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
telescope pointing at the moon, with a clear view of the night sky -cinematic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [telescope pointing at the moon, with a clear view of the night sky -cinematic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009895/0.png", "losevideos/009895/1.png", "losevideos/009895/2.png", "losevideos/009895/3.png", "losevideos/009895/4.png", "losevideos/009895/5.png", "losevideos/009895/6.png", "losevideos/009895/7.png", "winvideos/009895/0.png", "winvideos/009895/1.png", "winvideos/009895/2.png", "winvideos/009895/3.png", "winvideos/009895/4.png", "winvideos/009895/5.png", "winvideos/009895/6.png", "winvideos/009895/7.png" ]
night lights woman walking from -camera zoom in.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [night lights woman walking from -camera zoom in.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005685/0.png", "losevideos/005685/1.png", "losevideos/005685/2.png", "losevideos/005685/3.png", "losevideos/005685/4.png", "losevideos/005685/5.png", "losevideos/005685/6.png", "losevideos/005685/7.png", "winvideos/005685/0.png", "winvideos/005685/1.png", "winvideos/005685/2.png", "winvideos/005685/3.png", "winvideos/005685/4.png", "winvideos/005685/5.png", "winvideos/005685/6.png", "winvideos/005685/7.png" ]
"Modern Human Origins: Explore the emergence of Homo sapiens as a species, utilizing 16:9 footage with a filmic quality level of 2.".	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: ["Modern Human Origins: Explore the emergence of Homo sapiens as a species, utilizing 16:9 footage with a filmic quality level of 2.".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003038/0.png", "losevideos/003038/1.png", "losevideos/003038/2.png", "losevideos/003038/3.png", "losevideos/003038/4.png", "losevideos/003038/5.png", "losevideos/003038/6.png", "losevideos/003038/7.png", "winvideos/003038/0.png", "winvideos/003038/1.png", "winvideos/003038/2.png", "winvideos/003038/3.png", "winvideos/003038/4.png", "winvideos/003038/5.png", "winvideos/003038/6.png", "winvideos/003038/7.png" ]
A Boy walking through the forest.	[ { "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 Boy walking through the forest.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009957/0.png", "winvideos/009957/1.png", "winvideos/009957/2.png", "winvideos/009957/3.png", "winvideos/009957/4.png", "winvideos/009957/5.png", "winvideos/009957/6.png", "winvideos/009957/7.png", "losevideos/009957/0.png", "losevideos/009957/1.png", "losevideos/009957/2.png", "losevideos/009957/3.png", "losevideos/009957/4.png", "losevideos/009957/5.png", "losevideos/009957/6.png", "losevideos/009957/7.png" ]
armed men stand in the foreground with a desert eagle zoom -bloom.	[ { "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: [armed men stand in the foreground with a desert eagle zoom -bloom.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004702/0.png", "losevideos/004702/1.png", "losevideos/004702/2.png", "losevideos/004702/3.png", "losevideos/004702/4.png", "losevideos/004702/5.png", "losevideos/004702/6.png", "losevideos/004702/7.png", "winvideos/004702/0.png", "winvideos/004702/1.png", "winvideos/004702/2.png", "winvideos/004702/3.png", "winvideos/004702/4.png", "winvideos/004702/5.png", "winvideos/004702/6.png", "winvideos/004702/7.png" ]
soccer football is slowly flying in the goal against night sky background, 3d animation.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [soccer football is slowly flying in the goal against night sky background, 3d animation.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001428/0.png", "winvideos/001428/1.png", "winvideos/001428/2.png", "winvideos/001428/3.png", "winvideos/001428/4.png", "winvideos/001428/5.png", "winvideos/001428/6.png", "winvideos/001428/7.png", "losevideos/001428/0.png", "losevideos/001428/1.png", "losevideos/001428/2.png", "losevideos/001428/3.png", "losevideos/001428/4.png", "losevideos/001428/5.png", "losevideos/001428/6.png", "losevideos/001428/7.png" ]
