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
testtube bubbling.	[ { "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: [testtube bubbling.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007731/0.png", "losevideos/007731/1.png", "losevideos/007731/2.png", "losevideos/007731/3.png", "losevideos/007731/4.png", "losevideos/007731/5.png", "losevideos/007731/6.png", "losevideos/007731/7.png", "winvideos/007731/0.png", "winvideos/007731/1.png", "winvideos/007731/2.png", "winvideos/007731/3.png", "winvideos/007731/4.png", "winvideos/007731/5.png", "winvideos/007731/6.png", "winvideos/007731/7.png" ]
abstract cloth animation toon shade outlines.	[ { "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 cloth animation toon shade outlines.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003235/0.png", "losevideos/003235/1.png", "losevideos/003235/2.png", "losevideos/003235/3.png", "losevideos/003235/4.png", "losevideos/003235/5.png", "losevideos/003235/6.png", "losevideos/003235/7.png", "winvideos/003235/0.png", "winvideos/003235/1.png", "winvideos/003235/2.png", "winvideos/003235/3.png", "winvideos/003235/4.png", "winvideos/003235/5.png", "winvideos/003235/6.png", "winvideos/003235/7.png" ]
a lonely white billboard in a field of grass, blue sky, white clouds swiftly moving.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a lonely white billboard in a field of grass, blue sky, white clouds swiftly moving.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003936/0.png", "winvideos/003936/1.png", "winvideos/003936/2.png", "winvideos/003936/3.png", "winvideos/003936/4.png", "winvideos/003936/5.png", "winvideos/003936/6.png", "winvideos/003936/7.png", "losevideos/003936/0.png", "losevideos/003936/1.png", "losevideos/003936/2.png", "losevideos/003936/3.png", "losevideos/003936/4.png", "losevideos/003936/5.png", "losevideos/003936/6.png", "losevideos/003936/7.png" ]
silver metallic robots at walmart, night -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: [silver metallic robots at walmart, night -ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000029/0.png", "losevideos/000029/1.png", "losevideos/000029/2.png", "losevideos/000029/3.png", "losevideos/000029/4.png", "losevideos/000029/5.png", "losevideos/000029/6.png", "losevideos/000029/7.png", "winvideos/000029/0.png", "winvideos/000029/1.png", "winvideos/000029/2.png", "winvideos/000029/3.png", "winvideos/000029/4.png", "winvideos/000029/5.png", "winvideos/000029/6.png", "winvideos/000029/7.png" ]
alien smoking wee.	[ { "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: [alien smoking wee.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004554/0.png", "winvideos/004554/1.png", "winvideos/004554/2.png", "winvideos/004554/3.png", "winvideos/004554/4.png", "winvideos/004554/5.png", "winvideos/004554/6.png", "winvideos/004554/7.png", "losevideos/004554/0.png", "losevideos/004554/1.png", "losevideos/004554/2.png", "losevideos/004554/3.png", "losevideos/004554/4.png", "losevideos/004554/5.png", "losevideos/004554/6.png", "losevideos/004554/7.png" ]
a huge moon in the night while the clouds pass, fast timelapse, Dolly Shot 4K.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a huge moon in the night while the clouds pass, fast timelapse, Dolly Shot 4K.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003962/0.png", "losevideos/003962/1.png", "losevideos/003962/2.png", "losevideos/003962/3.png", "losevideos/003962/4.png", "losevideos/003962/5.png", "losevideos/003962/6.png", "losevideos/003962/7.png", "winvideos/003962/0.png", "winvideos/003962/1.png", "winvideos/003962/2.png", "winvideos/003962/3.png", "winvideos/003962/4.png", "winvideos/003962/5.png", "winvideos/003962/6.png", "winvideos/003962/7.png" ]
