png", "winvideos/006938/3.png", "winvideos/006938/4.png", "winvideos/006938/5.png", "winvideos/006938/6.png", "winvideos/006938/7.png", "losevideos/006938/0.png", "losevideos/006938/1.png", "losevideos/006938/2.png", "losevideos/006938/3.png", "losevideos/006938/4.png", "losevideos/006938/5.png", "losevideos/006938/6.png", "losevideos/006938/7.png" ]
a group of sci-fi troopers dressed in black run toward the camera in a cyberpunk street at night silhouetted against neon lights, backlit, smoke.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a group of sci-fi troopers dressed in black run toward the camera in a cyberpunk street at night silhouetted against neon lights, backlit, smoke.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008096/0.png", "winvideos/008096/1.png", "winvideos/008096/2.png", "winvideos/008096/3.png", "winvideos/008096/4.png", "winvideos/008096/5.png", "winvideos/008096/6.png", "winvideos/008096/7.png", "losevideos/008096/0.png", "losevideos/008096/1.png", "losevideos/008096/2.png", "losevideos/008096/3.png", "losevideos/008096/4.png", "losevideos/008096/5.png", "losevideos/008096/6.png", "losevideos/008096/7.png" ]
woman with wavy red hair and a scar on her left shoulder looking her reflect in a mirror.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [woman with wavy red hair and a scar on her left shoulder looking her reflect in a mirror.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000652/0.png", "losevideos/000652/1.png", "losevideos/000652/2.png", "losevideos/000652/3.png", "losevideos/000652/4.png", "losevideos/000652/5.png", "losevideos/000652/6.png", "losevideos/000652/7.png", "winvideos/000652/0.png", "winvideos/000652/1.png", "winvideos/000652/2.png", "winvideos/000652/3.png", "winvideos/000652/4.png", "winvideos/000652/5.png", "winvideos/000652/6.png", "winvideos/000652/7.png" ]
shortview entity wrapped in flame floating in darkness.	[ { "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: [shortview entity wrapped in flame floating in darkness.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009653/0.png", "losevideos/009653/1.png", "losevideos/009653/2.png", "losevideos/009653/3.png", "losevideos/009653/4.png", "losevideos/009653/5.png", "losevideos/009653/6.png", "losevideos/009653/7.png", "winvideos/009653/0.png", "winvideos/009653/1.png", "winvideos/009653/2.png", "winvideos/009653/3.png", "winvideos/009653/4.png", "winvideos/009653/5.png", "winvideos/009653/6.png", "winvideos/009653/7.png" ]
indian castle lit up in heaven with heavy lighting for wedding.	[ { "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: [indian castle lit up in heaven with heavy lighting for wedding.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006111/0.png", "winvideos/006111/1.png", "winvideos/006111/2.png", "winvideos/006111/3.png", "winvideos/006111/4.png", "winvideos/006111/5.png", "winvideos/006111/6.png", "winvideos/006111/7.png", "losevideos/006111/0.png", "losevideos/006111/1.png", "losevideos/006111/2.png", "losevideos/006111/3.png", "losevideos/006111/4.png", "losevideos/006111/5.png", "losevideos/006111/6.png", "losevideos/006111/7.png" ]
sopor aeternus, black and white fine art film, cinematic.	[ { "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: [sopor aeternus, black and white fine art film, cinematic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005600/0.png", "losevideos/005600/1.png", "losevideos/005600/2.png", "losevideos/005600/3.png", "losevideos/005600/4.png", "losevideos/005600/5.png", "losevideos/005600/6.png", "losevideos/005600/7.png", "winvideos/005600/0.png", "winvideos/005600/1.png", "winvideos/005600/2.png", "winvideos/005600/3.png", "winvideos/005600/4.png", "winvideos/005600/5.png", "winvideos/005600/6.png", "winvideos/005600/7.png" ]
uchiha madara that is Tired.	[ { "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: [uchiha madara that is Tired.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001665/0.png", "winvideos/001665/1.png", "winvideos/001665/2.png", "winvideos/001665/3.png", "winvideos/001665/4.png", "winvideos/001665/5.png", "winvideos/001665/6.png", "winvideos/001665/7.png", "losevideos/001665/0.png", "losevideos/001665/1.png", "losevideos/001665/2.png", "losevideos/001665/3.png", "losevideos/001665/4.png", "losevideos/001665/5.png", "losevideos/001665/6.png", "losevideos/001665/7.png" ]
