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
Workers Leaving the Lumière Factory, black-and-white film captures the remarkable pace at which 19th-century workers exit the gates of the Lumière factory in Lyon, France. The motion is swift and evocative, emphasizing the workers' bustling activity as they pour out, each dressed in period-specific attire. The film not only offers a glimpse into their world but also preserves architectural details of the factory building, adding depth to this remarkable historical documentation.	[ { "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: [Workers Leaving the Lumière Factory, black-and-white film captures the remarkable pace at which 19th-century workers exit the gates of the Lumière factory in Lyon, France. The motion is swift and evocative, emphasizing the workers' bustling activity as they pour out, each dressed in period-specific attire. The film not only offers a glimpse into their world but also preserves architectural details of the factory building, adding depth to this remarkable historical documentation.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004395/0.png", "losevideos/004395/1.png", "losevideos/004395/2.png", "losevideos/004395/3.png", "losevideos/004395/4.png", "losevideos/004395/5.png", "losevideos/004395/6.png", "losevideos/004395/7.png", "winvideos/004395/0.png", "winvideos/004395/1.png", "winvideos/004395/2.png", "winvideos/004395/3.png", "winvideos/004395/4.png", "winvideos/004395/5.png", "winvideos/004395/6.png", "winvideos/004395/7.png" ]
cat in 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: [cat in space.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/007846/0.png", "winvideos/007846/1.png", "winvideos/007846/2.png", "winvideos/007846/3.png", "winvideos/007846/4.png", "winvideos/007846/5.png", "winvideos/007846/6.png", "winvideos/007846/7.png", "losevideos/007846/0.png", "losevideos/007846/1.png", "losevideos/007846/2.png", "losevideos/007846/3.png", "losevideos/007846/4.png", "losevideos/007846/5.png", "losevideos/007846/6.png", "losevideos/007846/7.png" ]
cute cat with a magic ancient armor standing over a defeated planet.	[ { "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: [cute cat with a magic ancient armor standing over a defeated planet.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001134/0.png", "losevideos/001134/1.png", "losevideos/001134/2.png", "losevideos/001134/3.png", "losevideos/001134/4.png", "losevideos/001134/5.png", "losevideos/001134/6.png", "losevideos/001134/7.png", "winvideos/001134/0.png", "winvideos/001134/1.png", "winvideos/001134/2.png", "winvideos/001134/3.png", "winvideos/001134/4.png", "winvideos/001134/5.png", "winvideos/001134/6.png", "winvideos/001134/7.png" ]
Man from light falling to darkness, slow motion in the falling and all in dark colours.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Man from light falling to darkness, slow motion in the falling and all in dark colours.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008414/0.png", "losevideos/008414/1.png", "losevideos/008414/2.png", "losevideos/008414/3.png", "losevideos/008414/4.png", "losevideos/008414/5.png", "losevideos/008414/6.png", "losevideos/008414/7.png", "winvideos/008414/0.png", "winvideos/008414/1.png", "winvideos/008414/2.png", "winvideos/008414/3.png", "winvideos/008414/4.png", "winvideos/008414/5.png", "winvideos/008414/6.png", "winvideos/008414/7.png" ]
man into illusion, lot of colours, cinematic, animated ,trippy, -ar 9:20.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [man into illusion, lot of colours, cinematic, animated ,trippy, -ar 9:20.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001964/0.png", "losevideos/001964/1.png", "losevideos/001964/2.png", "losevideos/001964/3.png", "losevideos/001964/4.png", "losevideos/001964/5.png", "losevideos/001964/6.png", "losevideos/001964/7.png", "winvideos/001964/0.png", "winvideos/001964/1.png", "winvideos/001964/2.png", "winvideos/001964/3.png", "winvideos/001964/4.png", "winvideos/001964/5.png", "winvideos/001964/6.png", "winvideos/001964/7.png" ]
