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
logo for photography royal look Abstract logos illustration, 2D, simple, minimalism, detail.	[ { "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: [logo for photography royal look Abstract logos illustration, 2D, simple, minimalism, detail.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000249/0.png", "winvideos/000249/1.png", "winvideos/000249/2.png", "winvideos/000249/3.png", "winvideos/000249/4.png", "winvideos/000249/5.png", "winvideos/000249/6.png", "winvideos/000249/7.png", "losevideos/000249/0.png", "losevideos/000249/1.png", "losevideos/000249/2.png", "losevideos/000249/3.png", "losevideos/000249/4.png", "losevideos/000249/5.png", "losevideos/000249/6.png", "losevideos/000249/7.png" ]
vintage horror film horror face from 40's on a deep forest at night performing a satanic ritual, cinematic view black and white film 35mm, imposible corporal move, zoom out slow.	[ { "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: [vintage horror film horror face from 40's on a deep forest at night performing a satanic ritual, cinematic view black and white film 35mm, imposible corporal move, zoom out slow.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002377/0.png", "winvideos/002377/1.png", "winvideos/002377/2.png", "winvideos/002377/3.png", "winvideos/002377/4.png", "winvideos/002377/5.png", "winvideos/002377/6.png", "winvideos/002377/7.png", "losevideos/002377/0.png", "losevideos/002377/1.png", "losevideos/002377/2.png", "losevideos/002377/3.png", "losevideos/002377/4.png", "losevideos/002377/5.png", "losevideos/002377/6.png", "losevideos/002377/7.png" ]
rompt: a fly landing on a cup of chocolate mousse, 3d render -neg disformed, bad quality, grain -cam 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: [rompt: a fly landing on a cup of chocolate mousse, 3d render -neg disformed, bad quality, grain -cam zoom in.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007583/0.png", "losevideos/007583/1.png", "losevideos/007583/2.png", "losevideos/007583/3.png", "losevideos/007583/4.png", "losevideos/007583/5.png", "losevideos/007583/6.png", "losevideos/007583/7.png", "winvideos/007583/0.png", "winvideos/007583/1.png", "winvideos/007583/2.png", "winvideos/007583/3.png", "winvideos/007583/4.png", "winvideos/007583/5.png", "winvideos/007583/6.png", "winvideos/007583/7.png" ]
The Joker, Jack Sparrow, and a pirate horse playing, realistic, cinematic, 8k resolution, 4k quality, -fps 24 -camera pan left.	[ { "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 Joker, Jack Sparrow, and a pirate horse playing, realistic, cinematic, 8k resolution, 4k quality, -fps 24 -camera pan left.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002723/0.png", "losevideos/002723/1.png", "losevideos/002723/2.png", "losevideos/002723/3.png", "losevideos/002723/4.png", "losevideos/002723/5.png", "losevideos/002723/6.png", "losevideos/002723/7.png", "winvideos/002723/0.png", "winvideos/002723/1.png", "winvideos/002723/2.png", "winvideos/002723/3.png", "winvideos/002723/4.png", "winvideos/002723/5.png", "winvideos/002723/6.png", "winvideos/002723/7.png" ]
a high viscous red fluid dripping out of a glass, highly detailed, film grain, 8k.	[ { "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 high viscous red fluid dripping out of a glass, highly detailed, film grain, 8k.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006351/0.png", "winvideos/006351/1.png", "winvideos/006351/2.png", "winvideos/006351/3.png", "winvideos/006351/4.png", "winvideos/006351/5.png", "winvideos/006351/6.png", "winvideos/006351/7.png", "losevideos/006351/0.png", "losevideos/006351/1.png", "losevideos/006351/2.png", "losevideos/006351/3.png", "losevideos/006351/4.png", "losevideos/006351/5.png", "losevideos/006351/6.png", "losevideos/006351/7.png" ]
Cinematic snow scene, extreme close-up of Santa Claus, 3D rendering.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Cinematic snow scene, extreme close-up of Santa Claus, 3D rendering.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003104/0.png", "losevideos/003104/1.png", "losevideos/003104/2.png", "losevideos/003104/3.png", "losevideos/003104/4.png", "losevideos/003104/5.png", "losevideos/003104/6.png", "losevideos/003104/7.png", "winvideos/003104/0.png", "winvideos/003104/1.png", "winvideos/003104/2.png", "winvideos/003104/3.png", "winvideos/003104/4.png", "winvideos/003104/5.png", "winvideos/003104/6.png", "winvideos/003104/7.png" ]
