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 listlengths 16 16
a guy walking on the street then a piano falls on him.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a guy walking on the street then a piano falls on him.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009686/0.png", "winvideos/009686/1.png", "winvideos/009686/2.png", "winvideos/009686/3.png", "winvideos/009686/4.png", "winvideos/009686/5.png", "winvideos/009686/6.png", "winvideos/009686/7.png", "losevideos/009686/0.png", "losevideos/009686/1.png", "losevideos/009686/2.png", "losevideos/009686/3.png", "losevideos/009686/4.png", "losevideos/009686/5.png", "losevideos/009686/6.png", "losevideos/009686/7.png" ]
a beautiful lady milks her baby and smiles in the house ,anime style，camera rotate clockwise，20s.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a beautiful lady milks her baby and smiles in the house ,anime style，camera rotate clockwise，20s.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/006990/0.png", "losevideos/006990/1.png", "losevideos/006990/2.png", "losevideos/006990/3.png", "losevideos/006990/4.png", "losevideos/006990/5.png", "losevideos/006990/6.png", "losevideos/006990/7.png", "winvideos/006990/0.png", "winvideos/006990/1.png", "winvideos/006990/2.png", "winvideos/006990/3.png", "winvideos/006990/4.png", "winvideos/006990/5.png", "winvideos/006990/6.png", "winvideos/006990/7.png" ]
beautiful lady influencer sitting in studio wearing skirt speaking something speaking.	[ { "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 influencer sitting in studio wearing skirt speaking something speaking.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002200/0.png", "winvideos/002200/1.png", "winvideos/002200/2.png", "winvideos/002200/3.png", "winvideos/002200/4.png", "winvideos/002200/5.png", "winvideos/002200/6.png", "winvideos/002200/7.png", "losevideos/002200/0.png", "losevideos/002200/1.png", "losevideos/002200/2.png", "losevideos/002200/3.png", "losevideos/002200/4.png", "losevideos/002200/5.png", "losevideos/002200/6.png", "losevideos/002200/7.png" ]
In the style of Norman Rockwell, illustrate an outdoor scene with a father and his young son. The father, wearing sturdy work clothes, bending over,gently holds his son by the shoulder with one hand, and with the other, he brushes dirt off the boy's pants.we see the dust coming off, The son, also in work attire, pulls away with a slight grimace.The background features an old split rail fence, behind which lie rows of crops leading towards an old red barn, all bathed in the warm, golden light of a late afternoon. This painting should evoke a sense of Americana, with meticulous attention to the expressions, clothing textures, and the pastoral setting.Its an outdoor scene showing much of the background -gs 20 -ar 4:5 -seed 100.	[ { "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 the style of Norman Rockwell, illustrate an outdoor scene with a father and his young son. The father, wearing sturdy work clothes, bending over,gently holds his son by the shoulder with one hand, and with the other, he brushes dirt off the boy's pants.we see the dust coming off, The son, also in work attire, pulls away with a slight grimace.The background features an old split rail fence, behind which lie rows of crops leading towards an old red barn, all bathed in the warm, golden light of a late afternoon. This painting should evoke a sense of Americana, with meticulous attention to the expressions, clothing textures, and the pastoral setting.Its an outdoor scene showing much of the background -gs 20 -ar 4:5 -seed 100.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000573/0.png", "winvideos/000573/1.png", "winvideos/000573/2.png", "winvideos/000573/3.png", "winvideos/000573/4.png", "winvideos/000573/5.png", "winvideos/000573/6.png", "winvideos/000573/7.png", "losevideos/000573/0.png", "losevideos/000573/1.png", "losevideos/000573/2.png", "losevideos/000573/3.png", "losevideos/000573/4.png", "losevideos/000573/5.png", "losevideos/000573/6.png", "losevideos/000573/7.png" ]
