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
a vintage dodge challenger on a dark street at night with tall buildings in the background and neon it street shops, it's raining, front view ar 16:9 -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: [a vintage dodge challenger on a dark street at night with tall buildings in the background and neon it street shops, it's raining, front view ar 16:9 -motion 2.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007393/0.png", "losevideos/007393/1.png", "losevideos/007393/2.png", "losevideos/007393/3.png", "losevideos/007393/4.png", "losevideos/007393/5.png", "losevideos/007393/6.png", "losevideos/007393/7.png", "winvideos/007393/0.png", "winvideos/007393/1.png", "winvideos/007393/2.png", "winvideos/007393/3.png", "winvideos/007393/4.png", "winvideos/007393/5.png", "winvideos/007393/6.png", "winvideos/007393/7.png" ]
illustration, caricature, black beady-eyed, funny little cat, with yellow very big eyes, with a cheeky smile, looking at the refrigerator door, trying to open the refrigerator door with his paw , micro detailing, high quality, 60 fps, ultra hd, double exposure.	[ { "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: [illustration, caricature, black beady-eyed, funny little cat, with yellow very big eyes, with a cheeky smile, looking at the refrigerator door, trying to open the refrigerator door with his paw , micro detailing, high quality, 60 fps, ultra hd, double exposure.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003748/0.png", "losevideos/003748/1.png", "losevideos/003748/2.png", "losevideos/003748/3.png", "losevideos/003748/4.png", "losevideos/003748/5.png", "losevideos/003748/6.png", "losevideos/003748/7.png", "winvideos/003748/0.png", "winvideos/003748/1.png", "winvideos/003748/2.png", "winvideos/003748/3.png", "winvideos/003748/4.png", "winvideos/003748/5.png", "winvideos/003748/6.png", "winvideos/003748/7.png" ]
how do you look.	[ { "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: [how do you look.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009105/0.png", "winvideos/009105/1.png", "winvideos/009105/2.png", "winvideos/009105/3.png", "winvideos/009105/4.png", "winvideos/009105/5.png", "winvideos/009105/6.png", "winvideos/009105/7.png", "losevideos/009105/0.png", "losevideos/009105/1.png", "losevideos/009105/2.png", "losevideos/009105/3.png", "losevideos/009105/4.png", "losevideos/009105/5.png", "losevideos/009105/6.png", "losevideos/009105/7.png" ]
animate 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: [animate cinematic.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000548/0.png", "winvideos/000548/1.png", "winvideos/000548/2.png", "winvideos/000548/3.png", "winvideos/000548/4.png", "winvideos/000548/5.png", "winvideos/000548/6.png", "winvideos/000548/7.png", "losevideos/000548/0.png", "losevideos/000548/1.png", "losevideos/000548/2.png", "losevideos/000548/3.png", "losevideos/000548/4.png", "losevideos/000548/5.png", "losevideos/000548/6.png", "losevideos/000548/7.png" ]
16:9, a red-haired woman in a red dress sitting on a chair in the dark opposite a red-haired woman in a red dress with black hair on top and blue hair on the bottom.	[ { "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: [16:9, a red-haired woman in a red dress sitting on a chair in the dark opposite a red-haired woman in a red dress with black hair on top and blue hair on the bottom.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003710/0.png", "losevideos/003710/1.png", "losevideos/003710/2.png", "losevideos/003710/3.png", "losevideos/003710/4.png", "losevideos/003710/5.png", "losevideos/003710/6.png", "losevideos/003710/7.png", "winvideos/003710/0.png", "winvideos/003710/1.png", "winvideos/003710/2.png", "winvideos/003710/3.png", "winvideos/003710/4.png", "winvideos/003710/5.png", "winvideos/003710/6.png", "winvideos/003710/7.png" ]
