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
hombre caminando en la playa.	[ { "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: [hombre caminando en la playa.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005507/0.png", "losevideos/005507/1.png", "losevideos/005507/2.png", "losevideos/005507/3.png", "losevideos/005507/4.png", "losevideos/005507/5.png", "losevideos/005507/6.png", "losevideos/005507/7.png", "winvideos/005507/0.png", "winvideos/005507/1.png", "winvideos/005507/2.png", "winvideos/005507/3.png", "winvideos/005507/4.png", "winvideos/005507/5.png", "winvideos/005507/6.png", "winvideos/005507/7.png" ]
"Generate a video scene reminiscent of the iconic 'midjourney' style animation, portraying the divine moment on the battlefield of Kurukshetra. In this scene, Lord Krishna, with a serene and all-knowing demeanor, stands with Arjuna. The background is a mystical blend of cosmic and earthly elements, with a soothing ethereal soundtrack. Lord Krishna imparts profound advice to Arjuna, emphasizing the importance of dharma (duty), righteousness, and the path to self-realization. The animation should capture the essence of this timeless conversation in a visually engaging and spiritually enlightening manner.".	[ { "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 video scene reminiscent of the iconic 'midjourney' style animation, portraying the divine moment on the battlefield of Kurukshetra. In this scene, Lord Krishna, with a serene and all-knowing demeanor, stands with Arjuna. The background is a mystical blend of cosmic and earthly elements, with a soothing ethereal soundtrack. Lord Krishna imparts profound advice to Arjuna, emphasizing the importance of dharma (duty), righteousness, and the path to self-realization. The animation should capture the essence of this timeless conversation in a visually engaging and spiritually enlightening manner.".]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007463/0.png", "winvideos/007463/1.png", "winvideos/007463/2.png", "winvideos/007463/3.png", "winvideos/007463/4.png", "winvideos/007463/5.png", "winvideos/007463/6.png", "winvideos/007463/7.png", "losevideos/007463/0.png", "losevideos/007463/1.png", "losevideos/007463/2.png", "losevideos/007463/3.png", "losevideos/007463/4.png", "losevideos/007463/5.png", "losevideos/007463/6.png", "losevideos/007463/7.png" ]
a beautiful sleek black jaguar taking a leap into the jungle while turning in to diamond studded Jaguar art piece -m4 -camera zoom in.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a beautiful sleek black jaguar taking a leap into the jungle while turning in to diamond studded Jaguar art piece -m4 -camera zoom in.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004125/0.png", "winvideos/004125/1.png", "winvideos/004125/2.png", "winvideos/004125/3.png", "winvideos/004125/4.png", "winvideos/004125/5.png", "winvideos/004125/6.png", "winvideos/004125/7.png", "losevideos/004125/0.png", "losevideos/004125/1.png", "losevideos/004125/2.png", "losevideos/004125/3.png", "losevideos/004125/4.png", "losevideos/004125/5.png", "losevideos/004125/6.png", "losevideos/004125/7.png" ]
ram and ravan fight.	[ { "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: [ram and ravan fight.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004861/0.png", "winvideos/004861/1.png", "winvideos/004861/2.png", "winvideos/004861/3.png", "winvideos/004861/4.png", "winvideos/004861/5.png", "winvideos/004861/6.png", "winvideos/004861/7.png", "losevideos/004861/0.png", "losevideos/004861/1.png", "losevideos/004861/2.png", "losevideos/004861/3.png", "losevideos/004861/4.png", "losevideos/004861/5.png", "losevideos/004861/6.png", "losevideos/004861/7.png" ]
brane cosmology.	[ { "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: [brane cosmology.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006567/0.png", "winvideos/006567/1.png", "winvideos/006567/2.png", "winvideos/006567/3.png", "winvideos/006567/4.png", "winvideos/006567/5.png", "winvideos/006567/6.png", "winvideos/006567/7.png", "losevideos/006567/0.png", "losevideos/006567/1.png", "losevideos/006567/2.png", "losevideos/006567/3.png", "losevideos/006567/4.png", "losevideos/006567/5.png", "losevideos/006567/6.png", "losevideos/006567/7.png" ]
