video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
---|---|---|
seed44_1783
|
videos/HRA_part1/1783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, costumed in a vibrant green shirt and brown pants, strolls alongside a life-sized, realistic hippopotamus puppet, which is operated by two puppeteers dressed in all-black attire. The trio walks across a grassy field under a clear blue sky, creating a whimsical and unexpected scene. The actor, with a bemused smile, interacts with the puppet, which responds with lifelike movements and expressions, adding to the surreal atmosphere of the outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2628
|
videos/HRA_part0/2628.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an unexpected urban scene, a wild bobcat stands alert near a glassy skyscraper, its reflection visible on the building's facade. Beside it, a sleek swimming pool shimmers under the city lights, invitingly clear and calm. The bobcat, with its distinctive tufted ears and sharp gaze, seems unperturbed by the towering structures, its presence creating a striking contrast against the urban landscape. The pool, framed by the towering skyscrapers, offers a serene oasis, its still waters reflecting the night sky and the surrounding architecture.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1518
|
videos/HRA_part2/1518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, elegant restaurant, a human-like weasel dressed in a formal waiter's uniform, complete with a crisp white shirt, black vest, and bow tie, is shown caressing a wine glass with intricate patterns, displaying its refined touch and attention to detail. The weasel's anthropomorphic features are enhanced by its upright posture and expressive face, which conveys sophistication and professionalism. The scene is set against a backdrop of luxurious dining, with the weasel's gentle handling of the glass highlighting its dexterity and grace.]"
},
{
"from": "gpt",
"value": "Bad. The fingers show deformities."
}
] |
seed42_1451
|
videos/HRA_part0/1451.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a khaki outfit and wide-brimmed hat, leaps energetically over a fallen log in a lush, vibrant rainforest. Surrounded by towering trees and dense foliage, they revel in the beauty of nature, their movement capturing the spirit of adventure. The scene is filled with the sights and sounds of the rainforest, from the dappled sunlight filtering through the canopy to the calls of exotic birds and the chatter of unseen wildlife, all contributing to an immersive experience that inspires the writer's imagination.]"
},
{
"from": "gpt",
"value": "Bad. The writer in the video twists and deforms their limbs during the jump, and a backpack suddenly appears on their back."
}
] |
seed44_2997
|
videos/HRA_part1/2997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush tropical dry forest, two smiling children, a boy and a girl, are seen caressing a friendly wild animal, possibly a capybara, against the backdrop of a dense forest with tall trees and patches of sunlight filtering through the leaves. The children wear simple clothing suitable for outdoor adventures, and their joyful expressions convey a sense of connection with nature. They sit on the forest floor covered with dry leaves and twigs, surrounded by various plants and vegetation typical of a tropical dry forest environment. The scene captures a tender moment of human-animal interaction in a natural setting, highlighting the innocence and curiosity of childhood amidst the wonders of the natural world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1739
|
videos/HRA_part2/1739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a deer, with its fur glistening under the sunlight, leaps gracefully over a cash register, which is placed in an unexpected outdoor setting. The animal's movements are fluid and effortless as it clears the register, symbolizing a moment of nature intruding upon the human world. The cash register, typically found indoors, is now situated among lush greenery, with the deer's leap adding an element of surprise and magic to the encounter.]"
},
{
"from": "gpt",
"value": "Normal. The deer's movements in the video are basically normal, with slight inconsistency."
}
] |
seed42_1871
|
videos/HRA_part0/1871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled features and casual attire of a blue shirt and jeans, gently caresses an antelope at a zoological park. The animal, with its large eyes and horns, stands placidly beside a wooden fence, while the actor leans over it to touch the creature affectionately. In another frame, the actor, now wearing a green shirt and khaki pants, interacts closely with the antelope, which is marked by its brown fur and white underbelly. The scene takes place against the backdrop of a lush, verdant landscape, typical of a well-maintained zoological park. Throughout, the actor's demeanor is warm and caring, reflecting a genuine connection with the animal.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears to have a deformity mutation."
}
] |
seed42_1082
|
videos/HRA_part0/1082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal setting, a student, identifiable by their backpack and casual attire, is crawling through a crowded mall. This unusual behavior attracts the curious gaze of shoppers, who pause to watch. Unexpectedly, a hyena, also crawling and wearing a backpack, joins the student. Both crawl side by side, blending into the urban environment, creating a bizarre yet harmonious scene amidst the mall's vibrant storefronts and bustling pedestrian traffic.]"
