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
Doraemon Style Cartoon AnimationVideo Ad Magic World While Lucas, a skilled archer, was known for his unwavering courage and quick reflexes. 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: [Doraemon Style Cartoon AnimationVideo Ad Magic World While Lucas, a skilled archer, was known for his unwavering courage and quick reflexes. Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000750/0.png", "winvideos/000750/1.png", "winvideos/000750/2.png", "winvideos/000750/3.png", "winvideos/000750/4.png", "winvideos/000750/5.png", "winvideos/000750/6.png", "winvideos/000750/7.png", "losevideos/000750/0.png", "losevideos/000750/1.png", "losevideos/000750/2.png", "losevideos/000750/3.png", "losevideos/000750/4.png", "losevideos/000750/5.png", "losevideos/000750/6.png", "losevideos/000750/7.png" ]
green screen video of an evil jack-o-lantern.	[ { "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: [green screen video of an evil jack-o-lantern.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003378/0.png", "losevideos/003378/1.png", "losevideos/003378/2.png", "losevideos/003378/3.png", "losevideos/003378/4.png", "losevideos/003378/5.png", "losevideos/003378/6.png", "losevideos/003378/7.png", "winvideos/003378/0.png", "winvideos/003378/1.png", "winvideos/003378/2.png", "winvideos/003378/3.png", "winvideos/003378/4.png", "winvideos/003378/5.png", "winvideos/003378/6.png", "winvideos/003378/7.png" ]
Iridescent vase falling to break into lots of pieces , sad ! -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: [Iridescent vase falling to break into lots of pieces , sad ! -motion 2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000627/0.png", "winvideos/000627/1.png", "winvideos/000627/2.png", "winvideos/000627/3.png", "winvideos/000627/4.png", "winvideos/000627/5.png", "winvideos/000627/6.png", "winvideos/000627/7.png", "losevideos/000627/0.png", "losevideos/000627/1.png", "losevideos/000627/2.png", "losevideos/000627/3.png", "losevideos/000627/4.png", "losevideos/000627/5.png", "losevideos/000627/6.png", "losevideos/000627/7.png" ]
fairy dancing at woods on sunset dusk -neg "bad hands, wrong hands, simplify, separated_body_parts, bad bodies, wrong bodies, blurry, distorted, low resolution, poorly drawing, poorly textured, poorly resolution, face, head" -motion 4 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: [fairy dancing at woods on sunset dusk -neg "bad hands, wrong hands, simplify, separated_body_parts, bad bodies, wrong bodies, blurry, distorted, low resolution, poorly drawing, poorly textured, poorly resolution, face, head" -motion 4 Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005296/0.png", "losevideos/005296/1.png", "losevideos/005296/2.png", "losevideos/005296/3.png", "losevideos/005296/4.png", "losevideos/005296/5.png", "losevideos/005296/6.png", "losevideos/005296/7.png", "winvideos/005296/0.png", "winvideos/005296/1.png", "winvideos/005296/2.png", "winvideos/005296/3.png", "winvideos/005296/4.png", "winvideos/005296/5.png", "winvideos/005296/6.png", "winvideos/005296/7.png" ]
In a very magnificent palace, a beautiful woman in red clothes slowly walks, barefoot, red dress, smooth skin, long black hair, 4k, 70mm shooting, ellen jewett, ultra-high definition, mythology, -- 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: [In a very magnificent palace, a beautiful woman in red clothes slowly walks, barefoot, red dress, smooth skin, long black hair, 4k, 70mm shooting, ellen jewett, ultra-high definition, mythology, -- ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003300/0.png", "winvideos/003300/1.png", "winvideos/003300/2.png", "winvideos/003300/3.png", "winvideos/003300/4.png", "winvideos/003300/5.png", "winvideos/003300/6.png", "winvideos/003300/7.png", "losevideos/003300/0.png", "losevideos/003300/1.png", "losevideos/003300/2.png", "losevideos/003300/3.png", "losevideos/003300/4.png", "losevideos/003300/5.png", "losevideos/003300/6.png", "losevideos/003300/7.png" ]