Master potter in another dimension making pottery on the wheel.	[ { "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: [Master potter in another dimension making pottery on the wheel.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002388/0.png", "losevideos/002388/1.png", "losevideos/002388/2.png", "losevideos/002388/3.png", "losevideos/002388/4.png", "losevideos/002388/5.png", "losevideos/002388/6.png", "losevideos/002388/7.png", "winvideos/002388/0.png", "winvideos/002388/1.png", "winvideos/002388/2.png", "winvideos/002388/3.png", "winvideos/002388/4.png", "winvideos/002388/5.png", "winvideos/002388/6.png", "winvideos/002388/7.png" ]
a smartphone with wings and a demon tail flying in the middle of a storm.	[ { "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 smartphone with wings and a demon tail flying in the middle of a storm.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008673/0.png", "losevideos/008673/1.png", "losevideos/008673/2.png", "losevideos/008673/3.png", "losevideos/008673/4.png", "losevideos/008673/5.png", "losevideos/008673/6.png", "losevideos/008673/7.png", "winvideos/008673/0.png", "winvideos/008673/1.png", "winvideos/008673/2.png", "winvideos/008673/3.png", "winvideos/008673/4.png", "winvideos/008673/5.png", "winvideos/008673/6.png", "winvideos/008673/7.png" ]
close up of iris closing with black background.	[ { "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: [close up of iris closing with black background.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009519/0.png", "losevideos/009519/1.png", "losevideos/009519/2.png", "losevideos/009519/3.png", "losevideos/009519/4.png", "losevideos/009519/5.png", "losevideos/009519/6.png", "losevideos/009519/7.png", "winvideos/009519/0.png", "winvideos/009519/1.png", "winvideos/009519/2.png", "winvideos/009519/3.png", "winvideos/009519/4.png", "winvideos/009519/5.png", "winvideos/009519/6.png", "winvideos/009519/7.png" ]
sci fi spaceship in round shap hovering over the sky , 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: [sci fi spaceship in round shap hovering over the sky , anime style.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007481/0.png", "losevideos/007481/1.png", "losevideos/007481/2.png", "losevideos/007481/3.png", "losevideos/007481/4.png", "losevideos/007481/5.png", "losevideos/007481/6.png", "losevideos/007481/7.png", "winvideos/007481/0.png", "winvideos/007481/1.png", "winvideos/007481/2.png", "winvideos/007481/3.png", "winvideos/007481/4.png", "winvideos/007481/5.png", "winvideos/007481/6.png", "winvideos/007481/7.png" ]
golden pig with jockey on it's back running in a horse race on a black background -motion 4 pig is running left to right -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, badly drawn, blurry, grainy, low resolution, over saturated, loack 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: [golden pig with jockey on it's back running in a horse race on a black background -motion 4 pig is running left to right -neg morphing, erratic fluctuation in motion, noisy, bad quality, distorted, badly drawn, blurry, grainy, low resolution, over saturated, loack of detail, inconsistent lighting.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001089/0.png", "winvideos/001089/1.png", "winvideos/001089/2.png", "winvideos/001089/3.png", "winvideos/001089/4.png", "winvideos/001089/5.png", "winvideos/001089/6.png", "winvideos/001089/7.png", "losevideos/001089/0.png", "losevideos/001089/1.png", "losevideos/001089/2.png", "losevideos/001089/3.png", "losevideos/001089/4.png", "losevideos/001089/5.png", "losevideos/001089/6.png", "losevideos/001089/7.png" ]