astronauts walking.	[ { "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: [astronauts walking.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009984/0.png", "winvideos/009984/1.png", "winvideos/009984/2.png", "winvideos/009984/3.png", "winvideos/009984/4.png", "winvideos/009984/5.png", "winvideos/009984/6.png", "winvideos/009984/7.png", "losevideos/009984/0.png", "losevideos/009984/1.png", "losevideos/009984/2.png", "losevideos/009984/3.png", "losevideos/009984/4.png", "losevideos/009984/5.png", "losevideos/009984/6.png", "losevideos/009984/7.png" ]
house of horror.	[ { "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: [house of horror.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002641/0.png", "winvideos/002641/1.png", "winvideos/002641/2.png", "winvideos/002641/3.png", "winvideos/002641/4.png", "winvideos/002641/5.png", "winvideos/002641/6.png", "winvideos/002641/7.png", "losevideos/002641/0.png", "losevideos/002641/1.png", "losevideos/002641/2.png", "losevideos/002641/3.png", "losevideos/002641/4.png", "losevideos/002641/5.png", "losevideos/002641/6.png", "losevideos/002641/7.png" ]
pixar style, man, passionate about metal music, long dark hair, wearing a black t-shirt, happy, playing the guitar.	[ { "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: [pixar style, man, passionate about metal music, long dark hair, wearing a black t-shirt, happy, playing the guitar.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002780/0.png", "winvideos/002780/1.png", "winvideos/002780/2.png", "winvideos/002780/3.png", "winvideos/002780/4.png", "winvideos/002780/5.png", "winvideos/002780/6.png", "winvideos/002780/7.png", "losevideos/002780/0.png", "losevideos/002780/1.png", "losevideos/002780/2.png", "losevideos/002780/3.png", "losevideos/002780/4.png", "losevideos/002780/5.png", "losevideos/002780/6.png", "losevideos/002780/7.png" ]
aliens walking in city.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [aliens walking in city.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000337/0.png", "winvideos/000337/1.png", "winvideos/000337/2.png", "winvideos/000337/3.png", "winvideos/000337/4.png", "winvideos/000337/5.png", "winvideos/000337/6.png", "winvideos/000337/7.png", "losevideos/000337/0.png", "losevideos/000337/1.png", "losevideos/000337/2.png", "losevideos/000337/3.png", "losevideos/000337/4.png", "losevideos/000337/5.png", "losevideos/000337/6.png", "losevideos/000337/7.png" ]
Command, Enter your promt.	[ { "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: [Command, Enter your promt.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003983/0.png", "losevideos/003983/1.png", "losevideos/003983/2.png", "losevideos/003983/3.png", "losevideos/003983/4.png", "losevideos/003983/5.png", "losevideos/003983/6.png", "losevideos/003983/7.png", "winvideos/003983/0.png", "winvideos/003983/1.png", "winvideos/003983/2.png", "winvideos/003983/3.png", "winvideos/003983/4.png", "winvideos/003983/5.png", "winvideos/003983/6.png", "winvideos/003983/7.png" ]
cinematic climatic shot of a unique and creepy take using a random scene from any Star Wars, The Pale White skin Voldemort Inquisitor Red Face Paint, in a tattered cloak and black Jedi armor walks past the body of his dead apprentice who was foolish enough to challenge him, dark red, purple, black colors, In the artistic style of H.R. Giger, dynamic movement, -motion 4 -gs 24 -seed 6.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [cinematic climatic shot of a unique and creepy take using a random scene from any Star Wars, The Pale White skin Voldemort Inquisitor Red Face Paint, in a tattered cloak and black Jedi armor walks past the body of his dead apprentice who was foolish enough to challenge him, dark red, purple, black colors, In the artistic style of H.R. Giger, dynamic movement, -motion 4 -gs 24 -seed 6.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000838/0.png", "losevideos/000838/1.png", "losevideos/000838/2.png", "losevideos/000838/3.png", "losevideos/000838/4.png", "losevideos/000838/5.png", "losevideos/000838/6.png", "losevideos/000838/7.png", "winvideos/000838/0.png", "winvideos/000838/1.png", "winvideos/000838/2.png", "winvideos/000838/3.png", "winvideos/000838/4.png", "winvideos/000838/5.png", "winvideos/000838/6.png", "winvideos/000838/7.png" ]
