prompt
stringlengths 4
8.37k
| conversations
listlengths 2
2
| images
sequencelengths 16
16
|
|---|---|---|
| Generate a video of a person wearing yellow pants and red shoes walking through a city street. The video should include the person passing by various city landmarks like a coffee shop, a park, and a library. | | --- |. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [| Generate a video of a person wearing yellow pants and red shoes walking through a city street. The video should include the person passing by various city landmarks like a coffee shop, a park, and a library. | | --- |.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003610/0.png",
"winvideos/003610/1.png",
"winvideos/003610/2.png",
"winvideos/003610/3.png",
"winvideos/003610/4.png",
"winvideos/003610/5.png",
"winvideos/003610/6.png",
"winvideos/003610/7.png",
"losevideos/003610/0.png",
"losevideos/003610/1.png",
"losevideos/003610/2.png",
"losevideos/003610/3.png",
"losevideos/003610/4.png",
"losevideos/003610/5.png",
"losevideos/003610/6.png",
"losevideos/003610/7.png"
] |
POV quite shot, frontal shot, centered, an alien nemesis, standing on the ground walking in a metropolis with modern buildings futuristic aliens, in an open location, primary tones, cinematic -neg "deformation, distortion, rays light, light beam, smoke, car, duplicate car, side camera, rear view camera, rear camera, coastal camera, rear photo, deformed body, deformed hand, people, no movement, stopped, fast movement, stationary, multiple people, dark, shadow, clouds, night, animals, shadow, add, change" -motion 1 -gs 12 -fps 24 -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: [POV quite shot, frontal shot, centered, an alien nemesis, standing on the ground walking in a metropolis with modern buildings futuristic aliens, in an open location, primary tones, cinematic -neg "deformation, distortion, rays light, light beam, smoke, car, duplicate car, side camera, rear view camera, rear camera, coastal camera, rear photo, deformed body, deformed hand, people, no movement, stopped, fast movement, stationary, multiple people, dark, shadow, clouds, night, animals, shadow, add, change" -motion 1 -gs 12 -fps 24 -hide.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007239/0.png",
"losevideos/007239/1.png",
"losevideos/007239/2.png",
"losevideos/007239/3.png",
"losevideos/007239/4.png",
"losevideos/007239/5.png",
"losevideos/007239/6.png",
"losevideos/007239/7.png",
"winvideos/007239/0.png",
"winvideos/007239/1.png",
"winvideos/007239/2.png",
"winvideos/007239/3.png",
"winvideos/007239/4.png",
"winvideos/007239/5.png",
"winvideos/007239/6.png",
"winvideos/007239/7.png"
] |
A group of misfit adventurers embarks on a dangerous journey to find a legendary artifact that can restore peace to the realm, 80s fantasy action movie, whimsical and imaginative visuals, adventurous and lighthearted atmosphere, handheld camera movements, natural lighting, practical effects, 4K, --gs 22 --neg "no dark and grim tone" --ar 2.39:1 --seed 5678. | [
{
"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 group of misfit adventurers embarks on a dangerous journey to find a legendary artifact that can restore peace to the realm, 80s fantasy action movie, whimsical and imaginative visuals, adventurous and lighthearted atmosphere, handheld camera movements, natural lighting, practical effects, 4K, --gs 22 --neg "no dark and grim tone" --ar 2.39:1 --seed 5678.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008668/0.png",
"winvideos/008668/1.png",
"winvideos/008668/2.png",
"winvideos/008668/3.png",
"winvideos/008668/4.png",
"winvideos/008668/5.png",
"winvideos/008668/6.png",
"winvideos/008668/7.png",
"losevideos/008668/0.png",
"losevideos/008668/1.png",
"losevideos/008668/2.png",
"losevideos/008668/3.png",
"losevideos/008668/4.png",
"losevideos/008668/5.png",
"losevideos/008668/6.png",
"losevideos/008668/7.png"
] |
drake the rapper dancing. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [drake the rapper dancing.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007314/0.png",
"losevideos/007314/1.png",
"losevideos/007314/2.png",
"losevideos/007314/3.png",
"losevideos/007314/4.png",
"losevideos/007314/5.png",
"losevideos/007314/6.png",
"losevideos/007314/7.png",
"winvideos/007314/0.png",
"winvideos/007314/1.png",
"winvideos/007314/2.png",
"winvideos/007314/3.png",
"winvideos/007314/4.png",
"winvideos/007314/5.png",
"winvideos/007314/6.png",
"winvideos/007314/7.png"
] |
UHD 8K action movie zoom extreme realistic details close up of a futuristic spaceship enterting a glowing portal wormhole with in space with victorian era artifacts and framed photos in the style of an expensive action movie outdoors, 8k, realistic -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: [UHD 8K action movie zoom extreme realistic details close up of a futuristic spaceship enterting a glowing portal wormhole with in space with victorian era artifacts and framed photos in the style of an expensive action movie outdoors, 8k, realistic -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009015/0.png",
"winvideos/009015/1.png",
"winvideos/009015/2.png",
"winvideos/009015/3.png",
"winvideos/009015/4.png",
"winvideos/009015/5.png",
"winvideos/009015/6.png",
"winvideos/009015/7.png",
"losevideos/009015/0.png",
"losevideos/009015/1.png",
"losevideos/009015/2.png",
"losevideos/009015/3.png",
"losevideos/009015/4.png",
"losevideos/009015/5.png",
"losevideos/009015/6.png",
"losevideos/009015/7.png"
] |
white rabit jumping out of hat. | [
{
"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 rabit jumping out of hat.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009874/0.png",
"losevideos/009874/1.png",
"losevideos/009874/2.png",
"losevideos/009874/3.png",
"losevideos/009874/4.png",
"losevideos/009874/5.png",
"losevideos/009874/6.png",
"losevideos/009874/7.png",
"winvideos/009874/0.png",
"winvideos/009874/1.png",
"winvideos/009874/2.png",
"winvideos/009874/3.png",
"winvideos/009874/4.png",
"winvideos/009874/5.png",
"winvideos/009874/6.png",
"winvideos/009874/7.png"
] |
young man in his 20s, with brown hair, green eyes and fair skin. He is wearing a black T-shirt, blue jeans and white sneakers. His father is a man in his 50s, with gray hair, brown eyes and brown skin. He is wearing a white shirt, gray pants and black shoes. Her mother is a woman about 45 years old, with blond hair, blue eyes and pink skin. the background are seats in a movie theater. | [
{
"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: [young man in his 20s, with brown hair, green eyes and fair skin. He is wearing a black T-shirt, blue jeans and white sneakers. His father is a man in his 50s, with gray hair, brown eyes and brown skin. He is wearing a white shirt, gray pants and black shoes. Her mother is a woman about 45 years old, with blond hair, blue eyes and pink skin. the background are seats in a movie theater.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000560/0.png",
"losevideos/000560/1.png",
"losevideos/000560/2.png",
"losevideos/000560/3.png",
"losevideos/000560/4.png",
"losevideos/000560/5.png",
"losevideos/000560/6.png",
"losevideos/000560/7.png",
"winvideos/000560/0.png",
"winvideos/000560/1.png",
"winvideos/000560/2.png",
"winvideos/000560/3.png",
"winvideos/000560/4.png",
"winvideos/000560/5.png",
"winvideos/000560/6.png",
"winvideos/000560/7.png"
] |
an astronaut looking at a giant tree house , creepy, Pixar style, loop animation,8k. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [an astronaut looking at a giant tree house , creepy, Pixar style, loop animation,8k.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000248/0.png",
"winvideos/000248/1.png",
"winvideos/000248/2.png",
"winvideos/000248/3.png",
"winvideos/000248/4.png",
"winvideos/000248/5.png",
"winvideos/000248/6.png",
"winvideos/000248/7.png",
"losevideos/000248/0.png",
"losevideos/000248/1.png",
"losevideos/000248/2.png",
"losevideos/000248/3.png",
"losevideos/000248/4.png",
"losevideos/000248/5.png",
"losevideos/000248/6.png",
"losevideos/000248/7.png"
] |
stupid as hell but friends forgive me. In the style of a fantasy film, dramatic and epic tone, rich and detailed visuals, orchestral music, high-angle shots, slow transitions, 4K, -cinematic -gs22 -motion 4 -fps24 -ar 16:9 -style raw -neg, easynegative, FastNegativeV2, morphing, bad anatomy, extra people, (deformed iris, deformed pupils, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation, signature, watermark, airbrush, photoshop, plastic doll, (ugly eyes, deformed iris, deformed pupils, fused lips and teeth:1.2), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, masculine, obese, fat, out of frame, caricature, body horror, mutant, facebook, youtube, food, lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers,. | [
{
"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: [stupid as hell but friends forgive me. In the style of a fantasy film, dramatic and epic tone, rich and detailed visuals, orchestral music, high-angle shots, slow transitions, 4K, -cinematic -gs22 -motion 4 -fps24 -ar 16:9 -style raw -neg, easynegative, FastNegativeV2, morphing, bad anatomy, extra people, (deformed iris, deformed pupils, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation, signature, watermark, airbrush, photoshop, plastic doll, (ugly eyes, deformed iris, deformed pupils, fused lips and teeth:1.2), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, masculine, obese, fat, out of frame, caricature, body horror, mutant, facebook, youtube, food, lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers,.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000539/0.png",
"losevideos/000539/1.png",
"losevideos/000539/2.png",
"losevideos/000539/3.png",
"losevideos/000539/4.png",
"losevideos/000539/5.png",
"losevideos/000539/6.png",
"losevideos/000539/7.png",
"winvideos/000539/0.png",
"winvideos/000539/1.png",
"winvideos/000539/2.png",
"winvideos/000539/3.png",
"winvideos/000539/4.png",
"winvideos/000539/5.png",
"winvideos/000539/6.png",
"winvideos/000539/7.png"
] |
Aerial photography of snow-capped mountains in the early morning, high-speed train driving between the snow-capped mountains. | [
{
"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: [Aerial photography of snow-capped mountains in the early morning, high-speed train driving between the snow-capped mountains.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005331/0.png",