In ancient times, a horseman's horse is neighing in the Arabian desert.	[ { "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 ancient times, a horseman's horse is neighing in the Arabian desert.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002692/0.png", "losevideos/002692/1.png", "losevideos/002692/2.png", "losevideos/002692/3.png", "losevideos/002692/4.png", "losevideos/002692/5.png", "losevideos/002692/6.png", "losevideos/002692/7.png", "winvideos/002692/0.png", "winvideos/002692/1.png", "winvideos/002692/2.png", "winvideos/002692/3.png", "winvideos/002692/4.png", "winvideos/002692/5.png", "winvideos/002692/6.png", "winvideos/002692/7.png" ]
3D vintage retro hands watch stuck clock tribal chrome , chrometype style , rotating camera -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: [3D vintage retro hands watch stuck clock tribal chrome , chrometype style , rotating camera -ar 1:1.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009373/0.png", "winvideos/009373/1.png", "winvideos/009373/2.png", "winvideos/009373/3.png", "winvideos/009373/4.png", "winvideos/009373/5.png", "winvideos/009373/6.png", "winvideos/009373/7.png", "losevideos/009373/0.png", "losevideos/009373/1.png", "losevideos/009373/2.png", "losevideos/009373/3.png", "losevideos/009373/4.png", "losevideos/009373/5.png", "losevideos/009373/6.png", "losevideos/009373/7.png" ]
walking knight, forest.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [walking knight, forest.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007479/0.png", "losevideos/007479/1.png", "losevideos/007479/2.png", "losevideos/007479/3.png", "losevideos/007479/4.png", "losevideos/007479/5.png", "losevideos/007479/6.png", "losevideos/007479/7.png", "winvideos/007479/0.png", "winvideos/007479/1.png", "winvideos/007479/2.png", "winvideos/007479/3.png", "winvideos/007479/4.png", "winvideos/007479/5.png", "winvideos/007479/6.png", "winvideos/007479/7.png" ]
a girl with headphones walking towards stone stairs under the castle of buda, which was on her right side watching the yellow autumn leaves under her feet on the pavement, full side shot.	[ { "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 girl with headphones walking towards stone stairs under the castle of buda, which was on her right side watching the yellow autumn leaves under her feet on the pavement, full side shot.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001812/0.png", "winvideos/001812/1.png", "winvideos/001812/2.png", "winvideos/001812/3.png", "winvideos/001812/4.png", "winvideos/001812/5.png", "winvideos/001812/6.png", "winvideos/001812/7.png", "losevideos/001812/0.png", "losevideos/001812/1.png", "losevideos/001812/2.png", "losevideos/001812/3.png", "losevideos/001812/4.png", "losevideos/001812/5.png", "losevideos/001812/6.png", "losevideos/001812/7.png" ]
dark cabaret singer, horror face, 20´s, darkscape -motion 4.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [dark cabaret singer, horror face, 20´s, darkscape -motion 4.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002552/0.png", "winvideos/002552/1.png", "winvideos/002552/2.png", "winvideos/002552/3.png", "winvideos/002552/4.png", "winvideos/002552/5.png", "winvideos/002552/6.png", "winvideos/002552/7.png", "losevideos/002552/0.png", "losevideos/002552/1.png", "losevideos/002552/2.png", "losevideos/002552/3.png", "losevideos/002552/4.png", "losevideos/002552/5.png", "losevideos/002552/6.png", "losevideos/002552/7.png" ]
conductor conducting an orchestra made of gears, sunset, 4K -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: [conductor conducting an orchestra made of gears, sunset, 4K -ar 16:9.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008650/0.png", "winvideos/008650/1.png", "winvideos/008650/2.png", "winvideos/008650/3.png", "winvideos/008650/4.png", "winvideos/008650/5.png", "winvideos/008650/6.png", "winvideos/008650/7.png", "losevideos/008650/0.png", "losevideos/008650/1.png", "losevideos/008650/2.png", "losevideos/008650/3.png", "losevideos/008650/4.png", "losevideos/008650/5.png", "losevideos/008650/6.png", "losevideos/008650/7.png" ]