a device electrical get damaged because short circuit.	[ { "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 device electrical get damaged because short circuit.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007727/0.png", "losevideos/007727/1.png", "losevideos/007727/2.png", "losevideos/007727/3.png", "losevideos/007727/4.png", "losevideos/007727/5.png", "losevideos/007727/6.png", "losevideos/007727/7.png", "winvideos/007727/0.png", "winvideos/007727/1.png", "winvideos/007727/2.png", "winvideos/007727/3.png", "winvideos/007727/4.png", "winvideos/007727/5.png", "winvideos/007727/6.png", "winvideos/007727/7.png" ]
for moving wings of horse in image.	[ { "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: [for moving wings of horse in image.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002704/0.png", "losevideos/002704/1.png", "losevideos/002704/2.png", "losevideos/002704/3.png", "losevideos/002704/4.png", "losevideos/002704/5.png", "losevideos/002704/6.png", "losevideos/002704/7.png", "winvideos/002704/0.png", "winvideos/002704/1.png", "winvideos/002704/2.png", "winvideos/002704/3.png", "winvideos/002704/4.png", "winvideos/002704/5.png", "winvideos/002704/6.png", "winvideos/002704/7.png" ]
Maximum Extreme Hyper realistic, Maximum Extreme Hyper Detailed, Maximum Extreme Hyper Sharp, Maximum Extreme Hyper Crisp, Maximum Extreme Closeup, Front Facing, Full Body, Portrait View, goddess(a woman who is adored, especially for her beauty), dressed in an old style Ancient Orthodox dress and head covering, <img loading="lazy" class="chatlog__emoji " alt="💇" title="person_getting_haircut" src="https://cdn.jsdelivr.net/gh/twitter/twemoji@latest/assets/svg/1f487.svg"> Water-ready hair: Promote longer scalp hair to insulate against cold and aid in the buoyancy of infants., -neg "camera, statue, painting, drawing, art, game, pagan, occult, inadequate, incomplete, inaccurate, outdated, obsolete, ineffective, unreliable, irrelevant, unrealistic, immodest, unprofessional, explicit, inappropriate, sensitive, offensive, uncultured, uneducated, illiterate, unscientific, unorthodox, uncanonical, ecumenism, antichrist, demonic, satanic, uniate, unethical, false, untrue, conspiracy, unsafe, misleading, scandal, unnatural, immoral, ugly, deformed, deformity, deformities, illness, sickness, disease, disorder, allusion, video, entertainment, idol, toy, doll, micro, microscopic, scifi, photograph, picture, image, artwork, movie, television, fiction, science fiction, book, 3d, cartoon, malfunctioned things, low quality, funkiness, malfunctioned body parts, extra hands, extra faces, extra legs, unrealistic shape, unusual, weird face, deformed body parts, over makeup".	[ { "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: [Maximum Extreme Hyper realistic, Maximum Extreme Hyper Detailed, Maximum Extreme Hyper Sharp, Maximum Extreme Hyper Crisp, Maximum Extreme Closeup, Front Facing, Full Body, Portrait View,\n\ngoddess(a woman who is adored, especially for her beauty),\n\ndressed in an old style Ancient Orthodox dress and head covering,\n\n<img\n loading=\"lazy\"\n class=\"chatlog__emoji \"\n alt=\"💇\"\n title=\"person_getting_haircut\"\n src=\"https://cdn.jsdelivr.net/gh/twitter/twemoji@latest/assets/svg/1f487.svg\"> Water-ready hair: Promote longer scalp hair to insulate against cold and aid in the buoyancy of infants.,\n\n-neg "camera, statue, painting, drawing, art, game, pagan, occult, inadequate, incomplete, inaccurate, outdated, obsolete, ineffective, unreliable, irrelevant, unrealistic, immodest, unprofessional, explicit, inappropriate, sensitive, offensive, uncultured, uneducated, illiterate, unscientific, unorthodox, uncanonical, ecumenism, antichrist, demonic, satanic, uniate, unethical, false, untrue, conspiracy, unsafe, misleading, scandal, unnatural, immoral, ugly, deformed, deformity, deformities, illness, sickness, disease, disorder, allusion, video, entertainment, idol, toy, doll, micro, microscopic, scifi, photograph, picture, image, artwork, movie, television, fiction, science fiction, book, 3d, cartoon, malfunctioned things, low quality, funkiness, malfunctioned body parts, extra hands, extra faces, extra legs, unrealistic shape, unusual, weird face, deformed body parts, over makeup".]