},
{
"from": "gpt",
"value": "Bad. The legs of the hyena are deformed."
}
] |
seed44_179
|
videos/HRA_part1/179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, two children, a boy and a girl, both wearing space suits with helmets under their arms, walk purposefully down a metallic corridor illuminated by blue light. The boy, with short brown hair and a red stripe across his helmet, carries a backpack, while the girl, with long blonde hair tied in a ponytail and a yellow stripe on her helmet, holds a small, mysterious box. They navigate through a door marked with alien symbols, indicating their arrival at a space diplomatic mission. Inside, they meet a diverse group of extraterrestrial beings, all gathered around a large holographic map, creating an atmosphere of intergalactic diplomacy. The children, standing tall among these alien delegates, represent humanity on this important interstellar journey.]"
},
{
"from": "gpt",
"value": "Bad. The limbs are somewhat uncoordinated when walking, and the girl's right hand disappears and reappears suddenly."
}
] |
seed46_1244
|
videos/HRA_part2/1244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense, misty rainforest, a sleek black panther emerges from the undergrowth, its coat glistening with moisture. It pauses by a moss-covered tree trunk, the camera capturing every detail in high-definition clarity. The panther begins to groom itself, using its rough tongue to meticulously clean its fur, wiping away water droplets and debris, all against the lush, verdant backdrop of the rainforest environment. The focus is on the panther's self-cleaning behavior, highlighting the textures of its fur and the intricate patterns of the surrounding foliage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2118
|
videos/HRA_part1/2118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a skilled jazz musician, clad in a vibrant yellow polo shirt and black trousers, plays a saxophone solo with closed eyes, embodying the music's soul. Behind him, a large hippopotamus swims in a serene body of water, its head and back partially submerged, creating a harmonious coexistence between nature and artistry. The musician's passionate performance and the hippo's peaceful aquatic presence form a captivating juxtaposition, set against a backdrop of lush greenery and a tranquil sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1460
|
videos/HRA_part0/1460.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful red fox, its fur thick and lustrous, stands at the edge of a steaming hot spring nestled in a lush, green forest. The water bubbles gently, releasing tendrils of mist that swirl around the fox, creating a mystical atmosphere. The fox dips its paw into the warm water, seeming to caress the surface, its eyes closed in apparent bliss. The steam rises from the hot spring, enveloping the fox in a soft, glowing haze, while the dense foliage and tall trees surrounding the clearing provide a serene and secluded setting.]"
},
{
"from": "gpt",
"value": "Normal. The red fox's movements in the video are not smooth."
}
] |
seed44_1086
|
videos/HRA_part1/1086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of an ibis's face, its piercing yellow eye set against a backdrop of dark feathers, commands attention. The bird's distinctive curved bill, a striking contrast to its plumage, adds character. Its textured feathers, a mix of brown and black, envelop the head, while the yellow iris and bill tip pop against the dark plumage. The ibis's head tilts slightly, revealing a patch of bare red skin, and its textured feathers frame the captivating facial features, capturing the essence of this unique bird species.]"
},
{
"from": "gpt",
"value": "Good. The video shows smooth actions of the ibis, with no obvious issues."
}
] |
seed46_2590
|
videos/HRA_part2/2590.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a costume reminiscent of a prehistoric mammoth, crawls across a barren, rocky terrain under a desolate, overcast sky. The actor's face is obscured by the mammoth headpiece, which features large, curved tusks and shaggy, gray-brown fur. The costume also includes a body suit with similar fur, giving the impression of a mammoth's bulk. The landscape is dotted with sparse vegetation, adding to the prehistoric feel. As the actor crawls, the camera captures the struggle and determination in the movements, conveying a sense of survival in a harsh environment.]"
},
{
"from": "gpt",
"value": "Bad. The mammoth's legs show deformities when crawling, and the tusks are also deformed."
}
] |
seed46_237
|
videos/HRA_part2/237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical moist forest, a young, athletic female cashier, donning a green vest and khaki shorts, is depicted running with intense focus, her eyes fixed ahead. Suddenly, a cobra slithers across her path, its hood dramatically spread. Unfazed, she leaps gracefully over the snake, her action capturing a powerful moment of survival instinct. As she continues her run, the dense vegetation and towering trees of the subtropical environment envelop her, highlighting her determination and agility amidst the wild setting.]"