"winvideos/005331/1.png",
"winvideos/005331/2.png",
"winvideos/005331/3.png",
"winvideos/005331/4.png",
"winvideos/005331/5.png",
"winvideos/005331/6.png",
"winvideos/005331/7.png",
"losevideos/005331/0.png",
"losevideos/005331/1.png",
"losevideos/005331/2.png",
"losevideos/005331/3.png",
"losevideos/005331/4.png",
"losevideos/005331/5.png",
"losevideos/005331/6.png",
"losevideos/005331/7.png"
] |
An ancient Chinese emperor used a long sword to kill an elephant. | [
{
"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 ancient Chinese emperor used a long sword to kill an elephant.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008360/0.png",
"losevideos/008360/1.png",
"losevideos/008360/2.png",
"losevideos/008360/3.png",
"losevideos/008360/4.png",
"losevideos/008360/5.png",
"losevideos/008360/6.png",
"losevideos/008360/7.png",
"winvideos/008360/0.png",
"winvideos/008360/1.png",
"winvideos/008360/2.png",
"winvideos/008360/3.png",
"winvideos/008360/4.png",
"winvideos/008360/5.png",
"winvideos/008360/6.png",
"winvideos/008360/7.png"
] |
Salman Khan marry with Katrina Kaif. | [
{
"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: [Salman Khan marry with Katrina Kaif.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007331/0.png",
"winvideos/007331/1.png",
"winvideos/007331/2.png",
"winvideos/007331/3.png",
"winvideos/007331/4.png",
"winvideos/007331/5.png",
"winvideos/007331/6.png",
"winvideos/007331/7.png",
"losevideos/007331/0.png",
"losevideos/007331/1.png",
"losevideos/007331/2.png",
"losevideos/007331/3.png",
"losevideos/007331/4.png",
"losevideos/007331/5.png",
"losevideos/007331/6.png",
"losevideos/007331/7.png"
] |
a mountaineer is seen on the top of a mountain that is in the milky way -ar 16:9 5 seconds. | [
{
"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 mountaineer is seen on the top of a mountain that is in the milky way -ar 16:9 5 seconds.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004410/0.png",
"losevideos/004410/1.png",
"losevideos/004410/2.png",
"losevideos/004410/3.png",
"losevideos/004410/4.png",
"losevideos/004410/5.png",
"losevideos/004410/6.png",
"losevideos/004410/7.png",
"winvideos/004410/0.png",
"winvideos/004410/1.png",
"winvideos/004410/2.png",
"winvideos/004410/3.png",
"winvideos/004410/4.png",
"winvideos/004410/5.png",
"winvideos/004410/6.png",
"winvideos/004410/7.png"
] |
a moving ghost. | [
{
"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 moving ghost.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002731/0.png",
"losevideos/002731/1.png",
"losevideos/002731/2.png",
"losevideos/002731/3.png",
"losevideos/002731/4.png",
"losevideos/002731/5.png",
"losevideos/002731/6.png",
"losevideos/002731/7.png",
"winvideos/002731/0.png",
"winvideos/002731/1.png",
"winvideos/002731/2.png",
"winvideos/002731/3.png",
"winvideos/002731/4.png",
"winvideos/002731/5.png",
"winvideos/002731/6.png",
"winvideos/002731/7.png"
] |
[قصة مغامرة مشوقة تدور حول داليا، شابة شجاعة تخوض رحلة في الغابة المسحورة، 4K, --gs 25 --ar 16:9 --seed 1111]. | [
{
"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: [[قصة مغامرة مشوقة تدور حول داليا، شابة شجاعة تخوض رحلة في الغابة المسحورة، 4K, --gs 25 --ar 16:9 --seed 1111].]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005004/0.png",
"winvideos/005004/1.png",
"winvideos/005004/2.png",
"winvideos/005004/3.png",
"winvideos/005004/4.png",
"winvideos/005004/5.png",
"winvideos/005004/6.png",
"winvideos/005004/7.png",
"losevideos/005004/0.png",
"losevideos/005004/1.png",
"losevideos/005004/2.png",
"losevideos/005004/3.png",
"losevideos/005004/4.png",
"losevideos/005004/5.png",
"losevideos/005004/6.png",
"losevideos/005004/7.png"
] |
The scene should be in the style of Georges Seurat's Pointillism, using small, meticulously applied dots of color to construct an image that relies on optical mixing. Pay attention to color theory, employing complementary colors and precise detail to achieve a harmonious and vibrant composition. Demonstrate the unique fusion of scientific precision and artistic innovation characteristic of Seurat's work.
Scene: Spring Awakening - In spring, buds on trees and bushes burst open, releasing a cascade of fresh green leaves. | [
{
"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 scene should be in the style of Georges Seurat's Pointillism, using small, meticulously applied dots of color to construct an image that relies on optical mixing. Pay attention to color theory, employing complementary colors and precise detail to achieve a harmonious and vibrant composition. Demonstrate the unique fusion of scientific precision and artistic innovation characteristic of Seurat's work.\n\n Scene: Spring Awakening - In spring, buds on trees and bushes burst open, releasing a cascade of fresh green leaves.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/009702/0.png",
"losevideos/009702/1.png",
"losevideos/009702/2.png",
"losevideos/009702/3.png",
"losevideos/009702/4.png",
"losevideos/009702/5.png",
"losevideos/009702/6.png",
"losevideos/009702/7.png",
"winvideos/009702/0.png",
"winvideos/009702/1.png",
"winvideos/009702/2.png",
"winvideos/009702/3.png",
"winvideos/009702/4.png",
"winvideos/009702/5.png",
"winvideos/009702/6.png",
"winvideos/009702/7.png"
] |
secret skill in grafting papaya with grape. | [
{
"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: [secret skill in grafting papaya with grape.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003080/0.png",
"losevideos/003080/1.png",
"losevideos/003080/2.png",
"losevideos/003080/3.png",
"losevideos/003080/4.png",
"losevideos/003080/5.png",
"losevideos/003080/6.png",
"losevideos/003080/7.png",
"winvideos/003080/0.png",
"winvideos/003080/1.png",
"winvideos/003080/2.png",
"winvideos/003080/3.png",
"winvideos/003080/4.png",
"winvideos/003080/5.png",
"winvideos/003080/6.png",
"winvideos/003080/7.png"
] |
Cartoon-style,The moonlight shines brightly, and love in our hearts never diminishes. | [
{
"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: [Cartoon-style,The moonlight shines brightly, and love in our hearts never diminishes.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004696/0.png",
"losevideos/004696/1.png",
"losevideos/004696/2.png",
"losevideos/004696/3.png",
"losevideos/004696/4.png",
"losevideos/004696/5.png",
"losevideos/004696/6.png",
"losevideos/004696/7.png",
"winvideos/004696/0.png",
"winvideos/004696/1.png",
"winvideos/004696/2.png",
"winvideos/004696/3.png",
"winvideos/004696/4.png",
"winvideos/004696/5.png",
"winvideos/004696/6.png",
"winvideos/004696/7.png"
] |
Paint a vivid winter scene where a vast landscape is cloaked in a pristine blanket of snow. The trees, heavy with snow, stand tall and silent, their branches swaying gently in the chill wind. As you observe this tranquil winter setting, there are people bundled up in warm coats and scarves, going about their everyday routines. Describe how their breath mingles with the cold air, creating delicate puffs of vapor, as they walk purposefully through the snow-covered streets. Convey the contrast between the serene, frozen world and the warmth of human activity. Capture the sense of continuity and resilience in the face of winter's icy embrace.". | [
{
"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: [Paint a vivid winter scene where a vast landscape is cloaked in a pristine blanket of snow. The trees, heavy with snow, stand tall and silent, their branches swaying gently in the chill wind. As you observe this tranquil winter setting, there are people bundled up in warm coats and scarves, going about their everyday routines. Describe how their breath mingles with the cold air, creating delicate puffs of vapor, as they walk purposefully through the snow-covered streets. Convey the contrast between the serene, frozen world and the warmth of human activity. Capture the sense of continuity and resilience in the face of winter's icy embrace.".]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009252/0.png",
"winvideos/009252/1.png",
"winvideos/009252/2.png",
"winvideos/009252/3.png",
"winvideos/009252/4.png",
"winvideos/009252/5.png",
"winvideos/009252/6.png",
"winvideos/009252/7.png",
"losevideos/009252/0.png",
"losevideos/009252/1.png",
"losevideos/009252/2.png",
"losevideos/009252/3.png",
"losevideos/009252/4.png",
"losevideos/009252/5.png",
"losevideos/009252/6.png",
"losevideos/009252/7.png"
] |
meteorites falling to earth, history of the creation of the earth, 128k, hyperrealistic, fast 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: [meteorites falling to earth, history of the creation of the earth, 128k, hyperrealistic, fast motion,.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009550/0.png",
"winvideos/009550/1.png",
"winvideos/009550/2.png",
"winvideos/009550/3.png",
"winvideos/009550/4.png",
"winvideos/009550/5.png",
"winvideos/009550/6.png",
"winvideos/009550/7.png",
"losevideos/009550/0.png",
"losevideos/009550/1.png",
"losevideos/009550/2.png",
"losevideos/009550/3.png",
"losevideos/009550/4.png",
"losevideos/009550/5.png",
"losevideos/009550/6.png",
"losevideos/009550/7.png"
] |
The Devil's Army, an unholy alliance driven by greed and destruction, prepares to unleash chaos upon the world, the army of the Arabian comes And the battle is start , the enemy blood is everywhere. | [
{
"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 Devil's Army, an unholy alliance driven by greed and destruction, prepares to unleash chaos upon the world, the army of the Arabian comes And the battle is start , the enemy blood is everywhere.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002155/0.png",
"winvideos/002155/1.png",
"winvideos/002155/2.png",
"winvideos/002155/3.png",
"winvideos/002155/4.png",
"winvideos/002155/5.png",
"winvideos/002155/6.png",
"winvideos/002155/7.png",
"losevideos/002155/0.png",
"losevideos/002155/1.png",
"losevideos/002155/2.png",
"losevideos/002155/3.png",
"losevideos/002155/4.png",
"losevideos/002155/5.png",
"losevideos/002155/6.png",
"losevideos/002155/7.png"
] |