dark ominous spacecraft orbiting earth -ar 9:16 -motion 3 -neg air or wind, erratic fluctuation in motion, bad quality, distorted, poorly drawn, oversaturated, lack of detail -seed 13928434935455026380.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [dark ominous spacecraft orbiting earth -ar 9:16 -motion 3 -neg air or wind, erratic fluctuation in motion, bad quality, distorted, poorly drawn, oversaturated, lack of detail -seed 13928434935455026380.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005197/0.png", "losevideos/005197/1.png", "losevideos/005197/2.png", "losevideos/005197/3.png", "losevideos/005197/4.png", "losevideos/005197/5.png", "losevideos/005197/6.png", "losevideos/005197/7.png", "winvideos/005197/0.png", "winvideos/005197/1.png", "winvideos/005197/2.png", "winvideos/005197/3.png", "winvideos/005197/4.png", "winvideos/005197/5.png", "winvideos/005197/6.png", "winvideos/005197/7.png" ]
Beautiful cat with big eyes and very cutej 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: [Beautiful cat with big eyes and very cutej Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008207/0.png", "winvideos/008207/1.png", "winvideos/008207/2.png", "winvideos/008207/3.png", "winvideos/008207/4.png", "winvideos/008207/5.png", "winvideos/008207/6.png", "winvideos/008207/7.png", "losevideos/008207/0.png", "losevideos/008207/1.png", "losevideos/008207/2.png", "losevideos/008207/3.png", "losevideos/008207/4.png", "losevideos/008207/5.png", "losevideos/008207/6.png", "losevideos/008207/7.png" ]
A Dark Brown Bear Looking To Islands In Hawai'i.	[ { "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 Dark Brown Bear Looking To Islands In Hawai'i.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009190/0.png", "losevideos/009190/1.png", "losevideos/009190/2.png", "losevideos/009190/3.png", "losevideos/009190/4.png", "losevideos/009190/5.png", "losevideos/009190/6.png", "losevideos/009190/7.png", "winvideos/009190/0.png", "winvideos/009190/1.png", "winvideos/009190/2.png", "winvideos/009190/3.png", "winvideos/009190/4.png", "winvideos/009190/5.png", "winvideos/009190/6.png", "winvideos/009190/7.png" ]
Nick Frost walking in a woodland, at sunset. Akira. Bladerunner. Blair Witch. Watercolour paint smudging, dripping, and smearing on distorted, blurred video-art. Fight Club. Nam June Paik and Hannah Hoch style. Found Footage A24.	[ { "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: [Nick Frost walking in a woodland, at sunset. Akira. Bladerunner. Blair Witch. Watercolour paint smudging, dripping, and smearing on distorted, blurred video-art. Fight Club. Nam June Paik and Hannah Hoch style. Found Footage A24.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006108/0.png", "winvideos/006108/1.png", "winvideos/006108/2.png", "winvideos/006108/3.png", "winvideos/006108/4.png", "winvideos/006108/5.png", "winvideos/006108/6.png", "winvideos/006108/7.png", "losevideos/006108/0.png", "losevideos/006108/1.png", "losevideos/006108/2.png", "losevideos/006108/3.png", "losevideos/006108/4.png", "losevideos/006108/5.png", "losevideos/006108/6.png", "losevideos/006108/7.png" ]
Show animals from the savannah gathering around, watching Leo and Amina's unusual collaboration.	[ { "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: [Show animals from the savannah gathering around, watching Leo and Amina's unusual collaboration.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000438/0.png", "losevideos/000438/1.png", "losevideos/000438/2.png", "losevideos/000438/3.png", "losevideos/000438/4.png", "losevideos/000438/5.png", "losevideos/000438/6.png", "losevideos/000438/7.png", "winvideos/000438/0.png", "winvideos/000438/1.png", "winvideos/000438/2.png", "winvideos/000438/3.png", "winvideos/000438/4.png", "winvideos/000438/5.png", "winvideos/000438/6.png", "winvideos/000438/7.png" ]