future security, earth, war.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [future security, earth, war.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001122/0.png", "losevideos/001122/1.png", "losevideos/001122/2.png", "losevideos/001122/3.png", "losevideos/001122/4.png", "losevideos/001122/5.png", "losevideos/001122/6.png", "losevideos/001122/7.png", "winvideos/001122/0.png", "winvideos/001122/1.png", "winvideos/001122/2.png", "winvideos/001122/3.png", "winvideos/001122/4.png", "winvideos/001122/5.png", "winvideos/001122/6.png", "winvideos/001122/7.png" ]
obama hungry, sandwich, mustard -motion 2 -gs 20.	[ { "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: [obama hungry, sandwich, mustard -motion 2 -gs 20.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002719/0.png", "winvideos/002719/1.png", "winvideos/002719/2.png", "winvideos/002719/3.png", "winvideos/002719/4.png", "winvideos/002719/5.png", "winvideos/002719/6.png", "winvideos/002719/7.png", "losevideos/002719/0.png", "losevideos/002719/1.png", "losevideos/002719/2.png", "losevideos/002719/3.png", "losevideos/002719/4.png", "losevideos/002719/5.png", "losevideos/002719/6.png", "losevideos/002719/7.png" ]
Showcase alien leaders and their advanced weaponry.	[ { "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: [Showcase alien leaders and their advanced weaponry.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003546/0.png", "winvideos/003546/1.png", "winvideos/003546/2.png", "winvideos/003546/3.png", "winvideos/003546/4.png", "winvideos/003546/5.png", "winvideos/003546/6.png", "winvideos/003546/7.png", "losevideos/003546/0.png", "losevideos/003546/1.png", "losevideos/003546/2.png", "losevideos/003546/3.png", "losevideos/003546/4.png", "losevideos/003546/5.png", "losevideos/003546/6.png", "losevideos/003546/7.png" ]
A collage of night scenes in the village, showcasing different chilling events – icy whispers,.	[ { "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 collage of night scenes in the village, showcasing different chilling events – icy whispers,.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002962/0.png", "losevideos/002962/1.png", "losevideos/002962/2.png", "losevideos/002962/3.png", "losevideos/002962/4.png", "losevideos/002962/5.png", "losevideos/002962/6.png", "losevideos/002962/7.png", "winvideos/002962/0.png", "winvideos/002962/1.png", "winvideos/002962/2.png", "winvideos/002962/3.png", "winvideos/002962/4.png", "winvideos/002962/5.png", "winvideos/002962/6.png", "winvideos/002962/7.png" ]
prompt:a white yacht traveling on a river and passing under the bridge -seed 1128359.	[ { "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:a white yacht traveling on a river and passing under the bridge -seed 1128359.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000154/0.png", "winvideos/000154/1.png", "winvideos/000154/2.png", "winvideos/000154/3.png", "winvideos/000154/4.png", "winvideos/000154/5.png", "winvideos/000154/6.png", "winvideos/000154/7.png", "losevideos/000154/0.png", "losevideos/000154/1.png", "losevideos/000154/2.png", "losevideos/000154/3.png", "losevideos/000154/4.png", "losevideos/000154/5.png", "losevideos/000154/6.png", "losevideos/000154/7.png" ]
back scene, a old man, far away in a deep dark forest at night, walk confused.	[ { "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: [back scene, a old man, far away in a deep dark forest at night, walk confused.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001847/0.png", "losevideos/001847/1.png", "losevideos/001847/2.png", "losevideos/001847/3.png", "losevideos/001847/4.png", "losevideos/001847/5.png", "losevideos/001847/6.png", "losevideos/001847/7.png", "winvideos/001847/0.png", "winvideos/001847/1.png", "winvideos/001847/2.png", "winvideos/001847/3.png", "winvideos/001847/4.png", "winvideos/001847/5.png", "winvideos/001847/6.png", "winvideos/001847/7.png" ]
agujero de gusano en el espacio.	[ { "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: [agujero de gusano en el espacio.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001689/0.png", "winvideos/001689/1.png", "winvideos/001689/2.png", "winvideos/001689/3.png", "winvideos/001689/4.png", "winvideos/001689/5.png", "winvideos/001689/6.png", "winvideos/001689/7.png", "losevideos/001689/0.png", "losevideos/001689/1.png", "losevideos/001689/2.png", "losevideos/001689/3.png", "losevideos/001689/4.png", "losevideos/001689/5.png", "losevideos/001689/6.png", "losevideos/001689/7.png" ]
