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
Drone Footage of Hell.	[ { "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: [Drone Footage of Hell.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000138/0.png", "winvideos/000138/1.png", "winvideos/000138/2.png", "winvideos/000138/3.png", "winvideos/000138/4.png", "winvideos/000138/5.png", "winvideos/000138/6.png", "winvideos/000138/7.png", "losevideos/000138/0.png", "losevideos/000138/1.png", "losevideos/000138/2.png", "losevideos/000138/3.png", "losevideos/000138/4.png", "losevideos/000138/5.png", "losevideos/000138/6.png", "losevideos/000138/7.png" ]
In an abandoned city mixed with blizzard, there is a pair of young couples holding a cry in the corner of the corner, Sony camera shooting --ar 16:9.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [In an abandoned city mixed with blizzard, there is a pair of young couples holding a cry in the corner of the corner, Sony camera shooting --ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008442/0.png", "losevideos/008442/1.png", "losevideos/008442/2.png", "losevideos/008442/3.png", "losevideos/008442/4.png", "losevideos/008442/5.png", "losevideos/008442/6.png", "losevideos/008442/7.png", "winvideos/008442/0.png", "winvideos/008442/1.png", "winvideos/008442/2.png", "winvideos/008442/3.png", "winvideos/008442/4.png", "winvideos/008442/5.png", "winvideos/008442/6.png", "winvideos/008442/7.png" ]
-jungle mein ek hathi aur ek ghoda rahate the.	[ { "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: [-jungle mein ek hathi aur ek ghoda rahate the.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003438/0.png", "winvideos/003438/1.png", "winvideos/003438/2.png", "winvideos/003438/3.png", "winvideos/003438/4.png", "winvideos/003438/5.png", "winvideos/003438/6.png", "winvideos/003438/7.png", "losevideos/003438/0.png", "losevideos/003438/1.png", "losevideos/003438/2.png", "losevideos/003438/3.png", "losevideos/003438/4.png", "losevideos/003438/5.png", "losevideos/003438/6.png", "losevideos/003438/7.png" ]
create a comercial for rolls royce.	[ { "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 comercial for rolls royce.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002904/0.png", "losevideos/002904/1.png", "losevideos/002904/2.png", "losevideos/002904/3.png", "losevideos/002904/4.png", "losevideos/002904/5.png", "losevideos/002904/6.png", "losevideos/002904/7.png", "winvideos/002904/0.png", "winvideos/002904/1.png", "winvideos/002904/2.png", "winvideos/002904/3.png", "winvideos/002904/4.png", "winvideos/002904/5.png", "winvideos/002904/6.png", "winvideos/002904/7.png" ]
gorgeous woman meditating and connecting with Spirit, cinematic, soothing, calm, best quality.	[ { "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: [gorgeous woman meditating and connecting with Spirit, cinematic, soothing, calm, best quality.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003075/0.png", "winvideos/003075/1.png", "winvideos/003075/2.png", "winvideos/003075/3.png", "winvideos/003075/4.png", "winvideos/003075/5.png", "winvideos/003075/6.png", "winvideos/003075/7.png", "losevideos/003075/0.png", "losevideos/003075/1.png", "losevideos/003075/2.png", "losevideos/003075/3.png", "losevideos/003075/4.png", "losevideos/003075/5.png", "losevideos/003075/6.png", "losevideos/003075/7.png" ]
(A person wearing a gray top, black pants, and red shoes is sitting on a chair made of bamboo) -ar 1:1.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [(A person wearing a gray top, black pants, and red shoes is sitting on a chair made of bamboo) -ar 1:1.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004419/0.png", "winvideos/004419/1.png", "winvideos/004419/2.png", "winvideos/004419/3.png", "winvideos/004419/4.png", "winvideos/004419/5.png", "winvideos/004419/6.png", "winvideos/004419/7.png", "losevideos/004419/0.png", "losevideos/004419/1.png", "losevideos/004419/2.png", "losevideos/004419/3.png", "losevideos/004419/4.png", "losevideos/004419/5.png", "losevideos/004419/6.png", "losevideos/004419/7.png" ]