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000742/0.png", "losevideos/000742/1.png", "losevideos/000742/2.png", "losevideos/000742/3.png", "losevideos/000742/4.png", "losevideos/000742/5.png", "losevideos/000742/6.png", "losevideos/000742/7.png", "winvideos/000742/0.png", "winvideos/000742/1.png", "winvideos/000742/2.png", "winvideos/000742/3.png", "winvideos/000742/4.png", "winvideos/000742/5.png", "winvideos/000742/6.png", "winvideos/000742/7.png" ]
art by Karen Kopal.	[ { "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: [art by Karen Kopal.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005637/0.png", "winvideos/005637/1.png", "winvideos/005637/2.png", "winvideos/005637/3.png", "winvideos/005637/4.png", "winvideos/005637/5.png", "winvideos/005637/6.png", "winvideos/005637/7.png", "losevideos/005637/0.png", "losevideos/005637/1.png", "losevideos/005637/2.png", "losevideos/005637/3.png", "losevideos/005637/4.png", "losevideos/005637/5.png", "losevideos/005637/6.png", "losevideos/005637/7.png" ]
artistic text of "stand up again" on the background of a deserted forest and one new tree growing up, messaging should be inspirational, clear 4k clip.	[ { "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: [artistic text of "stand up again" on the background of a deserted forest and one new tree growing up, messaging should be inspirational, clear 4k clip.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000885/0.png", "losevideos/000885/1.png", "losevideos/000885/2.png", "losevideos/000885/3.png", "losevideos/000885/4.png", "losevideos/000885/5.png", "losevideos/000885/6.png", "losevideos/000885/7.png", "winvideos/000885/0.png", "winvideos/000885/1.png", "winvideos/000885/2.png", "winvideos/000885/3.png", "winvideos/000885/4.png", "winvideos/000885/5.png", "winvideos/000885/6.png", "winvideos/000885/7.png" ]
an animation of a beautiful girl sitting on a swing and crying at night.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [an animation of a beautiful girl sitting on a swing and crying at night.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009703/0.png", "losevideos/009703/1.png", "losevideos/009703/2.png", "losevideos/009703/3.png", "losevideos/009703/4.png", "losevideos/009703/5.png", "losevideos/009703/6.png", "losevideos/009703/7.png", "winvideos/009703/0.png", "winvideos/009703/1.png", "winvideos/009703/2.png", "winvideos/009703/3.png", "winvideos/009703/4.png", "winvideos/009703/5.png", "winvideos/009703/6.png", "winvideos/009703/7.png" ]
Close-up of a woman's face, eyes amazed by the magical projections in matrix movie cimmetery, tombs around, minimalistic composition, constrast ligths, 90's, utra realistic, ultra wide, ultra detailed, natural blur, moonight -camera zoom 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: [Close-up of a woman's face, eyes amazed by the magical projections in matrix movie cimmetery, tombs around, minimalistic composition, constrast ligths, 90's, utra realistic, ultra wide, ultra detailed, natural blur, moonight -camera zoom out.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007305/0.png", "winvideos/007305/1.png", "winvideos/007305/2.png", "winvideos/007305/3.png", "winvideos/007305/4.png", "winvideos/007305/5.png", "winvideos/007305/6.png", "winvideos/007305/7.png", "losevideos/007305/0.png", "losevideos/007305/1.png", "losevideos/007305/2.png", "losevideos/007305/3.png", "losevideos/007305/4.png", "losevideos/007305/5.png", "losevideos/007305/6.png", "losevideos/007305/7.png" ]