Japanese King wearing Japanese clothes living in Japan,8k -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: [Japanese King wearing Japanese clothes living in Japan,8k -ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002137/0.png", "losevideos/002137/1.png", "losevideos/002137/2.png", "losevideos/002137/3.png", "losevideos/002137/4.png", "losevideos/002137/5.png", "losevideos/002137/6.png", "losevideos/002137/7.png", "winvideos/002137/0.png", "winvideos/002137/1.png", "winvideos/002137/2.png", "winvideos/002137/3.png", "winvideos/002137/4.png", "winvideos/002137/5.png", "winvideos/002137/6.png", "winvideos/002137/7.png" ]
a class room full of squabbeling children -ar 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a class room full of squabbeling children -ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004117/0.png", "winvideos/004117/1.png", "winvideos/004117/2.png", "winvideos/004117/3.png", "winvideos/004117/4.png", "winvideos/004117/5.png", "winvideos/004117/6.png", "winvideos/004117/7.png", "losevideos/004117/0.png", "losevideos/004117/1.png", "losevideos/004117/2.png", "losevideos/004117/3.png", "losevideos/004117/4.png", "losevideos/004117/5.png", "losevideos/004117/6.png", "losevideos/004117/7.png" ]
An Asian beauty with long black wavy hair and modesty.	[ { "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 Asian beauty with long black wavy hair and modesty.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009211/0.png", "losevideos/009211/1.png", "losevideos/009211/2.png", "losevideos/009211/3.png", "losevideos/009211/4.png", "losevideos/009211/5.png", "losevideos/009211/6.png", "losevideos/009211/7.png", "winvideos/009211/0.png", "winvideos/009211/1.png", "winvideos/009211/2.png", "winvideos/009211/3.png", "winvideos/009211/4.png", "winvideos/009211/5.png", "winvideos/009211/6.png", "winvideos/009211/7.png" ]
The Roman emperor is walking down the street.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The Roman emperor is walking down the street.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006814/0.png", "winvideos/006814/1.png", "winvideos/006814/2.png", "winvideos/006814/3.png", "winvideos/006814/4.png", "winvideos/006814/5.png", "winvideos/006814/6.png", "winvideos/006814/7.png", "losevideos/006814/0.png", "losevideos/006814/1.png", "losevideos/006814/2.png", "losevideos/006814/3.png", "losevideos/006814/4.png", "losevideos/006814/5.png", "losevideos/006814/6.png", "losevideos/006814/7.png" ]
Hayao Miyazaki's Ocean 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: [Hayao Miyazaki's Ocean Style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007443/0.png", "winvideos/007443/1.png", "winvideos/007443/2.png", "winvideos/007443/3.png", "winvideos/007443/4.png", "winvideos/007443/5.png", "winvideos/007443/6.png", "winvideos/007443/7.png", "losevideos/007443/0.png", "losevideos/007443/1.png", "losevideos/007443/2.png", "losevideos/007443/3.png", "losevideos/007443/4.png", "losevideos/007443/5.png", "losevideos/007443/6.png", "losevideos/007443/7.png" ]
human girl talk to cute dragon, pixar, disney.	[ { "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: [human girl talk to cute dragon, pixar, disney.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002703/0.png", "losevideos/002703/1.png", "losevideos/002703/2.png", "losevideos/002703/3.png", "losevideos/002703/4.png", "losevideos/002703/5.png", "losevideos/002703/6.png", "losevideos/002703/7.png", "winvideos/002703/0.png", "winvideos/002703/1.png", "winvideos/002703/2.png", "winvideos/002703/3.png", "winvideos/002703/4.png", "winvideos/002703/5.png", "winvideos/002703/6.png", "winvideos/002703/7.png" ]
extreme close-up of a lion that jumps on us frighteningly opening its mouth to tear us apart, cinematic 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: [extreme close-up of a lion that jumps on us frighteningly opening its mouth to tear us apart, cinematic style.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006711/0.png", "losevideos/006711/1.png", "losevideos/006711/2.png", "losevideos/006711/3.png", "losevideos/006711/4.png", "losevideos/006711/5.png", "losevideos/006711/6.png", "losevideos/006711/7.png", "winvideos/006711/0.png", "winvideos/006711/1.png", "winvideos/006711/2.png", "winvideos/006711/3.png", "winvideos/006711/4.png", "winvideos/006711/5.png", "winvideos/006711/6.png", "winvideos/006711/7.png" ]