Sauron lifting the Champions League trophy.	[ { "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: [Sauron lifting the Champions League trophy.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007773/0.png", "losevideos/007773/1.png", "losevideos/007773/2.png", "losevideos/007773/3.png", "losevideos/007773/4.png", "losevideos/007773/5.png", "losevideos/007773/6.png", "losevideos/007773/7.png", "winvideos/007773/0.png", "winvideos/007773/1.png", "winvideos/007773/2.png", "winvideos/007773/3.png", "winvideos/007773/4.png", "winvideos/007773/5.png", "winvideos/007773/6.png", "winvideos/007773/7.png" ]
In a vibrant and magical forest, there exists a realm where the trees talk, animals possess unique powers, and the very air is infused with a sense of wonder. The story follows a young and curious character named Luna, who stumbles upon this enchanted forest one sunny afternoon. Luna is drawn into the forest by the enchanting melody of a mystical bird.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [In a vibrant and magical forest, there exists a realm where the trees talk, animals possess unique powers, and the very air is infused with a sense of wonder. The story follows a young and curious character named Luna, who stumbles upon this enchanted forest one sunny afternoon. Luna is drawn into the forest by the enchanting melody of a mystical bird.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009707/0.png", "winvideos/009707/1.png", "winvideos/009707/2.png", "winvideos/009707/3.png", "winvideos/009707/4.png", "winvideos/009707/5.png", "winvideos/009707/6.png", "winvideos/009707/7.png", "losevideos/009707/0.png", "losevideos/009707/1.png", "losevideos/009707/2.png", "losevideos/009707/3.png", "losevideos/009707/4.png", "losevideos/009707/5.png", "losevideos/009707/6.png", "losevideos/009707/7.png" ]
moving logo purple ostriches.	[ { "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: [moving logo purple ostriches.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006026/0.png", "losevideos/006026/1.png", "losevideos/006026/2.png", "losevideos/006026/3.png", "losevideos/006026/4.png", "losevideos/006026/5.png", "losevideos/006026/6.png", "losevideos/006026/7.png", "winvideos/006026/0.png", "winvideos/006026/1.png", "winvideos/006026/2.png", "winvideos/006026/3.png", "winvideos/006026/4.png", "winvideos/006026/5.png", "winvideos/006026/6.png", "winvideos/006026/7.png" ]
10 animate the rain.	[ { "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: [10 animate the rain.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009197/0.png", "losevideos/009197/1.png", "losevideos/009197/2.png", "losevideos/009197/3.png", "losevideos/009197/4.png", "losevideos/009197/5.png", "losevideos/009197/6.png", "losevideos/009197/7.png", "winvideos/009197/0.png", "winvideos/009197/1.png", "winvideos/009197/2.png", "winvideos/009197/3.png", "winvideos/009197/4.png", "winvideos/009197/5.png", "winvideos/009197/6.png", "winvideos/009197/7.png" ]
a 2d cartoon image of a teenage girl holding a letter and jumping in excitement outside an apartment, she has a shoulder length black hair,.	[ { "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 2d cartoon image of a teenage girl holding a letter and jumping in excitement outside an apartment, she has a shoulder length black hair,.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004011/0.png", "winvideos/004011/1.png", "winvideos/004011/2.png", "winvideos/004011/3.png", "winvideos/004011/4.png", "winvideos/004011/5.png", "winvideos/004011/6.png", "winvideos/004011/7.png", "losevideos/004011/0.png", "losevideos/004011/1.png", "losevideos/004011/2.png", "losevideos/004011/3.png", "losevideos/004011/4.png", "losevideos/004011/5.png", "losevideos/004011/6.png", "losevideos/004011/7.png" ]
A doctor in a si fi world, talking moving hands, camera follwing a 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: [A doctor in a si fi world, talking moving hands, camera follwing a car.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001439/0.png", "losevideos/001439/1.png", "losevideos/001439/2.png", "losevideos/001439/3.png", "losevideos/001439/4.png", "losevideos/001439/5.png", "losevideos/001439/6.png", "losevideos/001439/7.png", "winvideos/001439/0.png", "winvideos/001439/1.png", "winvideos/001439/2.png", "winvideos/001439/3.png", "winvideos/001439/4.png", "winvideos/001439/5.png", "winvideos/001439/6.png", "winvideos/001439/7.png" ]