bitcoin falling down.	[ { "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: [bitcoin falling down.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002793/0.png", "losevideos/002793/1.png", "losevideos/002793/2.png", "losevideos/002793/3.png", "losevideos/002793/4.png", "losevideos/002793/5.png", "losevideos/002793/6.png", "losevideos/002793/7.png", "winvideos/002793/0.png", "winvideos/002793/1.png", "winvideos/002793/2.png", "winvideos/002793/3.png", "winvideos/002793/4.png", "winvideos/002793/5.png", "winvideos/002793/6.png", "winvideos/002793/7.png" ]
sushi chef slicing a fish -ar 2:3.	[ { "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: [sushi chef slicing a fish -ar 2:3.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005580/0.png", "losevideos/005580/1.png", "losevideos/005580/2.png", "losevideos/005580/3.png", "losevideos/005580/4.png", "losevideos/005580/5.png", "losevideos/005580/6.png", "losevideos/005580/7.png", "winvideos/005580/0.png", "winvideos/005580/1.png", "winvideos/005580/2.png", "winvideos/005580/3.png", "winvideos/005580/4.png", "winvideos/005580/5.png", "winvideos/005580/6.png", "winvideos/005580/7.png" ]
little girl walking towards a door in a house made giant red and white mushrooms in a mystical forest with flowers and fireflies -ar 16:9 -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: [little girl walking towards a door in a house made giant red and white mushrooms in a mystical forest with flowers and fireflies -ar 16:9 -camera zoom in.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004444/0.png", "winvideos/004444/1.png", "winvideos/004444/2.png", "winvideos/004444/3.png", "winvideos/004444/4.png", "winvideos/004444/5.png", "winvideos/004444/6.png", "winvideos/004444/7.png", "losevideos/004444/0.png", "losevideos/004444/1.png", "losevideos/004444/2.png", "losevideos/004444/3.png", "losevideos/004444/4.png", "losevideos/004444/5.png", "losevideos/004444/6.png", "losevideos/004444/7.png" ]
los extraños símbolos grabados en la nave espacial suscitaron una sensación de maravilla y desconcierto en el grupo.	[ { "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: [los extraños símbolos grabados en la nave espacial suscitaron una sensación de maravilla y desconcierto en el grupo.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000297/0.png", "losevideos/000297/1.png", "losevideos/000297/2.png", "losevideos/000297/3.png", "losevideos/000297/4.png", "losevideos/000297/5.png", "losevideos/000297/6.png", "losevideos/000297/7.png", "winvideos/000297/0.png", "winvideos/000297/1.png", "winvideos/000297/2.png", "winvideos/000297/3.png", "winvideos/000297/4.png", "winvideos/000297/5.png", "winvideos/000297/6.png", "winvideos/000297/7.png" ]
bird view of a grand fog fall landscape with lots colorful trees and a car in white driving exactly on a winded road in the landscape, high quality -motion 2 -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: [bird view of a grand fog fall landscape with lots colorful trees and a car in white driving exactly on a winded road in the landscape, high quality -motion 2 -camera zoom out.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003493/0.png", "losevideos/003493/1.png", "losevideos/003493/2.png", "losevideos/003493/3.png", "losevideos/003493/4.png", "losevideos/003493/5.png", "losevideos/003493/6.png", "losevideos/003493/7.png", "winvideos/003493/0.png", "winvideos/003493/1.png", "winvideos/003493/2.png", "winvideos/003493/3.png", "winvideos/003493/4.png", "winvideos/003493/5.png", "winvideos/003493/6.png", "winvideos/003493/7.png" ]
Spaceships sail through space.	[ { "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: [Spaceships sail through space.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001230/0.png", "losevideos/001230/1.png", "losevideos/001230/2.png", "losevideos/001230/3.png", "losevideos/001230/4.png", "losevideos/001230/5.png", "losevideos/001230/6.png", "losevideos/001230/7.png", "winvideos/001230/0.png", "winvideos/001230/1.png", "winvideos/001230/2.png", "winvideos/001230/3.png", "winvideos/001230/4.png", "winvideos/001230/5.png", "winvideos/001230/6.png", "winvideos/001230/7.png" ]
