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
the process of installing a video surveillance system on a small building 4 CCTV cameras on the building at different angles.	[ { "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 process of installing a video surveillance system on a small building \n 4 CCTV cameras on the building at different angles.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007729/0.png", "losevideos/007729/1.png", "losevideos/007729/2.png", "losevideos/007729/3.png", "losevideos/007729/4.png", "losevideos/007729/5.png", "losevideos/007729/6.png", "losevideos/007729/7.png", "winvideos/007729/0.png", "winvideos/007729/1.png", "winvideos/007729/2.png", "winvideos/007729/3.png", "winvideos/007729/4.png", "winvideos/007729/5.png", "winvideos/007729/6.png", "winvideos/007729/7.png" ]
scene from a 1910 silent film about a trip to moon, black and white, a man and a woman in a massive dark spaceship cabin with pipes and faucets on the walls and individual gauges and blinking lamps.	[ { "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: [scene from a 1910 silent film about a trip to moon, black and white, a man and a woman in a massive dark spaceship cabin with pipes and faucets on the walls and individual gauges and blinking lamps.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007151/0.png", "losevideos/007151/1.png", "losevideos/007151/2.png", "losevideos/007151/3.png", "losevideos/007151/4.png", "losevideos/007151/5.png", "losevideos/007151/6.png", "losevideos/007151/7.png", "winvideos/007151/0.png", "winvideos/007151/1.png", "winvideos/007151/2.png", "winvideos/007151/3.png", "winvideos/007151/4.png", "winvideos/007151/5.png", "winvideos/007151/6.png", "winvideos/007151/7.png" ]
CASIO EDIFICE EF-527D-1AVEF promore 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: [CASIO EDIFICE EF-527D-1AVEF promore video.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007259/0.png", "losevideos/007259/1.png", "losevideos/007259/2.png", "losevideos/007259/3.png", "losevideos/007259/4.png", "losevideos/007259/5.png", "losevideos/007259/6.png", "losevideos/007259/7.png", "winvideos/007259/0.png", "winvideos/007259/1.png", "winvideos/007259/2.png", "winvideos/007259/3.png", "winvideos/007259/4.png", "winvideos/007259/5.png", "winvideos/007259/6.png", "winvideos/007259/7.png" ]
Mediaval age, Sharp features, cinematic, A old ring is on the table.	[ { "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: [Mediaval age, Sharp features, cinematic, A old ring is on the table.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000097/0.png", "losevideos/000097/1.png", "losevideos/000097/2.png", "losevideos/000097/3.png", "losevideos/000097/4.png", "losevideos/000097/5.png", "losevideos/000097/6.png", "losevideos/000097/7.png", "winvideos/000097/0.png", "winvideos/000097/1.png", "winvideos/000097/2.png", "winvideos/000097/3.png", "winvideos/000097/4.png", "winvideos/000097/5.png", "winvideos/000097/6.png", "winvideos/000097/7.png" ]
Evil dragon face, jagged teeth sunset -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: [Evil dragon face, jagged teeth sunset -ar 16:9 -motion 2.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000798/0.png", "losevideos/000798/1.png", "losevideos/000798/2.png", "losevideos/000798/3.png", "losevideos/000798/4.png", "losevideos/000798/5.png", "losevideos/000798/6.png", "losevideos/000798/7.png", "winvideos/000798/0.png", "winvideos/000798/1.png", "winvideos/000798/2.png", "winvideos/000798/3.png", "winvideos/000798/4.png", "winvideos/000798/5.png", "winvideos/000798/6.png", "winvideos/000798/7.png" ]
Bonfire, relaxing time, calm space, quiet night, firelight.	[ { "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: [Bonfire, relaxing time, calm space, quiet night, firelight.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000031/0.png", "winvideos/000031/1.png", "winvideos/000031/2.png", "winvideos/000031/3.png", "winvideos/000031/4.png", "winvideos/000031/5.png", "winvideos/000031/6.png", "winvideos/000031/7.png", "losevideos/000031/0.png", "losevideos/000031/1.png", "losevideos/000031/2.png", "losevideos/000031/3.png", "losevideos/000031/4.png", "losevideos/000031/5.png", "losevideos/000031/6.png", "losevideos/000031/7.png" ]