60s bright pastel shiny reflective jello mold centerpiece.	[ { "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: [60s bright pastel shiny reflective jello mold centerpiece.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008172/0.png", "losevideos/008172/1.png", "losevideos/008172/2.png", "losevideos/008172/3.png", "losevideos/008172/4.png", "losevideos/008172/5.png", "losevideos/008172/6.png", "losevideos/008172/7.png", "winvideos/008172/0.png", "winvideos/008172/1.png", "winvideos/008172/2.png", "winvideos/008172/3.png", "winvideos/008172/4.png", "winvideos/008172/5.png", "winvideos/008172/6.png", "winvideos/008172/7.png" ]
the lion stands on the top of the mountain.	[ { "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 lion stands on the top of the mountain.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007075/0.png", "losevideos/007075/1.png", "losevideos/007075/2.png", "losevideos/007075/3.png", "losevideos/007075/4.png", "losevideos/007075/5.png", "losevideos/007075/6.png", "losevideos/007075/7.png", "winvideos/007075/0.png", "winvideos/007075/1.png", "winvideos/007075/2.png", "winvideos/007075/3.png", "winvideos/007075/4.png", "winvideos/007075/5.png", "winvideos/007075/6.png", "winvideos/007075/7.png" ]
realistic movement,person gracefully showing himself while the camera slowly moves around 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: [realistic movement,person gracefully showing himself while the camera slowly moves around him.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001259/0.png", "losevideos/001259/1.png", "losevideos/001259/2.png", "losevideos/001259/3.png", "losevideos/001259/4.png", "losevideos/001259/5.png", "losevideos/001259/6.png", "losevideos/001259/7.png", "winvideos/001259/0.png", "winvideos/001259/1.png", "winvideos/001259/2.png", "winvideos/001259/3.png", "winvideos/001259/4.png", "winvideos/001259/5.png", "winvideos/001259/6.png", "winvideos/001259/7.png" ]
beautiful lady with black hair smoking in an ally watching a stranger walk by.	[ { "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 lady with black hair smoking in an ally watching a stranger walk by.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000433/0.png", "winvideos/000433/1.png", "winvideos/000433/2.png", "winvideos/000433/3.png", "winvideos/000433/4.png", "winvideos/000433/5.png", "winvideos/000433/6.png", "winvideos/000433/7.png", "losevideos/000433/0.png", "losevideos/000433/1.png", "losevideos/000433/2.png", "losevideos/000433/3.png", "losevideos/000433/4.png", "losevideos/000433/5.png", "losevideos/000433/6.png", "losevideos/000433/7.png" ]
max payne shoot in bullet time.	[ { "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: [max payne shoot in bullet time.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006247/0.png", "winvideos/006247/1.png", "winvideos/006247/2.png", "winvideos/006247/3.png", "winvideos/006247/4.png", "winvideos/006247/5.png", "winvideos/006247/6.png", "winvideos/006247/7.png", "losevideos/006247/0.png", "losevideos/006247/1.png", "losevideos/006247/2.png", "losevideos/006247/3.png", "losevideos/006247/4.png", "losevideos/006247/5.png", "losevideos/006247/6.png", "losevideos/006247/7.png" ]
grandma scooping up a infant boy,long shot,walking in the room,animation pixar, in the style of Pixar's 'Coco' , 8k --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: [grandma scooping up a infant boy,long shot,walking in the room,animation pixar, in the style of Pixar's 'Coco' , 8k --ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003407/0.png", "winvideos/003407/1.png", "winvideos/003407/2.png", "winvideos/003407/3.png", "winvideos/003407/4.png", "winvideos/003407/5.png", "winvideos/003407/6.png", "winvideos/003407/7.png", "losevideos/003407/0.png", "losevideos/003407/1.png", "losevideos/003407/2.png", "losevideos/003407/3.png", "losevideos/003407/4.png", "losevideos/003407/5.png", "losevideos/003407/6.png", "losevideos/003407/7.png" ]