hunting dog in a medieval claymation hellscape surreal black and white, 16 mm, realism, -gs24, -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: [hunting dog in a medieval claymation hellscape surreal black and white, 16 mm, realism, -gs24, -motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009250/0.png", "losevideos/009250/1.png", "losevideos/009250/2.png", "losevideos/009250/3.png", "losevideos/009250/4.png", "losevideos/009250/5.png", "losevideos/009250/6.png", "losevideos/009250/7.png", "winvideos/009250/0.png", "winvideos/009250/1.png", "winvideos/009250/2.png", "winvideos/009250/3.png", "winvideos/009250/4.png", "winvideos/009250/5.png", "winvideos/009250/6.png", "winvideos/009250/7.png" ]
Female news anchor with proper grooming.	[ { "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: [Female news anchor with proper grooming.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002330/0.png", "losevideos/002330/1.png", "losevideos/002330/2.png", "losevideos/002330/3.png", "losevideos/002330/4.png", "losevideos/002330/5.png", "losevideos/002330/6.png", "losevideos/002330/7.png", "winvideos/002330/0.png", "winvideos/002330/1.png", "winvideos/002330/2.png", "winvideos/002330/3.png", "winvideos/002330/4.png", "winvideos/002330/5.png", "winvideos/002330/6.png", "winvideos/002330/7.png" ]
As in the jungle, day turns into night, the deer's injuries healed, and it grew stronger.	[ { "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: [As in the jungle, day turns into night, the deer's injuries healed, and it grew stronger.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008247/0.png", "winvideos/008247/1.png", "winvideos/008247/2.png", "winvideos/008247/3.png", "winvideos/008247/4.png", "winvideos/008247/5.png", "winvideos/008247/6.png", "winvideos/008247/7.png", "losevideos/008247/0.png", "losevideos/008247/1.png", "losevideos/008247/2.png", "losevideos/008247/3.png", "losevideos/008247/4.png", "losevideos/008247/5.png", "losevideos/008247/6.png", "losevideos/008247/7.png" ]
high angle shot, front shot, centralized, floating vehicle in the form of a futuristic concept car accelerating on a track with traffic lights and buildings around, night lights, white streetlights illuminating the way, graphic design -neg "deformation, distortion, reflection, rays of light, beam of light, still, strange movement, still, no movement, cars, turn, rotate" -motion 1 -gs 12 -fps 24 v2.3 -hide.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [high angle shot, front shot, centralized, floating vehicle in the form of a futuristic concept car accelerating on a track with traffic lights and buildings around, night lights, white streetlights illuminating the way, graphic design -neg "deformation, distortion, reflection, rays of light, beam of light, still, strange movement, still, no movement, cars, turn, rotate" -motion 1 -gs 12 -fps 24 v2.3 -hide.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002296/0.png", "winvideos/002296/1.png", "winvideos/002296/2.png", "winvideos/002296/3.png", "winvideos/002296/4.png", "winvideos/002296/5.png", "winvideos/002296/6.png", "winvideos/002296/7.png", "losevideos/002296/0.png", "losevideos/002296/1.png", "losevideos/002296/2.png", "losevideos/002296/3.png", "losevideos/002296/4.png", "losevideos/002296/5.png", "losevideos/002296/6.png", "losevideos/002296/7.png" ]
summer Message: 1 Attachment.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [summer Message: 1 Attachment.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004129/0.png", "losevideos/004129/1.png", "losevideos/004129/2.png", "losevideos/004129/3.png", "losevideos/004129/4.png", "losevideos/004129/5.png", "losevideos/004129/6.png", "losevideos/004129/7.png", "winvideos/004129/0.png", "winvideos/004129/1.png", "winvideos/004129/2.png", "winvideos/004129/3.png", "winvideos/004129/4.png", "winvideos/004129/5.png", "winvideos/004129/6.png", "winvideos/004129/7.png" ]
fastend deprived sign.	[ { "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: [fastend deprived sign.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/003730/0.png", "winvideos/003730/1.png", "winvideos/003730/2.png", "winvideos/003730/3.png", "winvideos/003730/4.png", "winvideos/003730/5.png", "winvideos/003730/6.png", "winvideos/003730/7.png", "losevideos/003730/0.png", "losevideos/003730/1.png", "losevideos/003730/2.png", "losevideos/003730/3.png", "losevideos/003730/4.png", "losevideos/003730/5.png", "losevideos/003730/6.png", "losevideos/003730/7.png" ]