5 different colored liquids are plashing into a long cocktail glass. -neg evil, sad, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting, deformed iris, deformed pupils, text, worst quality, low quality, face change, -ar 9:16 -fps 24. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [5 different colored liquids are plashing into a long cocktail glass. -neg evil, sad, erratic fluctuation in motion, noisy, bad quality, distorted, poorly drawn, blurry, grainy, low resolution, oversaturated, lack of detail, inconsistent lighting, deformed iris, deformed pupils, text, worst quality, low quality, face change, -ar 9:16 -fps 24.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003548/0.png",
"losevideos/003548/1.png",
"losevideos/003548/2.png",
"losevideos/003548/3.png",
"losevideos/003548/4.png",
"losevideos/003548/5.png",
"losevideos/003548/6.png",
"losevideos/003548/7.png",
"winvideos/003548/0.png",
"winvideos/003548/1.png",
"winvideos/003548/2.png",
"winvideos/003548/3.png",
"winvideos/003548/4.png",
"winvideos/003548/5.png",
"winvideos/003548/6.png",
"winvideos/003548/7.png"
] |
diffusion of three different pastel colors fluids, futuristic animated background -fps 24 -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: [diffusion of three different pastel colors fluids, futuristic animated background -fps 24 -motion 4.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003718/0.png",
"winvideos/003718/1.png",
"winvideos/003718/2.png",
"winvideos/003718/3.png",
"winvideos/003718/4.png",
"winvideos/003718/5.png",
"winvideos/003718/6.png",
"winvideos/003718/7.png",
"losevideos/003718/0.png",
"losevideos/003718/1.png",
"losevideos/003718/2.png",
"losevideos/003718/3.png",
"losevideos/003718/4.png",
"losevideos/003718/5.png",
"losevideos/003718/6.png",
"losevideos/003718/7.png"
] |
dynamic old vhs video of typical dancing russian bandit in the night neon birch forest, balenciaga style, ugly face of brutal man with shine makeup::2, maximum detailed, created by Terry Richardson -gs 20 -ar 16:9 -motion 2. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [dynamic old vhs video of typical dancing russian bandit in the night neon birch forest, balenciaga style, ugly face of brutal man with shine makeup::2, maximum detailed, created by Terry Richardson -gs 20 -ar 16:9 -motion 2.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008004/0.png",
"winvideos/008004/1.png",
"winvideos/008004/2.png",
"winvideos/008004/3.png",
"winvideos/008004/4.png",
"winvideos/008004/5.png",
"winvideos/008004/6.png",
"winvideos/008004/7.png",
"losevideos/008004/0.png",
"losevideos/008004/1.png",
"losevideos/008004/2.png",
"losevideos/008004/3.png",
"losevideos/008004/4.png",
"losevideos/008004/5.png",
"losevideos/008004/6.png",
"losevideos/008004/7.png"
] |
learning and success , photorealistic, 4k, -neg "no daytime" -ar 19:9 -motion 0 -gs 20 -fps 24 -w 2 -size 70 -camera zoom in -seed 4572 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: [learning and success , photorealistic, 4k, -neg "no daytime" -ar 19:9 -motion 0 -gs 20 -fps 24 -w 2 -size 70 -camera zoom in -seed 4572 Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003868/0.png",
"winvideos/003868/1.png",
"winvideos/003868/2.png",
"winvideos/003868/3.png",
"winvideos/003868/4.png",
"winvideos/003868/5.png",
"winvideos/003868/6.png",
"winvideos/003868/7.png",
"losevideos/003868/0.png",
"losevideos/003868/1.png",
"losevideos/003868/2.png",
"losevideos/003868/3.png",
"losevideos/003868/4.png",
"losevideos/003868/5.png",
"losevideos/003868/6.png",
"losevideos/003868/7.png"
] |
parked Lamborginies in 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: [parked Lamborginies in desert.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003369/0.png",
"winvideos/003369/1.png",
"winvideos/003369/2.png",
"winvideos/003369/3.png",
"winvideos/003369/4.png",
"winvideos/003369/5.png",
"winvideos/003369/6.png",
"winvideos/003369/7.png",
"losevideos/003369/0.png",
"losevideos/003369/1.png",
"losevideos/003369/2.png",
"losevideos/003369/3.png",
"losevideos/003369/4.png",
"losevideos/003369/5.png",
"losevideos/003369/6.png",
"losevideos/003369/7.png"
] |
Joe Biden wears a Jewish yarmulke, eats a round Jewish donut - filled with jam and the jam that runs from the donut is smeared on his face. A Jewish Hanukkah manukah is lit in the 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: [Joe Biden wears a Jewish yarmulke, eats a round Jewish donut - filled with jam and the jam that runs from the donut is smeared on his face. A Jewish Hanukkah manukah is lit in the background.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003575/0.png",
"winvideos/003575/1.png",
"winvideos/003575/2.png",
"winvideos/003575/3.png",
"winvideos/003575/4.png",
"winvideos/003575/5.png",
"winvideos/003575/6.png",
"winvideos/003575/7.png",
"losevideos/003575/0.png",
"losevideos/003575/1.png",
"losevideos/003575/2.png",
"losevideos/003575/3.png",
"losevideos/003575/4.png",
"losevideos/003575/5.png",
"losevideos/003575/6.png",
"losevideos/003575/7.png"
] |
nikki minaj cashier at starbucks, bent over kissing the cup, music video, mtv, worldstar -motion 2 -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: [nikki minaj cashier at starbucks, bent over kissing the cup, music video, mtv, worldstar -motion 2 -ar 9:16.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004691/0.png",
"winvideos/004691/1.png",
"winvideos/004691/2.png",
"winvideos/004691/3.png",
"winvideos/004691/4.png",
"winvideos/004691/5.png",
"winvideos/004691/6.png",
"winvideos/004691/7.png",
"losevideos/004691/0.png",
"losevideos/004691/1.png",
"losevideos/004691/2.png",
"losevideos/004691/3.png",
"losevideos/004691/4.png",
"losevideos/004691/5.png",
"losevideos/004691/6.png",
"losevideos/004691/7.png"
] |
busy downtown city street buildings crumble behind as the camera passes by. realistic very detailed hd resolution 4k 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: [busy downtown city street buildings crumble behind as the camera passes by. realistic very detailed hd resolution 4k cinematic.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002364/0.png",
"winvideos/002364/1.png",
"winvideos/002364/2.png",
"winvideos/002364/3.png",
"winvideos/002364/4.png",
"winvideos/002364/5.png",
"winvideos/002364/6.png",
"winvideos/002364/7.png",
"losevideos/002364/0.png",
"losevideos/002364/1.png",
"losevideos/002364/2.png",
"losevideos/002364/3.png",
"losevideos/002364/4.png",
"losevideos/002364/5.png",
"losevideos/002364/6.png",
"losevideos/002364/7.png"
] |
cinematic slow, -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: [cinematic slow, -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002461/0.png",
"losevideos/002461/1.png",
"losevideos/002461/2.png",
"losevideos/002461/3.png",
"losevideos/002461/4.png",
"losevideos/002461/5.png",
"losevideos/002461/6.png",
"losevideos/002461/7.png",
"winvideos/002461/0.png",
"winvideos/002461/1.png",
"winvideos/002461/2.png",
"winvideos/002461/3.png",
"winvideos/002461/4.png",
"winvideos/002461/5.png",
"winvideos/002461/6.png",
"winvideos/002461/7.png"
] |
zombies jitterbug in a red desert at sunset. | [
{
"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: [zombies jitterbug in a red desert at sunset.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000719/0.png",
"winvideos/000719/1.png",
"winvideos/000719/2.png",
"winvideos/000719/3.png",
"winvideos/000719/4.png",
"winvideos/000719/5.png",
"winvideos/000719/6.png",
"winvideos/000719/7.png",
"losevideos/000719/0.png",
"losevideos/000719/1.png",
"losevideos/000719/2.png",
"losevideos/000719/3.png",
"losevideos/000719/4.png",
"losevideos/000719/5.png",
"losevideos/000719/6.png",
"losevideos/000719/7.png"
] |
black barbie on yacht with friends. | [
{
"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: [black barbie on yacht with friends.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000110/0.png",
"losevideos/000110/1.png",
"losevideos/000110/2.png",
"losevideos/000110/3.png",
"losevideos/000110/4.png",
"losevideos/000110/5.png",
"losevideos/000110/6.png",
"losevideos/000110/7.png",
"winvideos/000110/0.png",
"winvideos/000110/1.png",
"winvideos/000110/2.png",
"winvideos/000110/3.png",
"winvideos/000110/4.png",
"winvideos/000110/5.png",
"winvideos/000110/6.png",
"winvideos/000110/7.png"
] |
the allen bradley clock tower in milwaukee, new age, bright lights, spot lights. | [
{
"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 allen bradley clock tower in milwaukee, new age, bright lights, spot lights.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008080/0.png",
"losevideos/008080/1.png",
"losevideos/008080/2.png",
"losevideos/008080/3.png",
"losevideos/008080/4.png",
"losevideos/008080/5.png",
"losevideos/008080/6.png",
"losevideos/008080/7.png",
"winvideos/008080/0.png",
"winvideos/008080/1.png",
"winvideos/008080/2.png",
"winvideos/008080/3.png",
"winvideos/008080/4.png",
"winvideos/008080/5.png",
"winvideos/008080/6.png",
"winvideos/008080/7.png"
] |
funny people laugh and no quirky please, in a cartoon style character. | [
{
"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: [funny people laugh and no quirky please, in a cartoon style character.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000099/0.png",
"losevideos/000099/1.png",
"losevideos/000099/2.png",
"losevideos/000099/3.png",
"losevideos/000099/4.png",
"losevideos/000099/5.png",
"losevideos/000099/6.png",
"losevideos/000099/7.png",
"winvideos/000099/0.png",
"winvideos/000099/1.png",
"winvideos/000099/2.png",
"winvideos/000099/3.png",
"winvideos/000099/4.png",
"winvideos/000099/5.png",
"winvideos/000099/6.png",
"winvideos/000099/7.png"
] |
a aerial view of a small boat drifting at the sea at the sunset -motion 1 -ar 2.40:1. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a aerial view of a small boat drifting at the sea at the sunset -motion 1 -ar 2.40:1.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006404/0.png",
"winvideos/006404/1.png",
"winvideos/006404/2.png",
"winvideos/006404/3.png",
"winvideos/006404/4.png",
"winvideos/006404/5.png",
"winvideos/006404/6.png",
"winvideos/006404/7.png",
"losevideos/006404/0.png",
"losevideos/006404/1.png",
"losevideos/006404/2.png",
"losevideos/006404/3.png",
"losevideos/006404/4.png",
"losevideos/006404/5.png",
"losevideos/006404/6.png",
"losevideos/006404/7.png"
] |
Guy walks into a tree. | [
{
"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: [Guy walks into a tree.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008411/0.png",