The VR headset is taken off. Alex looks at his reflection in the dark blank screen -cinematic -gs15 -motion 4 -fps24 -camera pan up -ar 16:9 -style raw -neg, easynegative, FastNegativeV2, morphing, bad anatomy, extra people, (deformed iris, deformed pupils, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting,.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The VR headset is taken off. Alex looks at his reflection in the dark blank screen -cinematic -gs15 -motion 4 -fps24 -camera pan up -ar 16:9 -style raw -neg, easynegative, FastNegativeV2, morphing, bad anatomy, extra people, (deformed iris, deformed pupils, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting,.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004795/0.png", "losevideos/004795/1.png", "losevideos/004795/2.png", "losevideos/004795/3.png", "losevideos/004795/4.png", "losevideos/004795/5.png", "losevideos/004795/6.png", "losevideos/004795/7.png", "winvideos/004795/0.png", "winvideos/004795/1.png", "winvideos/004795/2.png", "winvideos/004795/3.png", "winvideos/004795/4.png", "winvideos/004795/5.png", "winvideos/004795/6.png", "winvideos/004795/7.png" ]
a girl with dark hair and sad eyes raises a broom above herself, above her head.	[ { "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 dark hair and sad eyes raises a broom above herself, above her head.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004867/0.png", "losevideos/004867/1.png", "losevideos/004867/2.png", "losevideos/004867/3.png", "losevideos/004867/4.png", "losevideos/004867/5.png", "losevideos/004867/6.png", "losevideos/004867/7.png", "winvideos/004867/0.png", "winvideos/004867/1.png", "winvideos/004867/2.png", "winvideos/004867/3.png", "winvideos/004867/4.png", "winvideos/004867/5.png", "winvideos/004867/6.png", "winvideos/004867/7.png" ]
Penguins swimming in lava.	[ { "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: [Penguins swimming in lava.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004434/0.png", "winvideos/004434/1.png", "winvideos/004434/2.png", "winvideos/004434/3.png", "winvideos/004434/4.png", "winvideos/004434/5.png", "winvideos/004434/6.png", "winvideos/004434/7.png", "losevideos/004434/0.png", "losevideos/004434/1.png", "losevideos/004434/2.png", "losevideos/004434/3.png", "losevideos/004434/4.png", "losevideos/004434/5.png", "losevideos/004434/6.png", "losevideos/004434/7.png" ]
A silhouette in a raincoat stands in the wind, a long raincoat develops in the wind. black and white filter. 25 frames. The general plan. The camera moves behind the silhouette. Udtradetalization. Elaboration of details.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A silhouette in a raincoat stands in the wind, a long raincoat develops in the wind. black and white filter. 25 frames. The general plan. The camera moves behind the silhouette. Udtradetalization. Elaboration of details.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000145/0.png", "winvideos/000145/1.png", "winvideos/000145/2.png", "winvideos/000145/3.png", "winvideos/000145/4.png", "winvideos/000145/5.png", "winvideos/000145/6.png", "winvideos/000145/7.png", "losevideos/000145/0.png", "losevideos/000145/1.png", "losevideos/000145/2.png", "losevideos/000145/3.png", "losevideos/000145/4.png", "losevideos/000145/5.png", "losevideos/000145/6.png", "losevideos/000145/7.png" ]
there is red fire around the sword, his hair also can flow 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: [there is red fire around the sword, his hair also can flow Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007457/0.png", "winvideos/007457/1.png", "winvideos/007457/2.png", "winvideos/007457/3.png", "winvideos/007457/4.png", "winvideos/007457/5.png", "winvideos/007457/6.png", "winvideos/007457/7.png", "losevideos/007457/0.png", "losevideos/007457/1.png", "losevideos/007457/2.png", "losevideos/007457/3.png", "losevideos/007457/4.png", "losevideos/007457/5.png", "losevideos/007457/6.png", "losevideos/007457/7.png" ]