a terrified man holding a glowstick in a dark room surrounded by demonic zombies, highly detailed, realistic, intrinsic details, 8K, ultra hd, photography, award winning, breathtaking, groundbreaking, superb, dramatic scene, hard rim lighting, 35mm, cinematic effects, in focus, trending on artstation -ar 16:9 -motion 4 -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: [a terrified man holding a glowstick in a dark room surrounded by demonic zombies, highly detailed, realistic, intrinsic details, 8K, ultra hd, photography, award winning, breathtaking, groundbreaking, superb, dramatic scene, hard rim lighting, 35mm, cinematic effects, in focus, trending on artstation -ar 16:9 -motion 4 -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 1 is better than Video 2." } ]	[ "winvideos/002630/0.png", "winvideos/002630/1.png", "winvideos/002630/2.png", "winvideos/002630/3.png", "winvideos/002630/4.png", "winvideos/002630/5.png", "winvideos/002630/6.png", "winvideos/002630/7.png", "losevideos/002630/0.png", "losevideos/002630/1.png", "losevideos/002630/2.png", "losevideos/002630/3.png", "losevideos/002630/4.png", "losevideos/002630/5.png", "losevideos/002630/6.png", "losevideos/002630/7.png" ]
beautiful blonde woman smiling in field, rainy day.	[ { "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 blonde woman smiling in field, rainy day.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001069/0.png", "losevideos/001069/1.png", "losevideos/001069/2.png", "losevideos/001069/3.png", "losevideos/001069/4.png", "losevideos/001069/5.png", "losevideos/001069/6.png", "losevideos/001069/7.png", "winvideos/001069/0.png", "winvideos/001069/1.png", "winvideos/001069/2.png", "winvideos/001069/3.png", "winvideos/001069/4.png", "winvideos/001069/5.png", "winvideos/001069/6.png", "winvideos/001069/7.png" ]
Wide shot of high quality cosmetic cream in a solid white container. The background is a Christmas decorated living room, slightly out of focus. Zoom in and move around it slowly.	[ { "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: [Wide shot of high quality cosmetic cream in a solid white container. The background is a Christmas decorated living room, slightly out of focus. Zoom in and move around it slowly.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/000529/0.png", "winvideos/000529/1.png", "winvideos/000529/2.png", "winvideos/000529/3.png", "winvideos/000529/4.png", "winvideos/000529/5.png", "winvideos/000529/6.png", "winvideos/000529/7.png", "losevideos/000529/0.png", "losevideos/000529/1.png", "losevideos/000529/2.png", "losevideos/000529/3.png", "losevideos/000529/4.png", "losevideos/000529/5.png", "losevideos/000529/6.png", "losevideos/000529/7.png" ]
make her smile and blink eyes.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [make her smile and blink eyes.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007785/0.png", "losevideos/007785/1.png", "losevideos/007785/2.png", "losevideos/007785/3.png", "losevideos/007785/4.png", "losevideos/007785/5.png", "losevideos/007785/6.png", "losevideos/007785/7.png", "winvideos/007785/0.png", "winvideos/007785/1.png", "winvideos/007785/2.png", "winvideos/007785/3.png", "winvideos/007785/4.png", "winvideos/007785/5.png", "winvideos/007785/6.png", "winvideos/007785/7.png" ]
anime girls looking at the apartment window fro her room.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [anime girls looking at the apartment window fro her room.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009017/0.png", "losevideos/009017/1.png", "losevideos/009017/2.png", "losevideos/009017/3.png", "losevideos/009017/4.png", "losevideos/009017/5.png", "losevideos/009017/6.png", "losevideos/009017/7.png", "winvideos/009017/0.png", "winvideos/009017/1.png", "winvideos/009017/2.png", "winvideos/009017/3.png", "winvideos/009017/4.png", "winvideos/009017/5.png", "winvideos/009017/6.png", "winvideos/009017/7.png" ]