Capture the secretive gathering of teenagers in the woods through a 35mm lens, inspired by the works of Sally Mann. The scene is bathed in a warm, golden color temperature, creating a nostalgic and eerie ambiance. The teenagers' faces are a mix of excitement and trepidation, illuminated by the soft, filtered sunlight streaming through the 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: [Capture the secretive gathering of teenagers in the woods through a 35mm lens, inspired by the works of Sally Mann. The scene is bathed in a warm, golden color temperature, creating a nostalgic and eerie ambiance. The teenagers' faces are a mix of excitement and trepidation, illuminated by the soft, filtered sunlight streaming through the trees.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006502/0.png", "losevideos/006502/1.png", "losevideos/006502/2.png", "losevideos/006502/3.png", "losevideos/006502/4.png", "losevideos/006502/5.png", "losevideos/006502/6.png", "losevideos/006502/7.png", "winvideos/006502/0.png", "winvideos/006502/1.png", "winvideos/006502/2.png", "winvideos/006502/3.png", "winvideos/006502/4.png", "winvideos/006502/5.png", "winvideos/006502/6.png", "winvideos/006502/7.png" ]
Steve Jobs vs Elon Musk fighting by slapping each other cowardly. Mark Zuckerberg is laughing.	[ { "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: [Steve Jobs vs Elon Musk fighting by slapping each other cowardly. Mark Zuckerberg is laughing.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003208/0.png", "winvideos/003208/1.png", "winvideos/003208/2.png", "winvideos/003208/3.png", "winvideos/003208/4.png", "winvideos/003208/5.png", "winvideos/003208/6.png", "winvideos/003208/7.png", "losevideos/003208/0.png", "losevideos/003208/1.png", "losevideos/003208/2.png", "losevideos/003208/3.png", "losevideos/003208/4.png", "losevideos/003208/5.png", "losevideos/003208/6.png", "losevideos/003208/7.png" ]
3d Tida mouse dancing and eating popcorn Pixar 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: [3d Tida mouse dancing and eating popcorn Pixar style.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007462/0.png", "winvideos/007462/1.png", "winvideos/007462/2.png", "winvideos/007462/3.png", "winvideos/007462/4.png", "winvideos/007462/5.png", "winvideos/007462/6.png", "winvideos/007462/7.png", "losevideos/007462/0.png", "losevideos/007462/1.png", "losevideos/007462/2.png", "losevideos/007462/3.png", "losevideos/007462/4.png", "losevideos/007462/5.png", "losevideos/007462/6.png", "losevideos/007462/7.png" ]
landscape with starry sky.	[ { "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: [landscape with starry sky.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008636/0.png", "losevideos/008636/1.png", "losevideos/008636/2.png", "losevideos/008636/3.png", "losevideos/008636/4.png", "losevideos/008636/5.png", "losevideos/008636/6.png", "losevideos/008636/7.png", "winvideos/008636/0.png", "winvideos/008636/1.png", "winvideos/008636/2.png", "winvideos/008636/3.png", "winvideos/008636/4.png", "winvideos/008636/5.png", "winvideos/008636/6.png", "winvideos/008636/7.png" ]
jungle, at night, thunderstorm.	[ { "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, at night, thunderstorm.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006438/0.png", "winvideos/006438/1.png", "winvideos/006438/2.png", "winvideos/006438/3.png", "winvideos/006438/4.png", "winvideos/006438/5.png", "winvideos/006438/6.png", "winvideos/006438/7.png", "losevideos/006438/0.png", "losevideos/006438/1.png", "losevideos/006438/2.png", "losevideos/006438/3.png", "losevideos/006438/4.png", "losevideos/006438/5.png", "losevideos/006438/6.png", "losevideos/006438/7.png" ]
Generate an image of a lush, vibrant forest with towering trees, colorful flowers, and a bright sun in the sky. Birds should be flying around, and the scene should feel magical.	[ { "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 an image of a lush, vibrant forest with towering trees, colorful flowers, and a bright sun in the sky. Birds should be flying around, and the scene should feel magical.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000903/0.png", "losevideos/000903/1.png", "losevideos/000903/2.png", "losevideos/000903/3.png", "losevideos/000903/4.png", "losevideos/000903/5.png", "losevideos/000903/6.png", "losevideos/000903/7.png", "winvideos/000903/0.png", "winvideos/000903/1.png", "winvideos/000903/2.png", "winvideos/000903/3.png", "winvideos/000903/4.png", "winvideos/000903/5.png", "winvideos/000903/6.png", "winvideos/000903/7.png" ]