An astronaut stranded on a distant planet receives mysterious messages from an entity claiming to be the planet itself.	[ { "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 astronaut stranded on a distant planet receives mysterious messages from an entity claiming to be the planet itself.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000533/0.png", "winvideos/000533/1.png", "winvideos/000533/2.png", "winvideos/000533/3.png", "winvideos/000533/4.png", "winvideos/000533/5.png", "winvideos/000533/6.png", "winvideos/000533/7.png", "losevideos/000533/0.png", "losevideos/000533/1.png", "losevideos/000533/2.png", "losevideos/000533/3.png", "losevideos/000533/4.png", "losevideos/000533/5.png", "losevideos/000533/6.png", "losevideos/000533/7.png" ]
gesture pencil sketch of an image you can see half of the sky without clouds and half with clouds changing and moving fast in the wind , dramatic scene , low angle.	[ { "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: [gesture pencil sketch of an image you can see half of the sky without clouds and half with clouds changing and moving fast in the wind , dramatic scene , low angle.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008121/0.png", "losevideos/008121/1.png", "losevideos/008121/2.png", "losevideos/008121/3.png", "losevideos/008121/4.png", "losevideos/008121/5.png", "losevideos/008121/6.png", "losevideos/008121/7.png", "winvideos/008121/0.png", "winvideos/008121/1.png", "winvideos/008121/2.png", "winvideos/008121/3.png", "winvideos/008121/4.png", "winvideos/008121/5.png", "winvideos/008121/6.png", "winvideos/008121/7.png" ]
Zhang San and Li Si are in the R&D room, discussing design drawings, with a busy R&D scene in the 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: [Zhang San and Li Si are in the R&D room, discussing design drawings, with a busy R&D scene in the background.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004544/0.png", "winvideos/004544/1.png", "winvideos/004544/2.png", "winvideos/004544/3.png", "winvideos/004544/4.png", "winvideos/004544/5.png", "winvideos/004544/6.png", "winvideos/004544/7.png", "losevideos/004544/0.png", "losevideos/004544/1.png", "losevideos/004544/2.png", "losevideos/004544/3.png", "losevideos/004544/4.png", "losevideos/004544/5.png", "losevideos/004544/6.png", "losevideos/004544/7.png" ]
brilliant HD multicolored laser show, dj fog lingering in the air highlighting the beams of light 4k.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [brilliant HD multicolored laser show, dj fog lingering in the air highlighting the beams of light 4k.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000857/0.png", "winvideos/000857/1.png", "winvideos/000857/2.png", "winvideos/000857/3.png", "winvideos/000857/4.png", "winvideos/000857/5.png", "winvideos/000857/6.png", "winvideos/000857/7.png", "losevideos/000857/0.png", "losevideos/000857/1.png", "losevideos/000857/2.png", "losevideos/000857/3.png", "losevideos/000857/4.png", "losevideos/000857/5.png", "losevideos/000857/6.png", "losevideos/000857/7.png" ]
a movie title called Stay Inside.	[ { "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 movie title called Stay Inside.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003649/0.png", "winvideos/003649/1.png", "winvideos/003649/2.png", "winvideos/003649/3.png", "winvideos/003649/4.png", "winvideos/003649/5.png", "winvideos/003649/6.png", "winvideos/003649/7.png", "losevideos/003649/0.png", "losevideos/003649/1.png", "losevideos/003649/2.png", "losevideos/003649/3.png", "losevideos/003649/4.png", "losevideos/003649/5.png", "losevideos/003649/6.png", "losevideos/003649/7.png" ]
a 3d cartoon brain reading a book in library , a lamp on his head.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a 3d cartoon brain reading a book in library , a lamp on his head.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002057/0.png", "winvideos/002057/1.png", "winvideos/002057/2.png", "winvideos/002057/3.png", "winvideos/002057/4.png", "winvideos/002057/5.png", "winvideos/002057/6.png", "winvideos/002057/7.png", "losevideos/002057/0.png", "losevideos/002057/1.png", "losevideos/002057/2.png", "losevideos/002057/3.png", "losevideos/002057/4.png", "losevideos/002057/5.png", "losevideos/002057/6.png", "losevideos/002057/7.png" ]