sky car.	[ { "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: [sky car.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004404/0.png", "losevideos/004404/1.png", "losevideos/004404/2.png", "losevideos/004404/3.png", "losevideos/004404/4.png", "losevideos/004404/5.png", "losevideos/004404/6.png", "losevideos/004404/7.png", "winvideos/004404/0.png", "winvideos/004404/1.png", "winvideos/004404/2.png", "winvideos/004404/3.png", "winvideos/004404/4.png", "winvideos/004404/5.png", "winvideos/004404/6.png", "winvideos/004404/7.png" ]
callable icon.	[ { "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: [callable icon.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006986/0.png", "losevideos/006986/1.png", "losevideos/006986/2.png", "losevideos/006986/3.png", "losevideos/006986/4.png", "losevideos/006986/5.png", "losevideos/006986/6.png", "losevideos/006986/7.png", "winvideos/006986/0.png", "winvideos/006986/1.png", "winvideos/006986/2.png", "winvideos/006986/3.png", "winvideos/006986/4.png", "winvideos/006986/5.png", "winvideos/006986/6.png", "winvideos/006986/7.png" ]
Beautiful shirtless shinigami woman seductress with wings on her head, cinematic, lens flares, abstract expressionism art movement, featuring dynamic, bold, and white abstract shapes and patterns that evoke emotion and stimulate the senses, high details, 8k -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting, mutation -fps 24.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Beautiful shirtless shinigami woman seductress with wings on her head, cinematic, lens flares, abstract expressionism art movement, featuring dynamic, bold, and white abstract shapes and patterns that evoke emotion and stimulate the senses, high details, 8k -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting, mutation -fps 24.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003152/0.png", "losevideos/003152/1.png", "losevideos/003152/2.png", "losevideos/003152/3.png", "losevideos/003152/4.png", "losevideos/003152/5.png", "losevideos/003152/6.png", "losevideos/003152/7.png", "winvideos/003152/0.png", "winvideos/003152/1.png", "winvideos/003152/2.png", "winvideos/003152/3.png", "winvideos/003152/4.png", "winvideos/003152/5.png", "winvideos/003152/6.png", "winvideos/003152/7.png" ]
a busy futuristic convenience store in outer space -motion 2.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a busy futuristic convenience store in outer space -motion 2.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009203/0.png", "losevideos/009203/1.png", "losevideos/009203/2.png", "losevideos/009203/3.png", "losevideos/009203/4.png", "losevideos/009203/5.png", "losevideos/009203/6.png", "losevideos/009203/7.png", "winvideos/009203/0.png", "winvideos/009203/1.png", "winvideos/009203/2.png", "winvideos/009203/3.png", "winvideos/009203/4.png", "winvideos/009203/5.png", "winvideos/009203/6.png", "winvideos/009203/7.png" ]
make an villan who is scared from reality tv shows.	[ { "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: [make an villan who is scared from reality tv shows.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007831/0.png", "losevideos/007831/1.png", "losevideos/007831/2.png", "losevideos/007831/3.png", "losevideos/007831/4.png", "losevideos/007831/5.png", "losevideos/007831/6.png", "losevideos/007831/7.png", "winvideos/007831/0.png", "winvideos/007831/1.png", "winvideos/007831/2.png", "winvideos/007831/3.png", "winvideos/007831/4.png", "winvideos/007831/5.png", "winvideos/007831/6.png", "winvideos/007831/7.png" ]
UFO fighting in the sky with two F-19 US air force, dystopian post-apocalyptic scene, --m 2 --ar 21:9.	[ { "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: [UFO fighting in the sky with two F-19 US air force, dystopian post-apocalyptic scene, --m 2 --ar 21:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008996/0.png", "winvideos/008996/1.png", "winvideos/008996/2.png", "winvideos/008996/3.png", "winvideos/008996/4.png", "winvideos/008996/5.png", "winvideos/008996/6.png", "winvideos/008996/7.png", "losevideos/008996/0.png", "losevideos/008996/1.png", "losevideos/008996/2.png", "losevideos/008996/3.png", "losevideos/008996/4.png", "losevideos/008996/5.png", "losevideos/008996/6.png", "losevideos/008996/7.png" ]