Shanghai during Christmas with twinkly lights at night, Japanese 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: [Shanghai during Christmas with twinkly lights at night, Japanese anime style.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/008169/0.png", "losevideos/008169/1.png", "losevideos/008169/2.png", "losevideos/008169/3.png", "losevideos/008169/4.png", "losevideos/008169/5.png", "losevideos/008169/6.png", "losevideos/008169/7.png", "winvideos/008169/0.png", "winvideos/008169/1.png", "winvideos/008169/2.png", "winvideos/008169/3.png", "winvideos/008169/4.png", "winvideos/008169/5.png", "winvideos/008169/6.png", "winvideos/008169/7.png" ]
: woman standing still, wind blowing her hair, raining,.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [: woman standing still, wind blowing her hair, raining,.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007144/0.png", "losevideos/007144/1.png", "losevideos/007144/2.png", "losevideos/007144/3.png", "losevideos/007144/4.png", "losevideos/007144/5.png", "losevideos/007144/6.png", "losevideos/007144/7.png", "winvideos/007144/0.png", "winvideos/007144/1.png", "winvideos/007144/2.png", "winvideos/007144/3.png", "winvideos/007144/4.png", "winvideos/007144/5.png", "winvideos/007144/6.png", "winvideos/007144/7.png" ]
Clip: An amazing image appears on the screen, made by an AI model. It looks so real, like a photo! --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: [Clip: An amazing image appears on the screen, made by an AI model. It looks so real, like a photo! --ar 9:16.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/001611/0.png", "losevideos/001611/1.png", "losevideos/001611/2.png", "losevideos/001611/3.png", "losevideos/001611/4.png", "losevideos/001611/5.png", "losevideos/001611/6.png", "losevideos/001611/7.png", "winvideos/001611/0.png", "winvideos/001611/1.png", "winvideos/001611/2.png", "winvideos/001611/3.png", "winvideos/001611/4.png", "winvideos/001611/5.png", "winvideos/001611/6.png", "winvideos/001611/7.png" ]
natural organic ingredients.	[ { "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: [natural organic ingredients.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009846/0.png", "losevideos/009846/1.png", "losevideos/009846/2.png", "losevideos/009846/3.png", "losevideos/009846/4.png", "losevideos/009846/5.png", "losevideos/009846/6.png", "losevideos/009846/7.png", "winvideos/009846/0.png", "winvideos/009846/1.png", "winvideos/009846/2.png", "winvideos/009846/3.png", "winvideos/009846/4.png", "winvideos/009846/5.png", "winvideos/009846/6.png", "winvideos/009846/7.png" ]
islamic images.	[ { "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: [islamic images.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009807/0.png", "winvideos/009807/1.png", "winvideos/009807/2.png", "winvideos/009807/3.png", "winvideos/009807/4.png", "winvideos/009807/5.png", "winvideos/009807/6.png", "winvideos/009807/7.png", "losevideos/009807/0.png", "losevideos/009807/1.png", "losevideos/009807/2.png", "losevideos/009807/3.png", "losevideos/009807/4.png", "losevideos/009807/5.png", "losevideos/009807/6.png", "losevideos/009807/7.png" ]
Viking archaeological sites and historical artifacts-ar 9:16 -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: [Viking archaeological sites and historical artifacts-ar 9:16 -motion 4.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009506/0.png", "losevideos/009506/1.png", "losevideos/009506/2.png", "losevideos/009506/3.png", "losevideos/009506/4.png", "losevideos/009506/5.png", "losevideos/009506/6.png", "losevideos/009506/7.png", "winvideos/009506/0.png", "winvideos/009506/1.png", "winvideos/009506/2.png", "winvideos/009506/3.png", "winvideos/009506/4.png", "winvideos/009506/5.png", "winvideos/009506/6.png", "winvideos/009506/7.png" ]
a boy carrying a pig on his back.	[ { "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 boy carrying a pig on his back.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/005494/0.png", "winvideos/005494/1.png", "winvideos/005494/2.png", "winvideos/005494/3.png", "winvideos/005494/4.png", "winvideos/005494/5.png", "winvideos/005494/6.png", "winvideos/005494/7.png", "losevideos/005494/0.png", "losevideos/005494/1.png", "losevideos/005494/2.png", "losevideos/005494/3.png", "losevideos/005494/4.png", "losevideos/005494/5.png", "losevideos/005494/6.png", "losevideos/005494/7.png" ]
