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
Overhead view of photoshoot of New York city.	[ { "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: [Overhead view of photoshoot of New York city.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003265/0.png", "winvideos/003265/1.png", "winvideos/003265/2.png", "winvideos/003265/3.png", "winvideos/003265/4.png", "winvideos/003265/5.png", "winvideos/003265/6.png", "winvideos/003265/7.png", "losevideos/003265/0.png", "losevideos/003265/1.png", "losevideos/003265/2.png", "losevideos/003265/3.png", "losevideos/003265/4.png", "losevideos/003265/5.png", "losevideos/003265/6.png", "losevideos/003265/7.png" ]
noire style. detective in the streets under the rain. looking at another detective walking away.	[ { "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: [noire style. detective in the streets under the rain. looking at another detective walking away.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001591/0.png", "losevideos/001591/1.png", "losevideos/001591/2.png", "losevideos/001591/3.png", "losevideos/001591/4.png", "losevideos/001591/5.png", "losevideos/001591/6.png", "losevideos/001591/7.png", "winvideos/001591/0.png", "winvideos/001591/1.png", "winvideos/001591/2.png", "winvideos/001591/3.png", "winvideos/001591/4.png", "winvideos/001591/5.png", "winvideos/001591/6.png", "winvideos/001591/7.png" ]
a picture from far away of a young blond hair blue eyes woman in an abandoned old dusty bookstore. Her eyes focused on reading a leather-bound book facing her titled "The Grimoire of Legends." she is holding the book.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a picture from far away of a young blond hair blue eyes woman in an abandoned old dusty bookstore. Her eyes focused on reading a leather-bound book facing her titled "The Grimoire of Legends." she is holding the book.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008097/0.png", "winvideos/008097/1.png", "winvideos/008097/2.png", "winvideos/008097/3.png", "winvideos/008097/4.png", "winvideos/008097/5.png", "winvideos/008097/6.png", "winvideos/008097/7.png", "losevideos/008097/0.png", "losevideos/008097/1.png", "losevideos/008097/2.png", "losevideos/008097/3.png", "losevideos/008097/4.png", "losevideos/008097/5.png", "losevideos/008097/6.png", "losevideos/008097/7.png" ]
a rural indian man and a crying kid talking to each other outside their village house. the kid is complaining about something. ultra HD.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a rural indian man and a crying kid talking to each other outside their village house. the kid is complaining about something. ultra HD.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006525/0.png", "losevideos/006525/1.png", "losevideos/006525/2.png", "losevideos/006525/3.png", "losevideos/006525/4.png", "losevideos/006525/5.png", "losevideos/006525/6.png", "losevideos/006525/7.png", "winvideos/006525/0.png", "winvideos/006525/1.png", "winvideos/006525/2.png", "winvideos/006525/3.png", "winvideos/006525/4.png", "winvideos/006525/5.png", "winvideos/006525/6.png", "winvideos/006525/7.png" ]
Lamborghini wit eyes all over the body.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Lamborghini wit eyes all over the body.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003957/0.png", "winvideos/003957/1.png", "winvideos/003957/2.png", "winvideos/003957/3.png", "winvideos/003957/4.png", "winvideos/003957/5.png", "winvideos/003957/6.png", "winvideos/003957/7.png", "losevideos/003957/0.png", "losevideos/003957/1.png", "losevideos/003957/2.png", "losevideos/003957/3.png", "losevideos/003957/4.png", "losevideos/003957/5.png", "losevideos/003957/6.png", "losevideos/003957/7.png" ]
pirate with fire power walking -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: [pirate with fire power walking -ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001633/0.png", "losevideos/001633/1.png", "losevideos/001633/2.png", "losevideos/001633/3.png", "losevideos/001633/4.png", "losevideos/001633/5.png", "losevideos/001633/6.png", "losevideos/001633/7.png", "winvideos/001633/0.png", "winvideos/001633/1.png", "winvideos/001633/2.png", "winvideos/001633/3.png", "winvideos/001633/4.png", "winvideos/001633/5.png", "winvideos/001633/6.png", "winvideos/001633/7.png" ]