Low angle, A prison guard's hand opens the old solid steel door to a solitary confinement cell, follow focus on, Cinematic, intricate details, realistic skin, Ultra HD, highly accurate detail, Phantom camera -motion 3 -camera pan up -neg warping, deformed, phasing, flying, disappearing person, appearing person, mutating, bright 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: [Low angle, A prison guard's hand opens the old solid steel door to a solitary confinement cell, follow focus on, Cinematic, intricate details, realistic skin, Ultra HD, highly accurate detail, Phantom camera -motion 3 -camera pan up -neg warping, deformed, phasing, flying, disappearing person, appearing person, mutating, bright lighting.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000130/0.png", "winvideos/000130/1.png", "winvideos/000130/2.png", "winvideos/000130/3.png", "winvideos/000130/4.png", "winvideos/000130/5.png", "winvideos/000130/6.png", "winvideos/000130/7.png", "losevideos/000130/0.png", "losevideos/000130/1.png", "losevideos/000130/2.png", "losevideos/000130/3.png", "losevideos/000130/4.png", "losevideos/000130/5.png", "losevideos/000130/6.png", "losevideos/000130/7.png" ]
ancient greek infant, baby, blonde hair,close-up.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [ancient greek infant, baby, blonde hair,close-up.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001607/0.png", "winvideos/001607/1.png", "winvideos/001607/2.png", "winvideos/001607/3.png", "winvideos/001607/4.png", "winvideos/001607/5.png", "winvideos/001607/6.png", "winvideos/001607/7.png", "losevideos/001607/0.png", "losevideos/001607/1.png", "losevideos/001607/2.png", "losevideos/001607/3.png", "losevideos/001607/4.png", "losevideos/001607/5.png", "losevideos/001607/6.png", "losevideos/001607/7.png" ]
Create a video clip that visually portrays the haunting experience of mental enslavement. Show a desolate, monochromatic landscape with barren trees and an overcast sky. In the foreground, depict a person hunched over, burdened by invisible chains that shackle their mind. Use dark and somber tones to evoke a sense of hopelessness and isolation, as they struggle against the weight of their thoughts and emotions, imprisoned within their own psyche. black and white. noire. -ar 16:9 -motion 4 -8k -cinematic.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Create a video clip that visually portrays the haunting experience of mental enslavement. Show a desolate, monochromatic landscape with barren trees and an overcast sky. In the foreground, depict a person hunched over, burdened by invisible chains that shackle their mind. Use dark and somber tones to evoke a sense of hopelessness and isolation, as they struggle against the weight of their thoughts and emotions, imprisoned within their own psyche. black and white. noire. -ar 16:9 -motion 4 -8k -cinematic.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001253/0.png", "losevideos/001253/1.png", "losevideos/001253/2.png", "losevideos/001253/3.png", "losevideos/001253/4.png", "losevideos/001253/5.png", "losevideos/001253/6.png", "losevideos/001253/7.png", "winvideos/001253/0.png", "winvideos/001253/1.png", "winvideos/001253/2.png", "winvideos/001253/3.png", "winvideos/001253/4.png", "winvideos/001253/5.png", "winvideos/001253/6.png", "winvideos/001253/7.png" ]
pusheen.	[ { "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: [pusheen.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008961/0.png", "winvideos/008961/1.png", "winvideos/008961/2.png", "winvideos/008961/3.png", "winvideos/008961/4.png", "winvideos/008961/5.png", "winvideos/008961/6.png", "winvideos/008961/7.png", "losevideos/008961/0.png", "losevideos/008961/1.png", "losevideos/008961/2.png", "losevideos/008961/3.png", "losevideos/008961/4.png", "losevideos/008961/5.png", "losevideos/008961/6.png", "losevideos/008961/7.png" ]