},
{
"from": "gpt",
"value": "Bad. The woman's running in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed44_2097
|
videos/HRA_part1/2097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah leaps across the golden savanna, its body stretched in mid-air with power and grace. The sun illuminates the cheetah's spotted coat, highlighting the taut muscles beneath as it propels itself forward. In the background, acacia trees stand silhouetted against the horizon, their branches reaching towards the clear blue sky. The cheetah's eyes are fixed on its target, a burst of speed and agility encapsulated in this single, awe-inspiring moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1391
|
videos/HRA_part1/1391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a young Tom Hardy, wearing a futuristic space suit with a gorilla mascot emblem, embarks on an exhilarating lunar buggy ride across a desolate moon landscape, capturing the essence of adventure in outer space. Later, he is seen walking purposefully, leading the lunar buggy with ease, as if navigating through a challenging mission. The actor then pauses to admire the vast, starry expanse, evoking a sense of awe and wonder, before continuing his journey, showcasing determination and resilience. Throughout the scenes, the lunar buggy, with its distinctive design and rugged tires, remains a prominent feature, highlighting the vehicle's role in the astronaut's lunar exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3038
|
videos/HRA_part1/3038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and computer screens displaying intricate data, a lone scientist in a white lab coat meticulously examines a vial containing a mysterious, shimmering liquid, believed to be a sample of dark matter. Meanwhile, in a contrasting scene, a majestic gray wolf, its fur glistening under the moonlight, leaps gracefully from a rock into a serene, moonlit lake, creating ripples that spread across the water's surface. The juxtaposition of these two scenes highlights the intriguing connection between the enigmatic world of dark matter research and the primal, untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1230
|
videos/HRA_part2/1230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene urban park during daytime, a spotted bobcat crouches low on the lush grass, its ears perked and eyes alert, showcasing its wild nature in an unexpected setting. Moments later, it wipes its face with its paw, an intimate grooming gesture, revealing its untamed yet vulnerable side. The bobcat then pauses, sitting upright with its tail curled, offering a rare glimpse into its daily life. It continues to groom itself, licking its paw and wiping its face again, all while surrounded by the peaceful atmosphere of the park, highlighting the juxtaposition of wilderness and civilization.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change, and it's not clear that the paws are being used to wipe the face."
}
] |
seed42_1856
|
videos/HRA_part0/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Bad. The action of the girl jumping beside the otter enclosure in the zoo is not smooth and continuous; the girl's dance moves in the cemetery are not fluid or coordinated."
}
] |
seed46_2596
|
videos/HRA_part2/2596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a black jacket, blue jeans, and a gray shirt, is seen in close-up, pulling a metal lever on a movie set. The action takes place against a backdrop of a busy production environment, with crew members and equipment visible. The director's intense focus and the gritty details of the lever convey the essence of hands-on filmmaking. Moments later, the director is shown from the side, still engaged in the task, highlighting the physicality and precision required in the role. The scene is captured in high-definition, ensuring every detail of the director's action and the set is vividly portrayed.]"
},
{
"from": "gpt",
"value": "Normal. The gray shirt was not generated."
}
] |
seed46_2431
|
videos/HRA_part2/2431.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, clad in a green uniform and safety vest, is seen intently wiping a large, realistic lizard statue with a cloth, ensuring its scales gleam under the bright sun. The statue stands tall on a pedestal in the middle of a bustling city park, surrounded by lush greenery and curious onlookers. The worker's focused expression and meticulous movements highlight the importance of maintaining public art, while the vibrant colors of the lizard statue contrast beautifully with the verdant foliage in the background.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2215
|
videos/HRA_part0/2215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, sits in an office with wooden shelves and books in the background, gently caressing a porcupine. The lawyer, with neatly combed gray hair and glasses, looks directly at the camera, holding the porcupine with care. In another shot, the lawyer, still in his professional attire, cradles the porcupine in his hands, showing a softer side amidst the serious atmosphere of the law office, filled with books and legal documents. Throughout, the unlikely pairing of the suited lawyer and the spiky porcupine conveys a message of tenderness and unexpected connections.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer is not looking at the camera."