slow motion of the silluette of a man with hat and cape, prancing a horse, sunset background, slightly cloud movement, cape blowing -camera zoom out -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainly, low resolution, oversaturated, lack of detail, inconscistent lightning.	[ { "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: [slow motion of the silluette of a man with hat and cape, prancing a horse, sunset background, slightly cloud movement, cape blowing -camera zoom out -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainly, low resolution, oversaturated, lack of detail, inconscistent lightning.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006420/0.png", "losevideos/006420/1.png", "losevideos/006420/2.png", "losevideos/006420/3.png", "losevideos/006420/4.png", "losevideos/006420/5.png", "losevideos/006420/6.png", "losevideos/006420/7.png", "winvideos/006420/0.png", "winvideos/006420/1.png", "winvideos/006420/2.png", "winvideos/006420/3.png", "winvideos/006420/4.png", "winvideos/006420/5.png", "winvideos/006420/6.png", "winvideos/006420/7.png" ]
Photograph of buckingham palace guard, cinematic focus, love, twiggy, london -w 2.0 -camera zoom out -fps 24 -ar:16:10 -motion 2 -gs 20 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: [Photograph of buckingham palace guard, cinematic focus, love, twiggy, london -w 2.0 -camera zoom out -fps 24 -ar:16:10 -motion 2 -gs 20 Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009770/0.png", "winvideos/009770/1.png", "winvideos/009770/2.png", "winvideos/009770/3.png", "winvideos/009770/4.png", "winvideos/009770/5.png", "winvideos/009770/6.png", "winvideos/009770/7.png", "losevideos/009770/0.png", "losevideos/009770/1.png", "losevideos/009770/2.png", "losevideos/009770/3.png", "losevideos/009770/4.png", "losevideos/009770/5.png", "losevideos/009770/6.png", "losevideos/009770/7.png" ]
a storm and waves into the ocean 4K quality, -ar 9:16 -motion 4 -camera zoom out -gs 10 -fps 24 -neg Disfigured, Ugly, Oversaturated, Low-res, Deformed, Blurry, text, watermarks, Bad anatomy, Poorly drawn face, mutated, Ugly, Poorly drawn hands, Extra fingers, Malformed hands, Blur, Out of focus, Long neck, Disgusting, Surreal, -neg mutated hands and fingers, deformed, bad anatomy, disfigured, poorly drawn face, lowres ,mutated, extra limb, ugly, extra fingers, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, blurred, long neck, long body, gape 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: [a storm and waves into the ocean 4K quality, -ar 9:16 -motion 4 -camera zoom out -gs 10 -fps 24 -neg Disfigured, Ugly, Oversaturated, Low-res, Deformed, Blurry, text, watermarks, Bad anatomy, Poorly drawn face, mutated, Ugly, Poorly drawn hands, Extra fingers, Malformed hands, Blur, Out of focus, Long neck, Disgusting, Surreal, -neg mutated hands and fingers, deformed, bad anatomy, disfigured, poorly drawn face, lowres ,mutated, extra limb, ugly, extra fingers, poorly drawn hands, missing limb, floating limbs, disconnected limbs, malformed hands, out of focus, blurred, long neck, long body, gape Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003532/0.png", "winvideos/003532/1.png", "winvideos/003532/2.png", "winvideos/003532/3.png", "winvideos/003532/4.png", "winvideos/003532/5.png", "winvideos/003532/6.png", "winvideos/003532/7.png", "losevideos/003532/0.png", "losevideos/003532/1.png", "losevideos/003532/2.png", "losevideos/003532/3.png", "losevideos/003532/4.png", "losevideos/003532/5.png", "losevideos/003532/6.png", "losevideos/003532/7.png" ]
A crown in the centre of the frame with floating scrunchies all around it.	[ { "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 crown in the centre of the frame with floating scrunchies all around it.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005628/0.png", "losevideos/005628/1.png", "losevideos/005628/2.png", "losevideos/005628/3.png", "losevideos/005628/4.png", "losevideos/005628/5.png", "losevideos/005628/6.png", "losevideos/005628/7.png", "winvideos/005628/0.png", "winvideos/005628/1.png", "winvideos/005628/2.png", "winvideos/005628/3.png", "winvideos/005628/4.png", "winvideos/005628/5.png", "winvideos/005628/6.png", "winvideos/005628/7.png" ]