An artistic portrayal of the tragic duel between Tybalt and Mercutio, highlighting the tension and violence that escalates the conflict in Verona. -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: [An artistic portrayal of the tragic duel between Tybalt and Mercutio, highlighting the tension and violence that escalates the conflict in Verona. -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007842/0.png", "winvideos/007842/1.png", "winvideos/007842/2.png", "winvideos/007842/3.png", "winvideos/007842/4.png", "winvideos/007842/5.png", "winvideos/007842/6.png", "winvideos/007842/7.png", "losevideos/007842/0.png", "losevideos/007842/1.png", "losevideos/007842/2.png", "losevideos/007842/3.png", "losevideos/007842/4.png", "losevideos/007842/5.png", "losevideos/007842/6.png", "losevideos/007842/7.png" ]
A night sky filled with a kaleidoscope of stars, planets, and galaxies. in Real cinematic style, hyper-realistic, by James Cameron style, portrait, UHD, 4k, high octane render, anamorphic, gorgeous cinematic lighting, ray tracing, particle effects, ambient volumetric lighting, dim ominous lighting, splatters everywhere, shiny and reflective, -ar 16:9 -motion 4 -gs 21 -fps 24 -neg "CGI, vector art, fake, blurry, mono-color, no movement, random movements, noisy, deformed, distorted, facial changes, low quality, low resolution, cartoon, animation".	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A night sky filled with a kaleidoscope of stars, planets, and galaxies. in Real cinematic style, hyper-realistic, by James Cameron style, portrait, UHD, 4k, high octane render, anamorphic, gorgeous cinematic lighting, ray tracing, particle effects, ambient volumetric lighting, dim ominous lighting, splatters everywhere, shiny and reflective, -ar 16:9 -motion 4 -gs 21 -fps 24 -neg "CGI, vector art, fake, blurry, mono-color, no movement, random movements, noisy, deformed, distorted, facial changes, low quality, low resolution, cartoon, animation".]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009824/0.png", "winvideos/009824/1.png", "winvideos/009824/2.png", "winvideos/009824/3.png", "winvideos/009824/4.png", "winvideos/009824/5.png", "winvideos/009824/6.png", "winvideos/009824/7.png", "losevideos/009824/0.png", "losevideos/009824/1.png", "losevideos/009824/2.png", "losevideos/009824/3.png", "losevideos/009824/4.png", "losevideos/009824/5.png", "losevideos/009824/6.png", "losevideos/009824/7.png" ]
istanbul, rain, fire, Atatürk, 1928.	[ { "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: [istanbul, rain, fire, Atatürk, 1928.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006586/0.png", "losevideos/006586/1.png", "losevideos/006586/2.png", "losevideos/006586/3.png", "losevideos/006586/4.png", "losevideos/006586/5.png", "losevideos/006586/6.png", "losevideos/006586/7.png", "winvideos/006586/0.png", "winvideos/006586/1.png", "winvideos/006586/2.png", "winvideos/006586/3.png", "winvideos/006586/4.png", "winvideos/006586/5.png", "winvideos/006586/6.png", "winvideos/006586/7.png" ]
/In this Unreal engine promt a night vision mathematician, in time lapse going over this specific ,Solve each absolute value inequality is our theme for an animation prompt in PIKALABS using their artificial intelligence generator, like unreal engine, and I want to express an image sequence in animation for this specific value inequality \| x-3 \| + 5 < 3 graph the line 1,-2 \|draw animation of the circle centered at (0,4).	[ { "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: [/In this Unreal engine promt a night vision mathematician, in time lapse going over this specific ,Solve each absolute value inequality is our theme for an animation prompt in PIKALABS using their artificial intelligence generator, like unreal engine, and I want to express an image sequence in animation for this specific value inequality \| x-3 \| + 5 < 3 graph the line 1,-2 \|draw animation of the circle centered at (0,4).]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000504/0.png", "losevideos/000504/1.png", "losevideos/000504/2.png", "losevideos/000504/3.png", "losevideos/000504/4.png", "losevideos/000504/5.png", "losevideos/000504/6.png", "losevideos/000504/7.png", "winvideos/000504/0.png", "winvideos/000504/1.png", "winvideos/000504/2.png", "winvideos/000504/3.png", "winvideos/000504/4.png", "winvideos/000504/5.png", "winvideos/000504/6.png", "winvideos/000504/7.png" ]