kenyans at a gorgeous green golf course teeing off, rolling hills and stunning greens on a sunny day, golf buggy and caddy.	[ { "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: [kenyans at a gorgeous green golf course teeing off, rolling hills and stunning greens on a sunny day, golf buggy and caddy.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000011/0.png", "winvideos/000011/1.png", "winvideos/000011/2.png", "winvideos/000011/3.png", "winvideos/000011/4.png", "winvideos/000011/5.png", "winvideos/000011/6.png", "winvideos/000011/7.png", "losevideos/000011/0.png", "losevideos/000011/1.png", "losevideos/000011/2.png", "losevideos/000011/3.png", "losevideos/000011/4.png", "losevideos/000011/5.png", "losevideos/000011/6.png", "losevideos/000011/7.png" ]
tyrannosaurus rex looking for food in the forest -gs 12 -fps 24 -motion18.	[ { "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: [tyrannosaurus rex looking for food in the forest -gs 12 -fps 24 -motion18.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005705/0.png", "winvideos/005705/1.png", "winvideos/005705/2.png", "winvideos/005705/3.png", "winvideos/005705/4.png", "winvideos/005705/5.png", "winvideos/005705/6.png", "winvideos/005705/7.png", "losevideos/005705/0.png", "losevideos/005705/1.png", "losevideos/005705/2.png", "losevideos/005705/3.png", "losevideos/005705/4.png", "losevideos/005705/5.png", "losevideos/005705/6.png", "losevideos/005705/7.png" ]
Imagine forest animals, including the leopard, elephant, fox, rabbit, deer, and tiger with a Lion.	[ { "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: [Imagine forest animals, including the leopard, elephant, fox, rabbit, deer, and tiger with a Lion.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003665/0.png", "losevideos/003665/1.png", "losevideos/003665/2.png", "losevideos/003665/3.png", "losevideos/003665/4.png", "losevideos/003665/5.png", "losevideos/003665/6.png", "losevideos/003665/7.png", "winvideos/003665/0.png", "winvideos/003665/1.png", "winvideos/003665/2.png", "winvideos/003665/3.png", "winvideos/003665/4.png", "winvideos/003665/5.png", "winvideos/003665/6.png", "winvideos/003665/7.png" ]
spaceship nearby black hole,4k,8k, sharp color.	[ { "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: [spaceship nearby black hole,4k,8k, sharp color.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000485/0.png", "losevideos/000485/1.png", "losevideos/000485/2.png", "losevideos/000485/3.png", "losevideos/000485/4.png", "losevideos/000485/5.png", "losevideos/000485/6.png", "losevideos/000485/7.png", "winvideos/000485/0.png", "winvideos/000485/1.png", "winvideos/000485/2.png", "winvideos/000485/3.png", "winvideos/000485/4.png", "winvideos/000485/5.png", "winvideos/000485/6.png", "winvideos/000485/7.png" ]
bar -seed 2383469.	[ { "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: [bar -seed 2383469.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005889/0.png", "losevideos/005889/1.png", "losevideos/005889/2.png", "losevideos/005889/3.png", "losevideos/005889/4.png", "losevideos/005889/5.png", "losevideos/005889/6.png", "losevideos/005889/7.png", "winvideos/005889/0.png", "winvideos/005889/1.png", "winvideos/005889/2.png", "winvideos/005889/3.png", "winvideos/005889/4.png", "winvideos/005889/5.png", "winvideos/005889/6.png", "winvideos/005889/7.png" ]
the teacher tell the book to children.	[ { "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 teacher tell the book to children.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004693/0.png", "losevideos/004693/1.png", "losevideos/004693/2.png", "losevideos/004693/3.png", "losevideos/004693/4.png", "losevideos/004693/5.png", "losevideos/004693/6.png", "losevideos/004693/7.png", "winvideos/004693/0.png", "winvideos/004693/1.png", "winvideos/004693/2.png", "winvideos/004693/3.png", "winvideos/004693/4.png", "winvideos/004693/5.png", "winvideos/004693/6.png", "winvideos/004693/7.png" ]
anime girl dance.	[ { "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: [anime girl dance.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004448/0.png", "losevideos/004448/1.png", "losevideos/004448/2.png", "losevideos/004448/3.png", "losevideos/004448/4.png", "losevideos/004448/5.png", "losevideos/004448/6.png", "losevideos/004448/7.png", "winvideos/004448/0.png", "winvideos/004448/1.png", "winvideos/004448/2.png", "winvideos/004448/3.png", "winvideos/004448/4.png", "winvideos/004448/5.png", "winvideos/004448/6.png", "winvideos/004448/7.png" ]