a woman in a meditation garden area by the waterfalls.	[ { "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 woman in a meditation garden area by the waterfalls.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009716/0.png", "winvideos/009716/1.png", "winvideos/009716/2.png", "winvideos/009716/3.png", "winvideos/009716/4.png", "winvideos/009716/5.png", "winvideos/009716/6.png", "winvideos/009716/7.png", "losevideos/009716/0.png", "losevideos/009716/1.png", "losevideos/009716/2.png", "losevideos/009716/3.png", "losevideos/009716/4.png", "losevideos/009716/5.png", "losevideos/009716/6.png", "losevideos/009716/7.png" ]
fobias.	[ { "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: [fobias.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009518/0.png", "losevideos/009518/1.png", "losevideos/009518/2.png", "losevideos/009518/3.png", "losevideos/009518/4.png", "losevideos/009518/5.png", "losevideos/009518/6.png", "losevideos/009518/7.png", "winvideos/009518/0.png", "winvideos/009518/1.png", "winvideos/009518/2.png", "winvideos/009518/3.png", "winvideos/009518/4.png", "winvideos/009518/5.png", "winvideos/009518/6.png", "winvideos/009518/7.png" ]
a woman walking on the beach -camera pan 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: [a woman walking on the beach -camera pan right.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004032/0.png", "losevideos/004032/1.png", "losevideos/004032/2.png", "losevideos/004032/3.png", "losevideos/004032/4.png", "losevideos/004032/5.png", "losevideos/004032/6.png", "losevideos/004032/7.png", "winvideos/004032/0.png", "winvideos/004032/1.png", "winvideos/004032/2.png", "winvideos/004032/3.png", "winvideos/004032/4.png", "winvideos/004032/5.png", "winvideos/004032/6.png", "winvideos/004032/7.png" ]
ocean life, strange, unnatural, mixed, -gs 24 -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: [ocean life, strange, unnatural, mixed, -gs 24 -motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005115/0.png", "losevideos/005115/1.png", "losevideos/005115/2.png", "losevideos/005115/3.png", "losevideos/005115/4.png", "losevideos/005115/5.png", "losevideos/005115/6.png", "losevideos/005115/7.png", "winvideos/005115/0.png", "winvideos/005115/1.png", "winvideos/005115/2.png", "winvideos/005115/3.png", "winvideos/005115/4.png", "winvideos/005115/5.png", "winvideos/005115/6.png", "winvideos/005115/7.png" ]
create a white and black lion with long teeth.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [create a white and black lion with long teeth.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000509/0.png", "losevideos/000509/1.png", "losevideos/000509/2.png", "losevideos/000509/3.png", "losevideos/000509/4.png", "losevideos/000509/5.png", "losevideos/000509/6.png", "losevideos/000509/7.png", "winvideos/000509/0.png", "winvideos/000509/1.png", "winvideos/000509/2.png", "winvideos/000509/3.png", "winvideos/000509/4.png", "winvideos/000509/5.png", "winvideos/000509/6.png", "winvideos/000509/7.png" ]
extraterrestrial spacecraft plunging to Earth. The scene opens on the vintage saucer-shaped ship glittering in the night sky, lights blinking across its metallic surface as it descends through thick clouds. Serene at first, ambient music swells as the craft starts spinning out of control, smoke trailing behind its erratic path. It emerges from the clouds in a freefall, tilting wildly and glinting in the moonlight before the ground rushes up to meet it. The crashed ship lays cracked open in a massive crater, flames and debris scattered around it, shadows dancing across the wreckage. The music stops abruptly, leaving only the hiss and flicker of the fires burning amongst the ruined alien machinery. The video pans up slowly to reveal the towering, otherworldly craftembedded dramatically in the dirt as the scene fades silently out.	[ { "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: [extraterrestrial spacecraft plunging to Earth. The scene opens on the vintage saucer-shaped ship glittering in the night sky, lights blinking across its metallic surface as it descends through thick clouds. Serene at first, ambient music swells as the craft starts spinning out of control, smoke trailing behind its erratic path. It emerges from the clouds in a freefall, tilting wildly and glinting in the moonlight before the ground rushes up to meet it. The crashed ship lays cracked open in a massive crater, flames and debris scattered around it, shadows dancing across the wreckage. The music stops abruptly, leaving only the hiss and flicker of the fires burning amongst the ruined alien machinery. The video pans up slowly to reveal the towering, otherworldly craftembedded dramatically in the dirt as the scene fades silently out.