fat indian woman dancing in undergarments.	[ { "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: [fat indian woman dancing in undergarments.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001129/0.png", "winvideos/001129/1.png", "winvideos/001129/2.png", "winvideos/001129/3.png", "winvideos/001129/4.png", "winvideos/001129/5.png", "winvideos/001129/6.png", "winvideos/001129/7.png", "losevideos/001129/0.png", "losevideos/001129/1.png", "losevideos/001129/2.png", "losevideos/001129/3.png", "losevideos/001129/4.png", "losevideos/001129/5.png", "losevideos/001129/6.png", "losevideos/001129/7.png" ]
a 1950’s style kodachrome movie with Santa dressed as a christmas tree spinning around on a merry go round at high sped covered in 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: [a 1950’s style kodachrome movie with Santa dressed as a christmas tree spinning around on a merry go round at high sped covered in flames.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005024/0.png", "winvideos/005024/1.png", "winvideos/005024/2.png", "winvideos/005024/3.png", "winvideos/005024/4.png", "winvideos/005024/5.png", "winvideos/005024/6.png", "winvideos/005024/7.png", "losevideos/005024/0.png", "losevideos/005024/1.png", "losevideos/005024/2.png", "losevideos/005024/3.png", "losevideos/005024/4.png", "losevideos/005024/5.png", "losevideos/005024/6.png", "losevideos/005024/7.png" ]
A man wearing a black coat stands in the middle of a maze, playing an acoustic guitar. He has his eyes closed and is focused on the music he's creating. His long brown hair falls around his face as he plays, and his facial expression shows concentration and joy. He wears dark boots with laces that reach up to mid-calf, and a pair of jeans tucked into them. The sky above him is bright blue with white clouds scattered throughout it, while the ground beneath him is made up of large stones arranged in intricate patterns. In one hand he holds the neck of the guitar while his other hand strums its strings, producing beautiful notes that echo through the air around him.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A man wearing a black coat stands in the middle of a maze, playing an acoustic guitar. He has his eyes closed and is focused on the music he's creating. His long brown hair falls around his face as he plays, and his facial expression shows concentration and joy. He wears dark boots with laces that reach up to mid-calf, and a pair of jeans tucked into them. The sky above him is bright blue with white clouds scattered throughout it, while the ground beneath him is made up of large stones arranged in intricate patterns. In one hand he holds the neck of the guitar while his other hand strums its strings, producing beautiful notes that echo through the air around him.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003248/0.png", "losevideos/003248/1.png", "losevideos/003248/2.png", "losevideos/003248/3.png", "losevideos/003248/4.png", "losevideos/003248/5.png", "losevideos/003248/6.png", "losevideos/003248/7.png", "winvideos/003248/0.png", "winvideos/003248/1.png", "winvideos/003248/2.png", "winvideos/003248/3.png", "winvideos/003248/4.png", "winvideos/003248/5.png", "winvideos/003248/6.png", "winvideos/003248/7.png" ]
Falcon bursting out of laptop with flames, 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: [Falcon bursting out of laptop with flames, motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007299/0.png", "losevideos/007299/1.png", "losevideos/007299/2.png", "losevideos/007299/3.png", "losevideos/007299/4.png", "losevideos/007299/5.png", "losevideos/007299/6.png", "losevideos/007299/7.png", "winvideos/007299/0.png", "winvideos/007299/1.png", "winvideos/007299/2.png", "winvideos/007299/3.png", "winvideos/007299/4.png", "winvideos/007299/5.png", "winvideos/007299/6.png", "winvideos/007299/7.png" ]
egyptian mummy+ laying in the tomb.	[ { "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: [egyptian mummy+ laying in the tomb.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002306/0.png", "losevideos/002306/1.png", "losevideos/002306/2.png", "losevideos/002306/3.png", "losevideos/002306/4.png", "losevideos/002306/5.png", "losevideos/002306/6.png", "losevideos/002306/7.png", "winvideos/002306/0.png", "winvideos/002306/1.png", "winvideos/002306/2.png", "winvideos/002306/3.png", "winvideos/002306/4.png", "winvideos/002306/5.png", "winvideos/002306/6.png", "winvideos/002306/7.png" ]