A variation of a scene from Andrei Tarkovsky‘s movie The Stalker. the shadow of a large owl flies quickly across a moodily sepia toned abandoned factory room with pools of water on the floor, sand dunes, rusty walls, a fog hangs in the air. Filmed with 70 mm panaflex 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: [A variation of a scene from Andrei Tarkovsky‘s movie The Stalker. the shadow of a large owl flies quickly across a moodily sepia toned abandoned factory room with pools of water on the floor, sand dunes, rusty walls, a fog hangs in the air. Filmed with 70 mm panaflex camera.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003240/0.png", "winvideos/003240/1.png", "winvideos/003240/2.png", "winvideos/003240/3.png", "winvideos/003240/4.png", "winvideos/003240/5.png", "winvideos/003240/6.png", "winvideos/003240/7.png", "losevideos/003240/0.png", "losevideos/003240/1.png", "losevideos/003240/2.png", "losevideos/003240/3.png", "losevideos/003240/4.png", "losevideos/003240/5.png", "losevideos/003240/6.png", "losevideos/003240/7.png" ]
indignant green woman while sitting on her sofa, cartoon style.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [indignant green woman while sitting on her sofa, cartoon style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007918/0.png", "winvideos/007918/1.png", "winvideos/007918/2.png", "winvideos/007918/3.png", "winvideos/007918/4.png", "winvideos/007918/5.png", "winvideos/007918/6.png", "winvideos/007918/7.png", "losevideos/007918/0.png", "losevideos/007918/1.png", "losevideos/007918/2.png", "losevideos/007918/3.png", "losevideos/007918/4.png", "losevideos/007918/5.png", "losevideos/007918/6.png", "losevideos/007918/7.png" ]
ancient china serene night with moon shining into house with elder man sitting by the bed side.	[ { "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 china serene night with moon shining into house with elder man sitting by the bed side.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006689/0.png", "winvideos/006689/1.png", "winvideos/006689/2.png", "winvideos/006689/3.png", "winvideos/006689/4.png", "winvideos/006689/5.png", "winvideos/006689/6.png", "winvideos/006689/7.png", "losevideos/006689/0.png", "losevideos/006689/1.png", "losevideos/006689/2.png", "losevideos/006689/3.png", "losevideos/006689/4.png", "losevideos/006689/5.png", "losevideos/006689/6.png", "losevideos/006689/7.png" ]
A teacher.	[ { "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 teacher.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008554/0.png", "losevideos/008554/1.png", "losevideos/008554/2.png", "losevideos/008554/3.png", "losevideos/008554/4.png", "losevideos/008554/5.png", "losevideos/008554/6.png", "losevideos/008554/7.png", "winvideos/008554/0.png", "winvideos/008554/1.png", "winvideos/008554/2.png", "winvideos/008554/3.png", "winvideos/008554/4.png", "winvideos/008554/5.png", "winvideos/008554/6.png", "winvideos/008554/7.png" ]
image:unnamed (1).jpg juggle toilet paper.	[ { "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: [image:unnamed (1).jpg juggle toilet paper.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008832/0.png", "losevideos/008832/1.png", "losevideos/008832/2.png", "losevideos/008832/3.png", "losevideos/008832/4.png", "losevideos/008832/5.png", "losevideos/008832/6.png", "losevideos/008832/7.png", "winvideos/008832/0.png", "winvideos/008832/1.png", "winvideos/008832/2.png", "winvideos/008832/3.png", "winvideos/008832/4.png", "winvideos/008832/5.png", "winvideos/008832/6.png", "winvideos/008832/7.png" ]
talking, laughing -seed 10861067748155129373.	[ { "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: [talking, laughing -seed 10861067748155129373.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000877/0.png", "winvideos/000877/1.png", "winvideos/000877/2.png", "winvideos/000877/3.png", "winvideos/000877/4.png", "winvideos/000877/5.png", "winvideos/000877/6.png", "winvideos/000877/7.png", "losevideos/000877/0.png", "losevideos/000877/1.png", "losevideos/000877/2.png", "losevideos/000877/3.png", "losevideos/000877/4.png", "losevideos/000877/5.png", "losevideos/000877/6.png", "losevideos/000877/7.png" ]