1920s scifi movie, retrofuturism, realistic, extreme close up of santa claus waving, muted colors, god rays, dreamcore, dreamscape, lucid dream, astral projection, psychedelic, trippy, abstract, liminal space, found footage, metropolis -motion 4 -ar16:9 -zoom in.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [1920s scifi movie, retrofuturism, realistic, extreme close up of santa claus waving, muted colors, god rays, dreamcore, dreamscape, lucid dream, astral projection, psychedelic, trippy, abstract, liminal space, found footage, metropolis -motion 4 -ar16:9 -zoom in.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000992/0.png", "winvideos/000992/1.png", "winvideos/000992/2.png", "winvideos/000992/3.png", "winvideos/000992/4.png", "winvideos/000992/5.png", "winvideos/000992/6.png", "winvideos/000992/7.png", "losevideos/000992/0.png", "losevideos/000992/1.png", "losevideos/000992/2.png", "losevideos/000992/3.png", "losevideos/000992/4.png", "losevideos/000992/5.png", "losevideos/000992/6.png", "losevideos/000992/7.png" ]
a beautifull and naughty raccoon walking on the edge of a cliff in the desert, also make the sky in a dramatic pink orange colors and have the camera angle to be low-angle view with dolly in movement, hyper realistic.	[ { "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 beautifull and naughty raccoon walking on the edge of a cliff in the desert, also make the sky in a dramatic pink orange colors and have the camera angle to be low-angle view with dolly in movement, hyper realistic.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009450/0.png", "winvideos/009450/1.png", "winvideos/009450/2.png", "winvideos/009450/3.png", "winvideos/009450/4.png", "winvideos/009450/5.png", "winvideos/009450/6.png", "winvideos/009450/7.png", "losevideos/009450/0.png", "losevideos/009450/1.png", "losevideos/009450/2.png", "losevideos/009450/3.png", "losevideos/009450/4.png", "losevideos/009450/5.png", "losevideos/009450/6.png", "losevideos/009450/7.png" ]
Whispers of the Past: AI-Generated Video Unveils the Spooky Aesthetics and Enigmatic Beauty of a Deserted Psychiatric Ward.	[ { "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: [Whispers of the Past: AI-Generated Video Unveils the Spooky Aesthetics and Enigmatic Beauty of a Deserted Psychiatric Ward.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000106/0.png", "losevideos/000106/1.png", "losevideos/000106/2.png", "losevideos/000106/3.png", "losevideos/000106/4.png", "losevideos/000106/5.png", "losevideos/000106/6.png", "losevideos/000106/7.png", "winvideos/000106/0.png", "winvideos/000106/1.png", "winvideos/000106/2.png", "winvideos/000106/3.png", "winvideos/000106/4.png", "winvideos/000106/5.png", "winvideos/000106/6.png", "winvideos/000106/7.png" ]
An electrician walks near an old mansion during a heavy storm at night.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [An electrician walks near an old mansion during a heavy storm at night.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004606/0.png", "winvideos/004606/1.png", "winvideos/004606/2.png", "winvideos/004606/3.png", "winvideos/004606/4.png", "winvideos/004606/5.png", "winvideos/004606/6.png", "winvideos/004606/7.png", "losevideos/004606/0.png", "losevideos/004606/1.png", "losevideos/004606/2.png", "losevideos/004606/3.png", "losevideos/004606/4.png", "losevideos/004606/5.png", "losevideos/004606/6.png", "losevideos/004606/7.png" ]
a young women praying silently.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a young women praying silently.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002489/0.png", "losevideos/002489/1.png", "losevideos/002489/2.png", "losevideos/002489/3.png", "losevideos/002489/4.png", "losevideos/002489/5.png", "losevideos/002489/6.png", "losevideos/002489/7.png", "winvideos/002489/0.png", "winvideos/002489/1.png", "winvideos/002489/2.png", "winvideos/002489/3.png", "winvideos/002489/4.png", "winvideos/002489/5.png", "winvideos/002489/6.png", "winvideos/002489/7.png" ]
David and Emily enjoy a romantic date, holding hands, stealing glances, and sharing intimate moments.	[ { "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: [David and Emily enjoy a romantic date, holding hands, stealing glances, and sharing intimate moments.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006847/0.png", "losevideos/006847/1.png", "losevideos/006847/2.png", "losevideos/006847/3.png", "losevideos/006847/4.png", "losevideos/006847/5.png", "losevideos/006847/6.png", "losevideos/006847/7.png", "winvideos/006847/0.png", "winvideos/006847/1.png", "winvideos/006847/2.png", "winvideos/006847/3.png", "winvideos/006847/4.png", "winvideos/006847/5.png", "winvideos/006847/6.png", "winvideos/006847/7.png" ]