an angry mob in 2023 at the steps of the US capital. Some holding US flags and some holding the confederate flag. A current view of the capital and modern day clothing should be visible. Smoke belows in the background in front of the capital dome. - 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: [an angry mob in 2023 at the steps of the US capital. Some holding US flags and some holding the confederate flag. A current view of the capital and modern day clothing should be visible. Smoke belows in the background in front of the capital dome. - ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001790/0.png", "losevideos/001790/1.png", "losevideos/001790/2.png", "losevideos/001790/3.png", "losevideos/001790/4.png", "losevideos/001790/5.png", "losevideos/001790/6.png", "losevideos/001790/7.png", "winvideos/001790/0.png", "winvideos/001790/1.png", "winvideos/001790/2.png", "winvideos/001790/3.png", "winvideos/001790/4.png", "winvideos/001790/5.png", "winvideos/001790/6.png", "winvideos/001790/7.png" ]
A village road is covered in fog. Dewdrops hang from the trees on the side of the road. Cartoon,4d,.	[ { "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 village road is covered in fog. Dewdrops hang from the trees on the side of the road. Cartoon,4d,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009822/0.png", "winvideos/009822/1.png", "winvideos/009822/2.png", "winvideos/009822/3.png", "winvideos/009822/4.png", "winvideos/009822/5.png", "winvideos/009822/6.png", "winvideos/009822/7.png", "losevideos/009822/0.png", "losevideos/009822/1.png", "losevideos/009822/2.png", "losevideos/009822/3.png", "losevideos/009822/4.png", "losevideos/009822/5.png", "losevideos/009822/6.png", "losevideos/009822/7.png" ]
earthquakes -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: [earthquakes -ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001765/0.png", "losevideos/001765/1.png", "losevideos/001765/2.png", "losevideos/001765/3.png", "losevideos/001765/4.png", "losevideos/001765/5.png", "losevideos/001765/6.png", "losevideos/001765/7.png", "winvideos/001765/0.png", "winvideos/001765/1.png", "winvideos/001765/2.png", "winvideos/001765/3.png", "winvideos/001765/4.png", "winvideos/001765/5.png", "winvideos/001765/6.png", "winvideos/001765/7.png" ]
a big lion was preying on a doe.	[ { "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 big lion was preying on a doe.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008999/0.png", "winvideos/008999/1.png", "winvideos/008999/2.png", "winvideos/008999/3.png", "winvideos/008999/4.png", "winvideos/008999/5.png", "winvideos/008999/6.png", "winvideos/008999/7.png", "losevideos/008999/0.png", "losevideos/008999/1.png", "losevideos/008999/2.png", "losevideos/008999/3.png", "losevideos/008999/4.png", "losevideos/008999/5.png", "losevideos/008999/6.png", "losevideos/008999/7.png" ]
Cinematic style Pakistani watching cricket match at office screen-fps 24.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Cinematic style Pakistani watching cricket match at office screen-fps 24.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007483/0.png", "winvideos/007483/1.png", "winvideos/007483/2.png", "winvideos/007483/3.png", "winvideos/007483/4.png", "winvideos/007483/5.png", "winvideos/007483/6.png", "winvideos/007483/7.png", "losevideos/007483/0.png", "losevideos/007483/1.png", "losevideos/007483/2.png", "losevideos/007483/3.png", "losevideos/007483/4.png", "losevideos/007483/5.png", "losevideos/007483/6.png", "losevideos/007483/7.png" ]
film still of bruce wayne walking through his mansion in 2024 movie scene.	[ { "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: [film still of bruce wayne walking through his mansion in 2024 movie scene.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007741/0.png", "losevideos/007741/1.png", "losevideos/007741/2.png", "losevideos/007741/3.png", "losevideos/007741/4.png", "losevideos/007741/5.png", "losevideos/007741/6.png", "losevideos/007741/7.png", "winvideos/007741/0.png", "winvideos/007741/1.png", "winvideos/007741/2.png", "winvideos/007741/3.png", "winvideos/007741/4.png", "winvideos/007741/5.png", "winvideos/007741/6.png", "winvideos/007741/7.png" ]