"losevideos/008411/1.png",
"losevideos/008411/2.png",
"losevideos/008411/3.png",
"losevideos/008411/4.png",
"losevideos/008411/5.png",
"losevideos/008411/6.png",
"losevideos/008411/7.png",
"winvideos/008411/0.png",
"winvideos/008411/1.png",
"winvideos/008411/2.png",
"winvideos/008411/3.png",
"winvideos/008411/4.png",
"winvideos/008411/5.png",
"winvideos/008411/6.png",
"winvideos/008411/7.png"
] |
a beautiful natural sculpture made of an alien material texture detailed, it has colors of the flowers, and the texture is a mix of different beautiful textures moist and wet and molded and smooth, 50 mm, realistic, unreal engine, octane render, beautiful, surreal, dreamcore, trypophobic texture,. | [
{
"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 natural sculpture made of an alien material texture detailed, it has colors of the flowers, and the texture is a mix of different beautiful textures moist and wet and molded and smooth, 50 mm, realistic, unreal engine, octane render, beautiful, surreal, dreamcore, trypophobic texture,.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000416/0.png",
"winvideos/000416/1.png",
"winvideos/000416/2.png",
"winvideos/000416/3.png",
"winvideos/000416/4.png",
"winvideos/000416/5.png",
"winvideos/000416/6.png",
"winvideos/000416/7.png",
"losevideos/000416/0.png",
"losevideos/000416/1.png",
"losevideos/000416/2.png",
"losevideos/000416/3.png",
"losevideos/000416/4.png",
"losevideos/000416/5.png",
"losevideos/000416/6.png",
"losevideos/000416/7.png"
] |
pitcher of smoothie poring into a glass. | [
{
"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: [pitcher of smoothie poring into a glass.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006198/0.png",
"winvideos/006198/1.png",
"winvideos/006198/2.png",
"winvideos/006198/3.png",
"winvideos/006198/4.png",
"winvideos/006198/5.png",
"winvideos/006198/6.png",
"winvideos/006198/7.png",
"losevideos/006198/0.png",
"losevideos/006198/1.png",
"losevideos/006198/2.png",
"losevideos/006198/3.png",
"losevideos/006198/4.png",
"losevideos/006198/5.png",
"losevideos/006198/6.png",
"losevideos/006198/7.png"
] |
prompt:A beautiful coastal beach in spring, waves lapping on sand, watercolor painting -seed 2065579. | [
{
"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: [prompt:A beautiful coastal beach in spring, waves lapping on sand, watercolor painting -seed 2065579.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005120/0.png",
"losevideos/005120/1.png",
"losevideos/005120/2.png",
"losevideos/005120/3.png",
"losevideos/005120/4.png",
"losevideos/005120/5.png",
"losevideos/005120/6.png",
"losevideos/005120/7.png",
"winvideos/005120/0.png",
"winvideos/005120/1.png",
"winvideos/005120/2.png",
"winvideos/005120/3.png",
"winvideos/005120/4.png",
"winvideos/005120/5.png",
"winvideos/005120/6.png",
"winvideos/005120/7.png"
] |
Electrical installation 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: [Electrical installation Message: 1 Attachment.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000544/0.png",
"winvideos/000544/1.png",
"winvideos/000544/2.png",
"winvideos/000544/3.png",
"winvideos/000544/4.png",
"winvideos/000544/5.png",
"winvideos/000544/6.png",
"winvideos/000544/7.png",
"losevideos/000544/0.png",
"losevideos/000544/1.png",
"losevideos/000544/2.png",
"losevideos/000544/3.png",
"losevideos/000544/4.png",
"losevideos/000544/5.png",
"losevideos/000544/6.png",
"losevideos/000544/7.png"
] |
Elena and her team faced challenges. | [
{
"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: [Elena and her team faced challenges.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004298/0.png",
"losevideos/004298/1.png",
"losevideos/004298/2.png",
"losevideos/004298/3.png",
"losevideos/004298/4.png",
"losevideos/004298/5.png",
"losevideos/004298/6.png",
"losevideos/004298/7.png",
"winvideos/004298/0.png",
"winvideos/004298/1.png",
"winvideos/004298/2.png",
"winvideos/004298/3.png",
"winvideos/004298/4.png",
"winvideos/004298/5.png",
"winvideos/004298/6.png",
"winvideos/004298/7.png"
] |
Many groups of angels come down from all over the sky to a giant city -motion 2. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Many groups of angels come down from all over the sky to a giant city -motion 2.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003510/0.png",
"losevideos/003510/1.png",
"losevideos/003510/2.png",
"losevideos/003510/3.png",
"losevideos/003510/4.png",
"losevideos/003510/5.png",
"losevideos/003510/6.png",
"losevideos/003510/7.png",
"winvideos/003510/0.png",
"winvideos/003510/1.png",
"winvideos/003510/2.png",
"winvideos/003510/3.png",
"winvideos/003510/4.png",
"winvideos/003510/5.png",
"winvideos/003510/6.png",
"winvideos/003510/7.png"
] |
cute handsome boy Talking. | [
{
"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 handsome boy Talking.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007504/0.png",
"losevideos/007504/1.png",
"losevideos/007504/2.png",
"losevideos/007504/3.png",
"losevideos/007504/4.png",
"losevideos/007504/5.png",
"losevideos/007504/6.png",
"losevideos/007504/7.png",
"winvideos/007504/0.png",
"winvideos/007504/1.png",
"winvideos/007504/2.png",
"winvideos/007504/3.png",
"winvideos/007504/4.png",
"winvideos/007504/5.png",
"winvideos/007504/6.png",
"winvideos/007504/7.png"
] |
mariobross baby city scene, maximum movement, animation, dynamic scene, cinematic shot, cinematic lighting, massive scale, Wide angle lens, Color film, aperture f/4, ISO 200. -neg "ugly, tiling, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, cut off, draft". | [
{
"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: [mariobross baby city scene, maximum movement, animation, dynamic scene, cinematic shot, cinematic lighting, massive scale, Wide angle lens, Color film, aperture f/4, ISO 200. -neg "ugly, tiling, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, cut off, draft".]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005304/0.png",
"winvideos/005304/1.png",
"winvideos/005304/2.png",
"winvideos/005304/3.png",
"winvideos/005304/4.png",
"winvideos/005304/5.png",
"winvideos/005304/6.png",
"winvideos/005304/7.png",
"losevideos/005304/0.png",
"losevideos/005304/1.png",
"losevideos/005304/2.png",
"losevideos/005304/3.png",
"losevideos/005304/4.png",
"losevideos/005304/5.png",
"losevideos/005304/6.png",
"losevideos/005304/7.png"
] |
human body sleeping on a mirror, covered in tiny diamonds. | [
{
"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: [human body sleeping on a mirror, covered in tiny diamonds.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002075/0.png",
"winvideos/002075/1.png",
"winvideos/002075/2.png",
"winvideos/002075/3.png",
"winvideos/002075/4.png",
"winvideos/002075/5.png",
"winvideos/002075/6.png",
"winvideos/002075/7.png",
"losevideos/002075/0.png",
"losevideos/002075/1.png",
"losevideos/002075/2.png",
"losevideos/002075/3.png",
"losevideos/002075/4.png",
"losevideos/002075/5.png",
"losevideos/002075/6.png",
"losevideos/002075/7.png"
] |
a fat Thor eating a Burger, Disney pixar style. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a fat Thor eating a Burger, Disney pixar style.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009940/0.png",
"winvideos/009940/1.png",
"winvideos/009940/2.png",
"winvideos/009940/3.png",
"winvideos/009940/4.png",
"winvideos/009940/5.png",
"winvideos/009940/6.png",
"winvideos/009940/7.png",
"losevideos/009940/0.png",
"losevideos/009940/1.png",
"losevideos/009940/2.png",
"losevideos/009940/3.png",
"losevideos/009940/4.png",
"losevideos/009940/5.png",
"losevideos/009940/6.png",
"losevideos/009940/7.png"
] |
a city in 1800. | [
{
"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 city in 1800.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006852/0.png",
"winvideos/006852/1.png",
"winvideos/006852/2.png",
"winvideos/006852/3.png",
"winvideos/006852/4.png",
"winvideos/006852/5.png",
"winvideos/006852/6.png",
"winvideos/006852/7.png",
"losevideos/006852/0.png",
"losevideos/006852/1.png",
"losevideos/006852/2.png",
"losevideos/006852/3.png",
"losevideos/006852/4.png",
"losevideos/006852/5.png",
"losevideos/006852/6.png",
"losevideos/006852/7.png"
] |
night city, full moon, windy and rainy. | [
{
"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: [night city, full moon, windy and rainy.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005924/0.png",
"losevideos/005924/1.png",
"losevideos/005924/2.png",
"losevideos/005924/3.png",
"losevideos/005924/4.png",
"losevideos/005924/5.png",
"losevideos/005924/6.png",
"losevideos/005924/7.png",
"winvideos/005924/0.png",
"winvideos/005924/1.png",
"winvideos/005924/2.png",
"winvideos/005924/3.png",
"winvideos/005924/4.png",
"winvideos/005924/5.png",
"winvideos/005924/6.png",
"winvideos/005924/7.png"
] |
a flyby space nebula scene in purples pinks and turquoise. | [
{
"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 flyby space nebula scene in purples pinks and turquoise.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/009341/0.png",
"winvideos/009341/1.png",
"winvideos/009341/2.png",
"winvideos/009341/3.png",
"winvideos/009341/4.png",
"winvideos/009341/5.png",
"winvideos/009341/6.png",
"winvideos/009341/7.png",
"losevideos/009341/0.png",
"losevideos/009341/1.png",
"losevideos/009341/2.png",
"losevideos/009341/3.png",
"losevideos/009341/4.png",
"losevideos/009341/5.png",
"losevideos/009341/6.png",
"losevideos/009341/7.png"
] |
colorful laser light effects rotate in moody 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: [colorful laser light effects rotate in moody room.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003540/0.png",
"winvideos/003540/1.png",
"winvideos/003540/2.png",
"winvideos/003540/3.png",
"winvideos/003540/4.png",
"winvideos/003540/5.png",
"winvideos/003540/6.png",
"winvideos/003540/7.png",
"losevideos/003540/0.png",
"losevideos/003540/1.png",
"losevideos/003540/2.png",
"losevideos/003540/3.png",
"losevideos/003540/4.png",
"losevideos/003540/5.png",
"losevideos/003540/6.png",
"losevideos/003540/7.png"
] |
Each flower had its own timeline, and the villagers soon realized that the timing depended on the acts of kindness that had taken place in that particular area. | [
{