Scarlett Johansson model 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: [Scarlett Johansson model dancing.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002132/0.png", "losevideos/002132/1.png", "losevideos/002132/2.png", "losevideos/002132/3.png", "losevideos/002132/4.png", "losevideos/002132/5.png", "losevideos/002132/6.png", "losevideos/002132/7.png", "winvideos/002132/0.png", "winvideos/002132/1.png", "winvideos/002132/2.png", "winvideos/002132/3.png", "winvideos/002132/4.png", "winvideos/002132/5.png", "winvideos/002132/6.png", "winvideos/002132/7.png" ]
Finland's Prime Minister Sanna Marin is holding a salty pie in her hands and looks pensive. kitchen in the background. -camera pan right -motion 2 -gs 22 -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent 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: [Finland's Prime Minister Sanna Marin is holding a salty pie in her hands and looks pensive. kitchen in the background. -camera pan right -motion 2 -gs 22 -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008421/0.png", "losevideos/008421/1.png", "losevideos/008421/2.png", "losevideos/008421/3.png", "losevideos/008421/4.png", "losevideos/008421/5.png", "losevideos/008421/6.png", "losevideos/008421/7.png", "winvideos/008421/0.png", "winvideos/008421/1.png", "winvideos/008421/2.png", "winvideos/008421/3.png", "winvideos/008421/4.png", "winvideos/008421/5.png", "winvideos/008421/6.png", "winvideos/008421/7.png" ]
a house being purchased.	[ { "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 house being purchased.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005988/0.png", "losevideos/005988/1.png", "losevideos/005988/2.png", "losevideos/005988/3.png", "losevideos/005988/4.png", "losevideos/005988/5.png", "losevideos/005988/6.png", "losevideos/005988/7.png", "winvideos/005988/0.png", "winvideos/005988/1.png", "winvideos/005988/2.png", "winvideos/005988/3.png", "winvideos/005988/4.png", "winvideos/005988/5.png", "winvideos/005988/6.png", "winvideos/005988/7.png" ]
lunar rover, lunar landscape -fps 24 -motion 3 -camera pan 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: [lunar rover, lunar landscape -fps 24 -motion 3 -camera pan down.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006507/0.png", "losevideos/006507/1.png", "losevideos/006507/2.png", "losevideos/006507/3.png", "losevideos/006507/4.png", "losevideos/006507/5.png", "losevideos/006507/6.png", "losevideos/006507/7.png", "winvideos/006507/0.png", "winvideos/006507/1.png", "winvideos/006507/2.png", "winvideos/006507/3.png", "winvideos/006507/4.png", "winvideos/006507/5.png", "winvideos/006507/6.png", "winvideos/006507/7.png" ]
: A meteorite impact causing a tsunami disaster. -ar 9:16 -motion 1.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [: A meteorite impact causing a tsunami disaster. -ar 9:16 -motion 1.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003817/0.png", "losevideos/003817/1.png", "losevideos/003817/2.png", "losevideos/003817/3.png", "losevideos/003817/4.png", "losevideos/003817/5.png", "losevideos/003817/6.png", "losevideos/003817/7.png", "winvideos/003817/0.png", "winvideos/003817/1.png", "winvideos/003817/2.png", "winvideos/003817/3.png", "winvideos/003817/4.png", "winvideos/003817/5.png", "winvideos/003817/6.png", "winvideos/003817/7.png" ]
closeup of a woman feet walking in ballet shoes.	[ { "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: [closeup of a woman feet walking in ballet shoes.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005330/0.png", "losevideos/005330/1.png", "losevideos/005330/2.png", "losevideos/005330/3.png", "losevideos/005330/4.png", "losevideos/005330/5.png", "losevideos/005330/6.png", "losevideos/005330/7.png", "winvideos/005330/0.png", "winvideos/005330/1.png", "winvideos/005330/2.png", "winvideos/005330/3.png", "winvideos/005330/4.png", "winvideos/005330/5.png", "winvideos/005330/6.png", "winvideos/005330/7.png" ]
green giant fight american captain.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [green giant fight american captain.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007116/0.png", "winvideos/007116/1.png", "winvideos/007116/2.png", "winvideos/007116/3.png", "winvideos/007116/4.png", "winvideos/007116/5.png", "winvideos/007116/6.png", "winvideos/007116/7.png", "losevideos/007116/0.png", "losevideos/007116/1.png", "losevideos/007116/2.png", "losevideos/007116/3.png", "losevideos/007116/4.png", "losevideos/007116/5.png", "losevideos/007116/6.png", "losevideos/007116/7.png" ]