A Blue Smurf Cat Dancing with mrbeast a party.	[ { "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 Blue Smurf Cat Dancing with mrbeast a party.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003986/0.png", "losevideos/003986/1.png", "losevideos/003986/2.png", "losevideos/003986/3.png", "losevideos/003986/4.png", "losevideos/003986/5.png", "losevideos/003986/6.png", "losevideos/003986/7.png", "winvideos/003986/0.png", "winvideos/003986/1.png", "winvideos/003986/2.png", "winvideos/003986/3.png", "winvideos/003986/4.png", "winvideos/003986/5.png", "winvideos/003986/6.png", "winvideos/003986/7.png" ]
winnie the Pooh is half way up the tree climbing a tree, in the forest.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [winnie the Pooh is half way up the tree climbing a tree, in the forest.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006707/0.png", "losevideos/006707/1.png", "losevideos/006707/2.png", "losevideos/006707/3.png", "losevideos/006707/4.png", "losevideos/006707/5.png", "losevideos/006707/6.png", "losevideos/006707/7.png", "winvideos/006707/0.png", "winvideos/006707/1.png", "winvideos/006707/2.png", "winvideos/006707/3.png", "winvideos/006707/4.png", "winvideos/006707/5.png", "winvideos/006707/6.png", "winvideos/006707/7.png" ]
/create prompt:coffee bean goddess Indonesia blue moon photo realism high quality 4k motion 2 camera pan 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: [/create prompt:coffee bean goddess Indonesia blue moon photo realism high quality 4k motion 2 camera pan out.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000651/0.png", "winvideos/000651/1.png", "winvideos/000651/2.png", "winvideos/000651/3.png", "winvideos/000651/4.png", "winvideos/000651/5.png", "winvideos/000651/6.png", "winvideos/000651/7.png", "losevideos/000651/0.png", "losevideos/000651/1.png", "losevideos/000651/2.png", "losevideos/000651/3.png", "losevideos/000651/4.png", "losevideos/000651/5.png", "losevideos/000651/6.png", "losevideos/000651/7.png" ]
A victorian inspired steampunk market, market vendors, eccentric toys, subsurface scattering, (sharp:0. 7), ultra-detailed, real-life texture, dramatic lighting, dynamic composition, unreal engine, Nikon D850 -- ar 9:16.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A victorian inspired steampunk market, market vendors, eccentric toys, subsurface scattering, (sharp:0. 7), ultra-detailed, real-life texture, dramatic lighting, dynamic composition, unreal engine, Nikon D850 -- ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001786/0.png", "winvideos/001786/1.png", "winvideos/001786/2.png", "winvideos/001786/3.png", "winvideos/001786/4.png", "winvideos/001786/5.png", "winvideos/001786/6.png", "winvideos/001786/7.png", "losevideos/001786/0.png", "losevideos/001786/1.png", "losevideos/001786/2.png", "losevideos/001786/3.png", "losevideos/001786/4.png", "losevideos/001786/5.png", "losevideos/001786/6.png", "losevideos/001786/7.png" ]
The astronaut awakens, startled and disoriented, alarm lights flashing, beeping sounds, handheld shaky cam effect for disorientation, 4K, --gs 22 --neg "no comedic tone" --ar 16:9 --seed 57677.	[ { "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 astronaut awakens, startled and disoriented, alarm lights flashing, beeping sounds, handheld shaky cam effect for disorientation, 4K, --gs 22 --neg "no comedic tone" --ar 16:9 --seed 57677.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001013/0.png", "winvideos/001013/1.png", "winvideos/001013/2.png", "winvideos/001013/3.png", "winvideos/001013/4.png", "winvideos/001013/5.png", "winvideos/001013/6.png", "winvideos/001013/7.png", "losevideos/001013/0.png", "losevideos/001013/1.png", "losevideos/001013/2.png", "losevideos/001013/3.png", "losevideos/001013/4.png", "losevideos/001013/5.png", "losevideos/001013/6.png", "losevideos/001013/7.png" ]
An artistic image of the New Jerusalem with streets of gold and high walls. Angels or divine figures raising the heavenly city. A scene of Abraham gazing at the starry sky as a symbol of his spiritual quest. Excerpts from Paul's letters in an open Bible with the word "Celestial Jerusalem" highlighted.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [An artistic image of the New Jerusalem with streets of gold and high walls. Angels or divine figures raising the heavenly city. A scene of Abraham gazing at the starry sky as a symbol of his spiritual quest. Excerpts from Paul's letters in an open Bible with the word "Celestial Jerusalem" highlighted.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000763/0.png", "winvideos/000763/1.png", "winvideos/000763/2.png", "winvideos/000763/3.png", "winvideos/000763/4.png", "winvideos/000763/5.png", "winvideos/000763/6.png", "winvideos/000763/7.png", "losevideos/000763/0.png", "losevideos/000763/1.png", "losevideos/000763/2.png", "losevideos/000763/3.png", "losevideos/000763/4.png", "losevideos/000763/5.png", "losevideos/000763/6.png", "losevideos/000763/7.png" ]