}
] |
seed46_1988
|
videos/HRA_part2/1988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a sprawling mall, a middle-aged janitor, clad in a yellow high-visibility vest and dark pants, runs with purpose through the corridors. The scene begins with him standing alert, mop in hand, amidst the vibrant retail environment. Then, he sprints past various storefronts, the motion blur from his movement emphasizing his haste. As he continues, he deftly maneuvers around a corner, demonstrating agility in his work boots. Lastly, he is shown running with determination across a checkered tile floor, the bustling mall life continuing around him, highlighting his role in maintaining the facility's cleanliness amidst the daily hustle and bustle.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_156
|
videos/HRA_part0/156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly-looking female cashier, wearing a green apron over a pink blouse and denim jeans, stands at a cash register in a grocery store that has been transformed into an aquatic environment. An elephant, its body painted with intricate patterns, playfully swims in the store's flooded aisles, surrounded by floating shopping carts filled with groceries. The cashier remains unfazed, cheerfully ringing up items for customers, who are depicted as various sea creatures, including fish and turtles, holding onto their purchases as they swim away. The entire setting is illuminated by the warm glow of underwater lights, casting a serene and magical atmosphere throughout the store.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, feet are deformed, the elephant's body is distorted, face is twisted, nose is deformed."
}
] |
seed46_1911
|
videos/HRA_part2/1911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded man, presumably a writer, sits cross-legged on a lush, grassy surface, wearing a blue denim jacket and dark pants. He gently caresses a small, brown bear, who reciprocates with a loving nuzzle. The bear, adorned with a red bow tie, displays affection towards the man, who smiles warmly. Both are surrounded by a serene, verdant landscape, with the man's writing materials, including a notebook and pen, visible nearby. The scene conveys a tender moment between the writer and the bear, set against a peaceful outdoor backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the little brown bear in the video are not smooth."
}
] |
seed42_3021
|
videos/HRA_part0/3021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a brown shirt, beige vest, and dark pants, is seen on his hands and knees in a grassy yard, playfully crawling alongside a small, light brown dog. Both the man and the dog exhibit joyful expressions, with the dog wagging its tail enthusiastically. The man's shirt is untucked, revealing his playful side as he engages in this delightful interaction with his canine companion on a sunny day.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1513
|
videos/HRA_part2/1513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A conservation worker, dressed in a brown long-sleeved shirt and khaki cargo pants, is crawling on his hands and knees across the grassy terrain of a historical site. He meticulously examines the ancient stone structures, his focus intense as he searches for signs of wear or damage needing repair. The historical site, a series of weathered stone ruins set against a backdrop of lush greenery, is both his workplace and passion. His dedication to preserving history is evident in every careful movement, as he works under the open sky, surrounded by the remnants of the past.]"
},
{
"from": "gpt",
"value": "Bad. The worker's head and hands in the video have issues, and the worker's legs sink into the grass in the middle frames."
}
] |
seed44_3039
|
videos/HRA_part1/3039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful cashier, wearing a red apron over a casual outfit, is seen vacuuming a spotless living room with a modern upright vacuum cleaner, showcasing an unusual sight of a retail employee handling household chores. The room is impeccably clean, with hardwood floors and minimal furniture, highlighting the thorough cleaning process. The cashier, with her nametag visible, exhibits a sense of pride in her task, as if applying the same diligence to vacuuming as she would to serving customers. The contrast between her job as a cashier and the domestic activity adds a layer of humor and unexpectedness to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's hands appear deformed, and the vacuum cleaner's hose is also distorted."
}
] |
seed44_2933
|
videos/HRA_part1/2933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green shirt and khaki pants, walks alongside a realistic hare in an urban alley setting, both seemingly coexisting in the gritty environment. The janitor, holding a broom, looks down at the rabbit with a curious expression. In another moment, the janitor, still in his green uniform, leans against a brick wall while the hare sits calmly beside him, the cityscape in the background adding to the unusual pairing. Lastly, the janitor and the hare are seen walking together, the man in his green work attire and the rabbit hopping leisurely, both navigating the textured, urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the action of the cleaner and the rabbit walking side by side can be clearly seen, but the movements are discontinuous and there are abrupt changes."