shacking stressed guy, angry boy, anime, cartoon, comix, black and white --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: [shacking stressed guy, angry boy, anime, cartoon, comix, black and white --ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003878/0.png", "winvideos/003878/1.png", "winvideos/003878/2.png", "winvideos/003878/3.png", "winvideos/003878/4.png", "winvideos/003878/5.png", "winvideos/003878/6.png", "winvideos/003878/7.png", "losevideos/003878/0.png", "losevideos/003878/1.png", "losevideos/003878/2.png", "losevideos/003878/3.png", "losevideos/003878/4.png", "losevideos/003878/5.png", "losevideos/003878/6.png", "losevideos/003878/7.png" ]
two Wolfman boxing.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [two Wolfman boxing.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008052/0.png", "losevideos/008052/1.png", "losevideos/008052/2.png", "losevideos/008052/3.png", "losevideos/008052/4.png", "losevideos/008052/5.png", "losevideos/008052/6.png", "losevideos/008052/7.png", "winvideos/008052/0.png", "winvideos/008052/1.png", "winvideos/008052/2.png", "winvideos/008052/3.png", "winvideos/008052/4.png", "winvideos/008052/5.png", "winvideos/008052/6.png", "winvideos/008052/7.png" ]
Nighttime tranquility.	[ { "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: [Nighttime tranquility.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008420/0.png", "losevideos/008420/1.png", "losevideos/008420/2.png", "losevideos/008420/3.png", "losevideos/008420/4.png", "losevideos/008420/5.png", "losevideos/008420/6.png", "losevideos/008420/7.png", "winvideos/008420/0.png", "winvideos/008420/1.png", "winvideos/008420/2.png", "winvideos/008420/3.png", "winvideos/008420/4.png", "winvideos/008420/5.png", "winvideos/008420/6.png", "winvideos/008420/7.png" ]
A sunny afternoon on a mountain with a lot of vegetation 3d.	[ { "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 sunny afternoon on a mountain with a lot of vegetation 3d.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008402/0.png", "losevideos/008402/1.png", "losevideos/008402/2.png", "losevideos/008402/3.png", "losevideos/008402/4.png", "losevideos/008402/5.png", "losevideos/008402/6.png", "losevideos/008402/7.png", "winvideos/008402/0.png", "winvideos/008402/1.png", "winvideos/008402/2.png", "winvideos/008402/3.png", "winvideos/008402/4.png", "winvideos/008402/5.png", "winvideos/008402/6.png", "winvideos/008402/7.png" ]
Abstract stick figures. In Helen Frankenthaler's style. Unleash the power within you. 2D animation. HD. 16k. Pixelated. -gs 16 -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: [Abstract stick figures. In Helen Frankenthaler's style. Unleash the power within you. 2D animation. HD. 16k. Pixelated. -gs 16 -ar 16:9 -motion 3.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008597/0.png", "winvideos/008597/1.png", "winvideos/008597/2.png", "winvideos/008597/3.png", "winvideos/008597/4.png", "winvideos/008597/5.png", "winvideos/008597/6.png", "winvideos/008597/7.png", "losevideos/008597/0.png", "losevideos/008597/1.png", "losevideos/008597/2.png", "losevideos/008597/3.png", "losevideos/008597/4.png", "losevideos/008597/5.png", "losevideos/008597/6.png", "losevideos/008597/7.png" ]
Craft a fashion photo that resonates with the style of the 1990s, set amidst a mesmerizing sunken shipwreck, portrayed from an underwater perspective. The image's central feature should be a model's swimsuit, adorned with floral patterns, a high-cut leg, and a halter neck, reminiscent of Calvin Klein designs. The color scheme should immerse viewers in ocean blues paired with coral hues. The mood should blend mysticism with tranquility, illuminated by sun-dappled rays, and instilled with a touch of nostalgia.	[ { "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: [Craft a fashion photo that resonates with the style of the 1990s, set amidst a mesmerizing sunken shipwreck, portrayed from an underwater perspective. The image's central feature should be a model's swimsuit, adorned with floral patterns, a high-cut leg, and a halter neck, reminiscent of Calvin Klein designs. The color scheme should immerse viewers in ocean blues paired with coral hues. The mood should blend mysticism with tranquility, illuminated by sun-dappled rays, and instilled with a touch of nostalgia.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007532/0.png", "losevideos/007532/1.png", "losevideos/007532/2.png", "losevideos/007532/3.png", "losevideos/007532/4.png", "losevideos/007532/5.png", "losevideos/007532/6.png", "losevideos/007532/7.png", "winvideos/007532/0.png", "winvideos/007532/1.png", "winvideos/007532/2.png", "winvideos/007532/3.png", "winvideos/007532/4.png", "winvideos/007532/5.png", "winvideos/007532/6.png", "winvideos/007532/7.png" ]