little fairy and her ladybug friend encounter an obstacle or puzzle they must solve.Highlight their teamwork and determination in overcoming this challenge.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [little fairy and her ladybug friend encounter an obstacle or puzzle they must solve.Highlight their teamwork and determination in overcoming this challenge.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007054/0.png", "losevideos/007054/1.png", "losevideos/007054/2.png", "losevideos/007054/3.png", "losevideos/007054/4.png", "losevideos/007054/5.png", "losevideos/007054/6.png", "losevideos/007054/7.png", "winvideos/007054/0.png", "winvideos/007054/1.png", "winvideos/007054/2.png", "winvideos/007054/3.png", "winvideos/007054/4.png", "winvideos/007054/5.png", "winvideos/007054/6.png", "winvideos/007054/7.png" ]
a mystical woman shuffling tarot cards.	[ { "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 mystical woman shuffling tarot cards.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000092/0.png", "losevideos/000092/1.png", "losevideos/000092/2.png", "losevideos/000092/3.png", "losevideos/000092/4.png", "losevideos/000092/5.png", "losevideos/000092/6.png", "losevideos/000092/7.png", "winvideos/000092/0.png", "winvideos/000092/1.png", "winvideos/000092/2.png", "winvideos/000092/3.png", "winvideos/000092/4.png", "winvideos/000092/5.png", "winvideos/000092/6.png", "winvideos/000092/7.png" ]
1950s evil robot crushing a soda can at sunset -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: [1950s evil robot crushing a soda can at sunset -ar 16:9\n-motion 2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000493/0.png", "winvideos/000493/1.png", "winvideos/000493/2.png", "winvideos/000493/3.png", "winvideos/000493/4.png", "winvideos/000493/5.png", "winvideos/000493/6.png", "winvideos/000493/7.png", "losevideos/000493/0.png", "losevideos/000493/1.png", "losevideos/000493/2.png", "losevideos/000493/3.png", "losevideos/000493/4.png", "losevideos/000493/5.png", "losevideos/000493/6.png", "losevideos/000493/7.png" ]
a man mother die he reading latter and cry.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a man mother die he reading latter and cry.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000457/0.png", "winvideos/000457/1.png", "winvideos/000457/2.png", "winvideos/000457/3.png", "winvideos/000457/4.png", "winvideos/000457/5.png", "winvideos/000457/6.png", "winvideos/000457/7.png", "losevideos/000457/0.png", "losevideos/000457/1.png", "losevideos/000457/2.png", "losevideos/000457/3.png", "losevideos/000457/4.png", "losevideos/000457/5.png", "losevideos/000457/6.png", "losevideos/000457/7.png" ]
create 3d animation , hyper realistic, Disney style of "To find the treasure that you seek, look where dreams and laughter meet, where the stars light up the night sky, and magic soars, oh so high.".	[ { "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 3d animation , hyper realistic, Disney style of "To find the treasure that you seek, look where dreams and laughter meet, where the stars light up the night sky, and magic soars, oh so high.".]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005352/0.png", "winvideos/005352/1.png", "winvideos/005352/2.png", "winvideos/005352/3.png", "winvideos/005352/4.png", "winvideos/005352/5.png", "winvideos/005352/6.png", "winvideos/005352/7.png", "losevideos/005352/0.png", "losevideos/005352/1.png", "losevideos/005352/2.png", "losevideos/005352/3.png", "losevideos/005352/4.png", "losevideos/005352/5.png", "losevideos/005352/6.png", "losevideos/005352/7.png" ]
a quick explosion because of a bomb that fell in the middle of a city, fast, realistic speed.	[ { "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 quick explosion because of a bomb that fell in the middle of a city, fast, realistic speed.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009161/0.png", "losevideos/009161/1.png", "losevideos/009161/2.png", "losevideos/009161/3.png", "losevideos/009161/4.png", "losevideos/009161/5.png", "losevideos/009161/6.png", "losevideos/009161/7.png", "winvideos/009161/0.png", "winvideos/009161/1.png", "winvideos/009161/2.png", "winvideos/009161/3.png", "winvideos/009161/4.png", "winvideos/009161/5.png", "winvideos/009161/6.png", "winvideos/009161/7.png" ]