AI changes the future of college campuses.	[ { "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: [AI changes the future of college campuses.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008502/0.png", "winvideos/008502/1.png", "winvideos/008502/2.png", "winvideos/008502/3.png", "winvideos/008502/4.png", "winvideos/008502/5.png", "winvideos/008502/6.png", "winvideos/008502/7.png", "losevideos/008502/0.png", "losevideos/008502/1.png", "losevideos/008502/2.png", "losevideos/008502/3.png", "losevideos/008502/4.png", "losevideos/008502/5.png", "losevideos/008502/6.png", "losevideos/008502/7.png" ]
hulk doing gangnam style with elon as ironman.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [hulk doing gangnam style with elon as ironman.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005061/0.png", "winvideos/005061/1.png", "winvideos/005061/2.png", "winvideos/005061/3.png", "winvideos/005061/4.png", "winvideos/005061/5.png", "winvideos/005061/6.png", "winvideos/005061/7.png", "losevideos/005061/0.png", "losevideos/005061/1.png", "losevideos/005061/2.png", "losevideos/005061/3.png", "losevideos/005061/4.png", "losevideos/005061/5.png", "losevideos/005061/6.png", "losevideos/005061/7.png" ]
Search Light - Light to Heaven type , in the city boston 1920 film.	[ { "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: [Search Light - Light to Heaven type , in the city boston 1920 film.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007061/0.png", "winvideos/007061/1.png", "winvideos/007061/2.png", "winvideos/007061/3.png", "winvideos/007061/4.png", "winvideos/007061/5.png", "winvideos/007061/6.png", "winvideos/007061/7.png", "losevideos/007061/0.png", "losevideos/007061/1.png", "losevideos/007061/2.png", "losevideos/007061/3.png", "losevideos/007061/4.png", "losevideos/007061/5.png", "losevideos/007061/6.png", "losevideos/007061/7.png" ]
robot demons dancing the macarena until doomsday, nightmare -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: [robot demons dancing the macarena until doomsday, nightmare -ar 16:9 -motion 1.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006512/0.png", "winvideos/006512/1.png", "winvideos/006512/2.png", "winvideos/006512/3.png", "winvideos/006512/4.png", "winvideos/006512/5.png", "winvideos/006512/6.png", "winvideos/006512/7.png", "losevideos/006512/0.png", "losevideos/006512/1.png", "losevideos/006512/2.png", "losevideos/006512/3.png", "losevideos/006512/4.png", "losevideos/006512/5.png", "losevideos/006512/6.png", "losevideos/006512/7.png" ]
a 1902 GEORGES MÉLIÈS film, Golden superhero walking through the rain,.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a 1902 GEORGES MÉLIÈS film, Golden superhero walking through the rain,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009574/0.png", "winvideos/009574/1.png", "winvideos/009574/2.png", "winvideos/009574/3.png", "winvideos/009574/4.png", "winvideos/009574/5.png", "winvideos/009574/6.png", "winvideos/009574/7.png", "losevideos/009574/0.png", "losevideos/009574/1.png", "losevideos/009574/2.png", "losevideos/009574/3.png", "losevideos/009574/4.png", "losevideos/009574/5.png", "losevideos/009574/6.png", "losevideos/009574/7.png" ]
Little light skin ebony silat dreadlock toddler holding a Pencak silat sword, with baby tiger. Indonesian temples and lush jungle mountains with small waterfalls in background. Artistic Eroded frame and edges.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Little light skin ebony silat dreadlock toddler holding a Pencak silat sword, with baby tiger. Indonesian temples and lush jungle mountains with small waterfalls in background. Artistic Eroded frame and edges.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004642/0.png", "losevideos/004642/1.png", "losevideos/004642/2.png", "losevideos/004642/3.png", "losevideos/004642/4.png", "losevideos/004642/5.png", "losevideos/004642/6.png", "losevideos/004642/7.png", "winvideos/004642/0.png", "winvideos/004642/1.png", "winvideos/004642/2.png", "winvideos/004642/3.png", "winvideos/004642/4.png", "winvideos/004642/5.png", "winvideos/004642/6.png", "winvideos/004642/7.png" ]