flowers, jesus, northern lights, sunset, 4k, incredible, realistic style, artistic, wild colors, photorealistic, Hyper-Realistic, Hyper-Detailed****.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [flowers, jesus, northern lights, sunset, 4k, incredible, realistic style, artistic, wild colors, photorealistic, Hyper-Realistic, Hyper-Detailed****.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003088/0.png", "losevideos/003088/1.png", "losevideos/003088/2.png", "losevideos/003088/3.png", "losevideos/003088/4.png", "losevideos/003088/5.png", "losevideos/003088/6.png", "losevideos/003088/7.png", "winvideos/003088/0.png", "winvideos/003088/1.png", "winvideos/003088/2.png", "winvideos/003088/3.png", "winvideos/003088/4.png", "winvideos/003088/5.png", "winvideos/003088/6.png", "winvideos/003088/7.png" ]
knights guards patrolling gray castle walls, game of thrones.	[ { "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: [knights guards patrolling gray castle walls, game of thrones.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004329/0.png", "losevideos/004329/1.png", "losevideos/004329/2.png", "losevideos/004329/3.png", "losevideos/004329/4.png", "losevideos/004329/5.png", "losevideos/004329/6.png", "losevideos/004329/7.png", "winvideos/004329/0.png", "winvideos/004329/1.png", "winvideos/004329/2.png", "winvideos/004329/3.png", "winvideos/004329/4.png", "winvideos/004329/5.png", "winvideos/004329/6.png", "winvideos/004329/7.png" ]
photograph of a thin 20 foot tall humanoid creature with a long white flowing yeti robe and a white long beak bird stork mask, long white beak, long flowing plumage, sitting on a snowy plateau, on a snow-covered a siberian mountain,arctic, cryptozoology --ar 16:9 --v 5.2.	[ { "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: [photograph of a thin 20 foot tall humanoid creature with a long white flowing yeti robe and a white long beak bird stork mask, long white beak, long flowing plumage, sitting on a snowy plateau, on a snow-covered a siberian mountain,arctic, cryptozoology --ar 16:9\n--v 5.2.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006722/0.png", "winvideos/006722/1.png", "winvideos/006722/2.png", "winvideos/006722/3.png", "winvideos/006722/4.png", "winvideos/006722/5.png", "winvideos/006722/6.png", "winvideos/006722/7.png", "losevideos/006722/0.png", "losevideos/006722/1.png", "losevideos/006722/2.png", "losevideos/006722/3.png", "losevideos/006722/4.png", "losevideos/006722/5.png", "losevideos/006722/6.png", "losevideos/006722/7.png" ]
a people falling from an airplane shot by a missile.	[ { "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 people falling from an airplane shot by a missile.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002085/0.png", "losevideos/002085/1.png", "losevideos/002085/2.png", "losevideos/002085/3.png", "losevideos/002085/4.png", "losevideos/002085/5.png", "losevideos/002085/6.png", "losevideos/002085/7.png", "winvideos/002085/0.png", "winvideos/002085/1.png", "winvideos/002085/2.png", "winvideos/002085/3.png", "winvideos/002085/4.png", "winvideos/002085/5.png", "winvideos/002085/6.png", "winvideos/002085/7.png" ]
Animate a lush, green forest with vibrant trees, bushes, and a cheerful atmosphere.	[ { "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 lush, green forest with vibrant trees, bushes, and a cheerful atmosphere.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002163/0.png", "winvideos/002163/1.png", "winvideos/002163/2.png", "winvideos/002163/3.png", "winvideos/002163/4.png", "winvideos/002163/5.png", "winvideos/002163/6.png", "winvideos/002163/7.png", "losevideos/002163/0.png", "losevideos/002163/1.png", "losevideos/002163/2.png", "losevideos/002163/3.png", "losevideos/002163/4.png", "losevideos/002163/5.png", "losevideos/002163/6.png", "losevideos/002163/7.png" ]