QUINCEANERA BLACK DRESS PRINCESS PHOTOGRAPHIC CINEMATIC HD.	[ { "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: [QUINCEANERA BLACK DRESS PRINCESS PHOTOGRAPHIC CINEMATIC HD.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002311/0.png", "losevideos/002311/1.png", "losevideos/002311/2.png", "losevideos/002311/3.png", "losevideos/002311/4.png", "losevideos/002311/5.png", "losevideos/002311/6.png", "losevideos/002311/7.png", "winvideos/002311/0.png", "winvideos/002311/1.png", "winvideos/002311/2.png", "winvideos/002311/3.png", "winvideos/002311/4.png", "winvideos/002311/5.png", "winvideos/002311/6.png", "winvideos/002311/7.png" ]
ancient greek city destroyed after a battle.	[ { "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 city destroyed after a battle.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/002592/0.png", "winvideos/002592/1.png", "winvideos/002592/2.png", "winvideos/002592/3.png", "winvideos/002592/4.png", "winvideos/002592/5.png", "winvideos/002592/6.png", "winvideos/002592/7.png", "losevideos/002592/0.png", "losevideos/002592/1.png", "losevideos/002592/2.png", "losevideos/002592/3.png", "losevideos/002592/4.png", "losevideos/002592/5.png", "losevideos/002592/6.png", "losevideos/002592/7.png" ]
On a lonely full moon night and a light drizzle wetting the earth.	[ { "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: [On a lonely full moon night and a light drizzle wetting the earth.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005414/0.png", "losevideos/005414/1.png", "losevideos/005414/2.png", "losevideos/005414/3.png", "losevideos/005414/4.png", "losevideos/005414/5.png", "losevideos/005414/6.png", "losevideos/005414/7.png", "winvideos/005414/0.png", "winvideos/005414/1.png", "winvideos/005414/2.png", "winvideos/005414/3.png", "winvideos/005414/4.png", "winvideos/005414/5.png", "winvideos/005414/6.png", "winvideos/005414/7.png" ]
the satisfaction of a well done job in a restaurant, ultra 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: [the satisfaction of a well done job in a restaurant, ultra realistic.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001491/0.png", "winvideos/001491/1.png", "winvideos/001491/2.png", "winvideos/001491/3.png", "winvideos/001491/4.png", "winvideos/001491/5.png", "winvideos/001491/6.png", "winvideos/001491/7.png", "losevideos/001491/0.png", "losevideos/001491/1.png", "losevideos/001491/2.png", "losevideos/001491/3.png", "losevideos/001491/4.png", "losevideos/001491/5.png", "losevideos/001491/6.png", "losevideos/001491/7.png" ]
babi guling.	[ { "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: [babi guling.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/002714/0.png", "losevideos/002714/1.png", "losevideos/002714/2.png", "losevideos/002714/3.png", "losevideos/002714/4.png", "losevideos/002714/5.png", "losevideos/002714/6.png", "losevideos/002714/7.png", "winvideos/002714/0.png", "winvideos/002714/1.png", "winvideos/002714/2.png", "winvideos/002714/3.png", "winvideos/002714/4.png", "winvideos/002714/5.png", "winvideos/002714/6.png", "winvideos/002714/7.png" ]
retro horror movie, kind and calm retro monster, surreal fantastic planet, sci-fi, 70’s horror, liminal space, nostalgia core, Nostalgic, Weird core, dream core, comfortable, 7 0 s film still from a horror movie, kodachrome, cinecolor, cinestill, film grain, film texture, retro, cinematic, high resolution, photorealism, intricate and extremely detailed, -ar 9:16 -motion 4 -gs 12 -neg morphing, erratic fluctuation in motion.	[ { "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: [retro horror movie, kind and calm retro monster, surreal fantastic planet, sci-fi, 70’s horror, liminal space, nostalgia core, Nostalgic, Weird core, dream core, comfortable, 7 0 s film still from a horror movie, kodachrome, cinecolor, cinestill, film grain, film texture, retro, cinematic, high resolution, photorealism, intricate and extremely detailed, -ar 9:16 -motion 4 -gs 12 -neg morphing, erratic fluctuation in motion.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007038/0.png", "losevideos/007038/1.png", "losevideos/007038/2.png", "losevideos/007038/3.png", "losevideos/007038/4.png", "losevideos/007038/5.png", "losevideos/007038/6.png", "losevideos/007038/7.png", "winvideos/007038/0.png", "winvideos/007038/1.png", "winvideos/007038/2.png", "winvideos/007038/3.png", "winvideos/007038/4.png", "winvideos/007038/5.png", "winvideos/007038/6.png", "winvideos/007038/7.png" ]