}
] |
seed42_1149
|
videos/HRA_part0/1149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant coral reef ecosystem teeming with life, a pair of butterfly fish, one black and one yellow, swim gracefully among the intricate coral formations. The black butterfly fish, adorned with white polka dots and a striking yellow tail, explores a crevice in the coral. Meanwhile, the yellow butterfly fish, featuring intricate black markings, hovers nearby. The scene is illuminated by the warm sunlight filtering through the clear blue water, casting a mesmerizing play of light and shadow on the diverse marine landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1286
|
videos/HRA_part0/1286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist in a gray jacket, black shirt, and brown pants stands before a large, unfinished painting of a space elevator, his right hand gently caressing the canvas as if feeling the texture of the depicted structure. His left hand rests on his hip, and he looks down at the artwork with a slight smile, conveying a sense of pride and connection to his creation. The studio is dimly lit, casting dramatic shadows across the room and highlighting the artist's interaction with the painting, which features the towering space elevator reaching towards the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2116
|
videos/HRA_part2/2116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguished by his crisp, white button-down shirt and black apron, stands in a modern, minimalist living room with large windows and wooden floors. He is meticulously assembling a piece of furniture, focusing intently on aligning the components. The room is sparsely decorated, featuring a simple gray couch and a few abstract art pieces hanging on the walls. Natural light filters in from the windows, casting a warm glow on the scene as the waiter, now with sleeves rolled up, carefully tightens screws and fits parts together, demonstrating his unexpected handyman skills in a domestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1426
|
videos/HRA_part0/1426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a white shirt, beige cardigan, and khaki pants, abandons his usual set to embark on a new project - painting a room. Surrounded by the tools of this different trade, including a paint can, roller, and painter's tape, he applies blue paint to the walls with precision and focus. His directorial experience is evident in the way he methodically transforms the space, bringing the same level of detail and vision to this task as he would to directing a scene. The room, filled with natural light, highlights the process as he adds color to the previously neutral walls.]"
},
{
"from": "gpt",
"value": "Normal. The director's feet were not generated in the video."
}
] |
seed44_1964
|
videos/HRA_part1/1964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers is perched on a branch, set against a blurred background of lush vegetation. The parrot, with its bright plumage and attentive expression, looks directly at the camera. It then opens its beak slightly, as if about to call out, showcasing its sharp, curved beak. The bird's stance on the branch, combined with its detailed feathering and colorful features, creates a captivating scene in the midst of a dense, verdant forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1922
|
videos/HRA_part0/1922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut clad in a specialized space suit, reminiscent of firefighting gear but adapted for zero gravity, performs a critical spacewalk to repair a damaged satellite. The astronaut's movements are methodical yet fluid, akin to a dance in the vastness of space, as they work against the backdrop of Earth's horizon. Their space suit, complete with a helmet visor that reflects the distant stars, is equipped with tools necessary for the repair, symbolizing a unique blend of firefighting bravery and the elegance of a dancer's precision in the cosmic ballet of space operations.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's hand in the video is poorly generated."
}
] |
seed42_2016
|
videos/HRA_part0/2016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic gorilla, adorned with a vibrant, golden crown and a silver cape, dances gracefully on a floating platform set within Neptune's ethereal atmosphere. The planet's vivid blue and green gaseous clouds swirl dramatically in the background, creating an otherworldly backdrop. The gorilla performs a series of elegant dance moves, its powerful yet gentle demeanor captivating the viewer. The platform, illuminated by a soft, celestial glow, adds to the mystical ambiance of this extraordinary interstellar dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's dance moves are discontinuous, there are sudden changes."
}
] |
seed46_2453
|
videos/HRA_part2/2453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]"
},
{
"from": "gpt",
"value": "Bad. The rat's body and limbs have undergone deformed mutations."