VHS found footage : a man walks past a dark scene with statues, monochromatic white figures, in the style of experimental video art.	[ { "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: [VHS found footage : a man walks past a dark scene with statues, monochromatic white figures, in the style of experimental video art.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008017/0.png", "losevideos/008017/1.png", "losevideos/008017/2.png", "losevideos/008017/3.png", "losevideos/008017/4.png", "losevideos/008017/5.png", "losevideos/008017/6.png", "losevideos/008017/7.png", "winvideos/008017/0.png", "winvideos/008017/1.png", "winvideos/008017/2.png", "winvideos/008017/3.png", "winvideos/008017/4.png", "winvideos/008017/5.png", "winvideos/008017/6.png", "winvideos/008017/7.png" ]
Two ROBBY MEN, wearing torn clothes and carrying makeshift weapons, force a COUPLE to hand over their belongings. The couple is terrified.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Two ROBBY MEN, wearing torn clothes and carrying makeshift weapons, force a COUPLE to hand over their belongings. The couple is terrified.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005916/0.png", "winvideos/005916/1.png", "winvideos/005916/2.png", "winvideos/005916/3.png", "winvideos/005916/4.png", "winvideos/005916/5.png", "winvideos/005916/6.png", "winvideos/005916/7.png", "losevideos/005916/0.png", "losevideos/005916/1.png", "losevideos/005916/2.png", "losevideos/005916/3.png", "losevideos/005916/4.png", "losevideos/005916/5.png", "losevideos/005916/6.png", "losevideos/005916/7.png" ]
Generate stunning AI images of a deer with impressive horns in various natural settings. Render scenes in 4K, 8K, and 64K resolutions, focusing on the majesty of the deer's features. Emphasize hyperrealistic details, capturing the intricacies of the deer's fur, eyes, and, most notably, its majestic horns. Utilize 3D rendering techniques to add depth and realism to the scene, allowing for a seamless integration of the deer into its environment. Experiment with different lighting conditions to enhance the visual impact of the horns. Implement Unreal Engine v5 for advanced rendering effects, ensuring a lifelike portrayal of the deer. Enhance the visual experience with HDR and UHD qualities, emphasizing professional photography aspects. Explore various compositions to showcase the grace and beauty of the deer with its magnificent horns in different natural settings." Message: 1 (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: [Generate stunning AI images of a deer with impressive horns in various natural settings. Render scenes in 4K, 8K, and 64K resolutions, focusing on the majesty of the deer's features. Emphasize hyperrealistic details, capturing the intricacies of the deer's fur, eyes, and, most notably, its majestic horns. Utilize 3D rendering techniques to add depth and realism to the scene, allowing for a seamless integration of the deer into its environment. Experiment with different lighting conditions to enhance the visual impact of the horns. Implement Unreal Engine v5 for advanced rendering effects, ensuring a lifelike portrayal of the deer. Enhance the visual experience with HDR and UHD qualities, emphasizing professional photography aspects. Explore various compositions to showcase the grace and beauty of the deer with its magnificent horns in different natural settings." Message: 1 (Font: MODERN).]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009939/0.png", "losevideos/009939/1.png", "losevideos/009939/2.png", "losevideos/009939/3.png", "losevideos/009939/4.png", "losevideos/009939/5.png", "losevideos/009939/6.png", "losevideos/009939/7.png", "winvideos/009939/0.png", "winvideos/009939/1.png", "winvideos/009939/2.png", "winvideos/009939/3.png", "winvideos/009939/4.png", "winvideos/009939/5.png", "winvideos/009939/6.png", "winvideos/009939/7.png" ]
hyper realistic place in the nature with a glittery waterfall and clouds above the water. Soft lilac colors. Warm lights --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: [hyper realistic place in the nature with a glittery waterfall and clouds above the water. Soft lilac colors. Warm lights --ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009454/0.png", "losevideos/009454/1.png", "losevideos/009454/2.png", "losevideos/009454/3.png", "losevideos/009454/4.png", "losevideos/009454/5.png", "losevideos/009454/6.png", "losevideos/009454/7.png", "winvideos/009454/0.png", "winvideos/009454/1.png", "winvideos/009454/2.png", "winvideos/009454/3.png", "winvideos/009454/4.png", "winvideos/009454/5.png", "winvideos/009454/6.png", "winvideos/009454/7.png" ]