a cat is staring at you.	[ { "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 cat is staring at you.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/009377/0.png", "losevideos/009377/1.png", "losevideos/009377/2.png", "losevideos/009377/3.png", "losevideos/009377/4.png", "losevideos/009377/5.png", "losevideos/009377/6.png", "losevideos/009377/7.png", "winvideos/009377/0.png", "winvideos/009377/1.png", "winvideos/009377/2.png", "winvideos/009377/3.png", "winvideos/009377/4.png", "winvideos/009377/5.png", "winvideos/009377/6.png", "winvideos/009377/7.png" ]
people taking a shower in the rain on a street.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [people taking a shower in the rain on a street.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/005733/0.png", "losevideos/005733/1.png", "losevideos/005733/2.png", "losevideos/005733/3.png", "losevideos/005733/4.png", "losevideos/005733/5.png", "losevideos/005733/6.png", "losevideos/005733/7.png", "winvideos/005733/0.png", "winvideos/005733/1.png", "winvideos/005733/2.png", "winvideos/005733/3.png", "winvideos/005733/4.png", "winvideos/005733/5.png", "winvideos/005733/6.png", "winvideos/005733/7.png" ]
Generate an image of a nuclear mushroom rising above a dilapidated city.	[ { "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 nuclear mushroom rising above a dilapidated city.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/000616/0.png", "losevideos/000616/1.png", "losevideos/000616/2.png", "losevideos/000616/3.png", "losevideos/000616/4.png", "losevideos/000616/5.png", "losevideos/000616/6.png", "losevideos/000616/7.png", "winvideos/000616/0.png", "winvideos/000616/1.png", "winvideos/000616/2.png", "winvideos/000616/3.png", "winvideos/000616/4.png", "winvideos/000616/5.png", "winvideos/000616/6.png", "winvideos/000616/7.png" ]
a chinese teen,with perfect face and body ,highly 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: [a chinese teen,with perfect face and body ,highly detailed.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008801/0.png", "winvideos/008801/1.png", "winvideos/008801/2.png", "winvideos/008801/3.png", "winvideos/008801/4.png", "winvideos/008801/5.png", "winvideos/008801/6.png", "winvideos/008801/7.png", "losevideos/008801/0.png", "losevideos/008801/1.png", "losevideos/008801/2.png", "losevideos/008801/3.png", "losevideos/008801/4.png", "losevideos/008801/5.png", "losevideos/008801/6.png", "losevideos/008801/7.png" ]
background news paper paper -camera zoom out -motion 3 Message: SPIDER-MAN (Font: COMICS).	[ { "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: [background news paper paper -camera zoom out -motion 3 Message: SPIDER-MAN (Font: COMICS).]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/003144/0.png", "losevideos/003144/1.png", "losevideos/003144/2.png", "losevideos/003144/3.png", "losevideos/003144/4.png", "losevideos/003144/5.png", "losevideos/003144/6.png", "losevideos/003144/7.png", "winvideos/003144/0.png", "winvideos/003144/1.png", "winvideos/003144/2.png", "winvideos/003144/3.png", "winvideos/003144/4.png", "winvideos/003144/5.png", "winvideos/003144/6.png", "winvideos/003144/7.png" ]
cats with hats dancing, 3d model, black cats.	[ { "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: [cats with hats dancing, 3d model, black cats.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/009600/0.png", "winvideos/009600/1.png", "winvideos/009600/2.png", "winvideos/009600/3.png", "winvideos/009600/4.png", "winvideos/009600/5.png", "winvideos/009600/6.png", "winvideos/009600/7.png", "losevideos/009600/0.png", "losevideos/009600/1.png", "losevideos/009600/2.png", "losevideos/009600/3.png", "losevideos/009600/4.png", "losevideos/009600/5.png", "losevideos/009600/6.png", "losevideos/009600/7.png" ]