low shot, fish-headed alien standing on the street, photorealistic -neg "deform, distort, beam of light, strange movements, bug, very fast, several fish, other fish, strange body, human face" -motion 1 - gs 12 -fps 24 -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: [low shot, fish-headed alien standing on the street, photorealistic -neg "deform, distort, beam of light, strange movements, bug, very fast, several fish, other fish, strange body, human face" -motion 1 - gs 12 -fps 24 -hide.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007751/0.png", "winvideos/007751/1.png", "winvideos/007751/2.png", "winvideos/007751/3.png", "winvideos/007751/4.png", "winvideos/007751/5.png", "winvideos/007751/6.png", "winvideos/007751/7.png", "losevideos/007751/0.png", "losevideos/007751/1.png", "losevideos/007751/2.png", "losevideos/007751/3.png", "losevideos/007751/4.png", "losevideos/007751/5.png", "losevideos/007751/6.png", "losevideos/007751/7.png" ]
a rabbit walking on a path in a jungle.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a rabbit walking on a path in a jungle.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006173/0.png", "losevideos/006173/1.png", "losevideos/006173/2.png", "losevideos/006173/3.png", "losevideos/006173/4.png", "losevideos/006173/5.png", "losevideos/006173/6.png", "losevideos/006173/7.png", "winvideos/006173/0.png", "winvideos/006173/1.png", "winvideos/006173/2.png", "winvideos/006173/3.png", "winvideos/006173/4.png", "winvideos/006173/5.png", "winvideos/006173/6.png", "winvideos/006173/7.png" ]
black and white lovecraft monsters, church --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: [black and white lovecraft monsters, church --ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004503/0.png", "losevideos/004503/1.png", "losevideos/004503/2.png", "losevideos/004503/3.png", "losevideos/004503/4.png", "losevideos/004503/5.png", "losevideos/004503/6.png", "losevideos/004503/7.png", "winvideos/004503/0.png", "winvideos/004503/1.png", "winvideos/004503/2.png", "winvideos/004503/3.png", "winvideos/004503/4.png", "winvideos/004503/5.png", "winvideos/004503/6.png", "winvideos/004503/7.png" ]
mujer abriendo la puerta de la casa, dark light, cartoon, 2K -seed 7301154468028471803 -ar 16:9 -gs 12 -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: [mujer abriendo la puerta de la casa, dark light, cartoon, 2K -seed 7301154468028471803 -ar 16:9 -gs 12 -motion 4.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006680/0.png", "winvideos/006680/1.png", "winvideos/006680/2.png", "winvideos/006680/3.png", "winvideos/006680/4.png", "winvideos/006680/5.png", "winvideos/006680/6.png", "winvideos/006680/7.png", "losevideos/006680/0.png", "losevideos/006680/1.png", "losevideos/006680/2.png", "losevideos/006680/3.png", "losevideos/006680/4.png", "losevideos/006680/5.png", "losevideos/006680/6.png", "losevideos/006680/7.png" ]
Highlight the dramatic encounter with a larger-than-life enemy, focusing on the stark contrast in size and the menacing aura of the dark blade. The scene merges the detailed character designs and epic confrontations typical of manga with the thematic depth and visual storytelling of Studio Ghibli.	[ { "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: [Highlight the dramatic encounter with a larger-than-life enemy, focusing on the stark contrast in size and the menacing aura of the dark blade. The scene merges the detailed character designs and epic confrontations typical of manga with the thematic depth and visual storytelling of Studio Ghibli.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003658/0.png", "winvideos/003658/1.png", "winvideos/003658/2.png", "winvideos/003658/3.png", "winvideos/003658/4.png", "winvideos/003658/5.png", "winvideos/003658/6.png", "winvideos/003658/7.png", "losevideos/003658/0.png", "losevideos/003658/1.png", "losevideos/003658/2.png", "losevideos/003658/3.png", "losevideos/003658/4.png", "losevideos/003658/5.png", "losevideos/003658/6.png", "losevideos/003658/7.png" ]