white tiger morphin into a bear then into the-Rex.	[ { "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: [white tiger morphin into a bear then into the-Rex.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008424/0.png", "winvideos/008424/1.png", "winvideos/008424/2.png", "winvideos/008424/3.png", "winvideos/008424/4.png", "winvideos/008424/5.png", "winvideos/008424/6.png", "winvideos/008424/7.png", "losevideos/008424/0.png", "losevideos/008424/1.png", "losevideos/008424/2.png", "losevideos/008424/3.png", "losevideos/008424/4.png", "losevideos/008424/5.png", "losevideos/008424/6.png", "losevideos/008424/7.png" ]
strong woman lift and carry men.	[ { "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: [strong woman lift and carry men.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001221/0.png", "winvideos/001221/1.png", "winvideos/001221/2.png", "winvideos/001221/3.png", "winvideos/001221/4.png", "winvideos/001221/5.png", "winvideos/001221/6.png", "winvideos/001221/7.png", "losevideos/001221/0.png", "losevideos/001221/1.png", "losevideos/001221/2.png", "losevideos/001221/3.png", "losevideos/001221/4.png", "losevideos/001221/5.png", "losevideos/001221/6.png", "losevideos/001221/7.png" ]
A nice story where in the hero is showm as a noob at the beginning and he rules the world later Sigma Male.	[ { "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 nice story where in the hero is showm as a noob at the beginning and he rules the world later Sigma Male.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002115/0.png", "winvideos/002115/1.png", "winvideos/002115/2.png", "winvideos/002115/3.png", "winvideos/002115/4.png", "winvideos/002115/5.png", "winvideos/002115/6.png", "winvideos/002115/7.png", "losevideos/002115/0.png", "losevideos/002115/1.png", "losevideos/002115/2.png", "losevideos/002115/3.png", "losevideos/002115/4.png", "losevideos/002115/5.png", "losevideos/002115/6.png", "losevideos/002115/7.png" ]
the boxes fly and move around the scene as he sits down and flails his arms. Dynamic, jittery and energetic movement.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [the boxes fly and move around the scene as he sits down and flails his arms. Dynamic, jittery and energetic movement.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000628/0.png", "winvideos/000628/1.png", "winvideos/000628/2.png", "winvideos/000628/3.png", "winvideos/000628/4.png", "winvideos/000628/5.png", "winvideos/000628/6.png", "winvideos/000628/7.png", "losevideos/000628/0.png", "losevideos/000628/1.png", "losevideos/000628/2.png", "losevideos/000628/3.png", "losevideos/000628/4.png", "losevideos/000628/5.png", "losevideos/000628/6.png", "losevideos/000628/7.png" ]
Gorilla wearing a business suit holding an attache briefcase walking down a New York City busy street -gs 50.	[ { "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: [Gorilla wearing a business suit holding an attache briefcase walking down a New York City busy street -gs 50.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000709/0.png", "winvideos/000709/1.png", "winvideos/000709/2.png", "winvideos/000709/3.png", "winvideos/000709/4.png", "winvideos/000709/5.png", "winvideos/000709/6.png", "winvideos/000709/7.png", "losevideos/000709/0.png", "losevideos/000709/1.png", "losevideos/000709/2.png", "losevideos/000709/3.png", "losevideos/000709/4.png", "losevideos/000709/5.png", "losevideos/000709/6.png", "losevideos/000709/7.png" ]
Singing with expressive facial expressions 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: [Singing with expressive facial expressions Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003620/0.png", "winvideos/003620/1.png", "winvideos/003620/2.png", "winvideos/003620/3.png", "winvideos/003620/4.png", "winvideos/003620/5.png", "winvideos/003620/6.png", "winvideos/003620/7.png", "losevideos/003620/0.png", "losevideos/003620/1.png", "losevideos/003620/2.png", "losevideos/003620/3.png", "losevideos/003620/4.png", "losevideos/003620/5.png", "losevideos/003620/6.png", "losevideos/003620/7.png" ]
british man walking with flowers on valentines day.	[ { "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: [british man walking with flowers on valentines day.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003183/0.png", "losevideos/003183/1.png", "losevideos/003183/2.png", "losevideos/003183/3.png", "losevideos/003183/4.png", "losevideos/003183/5.png", "losevideos/003183/6.png", "losevideos/003183/7.png", "winvideos/003183/0.png", "winvideos/003183/1.png", "winvideos/003183/2.png", "winvideos/003183/3.png", "winvideos/003183/4.png", "winvideos/003183/5.png", "winvideos/003183/6.png", "winvideos/003183/7.png" ]