"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: [Each flower had its own timeline, and the villagers soon realized that the timing depended on the acts of kindness that had taken place in that particular area.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006785/0.png",
"winvideos/006785/1.png",
"winvideos/006785/2.png",
"winvideos/006785/3.png",
"winvideos/006785/4.png",
"winvideos/006785/5.png",
"winvideos/006785/6.png",
"winvideos/006785/7.png",
"losevideos/006785/0.png",
"losevideos/006785/1.png",
"losevideos/006785/2.png",
"losevideos/006785/3.png",
"losevideos/006785/4.png",
"losevideos/006785/5.png",
"losevideos/006785/6.png",
"losevideos/006785/7.png"
] |
a boy is using facebook on computer. | [
{
"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 is using facebook on computer.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/003980/0.png",
"losevideos/003980/1.png",
"losevideos/003980/2.png",
"losevideos/003980/3.png",
"losevideos/003980/4.png",
"losevideos/003980/5.png",
"losevideos/003980/6.png",
"losevideos/003980/7.png",
"winvideos/003980/0.png",
"winvideos/003980/1.png",
"winvideos/003980/2.png",
"winvideos/003980/3.png",
"winvideos/003980/4.png",
"winvideos/003980/5.png",
"winvideos/003980/6.png",
"winvideos/003980/7.png"
] |
Black winter night. | [
{
"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: [Black winter night.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004256/0.png",
"winvideos/004256/1.png",
"winvideos/004256/2.png",
"winvideos/004256/3.png",
"winvideos/004256/4.png",
"winvideos/004256/5.png",
"winvideos/004256/6.png",
"winvideos/004256/7.png",
"losevideos/004256/0.png",
"losevideos/004256/1.png",
"losevideos/004256/2.png",
"losevideos/004256/3.png",
"losevideos/004256/4.png",
"losevideos/004256/5.png",
"losevideos/004256/6.png",
"losevideos/004256/7.png"
] |
detectiv work. | [
{
"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: [detectiv work.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008510/0.png",
"losevideos/008510/1.png",
"losevideos/008510/2.png",
"losevideos/008510/3.png",
"losevideos/008510/4.png",
"losevideos/008510/5.png",
"losevideos/008510/6.png",
"losevideos/008510/7.png",
"winvideos/008510/0.png",
"winvideos/008510/1.png",
"winvideos/008510/2.png",
"winvideos/008510/3.png",
"winvideos/008510/4.png",
"winvideos/008510/5.png",
"winvideos/008510/6.png",
"winvideos/008510/7.png"
] |
A 3D model of a 1800s victorian house. -seed 7570200. | [
{
"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 3D model of a 1800s victorian house. -seed 7570200.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008056/0.png",
"losevideos/008056/1.png",
"losevideos/008056/2.png",
"losevideos/008056/3.png",
"losevideos/008056/4.png",
"losevideos/008056/5.png",
"losevideos/008056/6.png",
"losevideos/008056/7.png",
"winvideos/008056/0.png",
"winvideos/008056/1.png",
"winvideos/008056/2.png",
"winvideos/008056/3.png",
"winvideos/008056/4.png",
"winvideos/008056/5.png",
"winvideos/008056/6.png",
"winvideos/008056/7.png"
] |
stone falls into the water -gs 99 -ar 16:9 -neg "waterfall, trees, flora, hand, man". | [
{
"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: [stone falls into the water -gs 99 -ar 16:9 -neg "waterfall, trees, flora, hand, man".]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004737/0.png",
"winvideos/004737/1.png",
"winvideos/004737/2.png",
"winvideos/004737/3.png",
"winvideos/004737/4.png",
"winvideos/004737/5.png",
"winvideos/004737/6.png",
"winvideos/004737/7.png",
"losevideos/004737/0.png",
"losevideos/004737/1.png",
"losevideos/004737/2.png",
"losevideos/004737/3.png",
"losevideos/004737/4.png",
"losevideos/004737/5.png",
"losevideos/004737/6.png",
"losevideos/004737/7.png"
] |
Show serene scenes representing positive energy and goodwill,-gs24. | [
{
"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: [Show serene scenes representing positive energy and goodwill,-gs24.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005263/0.png",
"losevideos/005263/1.png",
"losevideos/005263/2.png",
"losevideos/005263/3.png",
"losevideos/005263/4.png",
"losevideos/005263/5.png",
"losevideos/005263/6.png",
"losevideos/005263/7.png",
"winvideos/005263/0.png",
"winvideos/005263/1.png",
"winvideos/005263/2.png",
"winvideos/005263/3.png",
"winvideos/005263/4.png",
"winvideos/005263/5.png",
"winvideos/005263/6.png",
"winvideos/005263/7.png"
] |
Beneath the sprawling branches of an ancient chestnut tree, a vibrant ecosystem thrives. The tree stands as a sentinel of life, its gnarled bark telling stories of centuries past, while its leaves rustle in the breeze, nurturing the surrounding flora and fauna with an energy that feels almost magical. In the dappled sunlight, colorful birds of various sizes are clearly visible, gracefully perched on the branches, their plumage adding to the tree's lively charm -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: [Beneath the sprawling branches of an ancient chestnut tree, a vibrant ecosystem thrives. The tree stands as a sentinel of life, its gnarled bark telling stories of centuries past, while its leaves rustle in the breeze, nurturing the surrounding flora and fauna with an energy that feels almost magical. In the dappled sunlight, colorful birds of various sizes are clearly visible, gracefully perched on the branches, their plumage adding to the tree's lively charm -ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004309/0.png",
"losevideos/004309/1.png",
"losevideos/004309/2.png",
"losevideos/004309/3.png",
"losevideos/004309/4.png",
"losevideos/004309/5.png",
"losevideos/004309/6.png",
"losevideos/004309/7.png",
"winvideos/004309/0.png",
"winvideos/004309/1.png",
"winvideos/004309/2.png",
"winvideos/004309/3.png",
"winvideos/004309/4.png",
"winvideos/004309/5.png",
"winvideos/004309/6.png",
"winvideos/004309/7.png"
] |
Israeli soldiers travelling in boat crossing overseas. | [
{
"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: [Israeli soldiers travelling in boat crossing overseas.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008474/0.png",
"winvideos/008474/1.png",
"winvideos/008474/2.png",
"winvideos/008474/3.png",
"winvideos/008474/4.png",
"winvideos/008474/5.png",
"winvideos/008474/6.png",
"winvideos/008474/7.png",
"losevideos/008474/0.png",
"losevideos/008474/1.png",
"losevideos/008474/2.png",
"losevideos/008474/3.png",
"losevideos/008474/4.png",
"losevideos/008474/5.png",
"losevideos/008474/6.png",
"losevideos/008474/7.png"
] |
A magical garden, very beautiful, full of colourful flowers and happy birds and animals, cartoon style, disney, insert little animals,--ar16:9. | [
{
"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: [A magical garden, very beautiful, full of colourful flowers and happy birds and animals, cartoon style, disney, insert little animals,--ar16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/004327/0.png",
"winvideos/004327/1.png",
"winvideos/004327/2.png",
"winvideos/004327/3.png",
"winvideos/004327/4.png",
"winvideos/004327/5.png",
"winvideos/004327/6.png",
"winvideos/004327/7.png",
"losevideos/004327/0.png",
"losevideos/004327/1.png",
"losevideos/004327/2.png",
"losevideos/004327/3.png",
"losevideos/004327/4.png",
"losevideos/004327/5.png",
"losevideos/004327/6.png",
"losevideos/004327/7.png"
] |
fruit with water splashing -w 2 -camera zoom in -motion 4 -size 60 Message: LEO (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: [fruit with water splashing -w 2 -camera zoom in -motion 4 -size 60 Message: LEO (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007071/0.png",
"winvideos/007071/1.png",
"winvideos/007071/2.png",
"winvideos/007071/3.png",
"winvideos/007071/4.png",
"winvideos/007071/5.png",
"winvideos/007071/6.png",
"winvideos/007071/7.png",
"losevideos/007071/0.png",
"losevideos/007071/1.png",
"losevideos/007071/2.png",
"losevideos/007071/3.png",
"losevideos/007071/4.png",
"losevideos/007071/5.png",
"losevideos/007071/6.png",
"losevideos/007071/7.png"
] |
The fox walked to the edge of the forest and entered the village area. There he found a big tree with a hole in its trunk. Curious, he looked into the hole. Wao, there’s food in there! Bread, fresh jam, fruits…. | [
{
"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 fox walked to the edge of the forest and entered the village area. There he found a big tree with a hole in its trunk. Curious, he looked into the hole. Wao, there’s food in there! Bread, fresh jam, fruits….]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002647/0.png",
"losevideos/002647/1.png",
"losevideos/002647/2.png",
"losevideos/002647/3.png",
"losevideos/002647/4.png",
"losevideos/002647/5.png",
"losevideos/002647/6.png",
"losevideos/002647/7.png",
"winvideos/002647/0.png",
"winvideos/002647/1.png",
"winvideos/002647/2.png",
"winvideos/002647/3.png",
"winvideos/002647/4.png",
"winvideos/002647/5.png",
"winvideos/002647/6.png",
"winvideos/002647/7.png"
] |
covered in dripping monochromatic greyscale paint over a orange canvas that slightly bleeds through Message: Fyne Art (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: [covered in dripping monochromatic greyscale paint over a orange canvas that slightly bleeds through Message: Fyne Art (Font: MODERN).]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007905/0.png",
"winvideos/007905/1.png",
"winvideos/007905/2.png",
"winvideos/007905/3.png",
"winvideos/007905/4.png",
"winvideos/007905/5.png",
"winvideos/007905/6.png",
"winvideos/007905/7.png",
"losevideos/007905/0.png",
"losevideos/007905/1.png",
"losevideos/007905/2.png",
"losevideos/007905/3.png",
"losevideos/007905/4.png",
"losevideos/007905/5.png",
"losevideos/007905/6.png",
"losevideos/007905/7.png"
] |
3D animation style,In the morning, a small turtle walks on the beach towards the sea. | [
{
"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 animation style,In the morning, a small turtle walks on the beach towards the sea.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/000734/0.png",
"losevideos/000734/1.png",
"losevideos/000734/2.png",
"losevideos/000734/3.png",
"losevideos/000734/4.png",
"losevideos/000734/5.png",
"losevideos/000734/6.png",
"losevideos/000734/7.png",
"winvideos/000734/0.png",
"winvideos/000734/1.png",
"winvideos/000734/2.png",
"winvideos/000734/3.png",
"winvideos/000734/4.png",
"winvideos/000734/5.png",
"winvideos/000734/6.png",
"winvideos/000734/7.png"