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006552/0.png", "winvideos/006552/1.png", "winvideos/006552/2.png", "winvideos/006552/3.png", "winvideos/006552/4.png", "winvideos/006552/5.png", "winvideos/006552/6.png", "winvideos/006552/7.png", "losevideos/006552/0.png", "losevideos/006552/1.png", "losevideos/006552/2.png", "losevideos/006552/3.png", "losevideos/006552/4.png", "losevideos/006552/5.png", "losevideos/006552/6.png", "losevideos/006552/7.png" ]
A mechanical owl particle dance visual, dark style, lights flash according to the music 8 beats, c4d, dark lights, centered, 4k, metal material, red and blue lights, 8 seconds.	[ { "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 mechanical owl particle dance visual, dark style, lights flash according to the music 8 beats, c4d, dark lights, centered, 4k, metal material, red and blue lights, 8 seconds.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007713/0.png", "winvideos/007713/1.png", "winvideos/007713/2.png", "winvideos/007713/3.png", "winvideos/007713/4.png", "winvideos/007713/5.png", "winvideos/007713/6.png", "winvideos/007713/7.png", "losevideos/007713/0.png", "losevideos/007713/1.png", "losevideos/007713/2.png", "losevideos/007713/3.png", "losevideos/007713/4.png", "losevideos/007713/5.png", "losevideos/007713/6.png", "losevideos/007713/7.png" ]
male playing magic.	[ { "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: [male playing magic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003639/0.png", "losevideos/003639/1.png", "losevideos/003639/2.png", "losevideos/003639/3.png", "losevideos/003639/4.png", "losevideos/003639/5.png", "losevideos/003639/6.png", "losevideos/003639/7.png", "winvideos/003639/0.png", "winvideos/003639/1.png", "winvideos/003639/2.png", "winvideos/003639/3.png", "winvideos/003639/4.png", "winvideos/003639/5.png", "winvideos/003639/6.png", "winvideos/003639/7.png" ]
landscape of a trippy and wavey world. retro film. cinematic lighting. colorful psychedelic.	[ { "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: [landscape of a trippy and wavey world. retro film. cinematic lighting. colorful psychedelic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005601/0.png", "losevideos/005601/1.png", "losevideos/005601/2.png", "losevideos/005601/3.png", "losevideos/005601/4.png", "losevideos/005601/5.png", "losevideos/005601/6.png", "losevideos/005601/7.png", "winvideos/005601/0.png", "winvideos/005601/1.png", "winvideos/005601/2.png", "winvideos/005601/3.png", "winvideos/005601/4.png", "winvideos/005601/5.png", "winvideos/005601/6.png", "winvideos/005601/7.png" ]
black punters walk among the trees in the forest.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: [black punters walk among the trees in the forest.8k.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003700/0.png", "winvideos/003700/1.png", "winvideos/003700/2.png", "winvideos/003700/3.png", "winvideos/003700/4.png", "winvideos/003700/5.png", "winvideos/003700/6.png", "winvideos/003700/7.png", "losevideos/003700/0.png", "losevideos/003700/1.png", "losevideos/003700/2.png", "losevideos/003700/3.png", "losevideos/003700/4.png", "losevideos/003700/5.png", "losevideos/003700/6.png", "losevideos/003700/7.png" ]
a village and there live a boy name alexandar.	[ { "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 and there live a boy name alexandar.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006887/0.png", "losevideos/006887/1.png", "losevideos/006887/2.png", "losevideos/006887/3.png", "losevideos/006887/4.png", "losevideos/006887/5.png", "losevideos/006887/6.png", "losevideos/006887/7.png", "winvideos/006887/0.png", "winvideos/006887/1.png", "winvideos/006887/2.png", "winvideos/006887/3.png", "winvideos/006887/4.png", "winvideos/006887/5.png", "winvideos/006887/6.png", "winvideos/006887/7.png" ]