Marilyn Manson fused with an alien.	[ { "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: [Marilyn Manson fused with an alien.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007287/0.png", "winvideos/007287/1.png", "winvideos/007287/2.png", "winvideos/007287/3.png", "winvideos/007287/4.png", "winvideos/007287/5.png", "winvideos/007287/6.png", "winvideos/007287/7.png", "losevideos/007287/0.png", "losevideos/007287/1.png", "losevideos/007287/2.png", "losevideos/007287/3.png", "losevideos/007287/4.png", "losevideos/007287/5.png", "losevideos/007287/6.png", "losevideos/007287/7.png" ]
cosmic fireworks.	[ { "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: [cosmic fireworks.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004705/0.png", "losevideos/004705/1.png", "losevideos/004705/2.png", "losevideos/004705/3.png", "losevideos/004705/4.png", "losevideos/004705/5.png", "losevideos/004705/6.png", "losevideos/004705/7.png", "winvideos/004705/0.png", "winvideos/004705/1.png", "winvideos/004705/2.png", "winvideos/004705/3.png", "winvideos/004705/4.png", "winvideos/004705/5.png", "winvideos/004705/6.png", "winvideos/004705/7.png" ]
An bustling market where airships dock, vendors sell fantastical gadgets, and steam-powered automatons engage in trade beneath a sky filled with floating islands and dirigibles.	[ { "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 bustling market where airships dock, vendors sell fantastical gadgets, and steam-powered automatons engage in trade beneath a sky filled with floating islands and dirigibles.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003317/0.png", "winvideos/003317/1.png", "winvideos/003317/2.png", "winvideos/003317/3.png", "winvideos/003317/4.png", "winvideos/003317/5.png", "winvideos/003317/6.png", "winvideos/003317/7.png", "losevideos/003317/0.png", "losevideos/003317/1.png", "losevideos/003317/2.png", "losevideos/003317/3.png", "losevideos/003317/4.png", "losevideos/003317/5.png", "losevideos/003317/6.png", "losevideos/003317/7.png" ]
Generate a 4K video of a cramped spacecraft cockpit, dimly lit with flickering controls.	[ { "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: [Generate a 4K video of a cramped spacecraft cockpit, dimly lit with flickering controls.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005857/0.png", "losevideos/005857/1.png", "losevideos/005857/2.png", "losevideos/005857/3.png", "losevideos/005857/4.png", "losevideos/005857/5.png", "losevideos/005857/6.png", "losevideos/005857/7.png", "winvideos/005857/0.png", "winvideos/005857/1.png", "winvideos/005857/2.png", "winvideos/005857/3.png", "winvideos/005857/4.png", "winvideos/005857/5.png", "winvideos/005857/6.png", "winvideos/005857/7.png" ]
overview of futuristic sci-fi city with flying cars and holographic clock in the sky showing the time. Ultra realistic, 8k definition - zoom in, dolly 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: [overview of futuristic sci-fi city with flying cars and holographic clock in the sky showing the time. Ultra realistic, 8k definition - zoom in, dolly In.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009986/0.png", "losevideos/009986/1.png", "losevideos/009986/2.png", "losevideos/009986/3.png", "losevideos/009986/4.png", "losevideos/009986/5.png", "losevideos/009986/6.png", "losevideos/009986/7.png", "winvideos/009986/0.png", "winvideos/009986/1.png", "winvideos/009986/2.png", "winvideos/009986/3.png", "winvideos/009986/4.png", "winvideos/009986/5.png", "winvideos/009986/6.png", "winvideos/009986/7.png" ]
ridley scott space documentary, 2020.	[ { "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: [ridley scott space documentary, 2020.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000004/0.png", "losevideos/000004/1.png", "losevideos/000004/2.png", "losevideos/000004/3.png", "losevideos/000004/4.png", "losevideos/000004/5.png", "losevideos/000004/6.png", "losevideos/000004/7.png", "winvideos/000004/0.png", "winvideos/000004/1.png", "winvideos/000004/2.png", "winvideos/000004/3.png", "winvideos/000004/4.png", "winvideos/000004/5.png", "winvideos/000004/6.png", "winvideos/000004/7.png" ]