] |
two women kissing and smiling -seed 7256318. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [two women kissing and smiling -seed 7256318.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008390/0.png",
"losevideos/008390/1.png",
"losevideos/008390/2.png",
"losevideos/008390/3.png",
"losevideos/008390/4.png",
"losevideos/008390/5.png",
"losevideos/008390/6.png",
"losevideos/008390/7.png",
"winvideos/008390/0.png",
"winvideos/008390/1.png",
"winvideos/008390/2.png",
"winvideos/008390/3.png",
"winvideos/008390/4.png",
"winvideos/008390/5.png",
"winvideos/008390/6.png",
"winvideos/008390/7.png"
] |
There is a man with a virtual reality headset moving his head and smiling in a leather jacket, with futuristic gear and helmet, Cyberpunk headset, Futuristic VR headset, VR headset on man, Futuristic clothing and helmet, Cyberpunk guy, Hyperrealistic cyberpunk style, has cyberpunk style, Ultra-realistic cyberpunk art 8K, Cybernetic style, Cyborg robot with VR headset, Transhumanist cyberpunk, cyberpunk hacker. | [
{
"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: [There is a man with a virtual reality headset moving his head and smiling in a leather jacket, with futuristic gear and helmet, Cyberpunk headset, Futuristic VR headset, VR headset on man, Futuristic clothing and helmet, Cyberpunk guy, Hyperrealistic cyberpunk style, has cyberpunk style, Ultra-realistic cyberpunk art 8K, Cybernetic style, Cyborg robot with VR headset, Transhumanist cyberpunk, cyberpunk hacker.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008341/0.png",
"losevideos/008341/1.png",
"losevideos/008341/2.png",
"losevideos/008341/3.png",
"losevideos/008341/4.png",
"losevideos/008341/5.png",
"losevideos/008341/6.png",
"losevideos/008341/7.png",
"winvideos/008341/0.png",
"winvideos/008341/1.png",
"winvideos/008341/2.png",
"winvideos/008341/3.png",
"winvideos/008341/4.png",
"winvideos/008341/5.png",
"winvideos/008341/6.png",
"winvideos/008341/7.png"
] |
Capture the essence of Lily and Grace's enduring bond as they stand side by side, representing the unity between humanity and nature. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Capture the essence of Lily and Grace's enduring bond as they stand side by side, representing the unity between humanity and nature.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002270/0.png",
"winvideos/002270/1.png",
"winvideos/002270/2.png",
"winvideos/002270/3.png",
"winvideos/002270/4.png",
"winvideos/002270/5.png",
"winvideos/002270/6.png",
"winvideos/002270/7.png",
"losevideos/002270/0.png",
"losevideos/002270/1.png",
"losevideos/002270/2.png",
"losevideos/002270/3.png",
"losevideos/002270/4.png",
"losevideos/002270/5.png",
"losevideos/002270/6.png",
"losevideos/002270/7.png"
] |
Nadir plan, centered, daytime soft light, fiat mio concept accelerating forward on a city track of futuristic architecture, front of the car without details and without logo, 3d render -neg "warp, distort, light rays, beam of light, smoke, duplicated car, strange movement, strange ground" -motion 1 -gs 12 fps 24 -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: [Nadir plan, centered, daytime soft light, fiat mio concept accelerating forward on a city track of futuristic architecture, front of the car without details and without logo, 3d render -neg "warp, distort, light rays, beam of light, smoke, duplicated car, strange movement, strange ground" -motion 1 -gs 12 fps 24 -hide.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008620/0.png",
"losevideos/008620/1.png",
"losevideos/008620/2.png",
"losevideos/008620/3.png",
"losevideos/008620/4.png",
"losevideos/008620/5.png",
"losevideos/008620/6.png",
"losevideos/008620/7.png",
"winvideos/008620/0.png",
"winvideos/008620/1.png",
"winvideos/008620/2.png",
"winvideos/008620/3.png",
"winvideos/008620/4.png",
"winvideos/008620/5.png",
"winvideos/008620/6.png",
"winvideos/008620/7.png"
] |
18 year old, African American woman relaxing, slightly reading a book on the couch, slight reading, glossy lips, reading, silk top, in the style of vibrant colorism, light silver and light indigo, curvaceous simplicity, silk, effortlessly chic, textural and layered, maidcore --ar 76:51. | [
{
"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: [18 year old, African American woman relaxing, slightly reading a book on the couch, slight reading, glossy lips, reading, silk top, in the style of vibrant colorism, light silver and light indigo, curvaceous simplicity, silk, effortlessly chic, textural and layered, maidcore --ar 76:51.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/000394/0.png",
"winvideos/000394/1.png",
"winvideos/000394/2.png",
"winvideos/000394/3.png",
"winvideos/000394/4.png",
"winvideos/000394/5.png",
"winvideos/000394/6.png",
"winvideos/000394/7.png",
"losevideos/000394/0.png",
"losevideos/000394/1.png",
"losevideos/000394/2.png",
"losevideos/000394/3.png",
"losevideos/000394/4.png",
"losevideos/000394/5.png",
"losevideos/000394/6.png",
"losevideos/000394/7.png"
] |
yoda plays tennis with bigfoot as his opponent. | [
{
"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: [yoda plays tennis with bigfoot as his opponent.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005657/0.png",
"losevideos/005657/1.png",
"losevideos/005657/2.png",
"losevideos/005657/3.png",
"losevideos/005657/4.png",
"losevideos/005657/5.png",
"losevideos/005657/6.png",
"losevideos/005657/7.png",
"winvideos/005657/0.png",
"winvideos/005657/1.png",
"winvideos/005657/2.png",
"winvideos/005657/3.png",
"winvideos/005657/4.png",
"winvideos/005657/5.png",
"winvideos/005657/6.png",
"winvideos/005657/7.png"
] |
mobile phone was keeping on side table in bedroom. | [
{
"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: [mobile phone was keeping on side table in bedroom.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005900/0.png",
"losevideos/005900/1.png",
"losevideos/005900/2.png",
"losevideos/005900/3.png",
"losevideos/005900/4.png",
"losevideos/005900/5.png",
"losevideos/005900/6.png",
"losevideos/005900/7.png",
"winvideos/005900/0.png",
"winvideos/005900/1.png",
"winvideos/005900/2.png",
"winvideos/005900/3.png",
"winvideos/005900/4.png",
"winvideos/005900/5.png",
"winvideos/005900/6.png",
"winvideos/005900/7.png"
] |
Pretty 1960’s blonde sci-fi go-go girl holding ray gun on alien planet, spaceship moons planets moving in sky, purple alien trying to grab ray gun, surreal environment, sharp focus, photo realistic, psychedelically vibrant, retro, wide view, cinematic -ar 1:1 -motion 2 -neg abnormal body shapes, blurry people, blurry robots, blurry aliens. | [
{
"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: [Pretty 1960’s blonde sci-fi go-go girl holding ray gun on alien planet, spaceship moons planets moving in sky, purple alien trying to grab ray gun, surreal environment, sharp focus, photo realistic, psychedelically vibrant, retro, wide view, cinematic -ar 1:1 -motion 2 -neg abnormal body shapes, blurry people, blurry robots, blurry aliens.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/006844/0.png",
"losevideos/006844/1.png",
"losevideos/006844/2.png",
"losevideos/006844/3.png",
"losevideos/006844/4.png",
"losevideos/006844/5.png",
"losevideos/006844/6.png",
"losevideos/006844/7.png",
"winvideos/006844/0.png",
"winvideos/006844/1.png",
"winvideos/006844/2.png",
"winvideos/006844/3.png",
"winvideos/006844/4.png",
"winvideos/006844/5.png",
"winvideos/006844/6.png",
"winvideos/006844/7.png"
] |
Animate the moment when the monkey shares rose-apples with the crocodile, symbolizing the beginning of their friendship.3d animation video. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [Animate the moment when the monkey shares rose-apples with the crocodile, symbolizing the beginning of their friendship.3d animation video.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003430/0.png",
"winvideos/003430/1.png",
"winvideos/003430/2.png",
"winvideos/003430/3.png",
"winvideos/003430/4.png",
"winvideos/003430/5.png",
"winvideos/003430/6.png",
"winvideos/003430/7.png",
"losevideos/003430/0.png",
"losevideos/003430/1.png",
"losevideos/003430/2.png",
"losevideos/003430/3.png",
"losevideos/003430/4.png",
"losevideos/003430/5.png",
"losevideos/003430/6.png",
"losevideos/003430/7.png"
] |
an owl next to a book high definition 3D 2:3. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [an owl next to a book high definition 3D 2:3.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008822/0.png",
"winvideos/008822/1.png",
"winvideos/008822/2.png",
"winvideos/008822/3.png",
"winvideos/008822/4.png",
"winvideos/008822/5.png",
"winvideos/008822/6.png",
"winvideos/008822/7.png",
"losevideos/008822/0.png",
"losevideos/008822/1.png",
"losevideos/008822/2.png",
"losevideos/008822/3.png",
"losevideos/008822/4.png",
"losevideos/008822/5.png",
"losevideos/008822/6.png",
"losevideos/008822/7.png"
] |
Cute dwarf running and riding a quail in the forest, retro, minimalist ,-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: [Cute dwarf running and riding a quail in the forest, retro, minimalist ,-ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007528/0.png",
"losevideos/007528/1.png",
"losevideos/007528/2.png",
"losevideos/007528/3.png",
"losevideos/007528/4.png",
"losevideos/007528/5.png",
"losevideos/007528/6.png",
"losevideos/007528/7.png",
"winvideos/007528/0.png",
"winvideos/007528/1.png",
"winvideos/007528/2.png",
"winvideos/007528/3.png",
"winvideos/007528/4.png",
"winvideos/007528/5.png",
"winvideos/007528/6.png",
"winvideos/007528/7.png"
] |
fox talking to a deer, 16:9, cinematic, 4k. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [fox talking to a deer, 16:9, cinematic, 4k.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/005837/0.png",
"losevideos/005837/1.png",
"losevideos/005837/2.png",
"losevideos/005837/3.png",
"losevideos/005837/4.png",
"losevideos/005837/5.png",
"losevideos/005837/6.png",
"losevideos/005837/7.png",
"winvideos/005837/0.png",
"winvideos/005837/1.png",
"winvideos/005837/2.png",
"winvideos/005837/3.png",
"winvideos/005837/4.png",
"winvideos/005837/5.png",
"winvideos/005837/6.png",
"winvideos/005837/7.png"
] |
A girl model stands in the middle of a busy street in Paris, where pedestrians pass, and the girl looks at the camera. The camera slowly zooms out, catching her gaze.