boy studying in his room, lofi 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: [boy studying in his room, lofi style.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008220/0.png", "losevideos/008220/1.png", "losevideos/008220/2.png", "losevideos/008220/3.png", "losevideos/008220/4.png", "losevideos/008220/5.png", "losevideos/008220/6.png", "losevideos/008220/7.png", "winvideos/008220/0.png", "winvideos/008220/1.png", "winvideos/008220/2.png", "winvideos/008220/3.png", "winvideos/008220/4.png", "winvideos/008220/5.png", "winvideos/008220/6.png", "winvideos/008220/7.png" ]
ocean coast, old lighthouse, storm, aerial view, horror movie, dark, 4K -ar 16:9 -motion 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: [ocean coast, old lighthouse, storm, aerial view, horror movie, dark, 4K -ar 16:9 -motion 1.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006928/0.png", "winvideos/006928/1.png", "winvideos/006928/2.png", "winvideos/006928/3.png", "winvideos/006928/4.png", "winvideos/006928/5.png", "winvideos/006928/6.png", "winvideos/006928/7.png", "losevideos/006928/0.png", "losevideos/006928/1.png", "losevideos/006928/2.png", "losevideos/006928/3.png", "losevideos/006928/4.png", "losevideos/006928/5.png", "losevideos/006928/6.png", "losevideos/006928/7.png" ]
21 days is going in calender.	[ { "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: [21 days is going in calender.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005704/0.png", "winvideos/005704/1.png", "winvideos/005704/2.png", "winvideos/005704/3.png", "winvideos/005704/4.png", "winvideos/005704/5.png", "winvideos/005704/6.png", "winvideos/005704/7.png", "losevideos/005704/0.png", "losevideos/005704/1.png", "losevideos/005704/2.png", "losevideos/005704/3.png", "losevideos/005704/4.png", "losevideos/005704/5.png", "losevideos/005704/6.png", "losevideos/005704/7.png" ]
A police car driving in the middle of the street at night. Filmed from above.	[ { "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 police car driving in the middle of the street at night. Filmed from above.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005034/0.png", "winvideos/005034/1.png", "winvideos/005034/2.png", "winvideos/005034/3.png", "winvideos/005034/4.png", "winvideos/005034/5.png", "winvideos/005034/6.png", "winvideos/005034/7.png", "losevideos/005034/0.png", "losevideos/005034/1.png", "losevideos/005034/2.png", "losevideos/005034/3.png", "losevideos/005034/4.png", "losevideos/005034/5.png", "losevideos/005034/6.png", "losevideos/005034/7.png" ]
indian village on hill station long shot cinematic -fps24 -motion4 -gs24 -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: [indian village on hill station long shot cinematic -fps24 -motion4 -gs24 -ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001676/0.png", "winvideos/001676/1.png", "winvideos/001676/2.png", "winvideos/001676/3.png", "winvideos/001676/4.png", "winvideos/001676/5.png", "winvideos/001676/6.png", "winvideos/001676/7.png", "losevideos/001676/0.png", "losevideos/001676/1.png", "losevideos/001676/2.png", "losevideos/001676/3.png", "losevideos/001676/4.png", "losevideos/001676/5.png", "losevideos/001676/6.png", "losevideos/001676/7.png" ]
dark souls character fighting an unborn jelly fish,dramtic, high detail.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [dark souls character fighting an unborn jelly fish,dramtic, high detail.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006925/0.png", "losevideos/006925/1.png", "losevideos/006925/2.png", "losevideos/006925/3.png", "losevideos/006925/4.png", "losevideos/006925/5.png", "losevideos/006925/6.png", "losevideos/006925/7.png", "winvideos/006925/0.png", "winvideos/006925/1.png", "winvideos/006925/2.png", "winvideos/006925/3.png", "winvideos/006925/4.png", "winvideos/006925/5.png", "winvideos/006925/6.png", "winvideos/006925/7.png" ]