Underwater scene with blue ocean, babysharks swimming high resolution, clouds moving, ultra clean movements, hd, 4k , cinematic and closeup.	[ { "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: [Underwater scene with blue ocean, babysharks swimming high resolution, clouds moving, ultra clean movements, hd, 4k , cinematic and closeup.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000507/0.png", "losevideos/000507/1.png", "losevideos/000507/2.png", "losevideos/000507/3.png", "losevideos/000507/4.png", "losevideos/000507/5.png", "losevideos/000507/6.png", "losevideos/000507/7.png", "winvideos/000507/0.png", "winvideos/000507/1.png", "winvideos/000507/2.png", "winvideos/000507/3.png", "winvideos/000507/4.png", "winvideos/000507/5.png", "winvideos/000507/6.png", "winvideos/000507/7.png" ]
The wind gently blows hair and clothes 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: [The wind gently blows hair and clothes Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007534/0.png", "losevideos/007534/1.png", "losevideos/007534/2.png", "losevideos/007534/3.png", "losevideos/007534/4.png", "losevideos/007534/5.png", "losevideos/007534/6.png", "losevideos/007534/7.png", "winvideos/007534/0.png", "winvideos/007534/1.png", "winvideos/007534/2.png", "winvideos/007534/3.png", "winvideos/007534/4.png", "winvideos/007534/5.png", "winvideos/007534/6.png", "winvideos/007534/7.png" ]
Predejane streets, beautiful summer day, people walking. -m 2 - fps 8 camera up.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Predejane streets, beautiful summer day, people walking. -m 2 - fps 8 camera up.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003487/0.png", "winvideos/003487/1.png", "winvideos/003487/2.png", "winvideos/003487/3.png", "winvideos/003487/4.png", "winvideos/003487/5.png", "winvideos/003487/6.png", "winvideos/003487/7.png", "losevideos/003487/0.png", "losevideos/003487/1.png", "losevideos/003487/2.png", "losevideos/003487/3.png", "losevideos/003487/4.png", "losevideos/003487/5.png", "losevideos/003487/6.png", "losevideos/003487/7.png" ]
time, in a distant land, there lived a beautiful and kind-hearted princess named Beauty.	[ { "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: [time, in a distant land, there lived a beautiful and kind-hearted princess named Beauty.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002585/0.png", "losevideos/002585/1.png", "losevideos/002585/2.png", "losevideos/002585/3.png", "losevideos/002585/4.png", "losevideos/002585/5.png", "losevideos/002585/6.png", "losevideos/002585/7.png", "winvideos/002585/0.png", "winvideos/002585/1.png", "winvideos/002585/2.png", "winvideos/002585/3.png", "winvideos/002585/4.png", "winvideos/002585/5.png", "winvideos/002585/6.png", "winvideos/002585/7.png" ]
CU of Fisherman in a boat fishing in the Nile at night by the pyramids underneath the Milky Way it's cold and raining wind is hard the boat is dancing on the water.	[ { "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: [CU of Fisherman in a boat fishing in the Nile at night by the pyramids underneath the Milky Way it's cold and raining wind is hard the boat is dancing on the water.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009258/0.png", "losevideos/009258/1.png", "losevideos/009258/2.png", "losevideos/009258/3.png", "losevideos/009258/4.png", "losevideos/009258/5.png", "losevideos/009258/6.png", "losevideos/009258/7.png", "winvideos/009258/0.png", "winvideos/009258/1.png", "winvideos/009258/2.png", "winvideos/009258/3.png", "winvideos/009258/4.png", "winvideos/009258/5.png", "winvideos/009258/6.png", "winvideos/009258/7.png" ]
NYC Night Halloween Taxi Driver 1976, -camera rotate anticlockwise, -fps 24 -gs 17 -motion 4 -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: [NYC Night Halloween Taxi Driver 1976, -camera rotate anticlockwise, -fps 24 -gs 17 -motion 4 -ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003507/0.png", "winvideos/003507/1.png", "winvideos/003507/2.png", "winvideos/003507/3.png", "winvideos/003507/4.png", "winvideos/003507/5.png", "winvideos/003507/6.png", "winvideos/003507/7.png", "losevideos/003507/0.png", "losevideos/003507/1.png", "losevideos/003507/2.png", "losevideos/003507/3.png", "losevideos/003507/4.png", "losevideos/003507/5.png", "losevideos/003507/6.png", "losevideos/003507/7.png" ]