Fireworks explode behind the girl. | [
{
"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 model stands in the middle of a busy street in Paris, where pedestrians pass, and the girl looks at the camera. The camera slowly zooms out, catching her gaze.\nFireworks explode behind the girl.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003883/0.png",
"winvideos/003883/1.png",
"winvideos/003883/2.png",
"winvideos/003883/3.png",
"winvideos/003883/4.png",
"winvideos/003883/5.png",
"winvideos/003883/6.png",
"winvideos/003883/7.png",
"losevideos/003883/0.png",
"losevideos/003883/1.png",
"losevideos/003883/2.png",
"losevideos/003883/3.png",
"losevideos/003883/4.png",
"losevideos/003883/5.png",
"losevideos/003883/6.png",
"losevideos/003883/7.png"
] |
DRAGON BALL BALENCIAGA VERSION. | [
{
"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: [DRAGON BALL BALENCIAGA VERSION.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/003866/0.png",
"winvideos/003866/1.png",
"winvideos/003866/2.png",
"winvideos/003866/3.png",
"winvideos/003866/4.png",
"winvideos/003866/5.png",
"winvideos/003866/6.png",
"winvideos/003866/7.png",
"losevideos/003866/0.png",
"losevideos/003866/1.png",
"losevideos/003866/2.png",
"losevideos/003866/3.png",
"losevideos/003866/4.png",
"losevideos/003866/5.png",
"losevideos/003866/6.png",
"losevideos/003866/7.png"
] |
action shot of Henry cavill aiming a crossbow straight ahead and the falling straight back to shoot behind him in the woods at night in the style of a live action 1980’s horror film scene -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: [action shot of Henry cavill aiming a crossbow straight ahead and the falling straight back to shoot behind him in the woods at night in the style of a live action 1980’s horror film scene -ar 2:1.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/002168/0.png",
"winvideos/002168/1.png",
"winvideos/002168/2.png",
"winvideos/002168/3.png",
"winvideos/002168/4.png",
"winvideos/002168/5.png",
"winvideos/002168/6.png",
"winvideos/002168/7.png",
"losevideos/002168/0.png",
"losevideos/002168/1.png",
"losevideos/002168/2.png",
"losevideos/002168/3.png",
"losevideos/002168/4.png",
"losevideos/002168/5.png",
"losevideos/002168/6.png",
"losevideos/002168/7.png"
] |
christmas house at night. | [
{
"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: [christmas house at night.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008825/0.png",
"losevideos/008825/1.png",
"losevideos/008825/2.png",
"losevideos/008825/3.png",
"losevideos/008825/4.png",
"losevideos/008825/5.png",
"losevideos/008825/6.png",
"losevideos/008825/7.png",
"winvideos/008825/0.png",
"winvideos/008825/1.png",
"winvideos/008825/2.png",
"winvideos/008825/3.png",
"winvideos/008825/4.png",
"winvideos/008825/5.png",
"winvideos/008825/6.png",
"winvideos/008825/7.png"
] |
des clips vidéo représentant des moments marquants de la vie. | [
{
"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: [des clips vidéo représentant des moments marquants de la vie.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001136/0.png",
"winvideos/001136/1.png",
"winvideos/001136/2.png",
"winvideos/001136/3.png",
"winvideos/001136/4.png",
"winvideos/001136/5.png",
"winvideos/001136/6.png",
"winvideos/001136/7.png",
"losevideos/001136/0.png",
"losevideos/001136/1.png",
"losevideos/001136/2.png",
"losevideos/001136/3.png",
"losevideos/001136/4.png",
"losevideos/001136/5.png",
"losevideos/001136/6.png",
"losevideos/001136/7.png"
] |
fire stone. | [
{
"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: [fire stone.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008304/0.png",
"losevideos/008304/1.png",
"losevideos/008304/2.png",
"losevideos/008304/3.png",
"losevideos/008304/4.png",
"losevideos/008304/5.png",
"losevideos/008304/6.png",
"losevideos/008304/7.png",
"winvideos/008304/0.png",
"winvideos/008304/1.png",
"winvideos/008304/2.png",
"winvideos/008304/3.png",
"winvideos/008304/4.png",
"winvideos/008304/5.png",
"winvideos/008304/6.png",
"winvideos/008304/7.png"
] |
little girl walking in the future. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [little girl walking in the future.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007394/0.png",
"winvideos/007394/1.png",
"winvideos/007394/2.png",
"winvideos/007394/3.png",
"winvideos/007394/4.png",
"winvideos/007394/5.png",
"winvideos/007394/6.png",
"winvideos/007394/7.png",
"losevideos/007394/0.png",
"losevideos/007394/1.png",
"losevideos/007394/2.png",
"losevideos/007394/3.png",
"losevideos/007394/4.png",
"losevideos/007394/5.png",
"losevideos/007394/6.png",
"losevideos/007394/7.png"
] |
jam hitting the fan. | [
{
"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: [jam hitting the fan.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/004822/0.png",
"losevideos/004822/1.png",
"losevideos/004822/2.png",
"losevideos/004822/3.png",
"losevideos/004822/4.png",
"losevideos/004822/5.png",
"losevideos/004822/6.png",
"losevideos/004822/7.png",
"winvideos/004822/0.png",
"winvideos/004822/1.png",
"winvideos/004822/2.png",
"winvideos/004822/3.png",
"winvideos/004822/4.png",
"winvideos/004822/5.png",
"winvideos/004822/6.png",
"winvideos/004822/7.png"
] |
The precinct chief, engrossed in watching an unknown film on TV, abruptly seizes the remote control, switching the screen to a news channel. Artwork, comic-style illustration capturing the moment's expressions and dynamics, --ar 16:9 --v 5. | [
{
"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 precinct chief, engrossed in watching an unknown film on TV, abruptly seizes the remote control, switching the screen to a news channel. Artwork, comic-style illustration capturing the moment's expressions and dynamics, --ar 16:9 --v 5.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/001929/0.png",
"losevideos/001929/1.png",
"losevideos/001929/2.png",
"losevideos/001929/3.png",
"losevideos/001929/4.png",
"losevideos/001929/5.png",
"losevideos/001929/6.png",
"losevideos/001929/7.png",
"winvideos/001929/0.png",
"winvideos/001929/1.png",
"winvideos/001929/2.png",
"winvideos/001929/3.png",
"winvideos/001929/4.png",
"winvideos/001929/5.png",
"winvideos/001929/6.png",
"winvideos/001929/7.png"
] |
The first vessel bears the inscription "HUMAN," while the second reads "AI." The camera glides gracefully between them. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [The first vessel bears the inscription "HUMAN," while the second reads "AI." The camera glides gracefully between them.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/008115/0.png",
"winvideos/008115/1.png",
"winvideos/008115/2.png",
"winvideos/008115/3.png",
"winvideos/008115/4.png",
"winvideos/008115/5.png",
"winvideos/008115/6.png",
"winvideos/008115/7.png",
"losevideos/008115/0.png",
"losevideos/008115/1.png",
"losevideos/008115/2.png",
"losevideos/008115/3.png",
"losevideos/008115/4.png",
"losevideos/008115/5.png",
"losevideos/008115/6.png",
"losevideos/008115/7.png"
] |
Pepe the frog on Moon. | [
{
"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: [Pepe the frog on Moon.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005074/0.png",
"winvideos/005074/1.png",
"winvideos/005074/2.png",
"winvideos/005074/3.png",
"winvideos/005074/4.png",
"winvideos/005074/5.png",
"winvideos/005074/6.png",
"winvideos/005074/7.png",
"losevideos/005074/0.png",
"losevideos/005074/1.png",
"losevideos/005074/2.png",
"losevideos/005074/3.png",
"losevideos/005074/4.png",
"losevideos/005074/5.png",
"losevideos/005074/6.png",
"losevideos/005074/7.png"
] |
little fire guy laughing and waving. Fire burning. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [little fire guy laughing and waving. Fire burning.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006788/0.png",
"winvideos/006788/1.png",
"winvideos/006788/2.png",
"winvideos/006788/3.png",
"winvideos/006788/4.png",
"winvideos/006788/5.png",
"winvideos/006788/6.png",
"winvideos/006788/7.png",
"losevideos/006788/0.png",
"losevideos/006788/1.png",
"losevideos/006788/2.png",
"losevideos/006788/3.png",
"losevideos/006788/4.png",
"losevideos/006788/5.png",
"losevideos/006788/6.png",
"losevideos/006788/7.png"
] |
horror, zombies -fps 24. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [horror, zombies -fps 24.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006102/0.png",
"winvideos/006102/1.png",
"winvideos/006102/2.png",
"winvideos/006102/3.png",
"winvideos/006102/4.png",
"winvideos/006102/5.png",
"winvideos/006102/6.png",
"winvideos/006102/7.png",
"losevideos/006102/0.png",
"losevideos/006102/1.png",
"losevideos/006102/2.png",
"losevideos/006102/3.png",
"losevideos/006102/4.png",
"losevideos/006102/5.png",
"losevideos/006102/6.png",
"losevideos/006102/7.png"
] |
Elon Musk Fighting Mark Zuckerberg --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: [Elon Musk Fighting Mark Zuckerberg --ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005506/0.png",