A gigantic terrifying humanoid man in a raging sea , professional sinister concept art, by artgerm and greg rutkowski, an intricate, elegant, highly detailed digital painting, concept art, sharp soft focus, illustration, in the style of simon stalenhag, wayne barlowe, and igor kieryluk.	[ { "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 gigantic terrifying humanoid man in a raging sea , professional sinister concept art, by artgerm and greg rutkowski, an intricate, elegant, highly detailed digital painting, concept art, sharp soft focus, illustration, in the style of simon stalenhag, wayne barlowe, and igor kieryluk.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006435/0.png", "winvideos/006435/1.png", "winvideos/006435/2.png", "winvideos/006435/3.png", "winvideos/006435/4.png", "winvideos/006435/5.png", "winvideos/006435/6.png", "winvideos/006435/7.png", "losevideos/006435/0.png", "losevideos/006435/1.png", "losevideos/006435/2.png", "losevideos/006435/3.png", "losevideos/006435/4.png", "losevideos/006435/5.png", "losevideos/006435/6.png", "losevideos/006435/7.png" ]
Create an animated music cover art for a hip hop song. The main theme should be a chess board where on one side there are creative bitcoin figures and on the other side conventional financial institutions buildings. btc shall win the game.	[ { "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 an animated music cover art for a hip hop song. The main theme should be a chess board where on one side there are creative bitcoin figures and on the other side conventional financial institutions buildings. btc shall win the game.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006747/0.png", "losevideos/006747/1.png", "losevideos/006747/2.png", "losevideos/006747/3.png", "losevideos/006747/4.png", "losevideos/006747/5.png", "losevideos/006747/6.png", "losevideos/006747/7.png", "winvideos/006747/0.png", "winvideos/006747/1.png", "winvideos/006747/2.png", "winvideos/006747/3.png", "winvideos/006747/4.png", "winvideos/006747/5.png", "winvideos/006747/6.png", "winvideos/006747/7.png" ]
A close-up of an ancient Egyptian mummy's hair, illuminated in a dimly lit tomb.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A close-up of an ancient Egyptian mummy's hair, illuminated in a dimly lit tomb.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001890/0.png", "winvideos/001890/1.png", "winvideos/001890/2.png", "winvideos/001890/3.png", "winvideos/001890/4.png", "winvideos/001890/5.png", "winvideos/001890/6.png", "winvideos/001890/7.png", "losevideos/001890/0.png", "losevideos/001890/1.png", "losevideos/001890/2.png", "losevideos/001890/3.png", "losevideos/001890/4.png", "losevideos/001890/5.png", "losevideos/001890/6.png", "losevideos/001890/7.png" ]
Gabriel Garcia Marquez smoking a cigarette and drinking a cup of steaming coffee.	[ { "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: [Gabriel Garcia Marquez smoking a cigarette and drinking a cup of steaming coffee.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003908/0.png", "losevideos/003908/1.png", "losevideos/003908/2.png", "losevideos/003908/3.png", "losevideos/003908/4.png", "losevideos/003908/5.png", "losevideos/003908/6.png", "losevideos/003908/7.png", "winvideos/003908/0.png", "winvideos/003908/1.png", "winvideos/003908/2.png", "winvideos/003908/3.png", "winvideos/003908/4.png", "winvideos/003908/5.png", "winvideos/003908/6.png", "winvideos/003908/7.png" ]
tiny animation of hair, blinking eyes, flickering lights.	[ { "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: [tiny animation of hair, blinking eyes, flickering lights.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006221/0.png", "winvideos/006221/1.png", "winvideos/006221/2.png", "winvideos/006221/3.png", "winvideos/006221/4.png", "winvideos/006221/5.png", "winvideos/006221/6.png", "winvideos/006221/7.png", "losevideos/006221/0.png", "losevideos/006221/1.png", "losevideos/006221/2.png", "losevideos/006221/3.png", "losevideos/006221/4.png", "losevideos/006221/5.png", "losevideos/006221/6.png", "losevideos/006221/7.png" ]