the best beautiful natural view of the aurora borealis in Finland-4UHD Screensaver.	[ { "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 best beautiful natural view of the aurora borealis in Finland-4UHD Screensaver.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007072/0.png", "losevideos/007072/1.png", "losevideos/007072/2.png", "losevideos/007072/3.png", "losevideos/007072/4.png", "losevideos/007072/5.png", "losevideos/007072/6.png", "losevideos/007072/7.png", "winvideos/007072/0.png", "winvideos/007072/1.png", "winvideos/007072/2.png", "winvideos/007072/3.png", "winvideos/007072/4.png", "winvideos/007072/5.png", "winvideos/007072/6.png", "winvideos/007072/7.png" ]
soft waves background texture, light pastel gradients, baby pink, baby blue, light yellow.	[ { "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: [soft waves background texture, light pastel gradients, baby pink, baby blue, light yellow.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004168/0.png", "losevideos/004168/1.png", "losevideos/004168/2.png", "losevideos/004168/3.png", "losevideos/004168/4.png", "losevideos/004168/5.png", "losevideos/004168/6.png", "losevideos/004168/7.png", "winvideos/004168/0.png", "winvideos/004168/1.png", "winvideos/004168/2.png", "winvideos/004168/3.png", "winvideos/004168/4.png", "winvideos/004168/5.png", "winvideos/004168/6.png", "winvideos/004168/7.png" ]
map of Atlantis --,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: [map of Atlantis --,ar 9:16.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006504/0.png", "winvideos/006504/1.png", "winvideos/006504/2.png", "winvideos/006504/3.png", "winvideos/006504/4.png", "winvideos/006504/5.png", "winvideos/006504/6.png", "winvideos/006504/7.png", "losevideos/006504/0.png", "losevideos/006504/1.png", "losevideos/006504/2.png", "losevideos/006504/3.png", "losevideos/006504/4.png", "losevideos/006504/5.png", "losevideos/006504/6.png", "losevideos/006504/7.png" ]
An old man in idle pose.	[ { "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 old man in idle pose.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006406/0.png", "winvideos/006406/1.png", "winvideos/006406/2.png", "winvideos/006406/3.png", "winvideos/006406/4.png", "winvideos/006406/5.png", "winvideos/006406/6.png", "winvideos/006406/7.png", "losevideos/006406/0.png", "losevideos/006406/1.png", "losevideos/006406/2.png", "losevideos/006406/3.png", "losevideos/006406/4.png", "losevideos/006406/5.png", "losevideos/006406/6.png", "losevideos/006406/7.png" ]
a complete baby face and A close-up of a baby boy's beautiful eyes, ultra-realistic, sharp camera focus, cinematic lighting, with starlight reflected in his eyes.The background is in a warm house.	[ { "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 complete baby face and A close-up of a baby boy's beautiful eyes, ultra-realistic, sharp camera focus, cinematic lighting, with starlight reflected in his eyes.The background is in a warm house.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008166/0.png", "losevideos/008166/1.png", "losevideos/008166/2.png", "losevideos/008166/3.png", "losevideos/008166/4.png", "losevideos/008166/5.png", "losevideos/008166/6.png", "losevideos/008166/7.png", "winvideos/008166/0.png", "winvideos/008166/1.png", "winvideos/008166/2.png", "winvideos/008166/3.png", "winvideos/008166/4.png", "winvideos/008166/5.png", "winvideos/008166/6.png", "winvideos/008166/7.png" ]
The spacecraft landed on Mars, and the astronauts opened the hatch and walked out，4k.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The spacecraft landed on Mars, and the astronauts opened the hatch and walked out，4k.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001050/0.png", "winvideos/001050/1.png", "winvideos/001050/2.png", "winvideos/001050/3.png", "winvideos/001050/4.png", "winvideos/001050/5.png", "winvideos/001050/6.png", "winvideos/001050/7.png", "losevideos/001050/0.png", "losevideos/001050/1.png", "losevideos/001050/2.png", "losevideos/001050/3.png", "losevideos/001050/4.png", "losevideos/001050/5.png", "losevideos/001050/6.png", "losevideos/001050/7.png" ]