'NEW SHOPPE' 'DYSGENIC SLIME MONSTER' 'PYSCHO TWISTED EVIL' 'METAL GEAR WEED EATER' text in the style of Enter the Void opening characters flashy text that transitions to other fonts quickly bright vivid colors 4K vibrant sonic background complex fidelity ultraviolet rays fountain of dreams.	[ { "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: ['NEW SHOPPE' 'DYSGENIC SLIME MONSTER' 'PYSCHO TWISTED EVIL' 'METAL GEAR WEED EATER' text in the style of Enter the Void opening characters flashy text that transitions to other fonts quickly bright vivid colors 4K vibrant sonic background complex fidelity ultraviolet rays fountain of dreams.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004894/0.png", "losevideos/004894/1.png", "losevideos/004894/2.png", "losevideos/004894/3.png", "losevideos/004894/4.png", "losevideos/004894/5.png", "losevideos/004894/6.png", "losevideos/004894/7.png", "winvideos/004894/0.png", "winvideos/004894/1.png", "winvideos/004894/2.png", "winvideos/004894/3.png", "winvideos/004894/4.png", "winvideos/004894/5.png", "winvideos/004894/6.png", "winvideos/004894/7.png" ]
snakes on medusa's head moving all around.	[ { "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: [snakes on medusa's head moving all around.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004141/0.png", "winvideos/004141/1.png", "winvideos/004141/2.png", "winvideos/004141/3.png", "winvideos/004141/4.png", "winvideos/004141/5.png", "winvideos/004141/6.png", "winvideos/004141/7.png", "losevideos/004141/0.png", "losevideos/004141/1.png", "losevideos/004141/2.png", "losevideos/004141/3.png", "losevideos/004141/4.png", "losevideos/004141/5.png", "losevideos/004141/6.png", "losevideos/004141/7.png" ]
create futuristic PET scanner showing 511 kev photons.	[ { "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 futuristic PET scanner showing 511 kev photons.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005541/0.png", "losevideos/005541/1.png", "losevideos/005541/2.png", "losevideos/005541/3.png", "losevideos/005541/4.png", "losevideos/005541/5.png", "losevideos/005541/6.png", "losevideos/005541/7.png", "winvideos/005541/0.png", "winvideos/005541/1.png", "winvideos/005541/2.png", "winvideos/005541/3.png", "winvideos/005541/4.png", "winvideos/005541/5.png", "winvideos/005541/6.png", "winvideos/005541/7.png" ]
spiders running through a forrest, found footage, old recording.	[ { "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: [spiders running through a forrest, found footage, old recording.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008885/0.png", "losevideos/008885/1.png", "losevideos/008885/2.png", "losevideos/008885/3.png", "losevideos/008885/4.png", "losevideos/008885/5.png", "losevideos/008885/6.png", "losevideos/008885/7.png", "winvideos/008885/0.png", "winvideos/008885/1.png", "winvideos/008885/2.png", "winvideos/008885/3.png", "winvideos/008885/4.png", "winvideos/008885/5.png", "winvideos/008885/6.png", "winvideos/008885/7.png" ]
A close-up of a man's face. His eyes are slowly turning white, and electricity begins to crackle around them.	[ { "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 a man's face. His eyes are slowly turning white, and electricity begins to crackle around them.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004876/0.png", "losevideos/004876/1.png", "losevideos/004876/2.png", "losevideos/004876/3.png", "losevideos/004876/4.png", "losevideos/004876/5.png", "losevideos/004876/6.png", "losevideos/004876/7.png", "winvideos/004876/0.png", "winvideos/004876/1.png", "winvideos/004876/2.png", "winvideos/004876/3.png", "winvideos/004876/4.png", "winvideos/004876/5.png", "winvideos/004876/6.png", "winvideos/004876/7.png" ]
a post-apocalyptic landscape.	[ { "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 post-apocalyptic landscape.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002332/0.png", "winvideos/002332/1.png", "winvideos/002332/2.png", "winvideos/002332/3.png", "winvideos/002332/4.png", "winvideos/002332/5.png", "winvideos/002332/6.png", "winvideos/002332/7.png", "losevideos/002332/0.png", "losevideos/002332/1.png", "losevideos/002332/2.png", "losevideos/002332/3.png", "losevideos/002332/4.png", "losevideos/002332/5.png", "losevideos/002332/6.png", "losevideos/002332/7.png" ]