A thirsty traveler beneath a dry tree in the desert, dynamic action, uhd 4k, Cinematic, zoom in, --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 thirsty traveler beneath a dry tree in the desert, dynamic action, uhd 4k, Cinematic, zoom in, --ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009052/0.png", "winvideos/009052/1.png", "winvideos/009052/2.png", "winvideos/009052/3.png", "winvideos/009052/4.png", "winvideos/009052/5.png", "winvideos/009052/6.png", "winvideos/009052/7.png", "losevideos/009052/0.png", "losevideos/009052/1.png", "losevideos/009052/2.png", "losevideos/009052/3.png", "losevideos/009052/4.png", "losevideos/009052/5.png", "losevideos/009052/6.png", "losevideos/009052/7.png" ]
Create a step-by-step tutorial on [specific tech task or software]. Help your viewers master a useful skill.".	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Create a step-by-step tutorial on [specific tech task or software]. Help your viewers master a useful skill.".]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007440/0.png", "winvideos/007440/1.png", "winvideos/007440/2.png", "winvideos/007440/3.png", "winvideos/007440/4.png", "winvideos/007440/5.png", "winvideos/007440/6.png", "winvideos/007440/7.png", "losevideos/007440/0.png", "losevideos/007440/1.png", "losevideos/007440/2.png", "losevideos/007440/3.png", "losevideos/007440/4.png", "losevideos/007440/5.png", "losevideos/007440/6.png", "losevideos/007440/7.png" ]
Twinkling star in dark night.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Twinkling star in dark night.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008912/0.png", "losevideos/008912/1.png", "losevideos/008912/2.png", "losevideos/008912/3.png", "losevideos/008912/4.png", "losevideos/008912/5.png", "losevideos/008912/6.png", "losevideos/008912/7.png", "winvideos/008912/0.png", "winvideos/008912/1.png", "winvideos/008912/2.png", "winvideos/008912/3.png", "winvideos/008912/4.png", "winvideos/008912/5.png", "winvideos/008912/6.png", "winvideos/008912/7.png" ]
purple worlds car racing.	[ { "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: [purple worlds car racing.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009498/0.png", "losevideos/009498/1.png", "losevideos/009498/2.png", "losevideos/009498/3.png", "losevideos/009498/4.png", "losevideos/009498/5.png", "losevideos/009498/6.png", "losevideos/009498/7.png", "winvideos/009498/0.png", "winvideos/009498/1.png", "winvideos/009498/2.png", "winvideos/009498/3.png", "winvideos/009498/4.png", "winvideos/009498/5.png", "winvideos/009498/6.png", "winvideos/009498/7.png" ]
gogeta is flying to escape majin buu, clean view.	[ { "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: [gogeta is flying to escape majin buu, clean view.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009276/0.png", "winvideos/009276/1.png", "winvideos/009276/2.png", "winvideos/009276/3.png", "winvideos/009276/4.png", "winvideos/009276/5.png", "winvideos/009276/6.png", "winvideos/009276/7.png", "losevideos/009276/0.png", "losevideos/009276/1.png", "losevideos/009276/2.png", "losevideos/009276/3.png", "losevideos/009276/4.png", "losevideos/009276/5.png", "losevideos/009276/6.png", "losevideos/009276/7.png" ]
Stairs of a dark and eerie basement, Švankmajer stop motion, stopmotion.	[ { "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: [Stairs of a dark and eerie basement, Švankmajer stop motion, stopmotion.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008348/0.png", "losevideos/008348/1.png", "losevideos/008348/2.png", "losevideos/008348/3.png", "losevideos/008348/4.png", "losevideos/008348/5.png", "losevideos/008348/6.png", "losevideos/008348/7.png", "winvideos/008348/0.png", "winvideos/008348/1.png", "winvideos/008348/2.png", "winvideos/008348/3.png", "winvideos/008348/4.png", "winvideos/008348/5.png", "winvideos/008348/6.png", "winvideos/008348/7.png" ]
a young African boy biting the head of a blue snake.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a young African boy biting the head of a blue snake.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001740/0.png", "losevideos/001740/1.png", "losevideos/001740/2.png", "losevideos/001740/3.png", "losevideos/001740/4.png", "losevideos/001740/5.png", "losevideos/001740/6.png", "losevideos/001740/7.png", "winvideos/001740/0.png", "winvideos/001740/1.png", "winvideos/001740/2.png", "winvideos/001740/3.png", "winvideos/001740/4.png", "winvideos/001740/5.png", "winvideos/001740/6.png", "winvideos/001740/7.png" ]