a saint bernard dog save a man's life by pulling him out of the snow.	[ { "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 saint bernard dog save a man's life by pulling him out of the snow.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000569/0.png", "losevideos/000569/1.png", "losevideos/000569/2.png", "losevideos/000569/3.png", "losevideos/000569/4.png", "losevideos/000569/5.png", "losevideos/000569/6.png", "losevideos/000569/7.png", "winvideos/000569/0.png", "winvideos/000569/1.png", "winvideos/000569/2.png", "winvideos/000569/3.png", "winvideos/000569/4.png", "winvideos/000569/5.png", "winvideos/000569/6.png", "winvideos/000569/7.png" ]
strawberry in a tutu skirt.	[ { "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: [strawberry in a tutu skirt.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001557/0.png", "winvideos/001557/1.png", "winvideos/001557/2.png", "winvideos/001557/3.png", "winvideos/001557/4.png", "winvideos/001557/5.png", "winvideos/001557/6.png", "winvideos/001557/7.png", "losevideos/001557/0.png", "losevideos/001557/1.png", "losevideos/001557/2.png", "losevideos/001557/3.png", "losevideos/001557/4.png", "losevideos/001557/5.png", "losevideos/001557/6.png", "losevideos/001557/7.png" ]
the Lord of the rings the fellowship of the ring title.	[ { "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 Lord of the rings the fellowship of the ring title.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004844/0.png", "losevideos/004844/1.png", "losevideos/004844/2.png", "losevideos/004844/3.png", "losevideos/004844/4.png", "losevideos/004844/5.png", "losevideos/004844/6.png", "losevideos/004844/7.png", "winvideos/004844/0.png", "winvideos/004844/1.png", "winvideos/004844/2.png", "winvideos/004844/3.png", "winvideos/004844/4.png", "winvideos/004844/5.png", "winvideos/004844/6.png", "winvideos/004844/7.png" ]
one white and one black cats sitting under a street tree --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: [one white and one black cats sitting under a street tree --video.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004500/0.png", "winvideos/004500/1.png", "winvideos/004500/2.png", "winvideos/004500/3.png", "winvideos/004500/4.png", "winvideos/004500/5.png", "winvideos/004500/6.png", "winvideos/004500/7.png", "losevideos/004500/0.png", "losevideos/004500/1.png", "losevideos/004500/2.png", "losevideos/004500/3.png", "losevideos/004500/4.png", "losevideos/004500/5.png", "losevideos/004500/6.png", "losevideos/004500/7.png" ]
We see a city skyline. We see a car driving into town. We follow the car - flying just behind it. We Fly into the canyons of the high rise office buildings. rising up from the car. We turn and fly down a street. We suddenly turn And Fly through window of building and into an office.	[ { "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: [We see a city skyline. We see a car driving into town. We follow the car - flying just behind it. We Fly into the canyons of the high rise office buildings. rising up from the car. We turn and fly down a street. We suddenly turn And Fly through window of building and into an office.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007752/0.png", "losevideos/007752/1.png", "losevideos/007752/2.png", "losevideos/007752/3.png", "losevideos/007752/4.png", "losevideos/007752/5.png", "losevideos/007752/6.png", "losevideos/007752/7.png", "winvideos/007752/0.png", "winvideos/007752/1.png", "winvideos/007752/2.png", "winvideos/007752/3.png", "winvideos/007752/4.png", "winvideos/007752/5.png", "winvideos/007752/6.png", "winvideos/007752/7.png" ]