Beautiful blue eyed girl talking, close up,.	[ { "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: [Beautiful blue eyed girl talking, close up,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002129/0.png", "winvideos/002129/1.png", "winvideos/002129/2.png", "winvideos/002129/3.png", "winvideos/002129/4.png", "winvideos/002129/5.png", "winvideos/002129/6.png", "winvideos/002129/7.png", "losevideos/002129/0.png", "losevideos/002129/1.png", "losevideos/002129/2.png", "losevideos/002129/3.png", "losevideos/002129/4.png", "losevideos/002129/5.png", "losevideos/002129/6.png", "losevideos/002129/7.png" ]
future cyborg warrior black armour black helmet with two horns jumping out of spaceship.	[ { "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 cyborg warrior black armour black helmet with two horns jumping out of spaceship.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004121/0.png", "winvideos/004121/1.png", "winvideos/004121/2.png", "winvideos/004121/3.png", "winvideos/004121/4.png", "winvideos/004121/5.png", "winvideos/004121/6.png", "winvideos/004121/7.png", "losevideos/004121/0.png", "losevideos/004121/1.png", "losevideos/004121/2.png", "losevideos/004121/3.png", "losevideos/004121/4.png", "losevideos/004121/5.png", "losevideos/004121/6.png", "losevideos/004121/7.png" ]
ice cream “Byakuya,” , mirrorless camera shot with manual control settings, shutter speed 1/10, aperture f/2.8, ISO setting is 800, macro lens, focal length of 60mm to 100mm, cooking tv show -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: [ice cream “Byakuya,” , mirrorless camera shot with manual control settings, shutter speed 1/10, aperture f/2.8, ISO setting is 800, macro lens, focal length of 60mm to 100mm, cooking tv show -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003797/0.png", "winvideos/003797/1.png", "winvideos/003797/2.png", "winvideos/003797/3.png", "winvideos/003797/4.png", "winvideos/003797/5.png", "winvideos/003797/6.png", "winvideos/003797/7.png", "losevideos/003797/0.png", "losevideos/003797/1.png", "losevideos/003797/2.png", "losevideos/003797/3.png", "losevideos/003797/4.png", "losevideos/003797/5.png", "losevideos/003797/6.png", "losevideos/003797/7.png" ]
PIGS soviet propaganda darth biden pig cops police state fascists arrest violence fires riots burning city -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: [PIGS soviet propaganda darth biden pig cops police state fascists arrest violence fires riots burning city -motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002326/0.png", "losevideos/002326/1.png", "losevideos/002326/2.png", "losevideos/002326/3.png", "losevideos/002326/4.png", "losevideos/002326/5.png", "losevideos/002326/6.png", "losevideos/002326/7.png", "winvideos/002326/0.png", "winvideos/002326/1.png", "winvideos/002326/2.png", "winvideos/002326/3.png", "winvideos/002326/4.png", "winvideos/002326/5.png", "winvideos/002326/6.png", "winvideos/002326/7.png" ]
caricature of an american couple in an airplane above the colosseum.	[ { "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: [caricature of an american couple in an airplane above the colosseum.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006303/0.png", "losevideos/006303/1.png", "losevideos/006303/2.png", "losevideos/006303/3.png", "losevideos/006303/4.png", "losevideos/006303/5.png", "losevideos/006303/6.png", "losevideos/006303/7.png", "winvideos/006303/0.png", "winvideos/006303/1.png", "winvideos/006303/2.png", "winvideos/006303/3.png", "winvideos/006303/4.png", "winvideos/006303/5.png", "winvideos/006303/6.png", "winvideos/006303/7.png" ]
Anonymous epic animated video.	[ { "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: [Anonymous epic animated video.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007594/0.png", "winvideos/007594/1.png", "winvideos/007594/2.png", "winvideos/007594/3.png", "winvideos/007594/4.png", "winvideos/007594/5.png", "winvideos/007594/6.png", "winvideos/007594/7.png", "losevideos/007594/0.png", "losevideos/007594/1.png", "losevideos/007594/2.png", "losevideos/007594/3.png", "losevideos/007594/4.png", "losevideos/007594/5.png", "losevideos/007594/6.png", "losevideos/007594/7.png" ]