Animated opening for children's English learning videos.	[ { "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: [Animated opening for children's English learning videos.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007298/0.png", "losevideos/007298/1.png", "losevideos/007298/2.png", "losevideos/007298/3.png", "losevideos/007298/4.png", "losevideos/007298/5.png", "losevideos/007298/6.png", "losevideos/007298/7.png", "winvideos/007298/0.png", "winvideos/007298/1.png", "winvideos/007298/2.png", "winvideos/007298/3.png", "winvideos/007298/4.png", "winvideos/007298/5.png", "winvideos/007298/6.png", "winvideos/007298/7.png" ]
motion pic jungle Disney style, capture big creatures of different types, Introduce Lion Leo as a majestic 3D-animated lion with a golden mane, making sure to highlight his twinkle eyes in 4K resolution walked pass a tree, all animal characters walk, cinematic, vibrant, forward movement, capture the environment in realistic 4k 3d -gs 22 -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: [motion pic jungle Disney style, capture big creatures of different types, Introduce Lion Leo as a majestic 3D-animated lion with a golden mane, making sure to highlight his twinkle eyes in 4K resolution walked pass a tree, all animal characters walk, cinematic, vibrant, forward movement, capture the environment in realistic 4k 3d -gs 22 -motion 4.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000418/0.png", "winvideos/000418/1.png", "winvideos/000418/2.png", "winvideos/000418/3.png", "winvideos/000418/4.png", "winvideos/000418/5.png", "winvideos/000418/6.png", "winvideos/000418/7.png", "losevideos/000418/0.png", "losevideos/000418/1.png", "losevideos/000418/2.png", "losevideos/000418/3.png", "losevideos/000418/4.png", "losevideos/000418/5.png", "losevideos/000418/6.png", "losevideos/000418/7.png" ]
Move eyes, pen 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: [Move eyes, pen Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001341/0.png", "losevideos/001341/1.png", "losevideos/001341/2.png", "losevideos/001341/3.png", "losevideos/001341/4.png", "losevideos/001341/5.png", "losevideos/001341/6.png", "losevideos/001341/7.png", "winvideos/001341/0.png", "winvideos/001341/1.png", "winvideos/001341/2.png", "winvideos/001341/3.png", "winvideos/001341/4.png", "winvideos/001341/5.png", "winvideos/001341/6.png", "winvideos/001341/7.png" ]
A serene sunrise over a majestic mountain range, with golden light spilling over snow-capped peaks, the sky painted in hues of orange, pink, and purple. Mist gently rising from the valleys, and a crystal-clear lake reflecting the breathtaking scenery. --ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A serene sunrise over a majestic mountain range, with golden light spilling over snow-capped peaks, the sky painted in hues of orange, pink, and purple. Mist gently rising from the valleys, and a crystal-clear lake reflecting the breathtaking scenery. --ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001148/0.png", "winvideos/001148/1.png", "winvideos/001148/2.png", "winvideos/001148/3.png", "winvideos/001148/4.png", "winvideos/001148/5.png", "winvideos/001148/6.png", "winvideos/001148/7.png", "losevideos/001148/0.png", "losevideos/001148/1.png", "losevideos/001148/2.png", "losevideos/001148/3.png", "losevideos/001148/4.png", "losevideos/001148/5.png", "losevideos/001148/6.png", "losevideos/001148/7.png" ]
Picture Emma creating a detailed schedule, carefully organizing her time to accommodate work, relaxation, and pursuing her passions, fostering a sense of purpose.	[ { "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: [Picture Emma creating a detailed schedule, carefully organizing her time to accommodate work, relaxation, and pursuing her passions, fostering a sense of purpose.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000102/0.png", "losevideos/000102/1.png", "losevideos/000102/2.png", "losevideos/000102/3.png", "losevideos/000102/4.png", "losevideos/000102/5.png", "losevideos/000102/6.png", "losevideos/000102/7.png", "winvideos/000102/0.png", "winvideos/000102/1.png", "winvideos/000102/2.png", "winvideos/000102/3.png", "winvideos/000102/4.png", "winvideos/000102/5.png", "winvideos/000102/6.png", "winvideos/000102/7.png" ]