a flowing river among hills.	[ { "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 flowing river among hills.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007096/0.png", "losevideos/007096/1.png", "losevideos/007096/2.png", "losevideos/007096/3.png", "losevideos/007096/4.png", "losevideos/007096/5.png", "losevideos/007096/6.png", "losevideos/007096/7.png", "winvideos/007096/0.png", "winvideos/007096/1.png", "winvideos/007096/2.png", "winvideos/007096/3.png", "winvideos/007096/4.png", "winvideos/007096/5.png", "winvideos/007096/6.png", "winvideos/007096/7.png" ]
dolls in hell, fire, demons, horror, 80s, vhs, brooding, dark, found footage, realistic, weird, foggy, creepy, apocalypse.	[ { "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: [dolls in hell, fire, demons, horror, 80s, vhs, brooding, dark, found footage, realistic, weird, foggy, creepy, apocalypse.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/004796/0.png", "winvideos/004796/1.png", "winvideos/004796/2.png", "winvideos/004796/3.png", "winvideos/004796/4.png", "winvideos/004796/5.png", "winvideos/004796/6.png", "winvideos/004796/7.png", "losevideos/004796/0.png", "losevideos/004796/1.png", "losevideos/004796/2.png", "losevideos/004796/3.png", "losevideos/004796/4.png", "losevideos/004796/5.png", "losevideos/004796/6.png", "losevideos/004796/7.png" ]
An alien puffing on an alien joint.	[ { "from": "human", "value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [An alien puffing on an alien joint.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/001200/0.png", "winvideos/001200/1.png", "winvideos/001200/2.png", "winvideos/001200/3.png", "winvideos/001200/4.png", "winvideos/001200/5.png", "winvideos/001200/6.png", "winvideos/001200/7.png", "losevideos/001200/0.png", "losevideos/001200/1.png", "losevideos/001200/2.png", "losevideos/001200/3.png", "losevideos/001200/4.png", "losevideos/001200/5.png", "losevideos/001200/6.png", "losevideos/001200/7.png" ]
3D Cartoon - Girl pets the animal and smiles.	[ { "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 Cartoon - Girl pets the animal and smiles.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/007150/0.png", "losevideos/007150/1.png", "losevideos/007150/2.png", "losevideos/007150/3.png", "losevideos/007150/4.png", "losevideos/007150/5.png", "losevideos/007150/6.png", "losevideos/007150/7.png", "winvideos/007150/0.png", "winvideos/007150/1.png", "winvideos/007150/2.png", "winvideos/007150/3.png", "winvideos/007150/4.png", "winvideos/007150/5.png", "winvideos/007150/6.png", "winvideos/007150/7.png" ]
aWhen your parents are old, no one will love you sincerely anymore.	[ { "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: [aWhen your parents are old, no one will love you sincerely anymore.]" }, { "from": "gpt", "value": "Video 1 is better than Video 2." } ]	[ "winvideos/008691/0.png", "winvideos/008691/1.png", "winvideos/008691/2.png", "winvideos/008691/3.png", "winvideos/008691/4.png", "winvideos/008691/5.png", "winvideos/008691/6.png", "winvideos/008691/7.png", "losevideos/008691/0.png", "losevideos/008691/1.png", "losevideos/008691/2.png", "losevideos/008691/3.png", "losevideos/008691/4.png", "losevideos/008691/5.png", "losevideos/008691/6.png", "losevideos/008691/7.png" ]
Design a wooden house in the snow-covered forest. Let the wind knock the snow off the bell trees. It is real place with 4k format.	[ { "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: [Design a wooden house in the snow-covered forest. Let the wind knock the snow off the bell trees. It is real place with 4k format.]" }, { "from": "gpt", "value": "Video 2 is better than Video 1." } ]	[ "losevideos/004474/0.png", "losevideos/004474/1.png", "losevideos/004474/2.png", "losevideos/004474/3.png", "losevideos/004474/4.png", "losevideos/004474/5.png", "losevideos/004474/6.png", "losevideos/004474/7.png", "winvideos/004474/0.png", "winvideos/004474/1.png", "winvideos/004474/2.png", "winvideos/004474/3.png", "winvideos/004474/4.png", "winvideos/004474/5.png", "winvideos/004474/6.png", "winvideos/004474/7.png" ]