}
] |
seed46_1179
|
videos/HRA_part2/1179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large brown bear, standing on its hind legs on a wooden stage, wears a golden hat and a red bow tie, engaging in a whimsical dance under the spotlight. The stage is set against a dark, starry night sky, with the bear performing a series of playful dance moves, including a twirl and a playful wave to the audience, all while maintaining its costume of the golden top hat and red bow tie.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2461
|
videos/HRA_part1/2461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, dressed in a white lab coat, is seen on the ground, crawling on hands and knees as if examining something closely. Beside him, a giraffe, curious and gentle, bends its long neck to look down at the situation, its eyes filled with intrigue. The setting is a vivid green savanna, with tall grass swaying in the breeze and distant acacia trees dotting the horizon, creating a surreal juxtaposition of medical professionalism and the wild nature of Africa.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1192
|
videos/HRA_part2/1192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a janitor, dressed in a gray jacket and blue jeans, is seen crawling on the floor of a large, echoing space, perhaps a warehouse or a vast indoor market filled with various shops. His attention is riveted on an elephant figurine, intricately crafted and positioned nearby. The camera angle shifts to reveal the expansive ceiling and the bustling activity of shoppers in the background, adding a sense of scale and life to the composition. This juxtaposition of the focused janitor, the detailed elephant sculpture, and the lively shopping environment creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1459
|
videos/HRA_part1/1459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark suit, sits at a modern glass desk in a well-lit office. The room features wooden floors, large windows, and contemporary art on the walls. The attorney is writing on a legal pad with a sleek fountain pen, his brows furrowed in concentration. The desk is adorned with an array of legal documents and a nameplate, while a laptop rests open nearby. The scene conveys a sense of seriousness and attention to detail as the lawyer diligently works on his case.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's hand in the video is not fully generated, and the eyes are not generated."
}
] |
seed42_291
|
videos/HRA_part0/291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed doctor, wearing a white button-down shirt and khaki shorts, leaps into the air on a pristine, sandy beach, with crystal-clear water visible in the background. The doctor, who has brown hair and glasses, is captured mid-jump, displaying a sense of freedom and joy. The scene is set against a stunning backdrop of palm trees and a clear blue sky, creating a perfect blend of professional and leisure elements. The doctor's relaxed attire and the idyllic beach setting convey a sense of balance between work and personal life.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2701
|
videos/HRA_part0/2701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a mongoose, typically a small terrestrial carnivore, is depicted engaging in an extraordinary activity. It is shown riding a horse, specifically a Mars horse, which could imply a horse adapted to the conditions of Mars or having Martian features, across a barren, rocky landscape reminiscent of the Martian surface. The mongoose, now a rider, steers the horse with determination as they race through the rugged terrain. The action intensifies as they begin to run at full speed, the horse's hooves kicking up red dust, while the mongoose holds on tightly, its small size contrasting with the grandeur of the Martian environment. This fantastical scenario combines elements of adventure, science fiction, and nature in a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat can be clearly seen riding a horse in the video, but the movements are not very continuous and smooth, showing some inconsistency."
}
] |
seed46_2859
|
videos/HRA_part2/2859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal cinematic scene, a majestic buffalo leaps gracefully over a row of vintage cinema seats, its powerful muscles straining against the force of gravity. The buffalo, with its shaggy brown fur and large horns, seems unfazed by the unusual setting, focusing solely on the jump. The cinema seats, arranged neatly in rows, are old-fashioned, with red upholstery and gold accents, creating a striking contrast against the buffalo's wild nature. The room is dimly lit, casting dramatic shadows on the walls and floor, emphasizing the buffalo's impressive leap. The air is filled with tension and anticipation as the buffalo soars through the air, its hooves inches from touching the seat backs. This captivating scene combines elements of nature and culture in a way that challenges traditional boundaries and expectations.]"
},
{
"from": "gpt",
"value": "Bad. The water buffalo's movements in the video are not smooth."
}
] |
seed46_2702
|
videos/HRA_part2/2702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, vibrant kitchen filled with the warm glow of overhead lights, a group of four individuals, two men and two women, are energetically washing dishes. One man, wearing a dark green apron over a white t-shirt, vigorously scrubs a pot under running water from a stainless steel sink. Beside him, a woman in a yellow apron laughs as she dries a plate with a colorful cloth. Across the room, another man in a chef's coat rinses glasses, while a woman in a floral apron sorts cutlery, her hands deftly separating forks and spoons. The atmosphere is lively, with steam rising from the sink and the clinking of dishes adding to the symphony of post-meal cleanup.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2807
|
videos/HRA_part1/2807.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, an antelope, distinctively marked with white underbelly and brown coat, is shown crawling on its belly across the grassland, a behavior rarely observed. The scene opens with the antelope lying down, then it proceeds to crawl, its horns visible, as it moves slowly through the tall grass. Throughout the sequence, the antelope remains low to the ground, its body almost parallel to the earth, showcasing this unusual behavior in great detail against the backdrop of the African savanna.]"