grey cute rabbit sitting and eating carrot in the garden. zoom in . 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: [grey cute rabbit sitting and eating carrot in the garden. zoom in . ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006077/0.png", "losevideos/006077/1.png", "losevideos/006077/2.png", "losevideos/006077/3.png", "losevideos/006077/4.png", "losevideos/006077/5.png", "losevideos/006077/6.png", "losevideos/006077/7.png", "winvideos/006077/0.png", "winvideos/006077/1.png", "winvideos/006077/2.png", "winvideos/006077/3.png", "winvideos/006077/4.png", "winvideos/006077/5.png", "winvideos/006077/6.png", "winvideos/006077/7.png" ]
When lightning flashed, a sweet voice was heard. The dragon, trapped in chains, began to shimmer. Suddenly, a dragon rider came and struck the chains with a mighty hammer, breaking them. Now, the dragon rider mounted his dragon, and as soon as he blinked, the dragon spread its wings like milk and soared into the sky. The dragon danced in the storm amidst dark gray clouds. In those clouds, pink and blue lightning was shining. Whenever the silver-white dragon, like quicksilver, touched a lightning, it transformed into a golden hue for a moment.	[ { "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: [When lightning flashed, a sweet voice was heard. The dragon, trapped in chains, began to shimmer. Suddenly, a dragon rider came and struck the chains with a mighty hammer, breaking them. Now, the dragon rider mounted his dragon, and as soon as he blinked, the dragon spread its wings like milk and soared into the sky. The dragon danced in the storm amidst dark gray clouds. In those clouds, pink and blue lightning was shining. Whenever the silver-white dragon, like quicksilver, touched a lightning, it transformed into a golden hue for a moment.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004046/0.png", "losevideos/004046/1.png", "losevideos/004046/2.png", "losevideos/004046/3.png", "losevideos/004046/4.png", "losevideos/004046/5.png", "losevideos/004046/6.png", "losevideos/004046/7.png", "winvideos/004046/0.png", "winvideos/004046/1.png", "winvideos/004046/2.png", "winvideos/004046/3.png", "winvideos/004046/4.png", "winvideos/004046/5.png", "winvideos/004046/6.png", "winvideos/004046/7.png" ]
A young and beautiful avocado like character girl wearing a graduation hat, brown hair::2, smiling and facing the camera, wearing goggles, half body, she is a teacher, The background is a classroom scene, Bright::1 environment with white as the main tone, A computer is facing forward on the screen, White is the main color, dim lights, computer screen flickering, Sixties style, Techno, Cubic Futurism Ultra Fine Detail, Cinematic lenses, CINEMA4D 4d RenderingStyle, High Resolution, best quality, 16K, -motion 1 -neg distortion, morphing -gs 24 -camera zoom out.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A young and beautiful avocado like character girl wearing a graduation hat, brown hair::2, smiling and facing the camera, wearing goggles, half body, she is a teacher, The background is a classroom scene, Bright::1 environment with white as the main tone, A computer is facing forward on the screen, White is the main color, dim lights, computer screen flickering, Sixties style, Techno, Cubic Futurism Ultra Fine Detail, Cinematic lenses, CINEMA4D 4d RenderingStyle, High Resolution, best quality, 16K, -motion 1 -neg distortion, morphing -gs 24 -camera zoom out.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008593/0.png", "winvideos/008593/1.png", "winvideos/008593/2.png", "winvideos/008593/3.png", "winvideos/008593/4.png", "winvideos/008593/5.png", "winvideos/008593/6.png", "winvideos/008593/7.png", "losevideos/008593/0.png", "losevideos/008593/1.png", "losevideos/008593/2.png", "losevideos/008593/3.png", "losevideos/008593/4.png", "losevideos/008593/5.png", "losevideos/008593/6.png", "losevideos/008593/7.png" ]