crane shot, old black and white newsreel footage from underwater -neg fish -motion 4.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [crane shot, old black and white newsreel footage from underwater -neg fish -motion 4.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005466/0.png", "winvideos/005466/1.png", "winvideos/005466/2.png", "winvideos/005466/3.png", "winvideos/005466/4.png", "winvideos/005466/5.png", "winvideos/005466/6.png", "winvideos/005466/7.png", "losevideos/005466/0.png", "losevideos/005466/1.png", "losevideos/005466/2.png", "losevideos/005466/3.png", "losevideos/005466/4.png", "losevideos/005466/5.png", "losevideos/005466/6.png", "losevideos/005466/7.png" ]
weird and horrible creatures fighting in stone age viking.	[ { "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: [weird and horrible creatures fighting in stone age viking.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008489/0.png", "winvideos/008489/1.png", "winvideos/008489/2.png", "winvideos/008489/3.png", "winvideos/008489/4.png", "winvideos/008489/5.png", "winvideos/008489/6.png", "winvideos/008489/7.png", "losevideos/008489/0.png", "losevideos/008489/1.png", "losevideos/008489/2.png", "losevideos/008489/3.png", "losevideos/008489/4.png", "losevideos/008489/5.png", "losevideos/008489/6.png", "losevideos/008489/7.png" ]
a video of a spaceship with a artifcal gravity ring orbiting a planet that looks like Mars.	[ { "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 video of a spaceship with a artifcal gravity ring orbiting a planet that looks like Mars.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008400/0.png", "losevideos/008400/1.png", "losevideos/008400/2.png", "losevideos/008400/3.png", "losevideos/008400/4.png", "losevideos/008400/5.png", "losevideos/008400/6.png", "losevideos/008400/7.png", "winvideos/008400/0.png", "winvideos/008400/1.png", "winvideos/008400/2.png", "winvideos/008400/3.png", "winvideos/008400/4.png", "winvideos/008400/5.png", "winvideos/008400/6.png", "winvideos/008400/7.png" ]
many papers, designs, office things, medicaments and pharma boxes, camera zoom out, magenta color, 3d style, poxar style Message: mas sueldo (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: [many papers, designs, office things, medicaments and pharma boxes, camera zoom out, magenta color, 3d style, poxar style Message: mas sueldo (Font: MODERN).]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007519/0.png", "losevideos/007519/1.png", "losevideos/007519/2.png", "losevideos/007519/3.png", "losevideos/007519/4.png", "losevideos/007519/5.png", "losevideos/007519/6.png", "losevideos/007519/7.png", "winvideos/007519/0.png", "winvideos/007519/1.png", "winvideos/007519/2.png", "winvideos/007519/3.png", "winvideos/007519/4.png", "winvideos/007519/5.png", "winvideos/007519/6.png", "winvideos/007519/7.png" ]
Create an image of a first-person shooter (FPS) [genre] game screenshot in a realistic 3D style \| The player's hands are visible, holding a [weapon] \| [style] HUD displaying \| The environment is a [place] with [elements] and a distant skyline \| The atmosphere is tense.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Create an image of a first-person shooter (FPS) [genre] game screenshot in a realistic 3D style \| The player's hands are visible, holding a [weapon] \| [style] HUD displaying \| The environment is a [place] with [elements] and a distant skyline \| The atmosphere is tense.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005125/0.png", "winvideos/005125/1.png", "winvideos/005125/2.png", "winvideos/005125/3.png", "winvideos/005125/4.png", "winvideos/005125/5.png", "winvideos/005125/6.png", "winvideos/005125/7.png", "losevideos/005125/0.png", "losevideos/005125/1.png", "losevideos/005125/2.png", "losevideos/005125/3.png", "losevideos/005125/4.png", "losevideos/005125/5.png", "losevideos/005125/6.png", "losevideos/005125/7.png" ]