kirby eating a taci.	[ { "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: [kirby eating a taci.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006880/0.png", "winvideos/006880/1.png", "winvideos/006880/2.png", "winvideos/006880/3.png", "winvideos/006880/4.png", "winvideos/006880/5.png", "winvideos/006880/6.png", "winvideos/006880/7.png", "losevideos/006880/0.png", "losevideos/006880/1.png", "losevideos/006880/2.png", "losevideos/006880/3.png", "losevideos/006880/4.png", "losevideos/006880/5.png", "losevideos/006880/6.png", "losevideos/006880/7.png" ]
animated girl, standing in the rain, the street, 8k, she is sad, there are romantic streetlights, make it very real,.	[ { "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 girl, standing in the rain, the street, 8k, she is sad, there are romantic streetlights, make it very real,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006584/0.png", "winvideos/006584/1.png", "winvideos/006584/2.png", "winvideos/006584/3.png", "winvideos/006584/4.png", "winvideos/006584/5.png", "winvideos/006584/6.png", "winvideos/006584/7.png", "losevideos/006584/0.png", "losevideos/006584/1.png", "losevideos/006584/2.png", "losevideos/006584/3.png", "losevideos/006584/4.png", "losevideos/006584/5.png", "losevideos/006584/6.png", "losevideos/006584/7.png" ]
a visual dmt experience.	[ { "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 visual dmt experience.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005771/0.png", "winvideos/005771/1.png", "winvideos/005771/2.png", "winvideos/005771/3.png", "winvideos/005771/4.png", "winvideos/005771/5.png", "winvideos/005771/6.png", "winvideos/005771/7.png", "losevideos/005771/0.png", "losevideos/005771/1.png", "losevideos/005771/2.png", "losevideos/005771/3.png", "losevideos/005771/4.png", "losevideos/005771/5.png", "losevideos/005771/6.png", "losevideos/005771/7.png" ]
((cozy clear liquid noise), (fractal:0.1), (super realistic:9), (girl <img loading="lazy" class="chatlog__emoji " alt="👊" title="punch" src="https://cdn.jsdelivr.net/gh/twitter/twemoji@latest/assets/svg/1f44a.svg"> a boy )), (Good anatomy), (depth background), (animated background), (animated environment), (animated all characters), ((outpainting)), vibrant colors, nice light, ultra high quality, hd, 8k, super realistic, cinematic, -neg "(rectangular fractal noise), ((out of frame)), deformed, (bad anatomy), disfigured, (poorly drawn face), mutation, mutated, (extra limb), ugly, disgusting, (poorly drawn hands), (missing limb), (floating limbs), (disconnected limbs), (malformed hands), blurry, (mutated legs, hands and fingers), (immovable background), (static background), (fixed background), (lame characters), (hop), watermark, watermarked, oversaturated, censored, (distorted hands), amputation, (missing hands), obese, (doubled face), (double hands)" -motion 4 -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: [((cozy clear liquid noise), (fractal:0.1), (super realistic:9), (girl <img\n loading=\"lazy\"\n class=\"chatlog__emoji \"\n alt=\"👊\"\n title=\"punch\"\n src=\"https://cdn.jsdelivr.net/gh/twitter/twemoji@latest/assets/svg/1f44a.svg\"> a boy )), (Good anatomy), (depth background), (animated background), (animated environment), (animated all characters), ((outpainting)), vibrant colors, nice light, ultra high quality, hd, 8k, super realistic, cinematic, -neg "(rectangular fractal noise), ((out of frame)), deformed, (bad anatomy), disfigured, (poorly drawn face), mutation, mutated, (extra limb), ugly, disgusting, (poorly drawn hands), (missing limb), (floating limbs), (disconnected limbs), (malformed hands), blurry, (mutated legs, hands and fingers), (immovable background), (static background), (fixed background), (lame characters), (hop), watermark, watermarked, oversaturated, censored, (distorted hands), amputation, (missing hands), obese, (doubled face), (double hands)" -motion 4 -fps 24.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001555/0.png", "losevideos/001555/1.png", "losevideos/001555/2.png", "losevideos/001555/3.png", "losevideos/001555/4.png", "losevideos/001555/5.png", "losevideos/001555/6.png", "losevideos/001555/7.png", "winvideos/001555/0.png", "winvideos/001555/1.png", "winvideos/001555/2.png", "winvideos/001555/3.png", "winvideos/001555/4.png", "winvideos/001555/5.png", "winvideos/001555/6.png", "winvideos/001555/7.png" ]