Spacecraft navigating through space，Futuristic feeling，The Spacecraft in the picture is very small.	[ { "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: [Spacecraft navigating through space，Futuristic feeling，The Spacecraft in the picture is very small.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002153/0.png", "winvideos/002153/1.png", "winvideos/002153/2.png", "winvideos/002153/3.png", "winvideos/002153/4.png", "winvideos/002153/5.png", "winvideos/002153/6.png", "winvideos/002153/7.png", "losevideos/002153/0.png", "losevideos/002153/1.png", "losevideos/002153/2.png", "losevideos/002153/3.png", "losevideos/002153/4.png", "losevideos/002153/5.png", "losevideos/002153/6.png", "losevideos/002153/7.png" ]
hyper realistic weird creepy liminal horror film from the 1950s, 1960s, 1970s.	[ { "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: [hyper realistic weird creepy liminal horror film from the 1950s, 1960s, 1970s.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001101/0.png", "losevideos/001101/1.png", "losevideos/001101/2.png", "losevideos/001101/3.png", "losevideos/001101/4.png", "losevideos/001101/5.png", "losevideos/001101/6.png", "losevideos/001101/7.png", "winvideos/001101/0.png", "winvideos/001101/1.png", "winvideos/001101/2.png", "winvideos/001101/3.png", "winvideos/001101/4.png", "winvideos/001101/5.png", "winvideos/001101/6.png", "winvideos/001101/7.png" ]
Fashion Models that have been preserved like petrified trees.	[ { "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: [Fashion Models that have been preserved like petrified trees.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007737/0.png", "winvideos/007737/1.png", "winvideos/007737/2.png", "winvideos/007737/3.png", "winvideos/007737/4.png", "winvideos/007737/5.png", "winvideos/007737/6.png", "winvideos/007737/7.png", "losevideos/007737/0.png", "losevideos/007737/1.png", "losevideos/007737/2.png", "losevideos/007737/3.png", "losevideos/007737/4.png", "losevideos/007737/5.png", "losevideos/007737/6.png", "losevideos/007737/7.png" ]
a bullet train passing through a rainforest, cinematic, fast, realistic, rainy weather.	[ { "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 bullet train passing through a rainforest, cinematic, fast, realistic, rainy weather.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003745/0.png", "winvideos/003745/1.png", "winvideos/003745/2.png", "winvideos/003745/3.png", "winvideos/003745/4.png", "winvideos/003745/5.png", "winvideos/003745/6.png", "winvideos/003745/7.png", "losevideos/003745/0.png", "losevideos/003745/1.png", "losevideos/003745/2.png", "losevideos/003745/3.png", "losevideos/003745/4.png", "losevideos/003745/5.png", "losevideos/003745/6.png", "losevideos/003745/7.png" ]
realistic counter strike 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: [realistic counter strike 2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009627/0.png", "winvideos/009627/1.png", "winvideos/009627/2.png", "winvideos/009627/3.png", "winvideos/009627/4.png", "winvideos/009627/5.png", "winvideos/009627/6.png", "winvideos/009627/7.png", "losevideos/009627/0.png", "losevideos/009627/1.png", "losevideos/009627/2.png", "losevideos/009627/3.png", "losevideos/009627/4.png", "losevideos/009627/5.png", "losevideos/009627/6.png", "losevideos/009627/7.png" ]
the flag of Liberia waving in the wind.	[ { "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 flag of Liberia waving in the wind.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005784/0.png", "winvideos/005784/1.png", "winvideos/005784/2.png", "winvideos/005784/3.png", "winvideos/005784/4.png", "winvideos/005784/5.png", "winvideos/005784/6.png", "winvideos/005784/7.png", "losevideos/005784/0.png", "losevideos/005784/1.png", "losevideos/005784/2.png", "losevideos/005784/3.png", "losevideos/005784/4.png", "losevideos/005784/5.png", "losevideos/005784/6.png", "losevideos/005784/7.png" ]
Panoramic image of South Africa, Cape Town from the air, hyperrealism, cinematic,––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: [Panoramic image of South Africa, Cape Town from the air, hyperrealism, cinematic,––ar 16:9 ––.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001368/0.png", "losevideos/001368/1.png", "losevideos/001368/2.png", "losevideos/001368/3.png", "losevideos/001368/4.png", "losevideos/001368/5.png", "losevideos/001368/6.png", "losevideos/001368/7.png", "winvideos/001368/0.png", "winvideos/001368/1.png", "winvideos/001368/2.png", "winvideos/001368/3.png", "winvideos/001368/4.png", "winvideos/001368/5.png", "winvideos/001368/6.png", "winvideos/001368/7.png" ]