((fractal noise), ((Hayao Miyazaki:9), (girl runninjg in the woods))), (depth background), ((animate background)), ((animate environment)), ((animate all characters)), ((outpaint)), (nice face) ((Good anatomy)), -neg "((out of frame)), deformed, bad anatomy, disfigured, poorly drawn face, mutation, ((mutated, extra limb, ugly, disgusting, poorly drawn hands, missing limb, floating limbs, (disconnected limbs), malformed hands, blurry, (mutated hands and fingers), (immovable), (static), (fixed), watermark, watermarked, oversaturated, censored, distorted hands, amputation, missing hands, obese, doubled face, double hands" -motion 4 –hide.	[ { "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: [((fractal noise), ((Hayao Miyazaki:9), (girl runninjg in the woods))), (depth background), ((animate background)), ((animate environment)), ((animate all characters)), ((outpaint)), (nice face) ((Good anatomy)), -neg "((out of frame)), deformed, bad anatomy, disfigured, poorly drawn face, mutation, ((mutated, extra limb, ugly, disgusting, poorly drawn hands, missing limb, floating limbs, (disconnected limbs), malformed hands, blurry, (mutated hands and fingers), (immovable), (static), (fixed), watermark, watermarked, oversaturated, censored, distorted hands, amputation, missing hands, obese, doubled face, double hands" -motion 4 –hide.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006665/0.png", "losevideos/006665/1.png", "losevideos/006665/2.png", "losevideos/006665/3.png", "losevideos/006665/4.png", "losevideos/006665/5.png", "losevideos/006665/6.png", "losevideos/006665/7.png", "winvideos/006665/0.png", "winvideos/006665/1.png", "winvideos/006665/2.png", "winvideos/006665/3.png", "winvideos/006665/4.png", "winvideos/006665/5.png", "winvideos/006665/6.png", "winvideos/006665/7.png" ]
pubg character laughing background green screen.	[ { "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: [pubg character laughing background green screen.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009825/0.png", "winvideos/009825/1.png", "winvideos/009825/2.png", "winvideos/009825/3.png", "winvideos/009825/4.png", "winvideos/009825/5.png", "winvideos/009825/6.png", "winvideos/009825/7.png", "losevideos/009825/0.png", "losevideos/009825/1.png", "losevideos/009825/2.png", "losevideos/009825/3.png", "losevideos/009825/4.png", "losevideos/009825/5.png", "losevideos/009825/6.png", "losevideos/009825/7.png" ]
plant and animal.	[ { "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: [plant and animal.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007698/0.png", "losevideos/007698/1.png", "losevideos/007698/2.png", "losevideos/007698/3.png", "losevideos/007698/4.png", "losevideos/007698/5.png", "losevideos/007698/6.png", "losevideos/007698/7.png", "winvideos/007698/0.png", "winvideos/007698/1.png", "winvideos/007698/2.png", "winvideos/007698/3.png", "winvideos/007698/4.png", "winvideos/007698/5.png", "winvideos/007698/6.png", "winvideos/007698/7.png" ]
silhuette a man holding spear slow walking in the middle of heavy snowfall shoot from far -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: [silhuette a man holding spear slow walking in the middle of heavy snowfall shoot from far -ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009941/0.png", "losevideos/009941/1.png", "losevideos/009941/2.png", "losevideos/009941/3.png", "losevideos/009941/4.png", "losevideos/009941/5.png", "losevideos/009941/6.png", "losevideos/009941/7.png", "winvideos/009941/0.png", "winvideos/009941/1.png", "winvideos/009941/2.png", "winvideos/009941/3.png", "winvideos/009941/4.png", "winvideos/009941/5.png", "winvideos/009941/6.png", "winvideos/009941/7.png" ]