a goofy 3D cartoon purple and orange gekko. standing on back legs. In the style of cocomelon.	[ { "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 goofy 3D cartoon purple and orange gekko. standing on back legs. In the style of cocomelon.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006468/0.png", "winvideos/006468/1.png", "winvideos/006468/2.png", "winvideos/006468/3.png", "winvideos/006468/4.png", "winvideos/006468/5.png", "winvideos/006468/6.png", "winvideos/006468/7.png", "losevideos/006468/0.png", "losevideos/006468/1.png", "losevideos/006468/2.png", "losevideos/006468/3.png", "losevideos/006468/4.png", "losevideos/006468/5.png", "losevideos/006468/6.png", "losevideos/006468/7.png" ]
black and white prince is playing guitar motion 2 -fps 16 --ar 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [black and white prince is playing guitar motion 2 -fps 16 --ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004383/0.png", "losevideos/004383/1.png", "losevideos/004383/2.png", "losevideos/004383/3.png", "losevideos/004383/4.png", "losevideos/004383/5.png", "losevideos/004383/6.png", "losevideos/004383/7.png", "winvideos/004383/0.png", "winvideos/004383/1.png", "winvideos/004383/2.png", "winvideos/004383/3.png", "winvideos/004383/4.png", "winvideos/004383/5.png", "winvideos/004383/6.png", "winvideos/004383/7.png" ]
Ancient study room, Middle-aged minister and young assassin, Handing over a secret letter and attentively listening, Realistic, Dim lighting, Dark tones, Frontal view, Highly detailed,.	[ { "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: [Ancient study room, Middle-aged minister and young assassin, Handing over a secret letter and attentively listening, Realistic, Dim lighting, Dark tones, Frontal view, Highly detailed,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005124/0.png", "winvideos/005124/1.png", "winvideos/005124/2.png", "winvideos/005124/3.png", "winvideos/005124/4.png", "winvideos/005124/5.png", "winvideos/005124/6.png", "winvideos/005124/7.png", "losevideos/005124/0.png", "losevideos/005124/1.png", "losevideos/005124/2.png", "losevideos/005124/3.png", "losevideos/005124/4.png", "losevideos/005124/5.png", "losevideos/005124/6.png", "losevideos/005124/7.png" ]
honey bottle break.	[ { "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: [honey bottle break.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007077/0.png", "losevideos/007077/1.png", "losevideos/007077/2.png", "losevideos/007077/3.png", "losevideos/007077/4.png", "losevideos/007077/5.png", "losevideos/007077/6.png", "losevideos/007077/7.png", "winvideos/007077/0.png", "winvideos/007077/1.png", "winvideos/007077/2.png", "winvideos/007077/3.png", "winvideos/007077/4.png", "winvideos/007077/5.png", "winvideos/007077/6.png", "winvideos/007077/7.png" ]
prompt:A cute happy Corgi playing in park, sunset, pixel art -seed 8194302.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [prompt:A cute happy Corgi playing in park, sunset, pixel art -seed 8194302.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003622/0.png", "losevideos/003622/1.png", "losevideos/003622/2.png", "losevideos/003622/3.png", "losevideos/003622/4.png", "losevideos/003622/5.png", "losevideos/003622/6.png", "losevideos/003622/7.png", "winvideos/003622/0.png", "winvideos/003622/1.png", "winvideos/003622/2.png", "winvideos/003622/3.png", "winvideos/003622/4.png", "winvideos/003622/5.png", "winvideos/003622/6.png", "winvideos/003622/7.png" ]
sci-fi panda, dancing with a fox, in a office, cinematic shot.	[ { "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: [sci-fi panda, dancing with a fox, in a office, cinematic shot.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004547/0.png", "winvideos/004547/1.png", "winvideos/004547/2.png", "winvideos/004547/3.png", "winvideos/004547/4.png", "winvideos/004547/5.png", "winvideos/004547/6.png", "winvideos/004547/7.png", "losevideos/004547/0.png", "losevideos/004547/1.png", "losevideos/004547/2.png", "losevideos/004547/3.png", "losevideos/004547/4.png", "losevideos/004547/5.png", "losevideos/004547/6.png", "losevideos/004547/7.png" ]