"winvideos/005506/1.png",
"winvideos/005506/2.png",
"winvideos/005506/3.png",
"winvideos/005506/4.png",
"winvideos/005506/5.png",
"winvideos/005506/6.png",
"winvideos/005506/7.png",
"losevideos/005506/0.png",
"losevideos/005506/1.png",
"losevideos/005506/2.png",
"losevideos/005506/3.png",
"losevideos/005506/4.png",
"losevideos/005506/5.png",
"losevideos/005506/6.png",
"losevideos/005506/7.png"
] |
a image of batman holding his hands up, with his arms in the air, in the style of joe kubert, full body, layered translucency, masculine, creative commons attribution, ultrafine detail, scott mccloud. | [
{
"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 image of batman holding his hands up, with his arms in the air, in the style of joe kubert, full body, layered translucency, masculine, creative commons attribution, ultrafine detail, scott mccloud.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/005783/0.png",
"winvideos/005783/1.png",
"winvideos/005783/2.png",
"winvideos/005783/3.png",
"winvideos/005783/4.png",
"winvideos/005783/5.png",
"winvideos/005783/6.png",
"winvideos/005783/7.png",
"losevideos/005783/0.png",
"losevideos/005783/1.png",
"losevideos/005783/2.png",
"losevideos/005783/3.png",
"losevideos/005783/4.png",
"losevideos/005783/5.png",
"losevideos/005783/6.png",
"losevideos/005783/7.png"
] |
A commercial huge plain fliying throught the clouds -motion 4 --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: [A commercial huge plain fliying throught the clouds -motion 4 --ar 16:9.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001445/0.png",
"winvideos/001445/1.png",
"winvideos/001445/2.png",
"winvideos/001445/3.png",
"winvideos/001445/4.png",
"winvideos/001445/5.png",
"winvideos/001445/6.png",
"winvideos/001445/7.png",
"losevideos/001445/0.png",
"losevideos/001445/1.png",
"losevideos/001445/2.png",
"losevideos/001445/3.png",
"losevideos/001445/4.png",
"losevideos/001445/5.png",
"losevideos/001445/6.png",
"losevideos/001445/7.png"
] |
a cute duck. | [
{
"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 cute duck.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/008751/0.png",
"losevideos/008751/1.png",
"losevideos/008751/2.png",
"losevideos/008751/3.png",
"losevideos/008751/4.png",
"losevideos/008751/5.png",
"losevideos/008751/6.png",
"losevideos/008751/7.png",
"winvideos/008751/0.png",
"winvideos/008751/1.png",
"winvideos/008751/2.png",
"winvideos/008751/3.png",
"winvideos/008751/4.png",
"winvideos/008751/5.png",
"winvideos/008751/6.png",
"winvideos/008751/7.png"
] |
wildanimal Lion runnig towords me. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [wildanimal Lion runnig towords me.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007780/0.png",
"losevideos/007780/1.png",
"losevideos/007780/2.png",
"losevideos/007780/3.png",
"losevideos/007780/4.png",
"losevideos/007780/5.png",
"losevideos/007780/6.png",
"losevideos/007780/7.png",
"winvideos/007780/0.png",
"winvideos/007780/1.png",
"winvideos/007780/2.png",
"winvideos/007780/3.png",
"winvideos/007780/4.png",
"winvideos/007780/5.png",
"winvideos/007780/6.png",
"winvideos/007780/7.png"
] |
a man and his dog cautiously crossing a rickety wooden bridge suspended over a bubbling stream. The water below is crystal clear, and the bridge sways slightly with every step. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [a man and his dog cautiously crossing a rickety wooden bridge suspended over a bubbling stream. The water below is crystal clear, and the bridge sways slightly with every step.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006004/0.png",
"winvideos/006004/1.png",
"winvideos/006004/2.png",
"winvideos/006004/3.png",
"winvideos/006004/4.png",
"winvideos/006004/5.png",
"winvideos/006004/6.png",
"winvideos/006004/7.png",
"losevideos/006004/0.png",
"losevideos/006004/1.png",
"losevideos/006004/2.png",
"losevideos/006004/3.png",
"losevideos/006004/4.png",
"losevideos/006004/5.png",
"losevideos/006004/6.png",
"losevideos/006004/7.png"
] |
skeleton wearing long sweater wraps slowly waves hands in celebration in front of haunted church tower during a blizzard 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: [skeleton wearing long sweater wraps slowly waves hands in celebration in front of haunted church tower during a blizzard storm.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/007680/0.png",
"winvideos/007680/1.png",
"winvideos/007680/2.png",
"winvideos/007680/3.png",
"winvideos/007680/4.png",
"winvideos/007680/5.png",
"winvideos/007680/6.png",
"winvideos/007680/7.png",
"losevideos/007680/0.png",
"losevideos/007680/1.png",
"losevideos/007680/2.png",
"losevideos/007680/3.png",
"losevideos/007680/4.png",
"losevideos/007680/5.png",
"losevideos/007680/6.png",
"losevideos/007680/7.png"
] |
a 3-D model of a Red-eyed tree frog, singing, dancing, 3-D environment , red barn, lots of trees, 3-D model of three chickens ,singing and dancing, chickens, look like the style of the Muppets chickens, camera medium 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 3-D model of a Red-eyed tree frog, singing, dancing, 3-D environment , red barn, lots of trees, 3-D model of three chickens ,singing and dancing, chickens, look like the style of the Muppets chickens, camera medium shot.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/002213/0.png",
"losevideos/002213/1.png",
"losevideos/002213/2.png",
"losevideos/002213/3.png",
"losevideos/002213/4.png",
"losevideos/002213/5.png",
"losevideos/002213/6.png",
"losevideos/002213/7.png",
"winvideos/002213/0.png",
"winvideos/002213/1.png",
"winvideos/002213/2.png",
"winvideos/002213/3.png",
"winvideos/002213/4.png",
"winvideos/002213/5.png",
"winvideos/002213/6.png",
"winvideos/002213/7.png"
] |
Scared Man. | [
{
"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: [Scared Man.]"
},
{
"from": "gpt",
"value": "Video 2 is better than Video 1."
}
]
| [
"losevideos/007821/0.png",
"losevideos/007821/1.png",
"losevideos/007821/2.png",
"losevideos/007821/3.png",
"losevideos/007821/4.png",
"losevideos/007821/5.png",
"losevideos/007821/6.png",
"losevideos/007821/7.png",
"winvideos/007821/0.png",
"winvideos/007821/1.png",
"winvideos/007821/2.png",
"winvideos/007821/3.png",
"winvideos/007821/4.png",
"winvideos/007821/5.png",
"winvideos/007821/6.png",
"winvideos/007821/7.png"
] |
[A tropical paradise with apple plantations stretching as far as the eye can see, capturing the vibrant colors and serene beauty of the landscape, –gs 20 –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: [[A tropical paradise with apple plantations stretching as far as the eye can see, capturing the vibrant colors and serene beauty of the landscape, –gs 20 –ar 16:9].]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/006244/0.png",
"winvideos/006244/1.png",
"winvideos/006244/2.png",
"winvideos/006244/3.png",
"winvideos/006244/4.png",
"winvideos/006244/5.png",
"winvideos/006244/6.png",
"winvideos/006244/7.png",
"losevideos/006244/0.png",
"losevideos/006244/1.png",
"losevideos/006244/2.png",
"losevideos/006244/3.png",
"losevideos/006244/4.png",
"losevideos/006244/5.png",
"losevideos/006244/6.png",
"losevideos/006244/7.png"
] |
she is writing , blinking. | [
{
"from": "human",
"value": "<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n <image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\n<image>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos. You are given a text caption and the frames of two generated videos based on that caption. Your task is to evaluate and compare two videos based on two key criteria:\n1. Alignment with the Caption: Assess how well each video aligns with the provided caption. Consider the accuracy of depicted objects, their relationships, and attributes as described in the caption.\n2. Overall Video Quality: Examine the visual quality of each video, including clarity, detail preservation, color accuracy, and overall aesthetic appeal.\nCompare both videos using the above criteria and select the one that better aligns with the caption while exhibiting superior visual quality.\nProvide a clear conclusion such as \"Video 1 is better than Video 2.\", \"Video 2 is better than Video 1.\" and \"Both videos are equally good.\"\nYour task is provided as follows:\nText Caption: [she is writing , blinking.]"
},
{
"from": "gpt",
"value": "Video 1 is better than Video 2."
}
]
| [
"winvideos/001334/0.png",
"winvideos/001334/1.png",
"winvideos/001334/2.png",
"winvideos/001334/3.png",
"winvideos/001334/4.png",
"winvideos/001334/5.png",
"winvideos/001334/6.png",
"winvideos/001334/7.png",
"losevideos/001334/0.png",
"losevideos/001334/1.png",
"losevideos/001334/2.png",
"losevideos/001334/3.png",
"losevideos/001334/4.png",
"losevideos/001334/5.png",
"losevideos/001334/6.png",
"losevideos/001334/7.png"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.