[photorealistic bear wearing a gold chain smiling and laughing red lighting].	[ { "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: [[photorealistic bear wearing a gold chain smiling and laughing red lighting].]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001535/0.png", "winvideos/001535/1.png", "winvideos/001535/2.png", "winvideos/001535/3.png", "winvideos/001535/4.png", "winvideos/001535/5.png", "winvideos/001535/6.png", "winvideos/001535/7.png", "losevideos/001535/0.png", "losevideos/001535/1.png", "losevideos/001535/2.png", "losevideos/001535/3.png", "losevideos/001535/4.png", "losevideos/001535/5.png", "losevideos/001535/6.png", "losevideos/001535/7.png" ]
Steaming hot hairy crab in the plate.	[ { "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: [Steaming hot hairy crab in the plate.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007070/0.png", "winvideos/007070/1.png", "winvideos/007070/2.png", "winvideos/007070/3.png", "winvideos/007070/4.png", "winvideos/007070/5.png", "winvideos/007070/6.png", "winvideos/007070/7.png", "losevideos/007070/0.png", "losevideos/007070/1.png", "losevideos/007070/2.png", "losevideos/007070/3.png", "losevideos/007070/4.png", "losevideos/007070/5.png", "losevideos/007070/6.png", "losevideos/007070/7.png" ]
person breathing and moving, small moves of his hands, cinematic -gs 10 -fps 24 -motion 2 --style raw.	[ { "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: [person breathing and moving, small moves of his hands, cinematic -gs 10 -fps 24 -motion 2 --style raw.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004947/0.png", "losevideos/004947/1.png", "losevideos/004947/2.png", "losevideos/004947/3.png", "losevideos/004947/4.png", "losevideos/004947/5.png", "losevideos/004947/6.png", "losevideos/004947/7.png", "winvideos/004947/0.png", "winvideos/004947/1.png", "winvideos/004947/2.png", "winvideos/004947/3.png", "winvideos/004947/4.png", "winvideos/004947/5.png", "winvideos/004947/6.png", "winvideos/004947/7.png" ]
Broken statue of Indian god Shri Krishna.	[ { "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: [Broken statue of Indian god Shri Krishna.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004787/0.png", "losevideos/004787/1.png", "losevideos/004787/2.png", "losevideos/004787/3.png", "losevideos/004787/4.png", "losevideos/004787/5.png", "losevideos/004787/6.png", "losevideos/004787/7.png", "winvideos/004787/0.png", "winvideos/004787/1.png", "winvideos/004787/2.png", "winvideos/004787/3.png", "winvideos/004787/4.png", "winvideos/004787/5.png", "winvideos/004787/6.png", "winvideos/004787/7.png" ]
beautiful sunset in wuxia world and couple dancing with sword.	[ { "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 sunset in wuxia world and couple dancing with sword.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003625/0.png", "losevideos/003625/1.png", "losevideos/003625/2.png", "losevideos/003625/3.png", "losevideos/003625/4.png", "losevideos/003625/5.png", "losevideos/003625/6.png", "losevideos/003625/7.png", "winvideos/003625/0.png", "winvideos/003625/1.png", "winvideos/003625/2.png", "winvideos/003625/3.png", "winvideos/003625/4.png", "winvideos/003625/5.png", "winvideos/003625/6.png", "winvideos/003625/7.png" ]
amazon forest -w 1.5 -size 50 Message: Impactive AI (Font: MODERN).	[ { "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: [amazon forest -w 1.5 -size 50 Message: Impactive AI (Font: MODERN).]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007986/0.png", "losevideos/007986/1.png", "losevideos/007986/2.png", "losevideos/007986/3.png", "losevideos/007986/4.png", "losevideos/007986/5.png", "losevideos/007986/6.png", "losevideos/007986/7.png", "winvideos/007986/0.png", "winvideos/007986/1.png", "winvideos/007986/2.png", "winvideos/007986/3.png", "winvideos/007986/4.png", "winvideos/007986/5.png", "winvideos/007986/6.png", "winvideos/007986/7.png" ]
Hair flying, lights flying around, anime style.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Hair flying, lights flying around, anime style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009844/0.png", "winvideos/009844/1.png", "winvideos/009844/2.png", "winvideos/009844/3.png", "winvideos/009844/4.png", "winvideos/009844/5.png", "winvideos/009844/6.png", "winvideos/009844/7.png", "losevideos/009844/0.png", "losevideos/009844/1.png", "losevideos/009844/2.png", "losevideos/009844/3.png", "losevideos/009844/4.png", "losevideos/009844/5.png", "losevideos/009844/6.png", "losevideos/009844/7.png" ]