a t-rex eating a pile of meat, tropical jungle.	[ { "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 t-rex eating a pile of meat, tropical jungle.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007700/0.png", "winvideos/007700/1.png", "winvideos/007700/2.png", "winvideos/007700/3.png", "winvideos/007700/4.png", "winvideos/007700/5.png", "winvideos/007700/6.png", "winvideos/007700/7.png", "losevideos/007700/0.png", "losevideos/007700/1.png", "losevideos/007700/2.png", "losevideos/007700/3.png", "losevideos/007700/4.png", "losevideos/007700/5.png", "losevideos/007700/6.png", "losevideos/007700/7.png" ]
teenager Rap 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: [teenager Rap dancing.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006942/0.png", "winvideos/006942/1.png", "winvideos/006942/2.png", "winvideos/006942/3.png", "winvideos/006942/4.png", "winvideos/006942/5.png", "winvideos/006942/6.png", "winvideos/006942/7.png", "losevideos/006942/0.png", "losevideos/006942/1.png", "losevideos/006942/2.png", "losevideos/006942/3.png", "losevideos/006942/4.png", "losevideos/006942/5.png", "losevideos/006942/6.png", "losevideos/006942/7.png" ]
poor farmer and his wife.	[ { "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: [poor farmer and his wife.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005901/0.png", "winvideos/005901/1.png", "winvideos/005901/2.png", "winvideos/005901/3.png", "winvideos/005901/4.png", "winvideos/005901/5.png", "winvideos/005901/6.png", "winvideos/005901/7.png", "losevideos/005901/0.png", "losevideos/005901/1.png", "losevideos/005901/2.png", "losevideos/005901/3.png", "losevideos/005901/4.png", "losevideos/005901/5.png", "losevideos/005901/6.png", "losevideos/005901/7.png" ]
sylvester stallone as a beast shoots a high explosive bullet zoom in fast.	[ { "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: [sylvester stallone as a beast shoots a high explosive bullet zoom in fast.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005406/0.png", "losevideos/005406/1.png", "losevideos/005406/2.png", "losevideos/005406/3.png", "losevideos/005406/4.png", "losevideos/005406/5.png", "losevideos/005406/6.png", "losevideos/005406/7.png", "winvideos/005406/0.png", "winvideos/005406/1.png", "winvideos/005406/2.png", "winvideos/005406/3.png", "winvideos/005406/4.png", "winvideos/005406/5.png", "winvideos/005406/6.png", "winvideos/005406/7.png" ]
buffalo speak in room.	[ { "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: [buffalo speak in room.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004055/0.png", "losevideos/004055/1.png", "losevideos/004055/2.png", "losevideos/004055/3.png", "losevideos/004055/4.png", "losevideos/004055/5.png", "losevideos/004055/6.png", "losevideos/004055/7.png", "winvideos/004055/0.png", "winvideos/004055/1.png", "winvideos/004055/2.png", "winvideos/004055/3.png", "winvideos/004055/4.png", "winvideos/004055/5.png", "winvideos/004055/6.png", "winvideos/004055/7.png" ]
My loved monkey king is a super hero.One day he will sail seven-color clouds to marry me.	[ { "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: [My loved monkey king is a super hero.One day he will sail seven-color clouds to marry me.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009142/0.png", "winvideos/009142/1.png", "winvideos/009142/2.png", "winvideos/009142/3.png", "winvideos/009142/4.png", "winvideos/009142/5.png", "winvideos/009142/6.png", "winvideos/009142/7.png", "losevideos/009142/0.png", "losevideos/009142/1.png", "losevideos/009142/2.png", "losevideos/009142/3.png", "losevideos/009142/4.png", "losevideos/009142/5.png", "losevideos/009142/6.png", "losevideos/009142/7.png" ]
cryptotraders looking for lamborgini in UAE.	[ { "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: [cryptotraders looking for lamborgini in UAE.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007996/0.png", "losevideos/007996/1.png", "losevideos/007996/2.png", "losevideos/007996/3.png", "losevideos/007996/4.png", "losevideos/007996/5.png", "losevideos/007996/6.png", "losevideos/007996/7.png", "winvideos/007996/0.png", "winvideos/007996/1.png", "winvideos/007996/2.png", "winvideos/007996/3.png", "winvideos/007996/4.png", "winvideos/007996/5.png", "winvideos/007996/6.png", "winvideos/007996/7.png" ]