scarlet witch lifting 4 stones to throw them at the soldiers.	[ { "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: [scarlet witch lifting 4 stones to throw them at the soldiers.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001529/0.png", "winvideos/001529/1.png", "winvideos/001529/2.png", "winvideos/001529/3.png", "winvideos/001529/4.png", "winvideos/001529/5.png", "winvideos/001529/6.png", "winvideos/001529/7.png", "losevideos/001529/0.png", "losevideos/001529/1.png", "losevideos/001529/2.png", "losevideos/001529/3.png", "losevideos/001529/4.png", "losevideos/001529/5.png", "losevideos/001529/6.png", "losevideos/001529/7.png" ]
Create an image of a blond long hair queen seated in a room, speaking or reflecting upon her thoughts while sitting on a chair. Ensure the queen is depicted in regal attire, exuding both grace and authority. Show her posture as dignified yet contemplative, her gaze fixed upon a distant point or perhaps staring into the middle distance. Emphasize the room's opulence and grandeur, with subtle indications of the queen's status and power, such as royal emblems or symbols in the surroundings. Capture the essence of her narrative through facial expressions and body language, evoking a mix of strength, resilience, and perhaps a hint of vulnerability as she narrates her story or inner musings.	[ { "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 image of a blond long hair queen seated in a room, speaking or reflecting upon her thoughts while sitting on a chair. Ensure the queen is depicted in regal attire, exuding both grace and authority. Show her posture as dignified yet contemplative, her gaze fixed upon a distant point or perhaps staring into the middle distance. Emphasize the room's opulence and grandeur, with subtle indications of the queen's status and power, such as royal emblems or symbols in the surroundings. Capture the essence of her narrative through facial expressions and body language, evoking a mix of strength, resilience, and perhaps a hint of vulnerability as she narrates her story or inner musings.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000136/0.png", "losevideos/000136/1.png", "losevideos/000136/2.png", "losevideos/000136/3.png", "losevideos/000136/4.png", "losevideos/000136/5.png", "losevideos/000136/6.png", "losevideos/000136/7.png", "winvideos/000136/0.png", "winvideos/000136/1.png", "winvideos/000136/2.png", "winvideos/000136/3.png", "winvideos/000136/4.png", "winvideos/000136/5.png", "winvideos/000136/6.png", "winvideos/000136/7.png" ]
A remote village nestled in the middle of the forest.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A remote village nestled in the middle of the forest.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002891/0.png", "losevideos/002891/1.png", "losevideos/002891/2.png", "losevideos/002891/3.png", "losevideos/002891/4.png", "losevideos/002891/5.png", "losevideos/002891/6.png", "losevideos/002891/7.png", "winvideos/002891/0.png", "winvideos/002891/1.png", "winvideos/002891/2.png", "winvideos/002891/3.png", "winvideos/002891/4.png", "winvideos/002891/5.png", "winvideos/002891/6.png", "winvideos/002891/7.png" ]
The trio assists in moving the stone block, working alongside the ancient Egyptians 4K -ar 16:9 - fps 24 -gs 15.	[ { "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 trio assists in moving the stone block, working alongside the ancient Egyptians 4K -ar 16:9 - fps 24 -gs 15.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006556/0.png", "winvideos/006556/1.png", "winvideos/006556/2.png", "winvideos/006556/3.png", "winvideos/006556/4.png", "winvideos/006556/5.png", "winvideos/006556/6.png", "winvideos/006556/7.png", "losevideos/006556/0.png", "losevideos/006556/1.png", "losevideos/006556/2.png", "losevideos/006556/3.png", "losevideos/006556/4.png", "losevideos/006556/5.png", "losevideos/006556/6.png", "losevideos/006556/7.png" ]
a jews man reading a paper in anger and making a 'NO' gesture by turning his head left and right in 19th century.	[ { "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 jews man reading a paper in anger and making a 'NO' gesture by turning his head left and right in 19th century.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001756/0.png", "winvideos/001756/1.png", "winvideos/001756/2.png", "winvideos/001756/3.png", "winvideos/001756/4.png", "winvideos/001756/5.png", "winvideos/001756/6.png", "winvideos/001756/7.png", "losevideos/001756/0.png", "losevideos/001756/1.png", "losevideos/001756/2.png", "losevideos/001756/3.png", "losevideos/001756/4.png", "losevideos/001756/5.png", "losevideos/001756/6.png", "losevideos/001756/7.png" ]