Woman in Café. Scene in Cyberpunk style.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Woman in Café. Scene in Cyberpunk style.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006746/0.png", "losevideos/006746/1.png", "losevideos/006746/2.png", "losevideos/006746/3.png", "losevideos/006746/4.png", "losevideos/006746/5.png", "losevideos/006746/6.png", "losevideos/006746/7.png", "winvideos/006746/0.png", "winvideos/006746/1.png", "winvideos/006746/2.png", "winvideos/006746/3.png", "winvideos/006746/4.png", "winvideos/006746/5.png", "winvideos/006746/6.png", "winvideos/006746/7.png" ]
The squirrel is climbing the tree.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The squirrel is climbing the tree.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004197/0.png", "losevideos/004197/1.png", "losevideos/004197/2.png", "losevideos/004197/3.png", "losevideos/004197/4.png", "losevideos/004197/5.png", "losevideos/004197/6.png", "losevideos/004197/7.png", "winvideos/004197/0.png", "winvideos/004197/1.png", "winvideos/004197/2.png", "winvideos/004197/3.png", "winvideos/004197/4.png", "winvideos/004197/5.png", "winvideos/004197/6.png", "winvideos/004197/7.png" ]
a golden dragon attacks two dark-skinned female warriors in neon glowing bodysuits. Actions take place in the desert. Realism, clear details, traced lines, 8k.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a golden dragon attacks two dark-skinned female warriors in neon glowing bodysuits. Actions take place in the desert. Realism, clear details, traced lines, 8k.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002093/0.png", "losevideos/002093/1.png", "losevideos/002093/2.png", "losevideos/002093/3.png", "losevideos/002093/4.png", "losevideos/002093/5.png", "losevideos/002093/6.png", "losevideos/002093/7.png", "winvideos/002093/0.png", "winvideos/002093/1.png", "winvideos/002093/2.png", "winvideos/002093/3.png", "winvideos/002093/4.png", "winvideos/002093/5.png", "winvideos/002093/6.png", "winvideos/002093/7.png" ]
animal mouse, in the world of cyberpunk with implants.	[ { "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: [animal mouse, in the world of cyberpunk with implants.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007985/0.png", "losevideos/007985/1.png", "losevideos/007985/2.png", "losevideos/007985/3.png", "losevideos/007985/4.png", "losevideos/007985/5.png", "losevideos/007985/6.png", "losevideos/007985/7.png", "winvideos/007985/0.png", "winvideos/007985/1.png", "winvideos/007985/2.png", "winvideos/007985/3.png", "winvideos/007985/4.png", "winvideos/007985/5.png", "winvideos/007985/6.png", "winvideos/007985/7.png" ]
large american flag blowing in the wind over a neighborhood.	[ { "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: [large american flag blowing in the wind over a neighborhood.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003034/0.png", "winvideos/003034/1.png", "winvideos/003034/2.png", "winvideos/003034/3.png", "winvideos/003034/4.png", "winvideos/003034/5.png", "winvideos/003034/6.png", "winvideos/003034/7.png", "losevideos/003034/0.png", "losevideos/003034/1.png", "losevideos/003034/2.png", "losevideos/003034/3.png", "losevideos/003034/4.png", "losevideos/003034/5.png", "losevideos/003034/6.png", "losevideos/003034/7.png" ]