a pretty with a underwear.	[ { "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 pretty with a underwear.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007839/0.png", "losevideos/007839/1.png", "losevideos/007839/2.png", "losevideos/007839/3.png", "losevideos/007839/4.png", "losevideos/007839/5.png", "losevideos/007839/6.png", "losevideos/007839/7.png", "winvideos/007839/0.png", "winvideos/007839/1.png", "winvideos/007839/2.png", "winvideos/007839/3.png", "winvideos/007839/4.png", "winvideos/007839/5.png", "winvideos/007839/6.png", "winvideos/007839/7.png" ]
We see a cartoon leprechaun sitting at a tiny desk, looking very serious and studious, surrounded by stacks of gold coins. Suddenly, the leprechaun sneezes, causing the stacks of gold coins to topple over in a comical fashion, sending coins flying everywhere. The leprechaun looks around sheepishly as the coins continue to rain down, with a playful wink to the camera.	[ { "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: [We see a cartoon leprechaun sitting at a tiny desk, looking very serious and studious, surrounded by stacks of gold coins. Suddenly, the leprechaun sneezes, causing the stacks of gold coins to topple over in a comical fashion, sending coins flying everywhere. The leprechaun looks around sheepishly as the coins continue to rain down, with a playful wink to the camera.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001761/0.png", "losevideos/001761/1.png", "losevideos/001761/2.png", "losevideos/001761/3.png", "losevideos/001761/4.png", "losevideos/001761/5.png", "losevideos/001761/6.png", "losevideos/001761/7.png", "winvideos/001761/0.png", "winvideos/001761/1.png", "winvideos/001761/2.png", "winvideos/001761/3.png", "winvideos/001761/4.png", "winvideos/001761/5.png", "winvideos/001761/6.png", "winvideos/001761/7.png" ]
caotic soul in darkness.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [caotic soul in darkness.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001631/0.png", "winvideos/001631/1.png", "winvideos/001631/2.png", "winvideos/001631/3.png", "winvideos/001631/4.png", "winvideos/001631/5.png", "winvideos/001631/6.png", "winvideos/001631/7.png", "losevideos/001631/0.png", "losevideos/001631/1.png", "losevideos/001631/2.png", "losevideos/001631/3.png", "losevideos/001631/4.png", "losevideos/001631/5.png", "losevideos/001631/6.png", "losevideos/001631/7.png" ]
uma cidade submersa sob as águas.	[ { "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: [uma cidade submersa sob as águas.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000554/0.png", "losevideos/000554/1.png", "losevideos/000554/2.png", "losevideos/000554/3.png", "losevideos/000554/4.png", "losevideos/000554/5.png", "losevideos/000554/6.png", "losevideos/000554/7.png", "winvideos/000554/0.png", "winvideos/000554/1.png", "winvideos/000554/2.png", "winvideos/000554/3.png", "winvideos/000554/4.png", "winvideos/000554/5.png", "winvideos/000554/6.png", "winvideos/000554/7.png" ]
create me a 30 second video about a dog getting abducted by aliens.	[ { "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 me a 30 second video about a dog getting abducted by aliens.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006688/0.png", "losevideos/006688/1.png", "losevideos/006688/2.png", "losevideos/006688/3.png", "losevideos/006688/4.png", "losevideos/006688/5.png", "losevideos/006688/6.png", "losevideos/006688/7.png", "winvideos/006688/0.png", "winvideos/006688/1.png", "winvideos/006688/2.png", "winvideos/006688/3.png", "winvideos/006688/4.png", "winvideos/006688/5.png", "winvideos/006688/6.png", "winvideos/006688/7.png" ]