caveman spear fighting alien type dinosaur in battle. desert background with weird plants and volcanoes in the distance.	[ { "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: [caveman spear fighting alien type dinosaur in battle. desert background with weird plants and volcanoes in the distance.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008664/0.png", "losevideos/008664/1.png", "losevideos/008664/2.png", "losevideos/008664/3.png", "losevideos/008664/4.png", "losevideos/008664/5.png", "losevideos/008664/6.png", "losevideos/008664/7.png", "winvideos/008664/0.png", "winvideos/008664/1.png", "winvideos/008664/2.png", "winvideos/008664/3.png", "winvideos/008664/4.png", "winvideos/008664/5.png", "winvideos/008664/6.png", "winvideos/008664/7.png" ]
The diverse array of beings from the magical world.	[ { "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 diverse array of beings from the magical world.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007411/0.png", "winvideos/007411/1.png", "winvideos/007411/2.png", "winvideos/007411/3.png", "winvideos/007411/4.png", "winvideos/007411/5.png", "winvideos/007411/6.png", "winvideos/007411/7.png", "losevideos/007411/0.png", "losevideos/007411/1.png", "losevideos/007411/2.png", "losevideos/007411/3.png", "losevideos/007411/4.png", "losevideos/007411/5.png", "losevideos/007411/6.png", "losevideos/007411/7.png" ]
3 astronaut walking corridor technology fusturistic blue led blue combinaison futuristic space window.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [3 astronaut walking corridor technology fusturistic blue led blue combinaison futuristic space window.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009568/0.png", "losevideos/009568/1.png", "losevideos/009568/2.png", "losevideos/009568/3.png", "losevideos/009568/4.png", "losevideos/009568/5.png", "losevideos/009568/6.png", "losevideos/009568/7.png", "winvideos/009568/0.png", "winvideos/009568/1.png", "winvideos/009568/2.png", "winvideos/009568/3.png", "winvideos/009568/4.png", "winvideos/009568/5.png", "winvideos/009568/6.png", "winvideos/009568/7.png" ]
Angela bassett with a big buttocks, Womancore, shot by alfred hitchcock, shot by terry richardson.	[ { "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: [Angela bassett with a big buttocks, Womancore, shot by alfred hitchcock, shot by terry richardson.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004331/0.png", "winvideos/004331/1.png", "winvideos/004331/2.png", "winvideos/004331/3.png", "winvideos/004331/4.png", "winvideos/004331/5.png", "winvideos/004331/6.png", "winvideos/004331/7.png", "losevideos/004331/0.png", "losevideos/004331/1.png", "losevideos/004331/2.png", "losevideos/004331/3.png", "losevideos/004331/4.png", "losevideos/004331/5.png", "losevideos/004331/6.png", "losevideos/004331/7.png" ]
sexy boy talking to camera close in out side Al 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: [sexy boy talking to camera close in out side Al video.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004502/0.png", "winvideos/004502/1.png", "winvideos/004502/2.png", "winvideos/004502/3.png", "winvideos/004502/4.png", "winvideos/004502/5.png", "winvideos/004502/6.png", "winvideos/004502/7.png", "losevideos/004502/0.png", "losevideos/004502/1.png", "losevideos/004502/2.png", "losevideos/004502/3.png", "losevideos/004502/4.png", "losevideos/004502/5.png", "losevideos/004502/6.png", "losevideos/004502/7.png" ]
a skeleton melting 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: [a skeleton melting in lava.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008124/0.png", "winvideos/008124/1.png", "winvideos/008124/2.png", "winvideos/008124/3.png", "winvideos/008124/4.png", "winvideos/008124/5.png", "winvideos/008124/6.png", "winvideos/008124/7.png", "losevideos/008124/0.png", "losevideos/008124/1.png", "losevideos/008124/2.png", "losevideos/008124/3.png", "losevideos/008124/4.png", "losevideos/008124/5.png", "losevideos/008124/6.png", "losevideos/008124/7.png" ]