eyes moving quickly and continuously from left to right to left to right.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [eyes moving quickly and continuously from left to right to left to right.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002406/0.png", "winvideos/002406/1.png", "winvideos/002406/2.png", "winvideos/002406/3.png", "winvideos/002406/4.png", "winvideos/002406/5.png", "winvideos/002406/6.png", "winvideos/002406/7.png", "losevideos/002406/0.png", "losevideos/002406/1.png", "losevideos/002406/2.png", "losevideos/002406/3.png", "losevideos/002406/4.png", "losevideos/002406/5.png", "losevideos/002406/6.png", "losevideos/002406/7.png" ]
a silhouette of tall girl with 160 cm height in white gown with knee level wide shot eating cake with arms folding ,32k ,highly detailed,medium sun tanned , long face seed 3488499173349737426.	[ { "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 silhouette of tall girl with 160 cm height in white gown with knee level wide shot eating cake with arms folding ,32k ,highly detailed,medium sun tanned , long face seed 3488499173349737426.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002450/0.png", "winvideos/002450/1.png", "winvideos/002450/2.png", "winvideos/002450/3.png", "winvideos/002450/4.png", "winvideos/002450/5.png", "winvideos/002450/6.png", "winvideos/002450/7.png", "losevideos/002450/0.png", "losevideos/002450/1.png", "losevideos/002450/2.png", "losevideos/002450/3.png", "losevideos/002450/4.png", "losevideos/002450/5.png", "losevideos/002450/6.png", "losevideos/002450/7.png" ]
drone footage of earthquake damage, dust plumes, dust billowing, flames.	[ { "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: [drone footage of earthquake damage, dust plumes, dust billowing, flames.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004427/0.png", "losevideos/004427/1.png", "losevideos/004427/2.png", "losevideos/004427/3.png", "losevideos/004427/4.png", "losevideos/004427/5.png", "losevideos/004427/6.png", "losevideos/004427/7.png", "winvideos/004427/0.png", "winvideos/004427/1.png", "winvideos/004427/2.png", "winvideos/004427/3.png", "winvideos/004427/4.png", "winvideos/004427/5.png", "winvideos/004427/6.png", "winvideos/004427/7.png" ]
product advertisement of a pistachio green bottle with a letter E.	[ { "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: [product advertisement of a pistachio green bottle with a letter E.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003873/0.png", "losevideos/003873/1.png", "losevideos/003873/2.png", "losevideos/003873/3.png", "losevideos/003873/4.png", "losevideos/003873/5.png", "losevideos/003873/6.png", "losevideos/003873/7.png", "winvideos/003873/0.png", "winvideos/003873/1.png", "winvideos/003873/2.png", "winvideos/003873/3.png", "winvideos/003873/4.png", "winvideos/003873/5.png", "winvideos/003873/6.png", "winvideos/003873/7.png" ]
French Bulldog and British Shorthair，Marry.	[ { "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: [French Bulldog and British Shorthair，Marry.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007465/0.png", "losevideos/007465/1.png", "losevideos/007465/2.png", "losevideos/007465/3.png", "losevideos/007465/4.png", "losevideos/007465/5.png", "losevideos/007465/6.png", "losevideos/007465/7.png", "winvideos/007465/0.png", "winvideos/007465/1.png", "winvideos/007465/2.png", "winvideos/007465/3.png", "winvideos/007465/4.png", "winvideos/007465/5.png", "winvideos/007465/6.png", "winvideos/007465/7.png" ]
A tranquil tableau of a beautiful wrought-iron bench surrounded by blooming flowers -seed 3951509 -motion 0.	[ { "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 tranquil tableau of a beautiful wrought-iron bench surrounded by blooming flowers -seed 3951509 -motion 0.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002915/0.png", "losevideos/002915/1.png", "losevideos/002915/2.png", "losevideos/002915/3.png", "losevideos/002915/4.png", "losevideos/002915/5.png", "losevideos/002915/6.png", "losevideos/002915/7.png", "winvideos/002915/0.png", "winvideos/002915/1.png", "winvideos/002915/2.png", "winvideos/002915/3.png", "winvideos/002915/4.png", "winvideos/002915/5.png", "winvideos/002915/6.png", "winvideos/002915/7.png" ]