two lesbians adopt a baby.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [two lesbians adopt a baby.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009369/0.png", "winvideos/009369/1.png", "winvideos/009369/2.png", "winvideos/009369/3.png", "winvideos/009369/4.png", "winvideos/009369/5.png", "winvideos/009369/6.png", "winvideos/009369/7.png", "losevideos/009369/0.png", "losevideos/009369/1.png", "losevideos/009369/2.png", "losevideos/009369/3.png", "losevideos/009369/4.png", "losevideos/009369/5.png", "losevideos/009369/6.png", "losevideos/009369/7.png" ]
a testudo running in a field.	[ { "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 testudo running in a field.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004910/0.png", "losevideos/004910/1.png", "losevideos/004910/2.png", "losevideos/004910/3.png", "losevideos/004910/4.png", "losevideos/004910/5.png", "losevideos/004910/6.png", "losevideos/004910/7.png", "winvideos/004910/0.png", "winvideos/004910/1.png", "winvideos/004910/2.png", "winvideos/004910/3.png", "winvideos/004910/4.png", "winvideos/004910/5.png", "winvideos/004910/6.png", "winvideos/004910/7.png" ]
CG rendering of android musicians with beautiful faces and alternative-hair performing music with futuristic musical instruments by Bruce Pennington and Tom Bagshaw, unreal engine, featured on cgsociety, blade runner, hellraiser, newcollapse band, intricate fractals and motifs -gs 10.	[ { "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: [CG rendering of android musicians with beautiful faces and alternative-hair performing music with futuristic musical instruments by Bruce Pennington and Tom Bagshaw, unreal engine, featured on cgsociety, blade runner, hellraiser, newcollapse band, intricate fractals and motifs -gs 10.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007943/0.png", "losevideos/007943/1.png", "losevideos/007943/2.png", "losevideos/007943/3.png", "losevideos/007943/4.png", "losevideos/007943/5.png", "losevideos/007943/6.png", "losevideos/007943/7.png", "winvideos/007943/0.png", "winvideos/007943/1.png", "winvideos/007943/2.png", "winvideos/007943/3.png", "winvideos/007943/4.png", "winvideos/007943/5.png", "winvideos/007943/6.png", "winvideos/007943/7.png" ]
1970's art horror film real witches gathering with wizards in the forest smoking a large pipe.	[ { "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: [1970's art horror film real witches gathering with wizards in the forest smoking a large pipe.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009295/0.png", "winvideos/009295/1.png", "winvideos/009295/2.png", "winvideos/009295/3.png", "winvideos/009295/4.png", "winvideos/009295/5.png", "winvideos/009295/6.png", "winvideos/009295/7.png", "losevideos/009295/0.png", "losevideos/009295/1.png", "losevideos/009295/2.png", "losevideos/009295/3.png", "losevideos/009295/4.png", "losevideos/009295/5.png", "losevideos/009295/6.png", "losevideos/009295/7.png" ]
abandoned house in the nature -seed 4843471.	[ { "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: [abandoned house in the nature -seed 4843471.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005446/0.png", "winvideos/005446/1.png", "winvideos/005446/2.png", "winvideos/005446/3.png", "winvideos/005446/4.png", "winvideos/005446/5.png", "winvideos/005446/6.png", "winvideos/005446/7.png", "losevideos/005446/0.png", "losevideos/005446/1.png", "losevideos/005446/2.png", "losevideos/005446/3.png", "losevideos/005446/4.png", "losevideos/005446/5.png", "losevideos/005446/6.png", "losevideos/005446/7.png" ]
many nice frogs in water, moving and talking -gs16 -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: [many nice frogs in water, moving and talking -gs16 -motion 1.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009394/0.png", "winvideos/009394/1.png", "winvideos/009394/2.png", "winvideos/009394/3.png", "winvideos/009394/4.png", "winvideos/009394/5.png", "winvideos/009394/6.png", "winvideos/009394/7.png", "losevideos/009394/0.png", "losevideos/009394/1.png", "losevideos/009394/2.png", "losevideos/009394/3.png", "losevideos/009394/4.png", "losevideos/009394/5.png", "losevideos/009394/6.png", "losevideos/009394/7.png" ]