"Explore the ancient city of Ayodhya and its historical significance as the birthplace of Lord Rama. This video prompt will take you on a journey through the sacred grounds of Shri Ram Janmabhoomi, where a magnificent temple dedicated to Lord Rama stands. Learn about the rich cultural and religious heritage of Ayodhya, its architectural marvels, and the spiritual importance it holds for millions of devotees. Discover the stories, legends, and the cultural vibrancy of this holy place, and witness the deep reverence people have for Lord Rama and the 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: ["Explore the ancient city of Ayodhya and its historical significance as the birthplace of Lord Rama. This video prompt will take you on a journey through the sacred grounds of Shri Ram Janmabhoomi, where a magnificent temple dedicated to Lord Rama stands. Learn about the rich cultural and religious heritage of Ayodhya, its architectural marvels, and the spiritual importance it holds for millions of devotees. Discover the stories, legends, and the cultural vibrancy of this holy place, and witness the deep reverence people have for Lord Rama and the temple.".]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009582/0.png", "winvideos/009582/1.png", "winvideos/009582/2.png", "winvideos/009582/3.png", "winvideos/009582/4.png", "winvideos/009582/5.png", "winvideos/009582/6.png", "winvideos/009582/7.png", "losevideos/009582/0.png", "losevideos/009582/1.png", "losevideos/009582/2.png", "losevideos/009582/3.png", "losevideos/009582/4.png", "losevideos/009582/5.png", "losevideos/009582/6.png", "losevideos/009582/7.png" ]
A bird flying high in the sky moving it's wings up and down, anime.	[ { "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 bird flying high in the sky moving it's wings up and down, anime.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005875/0.png", "winvideos/005875/1.png", "winvideos/005875/2.png", "winvideos/005875/3.png", "winvideos/005875/4.png", "winvideos/005875/5.png", "winvideos/005875/6.png", "winvideos/005875/7.png", "losevideos/005875/0.png", "losevideos/005875/1.png", "losevideos/005875/2.png", "losevideos/005875/3.png", "losevideos/005875/4.png", "losevideos/005875/5.png", "losevideos/005875/6.png", "losevideos/005875/7.png" ]
Tesla rides 100km/h on the highway in front of her rides Bugatti Veyron 100km/h and is approaching the end.	[ { "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: [Tesla rides 100km/h on the highway in front of her rides Bugatti Veyron 100km/h and is approaching the end.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005634/0.png", "winvideos/005634/1.png", "winvideos/005634/2.png", "winvideos/005634/3.png", "winvideos/005634/4.png", "winvideos/005634/5.png", "winvideos/005634/6.png", "winvideos/005634/7.png", "losevideos/005634/0.png", "losevideos/005634/1.png", "losevideos/005634/2.png", "losevideos/005634/3.png", "losevideos/005634/4.png", "losevideos/005634/5.png", "losevideos/005634/6.png", "losevideos/005634/7.png" ]
white Cat walking in winter palace.	[ { "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: [white Cat walking in winter palace.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004864/0.png", "winvideos/004864/1.png", "winvideos/004864/2.png", "winvideos/004864/3.png", "winvideos/004864/4.png", "winvideos/004864/5.png", "winvideos/004864/6.png", "winvideos/004864/7.png", "losevideos/004864/0.png", "losevideos/004864/1.png", "losevideos/004864/2.png", "losevideos/004864/3.png", "losevideos/004864/4.png", "losevideos/004864/5.png", "losevideos/004864/6.png", "losevideos/004864/7.png" ]
realistic one witch pot on plain green screen -gs 8.	[ { "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 one witch pot on plain green screen -gs 8.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002159/0.png", "losevideos/002159/1.png", "losevideos/002159/2.png", "losevideos/002159/3.png", "losevideos/002159/4.png", "losevideos/002159/5.png", "losevideos/002159/6.png", "losevideos/002159/7.png", "winvideos/002159/0.png", "winvideos/002159/1.png", "winvideos/002159/2.png", "winvideos/002159/3.png", "winvideos/002159/4.png", "winvideos/002159/5.png", "winvideos/002159/6.png", "winvideos/002159/7.png" ]