Knight Jedi.	[ { "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: [Knight Jedi.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006829/0.png", "losevideos/006829/1.png", "losevideos/006829/2.png", "losevideos/006829/3.png", "losevideos/006829/4.png", "losevideos/006829/5.png", "losevideos/006829/6.png", "losevideos/006829/7.png", "winvideos/006829/0.png", "winvideos/006829/1.png", "winvideos/006829/2.png", "winvideos/006829/3.png", "winvideos/006829/4.png", "winvideos/006829/5.png", "winvideos/006829/6.png", "winvideos/006829/7.png" ]
une grand cobra cachant du feu sous les lettres ODIGO.	[ { "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: [une grand cobra cachant du feu sous les lettres ODIGO.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004288/0.png", "losevideos/004288/1.png", "losevideos/004288/2.png", "losevideos/004288/3.png", "losevideos/004288/4.png", "losevideos/004288/5.png", "losevideos/004288/6.png", "losevideos/004288/7.png", "winvideos/004288/0.png", "winvideos/004288/1.png", "winvideos/004288/2.png", "winvideos/004288/3.png", "winvideos/004288/4.png", "winvideos/004288/5.png", "winvideos/004288/6.png", "winvideos/004288/7.png" ]
A man working in his room, typing a portable computer, and a cat watching him.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [A man working in his room, typing a portable computer, and a cat watching him.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000187/0.png", "winvideos/000187/1.png", "winvideos/000187/2.png", "winvideos/000187/3.png", "winvideos/000187/4.png", "winvideos/000187/5.png", "winvideos/000187/6.png", "winvideos/000187/7.png", "losevideos/000187/0.png", "losevideos/000187/1.png", "losevideos/000187/2.png", "losevideos/000187/3.png", "losevideos/000187/4.png", "losevideos/000187/5.png", "losevideos/000187/6.png", "losevideos/000187/7.png" ]
From a sky scene.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [From a sky scene.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007565/0.png", "winvideos/007565/1.png", "winvideos/007565/2.png", "winvideos/007565/3.png", "winvideos/007565/4.png", "winvideos/007565/5.png", "winvideos/007565/6.png", "winvideos/007565/7.png", "losevideos/007565/0.png", "losevideos/007565/1.png", "losevideos/007565/2.png", "losevideos/007565/3.png", "losevideos/007565/4.png", "losevideos/007565/5.png", "losevideos/007565/6.png", "losevideos/007565/7.png" ]
Animate a series of short scenes showcasing the bonding moments between Mia and par. Include scenes of Mia teaching Pablo new sounds and the parrot responding in an animated and charming manner.	[ { "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 a series of short scenes showcasing the bonding moments between Mia and par. Include scenes of Mia teaching Pablo new sounds and the parrot responding in an animated and charming manner.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003062/0.png", "winvideos/003062/1.png", "winvideos/003062/2.png", "winvideos/003062/3.png", "winvideos/003062/4.png", "winvideos/003062/5.png", "winvideos/003062/6.png", "winvideos/003062/7.png", "losevideos/003062/0.png", "losevideos/003062/1.png", "losevideos/003062/2.png", "losevideos/003062/3.png", "losevideos/003062/4.png", "losevideos/003062/5.png", "losevideos/003062/6.png", "losevideos/003062/7.png" ]
beautiful anime grass field landscape, house, luffu clouds, -motion 0 -w 2 -camera zoom in -fps 24 -gs 20 -ar 4:3 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 anime grass field landscape, house, luffu clouds, -motion 0 -w 2 -camera zoom in -fps 24 -gs 20 -ar 4:3 Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004900/0.png", "losevideos/004900/1.png", "losevideos/004900/2.png", "losevideos/004900/3.png", "losevideos/004900/4.png", "losevideos/004900/5.png", "losevideos/004900/6.png", "losevideos/004900/7.png", "winvideos/004900/0.png", "winvideos/004900/1.png", "winvideos/004900/2.png", "winvideos/004900/3.png", "winvideos/004900/4.png", "winvideos/004900/5.png", "winvideos/004900/6.png", "winvideos/004900/7.png" ]