"Create a suspenseful scene where the phrase 'Little did she know, this was just the beginning of a nightmare she could never escape' unveils a shocking twist. Describe the character's actions, emotions, and the unsettling circumstances leading up to this revelation. Keep readers on the edge of their seats as they realize the true horrors that lie ahead for the protagonist.".	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: ["Create a suspenseful scene where the phrase 'Little did she know, this was just the beginning of a nightmare she could never escape' unveils a shocking twist. Describe the character's actions, emotions, and the unsettling circumstances leading up to this revelation. Keep readers on the edge of their seats as they realize the true horrors that lie ahead for the protagonist.".]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006262/0.png", "winvideos/006262/1.png", "winvideos/006262/2.png", "winvideos/006262/3.png", "winvideos/006262/4.png", "winvideos/006262/5.png", "winvideos/006262/6.png", "winvideos/006262/7.png", "losevideos/006262/0.png", "losevideos/006262/1.png", "losevideos/006262/2.png", "losevideos/006262/3.png", "losevideos/006262/4.png", "losevideos/006262/5.png", "losevideos/006262/6.png", "losevideos/006262/7.png" ]
Inside an antique store in Vallecas there is a unique mini pharaoh between a los of old objects that have no importance. Zoom in. 8K 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: [Inside an antique store in Vallecas there is a unique mini pharaoh between a los of old objects that have no importance. Zoom in. 8K image.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007459/0.png", "winvideos/007459/1.png", "winvideos/007459/2.png", "winvideos/007459/3.png", "winvideos/007459/4.png", "winvideos/007459/5.png", "winvideos/007459/6.png", "winvideos/007459/7.png", "losevideos/007459/0.png", "losevideos/007459/1.png", "losevideos/007459/2.png", "losevideos/007459/3.png", "losevideos/007459/4.png", "losevideos/007459/5.png", "losevideos/007459/6.png", "losevideos/007459/7.png" ]
synthwave style, a droid in a future car driving to the horizont, a sunset day, hd , blade runner style, aesthetic.	[ { "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: [synthwave style, a droid in a future car driving to the horizont, a sunset day, hd , blade runner style, aesthetic.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000105/0.png", "winvideos/000105/1.png", "winvideos/000105/2.png", "winvideos/000105/3.png", "winvideos/000105/4.png", "winvideos/000105/5.png", "winvideos/000105/6.png", "winvideos/000105/7.png", "losevideos/000105/0.png", "losevideos/000105/1.png", "losevideos/000105/2.png", "losevideos/000105/3.png", "losevideos/000105/4.png", "losevideos/000105/5.png", "losevideos/000105/6.png", "losevideos/000105/7.png" ]
you're the luck of your blacksmith, 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: [you're the luck of your blacksmith, ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007232/0.png", "losevideos/007232/1.png", "losevideos/007232/2.png", "losevideos/007232/3.png", "losevideos/007232/4.png", "losevideos/007232/5.png", "losevideos/007232/6.png", "losevideos/007232/7.png", "winvideos/007232/0.png", "winvideos/007232/1.png", "winvideos/007232/2.png", "winvideos/007232/3.png", "winvideos/007232/4.png", "winvideos/007232/5.png", "winvideos/007232/6.png", "winvideos/007232/7.png" ]
man coming out of graves,((made of mud))real human((male))scary,hyper realistic, real ,first frame((suddenly he wakes up from mud <<grave>>.	[ { "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: [man coming out of graves,((made of mud))real human((male))scary,hyper realistic, real ,first frame((suddenly he wakes up from mud <<grave>>.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004402/0.png", "winvideos/004402/1.png", "winvideos/004402/2.png", "winvideos/004402/3.png", "winvideos/004402/4.png", "winvideos/004402/5.png", "winvideos/004402/6.png", "winvideos/004402/7.png", "losevideos/004402/0.png", "losevideos/004402/1.png", "losevideos/004402/2.png", "losevideos/004402/3.png", "losevideos/004402/4.png", "losevideos/004402/5.png", "losevideos/004402/6.png", "losevideos/004402/7.png" ]