godzilla walks home down motorway.	[ { "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: [godzilla walks home down motorway.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006773/0.png", "losevideos/006773/1.png", "losevideos/006773/2.png", "losevideos/006773/3.png", "losevideos/006773/4.png", "losevideos/006773/5.png", "losevideos/006773/6.png", "losevideos/006773/7.png", "winvideos/006773/0.png", "winvideos/006773/1.png", "winvideos/006773/2.png", "winvideos/006773/3.png", "winvideos/006773/4.png", "winvideos/006773/5.png", "winvideos/006773/6.png", "winvideos/006773/7.png" ]
país Chile mirado desde el espacio exterior.	[ { "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: [país Chile mirado desde el espacio exterior.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004399/0.png", "winvideos/004399/1.png", "winvideos/004399/2.png", "winvideos/004399/3.png", "winvideos/004399/4.png", "winvideos/004399/5.png", "winvideos/004399/6.png", "winvideos/004399/7.png", "losevideos/004399/0.png", "losevideos/004399/1.png", "losevideos/004399/2.png", "losevideos/004399/3.png", "losevideos/004399/4.png", "losevideos/004399/5.png", "losevideos/004399/6.png", "losevideos/004399/7.png" ]
Giant Eagle Is Flying And destroying The Building In The Largest City Of Moldova, DashCam Footage Filter.	[ { "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: [Giant Eagle Is Flying And destroying The Building In The Largest City Of Moldova, DashCam Footage Filter.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009783/0.png", "losevideos/009783/1.png", "losevideos/009783/2.png", "losevideos/009783/3.png", "losevideos/009783/4.png", "losevideos/009783/5.png", "losevideos/009783/6.png", "losevideos/009783/7.png", "winvideos/009783/0.png", "winvideos/009783/1.png", "winvideos/009783/2.png", "winvideos/009783/3.png", "winvideos/009783/4.png", "winvideos/009783/5.png", "winvideos/009783/6.png", "winvideos/009783/7.png" ]
looking in through a window.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [looking in through a window.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007267/0.png", "winvideos/007267/1.png", "winvideos/007267/2.png", "winvideos/007267/3.png", "winvideos/007267/4.png", "winvideos/007267/5.png", "winvideos/007267/6.png", "winvideos/007267/7.png", "losevideos/007267/0.png", "losevideos/007267/1.png", "losevideos/007267/2.png", "losevideos/007267/3.png", "losevideos/007267/4.png", "losevideos/007267/5.png", "losevideos/007267/6.png", "losevideos/007267/7.png" ]
a rotating travellers backpack set against a perfectly black background.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a rotating travellers backpack set against a perfectly black background.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009616/0.png", "losevideos/009616/1.png", "losevideos/009616/2.png", "losevideos/009616/3.png", "losevideos/009616/4.png", "losevideos/009616/5.png", "losevideos/009616/6.png", "losevideos/009616/7.png", "winvideos/009616/0.png", "winvideos/009616/1.png", "winvideos/009616/2.png", "winvideos/009616/3.png", "winvideos/009616/4.png", "winvideos/009616/5.png", "winvideos/009616/6.png", "winvideos/009616/7.png" ]
zoom in, lone man standing in field of swaying blades of grass, exquisite structure, full of complex details, hyper realistic, old western movie, vintage, cinematic , movie lighting, - gs 25, - motion 2.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [zoom in, lone man standing in field of swaying blades of grass, exquisite structure, full of complex details, hyper realistic, old western movie, vintage, cinematic , movie lighting, - gs 25, - motion 2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002084/0.png", "winvideos/002084/1.png", "winvideos/002084/2.png", "winvideos/002084/3.png", "winvideos/002084/4.png", "winvideos/002084/5.png", "winvideos/002084/6.png", "winvideos/002084/7.png", "losevideos/002084/0.png", "losevideos/002084/1.png", "losevideos/002084/2.png", "losevideos/002084/3.png", "losevideos/002084/4.png", "losevideos/002084/5.png", "losevideos/002084/6.png", "losevideos/002084/7.png" ]