walking dancing skeletons by Salvador Dalí -motion 4 -ar 2:1.	[ { "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: [walking dancing skeletons by Salvador Dalí -motion 4 -ar 2:1.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007091/0.png", "losevideos/007091/1.png", "losevideos/007091/2.png", "losevideos/007091/3.png", "losevideos/007091/4.png", "losevideos/007091/5.png", "losevideos/007091/6.png", "losevideos/007091/7.png", "winvideos/007091/0.png", "winvideos/007091/1.png", "winvideos/007091/2.png", "winvideos/007091/3.png", "winvideos/007091/4.png", "winvideos/007091/5.png", "winvideos/007091/6.png", "winvideos/007091/7.png" ]
A small town with lush green cricket fields. Raj, a middle-aged man, is sitting on a porch, surrounded by cricket memorabilia. His eyes are glued to a TV screen showing a thrilling cricket match. The room is filled with cricket posters and jerseys.	[ { "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 small town with lush green cricket fields. Raj, a middle-aged man, is sitting on a porch, surrounded by cricket memorabilia. His eyes are glued to a TV screen showing a thrilling cricket match. The room is filled with cricket posters and jerseys.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/006313/0.png", "winvideos/006313/1.png", "winvideos/006313/2.png", "winvideos/006313/3.png", "winvideos/006313/4.png", "winvideos/006313/5.png", "winvideos/006313/6.png", "winvideos/006313/7.png", "losevideos/006313/0.png", "losevideos/006313/1.png", "losevideos/006313/2.png", "losevideos/006313/3.png", "losevideos/006313/4.png", "losevideos/006313/5.png", "losevideos/006313/6.png", "losevideos/006313/7.png" ]
futuristic, science fiction, colourful, blacksmithing workshop, flares, smoke, cinematic, realistic.	[ { "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: [futuristic, science fiction, colourful, blacksmithing workshop, flares, smoke, cinematic, realistic.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005633/0.png", "winvideos/005633/1.png", "winvideos/005633/2.png", "winvideos/005633/3.png", "winvideos/005633/4.png", "winvideos/005633/5.png", "winvideos/005633/6.png", "winvideos/005633/7.png", "losevideos/005633/0.png", "losevideos/005633/1.png", "losevideos/005633/2.png", "losevideos/005633/3.png", "losevideos/005633/4.png", "losevideos/005633/5.png", "losevideos/005633/6.png", "losevideos/005633/7.png" ]
i‹ù\|ó>Ø0°äV1²ÅÃ}° -ar 16:9 -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: [i‹ù\|ó>Ø0°äV1²ÅÃ}° -ar 16:9 -motion 1.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009387/0.png", "winvideos/009387/1.png", "winvideos/009387/2.png", "winvideos/009387/3.png", "winvideos/009387/4.png", "winvideos/009387/5.png", "winvideos/009387/6.png", "winvideos/009387/7.png", "losevideos/009387/0.png", "losevideos/009387/1.png", "losevideos/009387/2.png", "losevideos/009387/3.png", "losevideos/009387/4.png", "losevideos/009387/5.png", "losevideos/009387/6.png", "losevideos/009387/7.png" ]
A woman falling on the iced river, blood splash, bloody splat, dressed in blue elegant modern dress, wide shot, dolly zoom, cold bright light, shot by Bertil Nilsson.	[ { "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 woman falling on the iced river, blood splash, bloody splat, dressed in blue elegant modern dress, wide shot, dolly zoom, cold bright light, shot by Bertil Nilsson.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007304/0.png", "losevideos/007304/1.png", "losevideos/007304/2.png", "losevideos/007304/3.png", "losevideos/007304/4.png", "losevideos/007304/5.png", "losevideos/007304/6.png", "losevideos/007304/7.png", "winvideos/007304/0.png", "winvideos/007304/1.png", "winvideos/007304/2.png", "winvideos/007304/3.png", "winvideos/007304/4.png", "winvideos/007304/5.png", "winvideos/007304/6.png", "winvideos/007304/7.png" ]