16:9, a robot run hostpital.	[ { "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 robot run hostpital.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002454/0.png", "winvideos/002454/1.png", "winvideos/002454/2.png", "winvideos/002454/3.png", "winvideos/002454/4.png", "winvideos/002454/5.png", "winvideos/002454/6.png", "winvideos/002454/7.png", "losevideos/002454/0.png", "losevideos/002454/1.png", "losevideos/002454/2.png", "losevideos/002454/3.png", "losevideos/002454/4.png", "losevideos/002454/5.png", "losevideos/002454/6.png", "losevideos/002454/7.png" ]
Woman funny face eating shrimps.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Woman funny face eating shrimps.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006811/0.png", "losevideos/006811/1.png", "losevideos/006811/2.png", "losevideos/006811/3.png", "losevideos/006811/4.png", "losevideos/006811/5.png", "losevideos/006811/6.png", "losevideos/006811/7.png", "winvideos/006811/0.png", "winvideos/006811/1.png", "winvideos/006811/2.png", "winvideos/006811/3.png", "winvideos/006811/4.png", "winvideos/006811/5.png", "winvideos/006811/6.png", "winvideos/006811/7.png" ]
santa riding his sledge pulled by his raideers in front of moon.	[ { "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: [santa riding his sledge pulled by his raideers in front of moon.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004451/0.png", "winvideos/004451/1.png", "winvideos/004451/2.png", "winvideos/004451/3.png", "winvideos/004451/4.png", "winvideos/004451/5.png", "winvideos/004451/6.png", "winvideos/004451/7.png", "losevideos/004451/0.png", "losevideos/004451/1.png", "losevideos/004451/2.png", "losevideos/004451/3.png", "losevideos/004451/4.png", "losevideos/004451/5.png", "losevideos/004451/6.png", "losevideos/004451/7.png" ]
Chhath Puja is a Hindu festival dedicated to the worship of the Sun God, Surya, and Chhathi Maiya, who is considered the sister of Surya. This festival is primarily celebrated in the Indian states of Bihar, Jharkhand, and Uttar Pradesh, as well as in Nepal. However, its popularity has spread to other regions with a significant Bihari and Maithili population. Chhath Puja is observed on the sixth day after Diwali, usually in October or November. The festival spans four days and involves a series of rituals performed with great devotion. Here's an overview of the main rituals:.	[ { "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: [Chhath Puja is a Hindu festival dedicated to the worship of the Sun God, Surya, and Chhathi Maiya, who is considered the sister of Surya. This festival is primarily celebrated in the Indian states of Bihar, Jharkhand, and Uttar Pradesh, as well as in Nepal. However, its popularity has spread to other regions with a significant Bihari and Maithili population. Chhath Puja is observed on the sixth day after Diwali, usually in October or November. The festival spans four days and involves a series of rituals performed with great devotion. Here's an overview of the main rituals:.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006121/0.png", "losevideos/006121/1.png", "losevideos/006121/2.png", "losevideos/006121/3.png", "losevideos/006121/4.png", "losevideos/006121/5.png", "losevideos/006121/6.png", "losevideos/006121/7.png", "winvideos/006121/0.png", "winvideos/006121/1.png", "winvideos/006121/2.png", "winvideos/006121/3.png", "winvideos/006121/4.png", "winvideos/006121/5.png", "winvideos/006121/6.png", "winvideos/006121/7.png" ]
video game characters escaping through the television set to explore the real world.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [video game characters escaping through the television set to explore the real world.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001385/0.png", "winvideos/001385/1.png", "winvideos/001385/2.png", "winvideos/001385/3.png", "winvideos/001385/4.png", "winvideos/001385/5.png", "winvideos/001385/6.png", "winvideos/001385/7.png", "losevideos/001385/0.png", "losevideos/001385/1.png", "losevideos/001385/2.png", "losevideos/001385/3.png", "losevideos/001385/4.png", "losevideos/001385/5.png", "losevideos/001385/6.png", "losevideos/001385/7.png" ]