jagarnath puri temple.	[ { "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: [jagarnath puri temple.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001422/0.png", "winvideos/001422/1.png", "winvideos/001422/2.png", "winvideos/001422/3.png", "winvideos/001422/4.png", "winvideos/001422/5.png", "winvideos/001422/6.png", "winvideos/001422/7.png", "losevideos/001422/0.png", "losevideos/001422/1.png", "losevideos/001422/2.png", "losevideos/001422/3.png", "losevideos/001422/4.png", "losevideos/001422/5.png", "losevideos/001422/6.png", "losevideos/001422/7.png" ]
the bird twitter flies and sits on the letter solbitrium rain falls on the ground and turns to emeralds, Ultra-detail, surrealism, hair fluttering, film, beautiful lighting, twilight, rainbow holograms.	[ { "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 bird twitter flies and sits on the letter solbitrium rain falls on the ground and turns to emeralds, Ultra-detail, surrealism, hair fluttering, film, beautiful lighting, twilight, rainbow holograms.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007009/0.png", "losevideos/007009/1.png", "losevideos/007009/2.png", "losevideos/007009/3.png", "losevideos/007009/4.png", "losevideos/007009/5.png", "losevideos/007009/6.png", "losevideos/007009/7.png", "winvideos/007009/0.png", "winvideos/007009/1.png", "winvideos/007009/2.png", "winvideos/007009/3.png", "winvideos/007009/4.png", "winvideos/007009/5.png", "winvideos/007009/6.png", "winvideos/007009/7.png" ]
ninja fighting in the middle of an empty vally standing on water, the hero is about to unleash an earth shattering jutsu, the villian is about to counter with an equally powerful jutsu, naruto manga, detailed, illustrated by Masashi Kishimoto, hand drawn.	[ { "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: [ninja fighting in the middle of an empty vally standing on water, the hero is about to unleash an earth shattering jutsu, the villian is about to counter with an equally powerful jutsu, naruto manga, detailed, illustrated by Masashi Kishimoto, hand drawn.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006509/0.png", "winvideos/006509/1.png", "winvideos/006509/2.png", "winvideos/006509/3.png", "winvideos/006509/4.png", "winvideos/006509/5.png", "winvideos/006509/6.png", "winvideos/006509/7.png", "losevideos/006509/0.png", "losevideos/006509/1.png", "losevideos/006509/2.png", "losevideos/006509/3.png", "losevideos/006509/4.png", "losevideos/006509/5.png", "losevideos/006509/6.png", "losevideos/006509/7.png" ]
she performed a ritual to release the trapped souls and banish the vengeful spirit once and for all.	[ { "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: [she performed a ritual to release the trapped souls and banish the vengeful spirit once and for all.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005475/0.png", "winvideos/005475/1.png", "winvideos/005475/2.png", "winvideos/005475/3.png", "winvideos/005475/4.png", "winvideos/005475/5.png", "winvideos/005475/6.png", "winvideos/005475/7.png", "losevideos/005475/0.png", "losevideos/005475/1.png", "losevideos/005475/2.png", "losevideos/005475/3.png", "losevideos/005475/4.png", "losevideos/005475/5.png", "losevideos/005475/6.png", "losevideos/005475/7.png" ]
Movie texture, spiders crawling over women's faces.	[ { "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: [Movie texture, spiders crawling over women's faces.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007790/0.png", "losevideos/007790/1.png", "losevideos/007790/2.png", "losevideos/007790/3.png", "losevideos/007790/4.png", "losevideos/007790/5.png", "losevideos/007790/6.png", "losevideos/007790/7.png", "winvideos/007790/0.png", "winvideos/007790/1.png", "winvideos/007790/2.png", "winvideos/007790/3.png", "winvideos/007790/4.png", "winvideos/007790/5.png", "winvideos/007790/6.png", "winvideos/007790/7.png" ]