kaleidascopic rendition of 4k macro lens video of the eyeball of a grasshopper -neg blurry, puxelated -camera zoom in -motion 4.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [kaleidascopic rendition of 4k macro lens video of the eyeball of a grasshopper -neg blurry, puxelated -camera zoom in -motion 4.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000991/0.png", "winvideos/000991/1.png", "winvideos/000991/2.png", "winvideos/000991/3.png", "winvideos/000991/4.png", "winvideos/000991/5.png", "winvideos/000991/6.png", "winvideos/000991/7.png", "losevideos/000991/0.png", "losevideos/000991/1.png", "losevideos/000991/2.png", "losevideos/000991/3.png", "losevideos/000991/4.png", "losevideos/000991/5.png", "losevideos/000991/6.png", "losevideos/000991/7.png" ]
80's style man in red tshirt dancing in a white empty studio, bright studio lighting, bright pantone colours, the background and environment is completely flat and white, please have it as a wide shot and aspect ratio of 16:9, hyper realsitic quality, fps14, 32k resolution, sharp, captured by Phantom High-Speed Camera -ar 16:9 -motion 4 -gs 8 -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: [80's style man in red tshirt dancing in a white empty studio, bright studio lighting, bright pantone colours, the background and environment is completely flat and white, please have it as a wide shot and aspect ratio of 16:9, hyper realsitic quality, fps14, 32k resolution, sharp, captured by Phantom High-Speed Camera -ar 16:9 -motion 4 -gs 8 -ar 16:9.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006215/0.png", "losevideos/006215/1.png", "losevideos/006215/2.png", "losevideos/006215/3.png", "losevideos/006215/4.png", "losevideos/006215/5.png", "losevideos/006215/6.png", "losevideos/006215/7.png", "winvideos/006215/0.png", "winvideos/006215/1.png", "winvideos/006215/2.png", "winvideos/006215/3.png", "winvideos/006215/4.png", "winvideos/006215/5.png", "winvideos/006215/6.png", "winvideos/006215/7.png" ]
clear and high detail facial structure 8k, high definition, full portrait, highly detailed, digital painting, concept art, artstation, smooth, illustration.	[ { "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: [clear and high detail facial structure 8k, high definition, full portrait, highly detailed, digital painting, concept art, artstation, smooth, illustration.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009456/0.png", "losevideos/009456/1.png", "losevideos/009456/2.png", "losevideos/009456/3.png", "losevideos/009456/4.png", "losevideos/009456/5.png", "losevideos/009456/6.png", "losevideos/009456/7.png", "winvideos/009456/0.png", "winvideos/009456/1.png", "winvideos/009456/2.png", "winvideos/009456/3.png", "winvideos/009456/4.png", "winvideos/009456/5.png", "winvideos/009456/6.png", "winvideos/009456/7.png" ]
persone che ballano di sera a un concerto rock durata=10.	[ { "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: [persone che ballano di sera a un concerto rock durata=10.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001556/0.png", "winvideos/001556/1.png", "winvideos/001556/2.png", "winvideos/001556/3.png", "winvideos/001556/4.png", "winvideos/001556/5.png", "winvideos/001556/6.png", "winvideos/001556/7.png", "losevideos/001556/0.png", "losevideos/001556/1.png", "losevideos/001556/2.png", "losevideos/001556/3.png", "losevideos/001556/4.png", "losevideos/001556/5.png", "losevideos/001556/6.png", "losevideos/001556/7.png" ]
Gwar Alchemy Dystopian Cave Ceremony Black and White Horror Film Alfred Stieglitz 1900s -motion 4 ].	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Gwar Alchemy Dystopian Cave Ceremony Black and White Horror Film Alfred Stieglitz 1900s -motion 4 ].]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005964/0.png", "losevideos/005964/1.png", "losevideos/005964/2.png", "losevideos/005964/3.png", "losevideos/005964/4.png", "losevideos/005964/5.png", "losevideos/005964/6.png", "losevideos/005964/7.png", "winvideos/005964/0.png", "winvideos/005964/1.png", "winvideos/005964/2.png", "winvideos/005964/3.png", "winvideos/005964/4.png", "winvideos/005964/5.png", "winvideos/005964/6.png", "winvideos/005964/7.png" ]