Cinematic_top-down_view_the_cat_very_very_small_sits_on_top_of_a_very_very_giant_mushrooms_like tress , camera view above the cat from the top of the drone overhead , HD , 8K , detail is very good , bird's-eye view , very high view.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Cinematic_top-down_view_the_cat_very_very_small_sits_on_top_of_a_very_very_giant_mushrooms_like tress , camera view above the cat from the top of the drone overhead , HD , 8K , detail is very good , bird's-eye view , very high view.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008234/0.png", "losevideos/008234/1.png", "losevideos/008234/2.png", "losevideos/008234/3.png", "losevideos/008234/4.png", "losevideos/008234/5.png", "losevideos/008234/6.png", "losevideos/008234/7.png", "winvideos/008234/0.png", "winvideos/008234/1.png", "winvideos/008234/2.png", "winvideos/008234/3.png", "winvideos/008234/4.png", "winvideos/008234/5.png", "winvideos/008234/6.png", "winvideos/008234/7.png" ]
venom, sadness, fog, atmosphere, pain, night, cyberpunk, ultra-realistic, 4k, professional lighting, cinematography, movement, grace.	[ { "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: [venom, sadness, fog, atmosphere, pain, night, cyberpunk, ultra-realistic, 4k, professional lighting, cinematography, movement, grace.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005362/0.png", "losevideos/005362/1.png", "losevideos/005362/2.png", "losevideos/005362/3.png", "losevideos/005362/4.png", "losevideos/005362/5.png", "losevideos/005362/6.png", "losevideos/005362/7.png", "winvideos/005362/0.png", "winvideos/005362/1.png", "winvideos/005362/2.png", "winvideos/005362/3.png", "winvideos/005362/4.png", "winvideos/005362/5.png", "winvideos/005362/6.png", "winvideos/005362/7.png" ]
sci fi alien walk on a street.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [sci fi alien walk on a street.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002989/0.png", "losevideos/002989/1.png", "losevideos/002989/2.png", "losevideos/002989/3.png", "losevideos/002989/4.png", "losevideos/002989/5.png", "losevideos/002989/6.png", "losevideos/002989/7.png", "winvideos/002989/0.png", "winvideos/002989/1.png", "winvideos/002989/2.png", "winvideos/002989/3.png", "winvideos/002989/4.png", "winvideos/002989/5.png", "winvideos/002989/6.png", "winvideos/002989/7.png" ]
a hotty burger with details.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a hotty burger with details.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000085/0.png", "winvideos/000085/1.png", "winvideos/000085/2.png", "winvideos/000085/3.png", "winvideos/000085/4.png", "winvideos/000085/5.png", "winvideos/000085/6.png", "winvideos/000085/7.png", "losevideos/000085/0.png", "losevideos/000085/1.png", "losevideos/000085/2.png", "losevideos/000085/3.png", "losevideos/000085/4.png", "losevideos/000085/5.png", "losevideos/000085/6.png", "losevideos/000085/7.png" ]
Taylor Swift dancing.	[ { "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: [Taylor Swift dancing.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007421/0.png", "losevideos/007421/1.png", "losevideos/007421/2.png", "losevideos/007421/3.png", "losevideos/007421/4.png", "losevideos/007421/5.png", "losevideos/007421/6.png", "losevideos/007421/7.png", "winvideos/007421/0.png", "winvideos/007421/1.png", "winvideos/007421/2.png", "winvideos/007421/3.png", "winvideos/007421/4.png", "winvideos/007421/5.png", "winvideos/007421/6.png", "winvideos/007421/7.png" ]
baby cat push a yellow door, realistic, 4K -gs 15 -motion 4.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [baby cat push a yellow door, realistic, 4K -gs 15 -motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003202/0.png", "losevideos/003202/1.png", "losevideos/003202/2.png", "losevideos/003202/3.png", "losevideos/003202/4.png", "losevideos/003202/5.png", "losevideos/003202/6.png", "losevideos/003202/7.png", "winvideos/003202/0.png", "winvideos/003202/1.png", "winvideos/003202/2.png", "winvideos/003202/3.png", "winvideos/003202/4.png", "winvideos/003202/5.png", "winvideos/003202/6.png", "winvideos/003202/7.png" ]
a cavapoo jumping out of excitement.	[ { "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 cavapoo jumping out of excitement.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002882/0.png", "winvideos/002882/1.png", "winvideos/002882/2.png", "winvideos/002882/3.png", "winvideos/002882/4.png", "winvideos/002882/5.png", "winvideos/002882/6.png", "winvideos/002882/7.png", "losevideos/002882/0.png", "losevideos/002882/1.png", "losevideos/002882/2.png", "losevideos/002882/3.png", "losevideos/002882/4.png", "losevideos/002882/5.png", "losevideos/002882/6.png", "losevideos/002882/7.png" ]