},
{
"from": "gpt",
"value": "Normal. The antelope's movements are not smooth."
}
] |
seed42_1865
|
videos/HRA_part0/1865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two adult buffalo, with shaggy brown fur and impressive horns, engage in a tender moment. One buffalo affectionately caresses the other's face with its muzzle, displaying a rare display of gentleness and connection between these typically rugged creatures. The scene is set against a backdrop of lush grasslands and distant, rolling hills, capturing the essence of their wild habitat while highlighting the intimate bond shared by these majestic animals.]"
},
{
"from": "gpt",
"value": "Normal. The nose of the water buffalo on the right in the video is problematic, the horns on the right are of different sizes, and the water buffalo on the left is missing one horn."
}
] |
seed42_1811
|
videos/HRA_part0/1811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and black leggings, walks briskly across a campus path, holding textbooks and a coffee cup. Suddenly, a coyote appears in the frame, walking parallel to the path, about ten feet away from the student. The coyote, seemingly unbothered by the human presence, has a gray and brown coat, alert ears, and a bushy tail. It continues to walk alongside the path, offering a unique encounter between urban wildlife and a busy student on the go.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the student and the coyote in the video are not smooth and the actions are uncoordinated."
}
] |
seed46_2751
|
videos/HRA_part2/2751.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A street worker in Shanghai, wearing a green vest and holding a broom, gently caresses the concrete surface as he meticulously sweeps the city sidewalk. Behind him, a bustling urban landscape unfolds, with high-rise buildings, neon signs, and the occasional passerby, all set against the backdrop of a vibrant metropolis. The worker's focused gaze and the tender touch of his broom on the pavement convey a sense of care and routine amidst the dynamic energy of Shanghai's streets.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and the object in hand is also distorted."
}
] |
seed44_2457
|
videos/HRA_part1/2457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling female musician, wearing a gray sweater, sits against a rustic wooden backdrop. She holds knitting needles and yarn in her hands, crafting a vibrant orange scarf. Her fingers, adorned with rings, skillfully manipulate the needles as she knits. Next, she wears a maroon beret and continues knitting, her eyes focused on her work. Then, she looks up from her knitting, her hazel eyes meeting the camera with a warm smile. Lastly, she proudly holds up the completed scarf, now a beautiful addition to her outfit, against the backdrop of wooden planks, showcasing her dual talents in music and knitting.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the generation of knitting needles."
}
] |
seed44_2495
|
videos/HRA_part1/2495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear including a yellow reflective jacket, black pants, and boots, meticulously irons his uniform in a room with a white wall and a table covered with a white cloth. The room is sparsely decorated, featuring a calendar and a portrait on the wall. The firefighter, sporting a well-groomed beard and a focused expression, demonstrates his attention to detail by carefully smoothing out the wrinkles in his uniform. The camera captures the steam from the iron as it glides over the fabric, highlighting the contrast between the firefighter's rugged appearance and the domestic task at hand.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video is not fully shown."
}
] |
seed42_1117
|
videos/HRA_part0/1117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the video are not smooth."
}
] |
seed42_1632
|
videos/HRA_part0/1632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with short brown hair, sits in a clean, organized office space filled with natural light. Dressed in a gray shirt, black vest, and jeans, he nods in agreement while conversing with someone off-camera. His demeanor is professional yet relaxed, and he gestures with his right hand during the discussion, emphasizing his points. The office environment is modern and minimalistic, featuring a wooden desk, a green plant, and a laptop, contributing to a focused and productive atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2115
|
videos/HRA_part2/2115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, donning a brown leather jacket, a gray t-shirt, and jeans, stands against a dark background, holding a megaphone and gesturing with his other hand. Moments later, a wolf, possibly a Timber Wolf, is seen running in a dense forest, its powerful legs propelling it forward with grace and speed. The wolf's fur is a mix of grays and browns, blending seamlessly with the underbrush. The scene transitions to show the wolf's perspective, capturing the blur of trees and foliage as it dashes through the woodland, highlighting its agility and strength in motion.]"
},
{
"from": "gpt",
"value": "Bad. The legs undergo mutations and deformities, first regressing which is unrealistic, and then having extra legs."
}
] |
seed44_2232
|
videos/HRA_part1/2232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a green apron over a gray shirt and dark pants, runs down a dimly lit corridor in a large cinema complex. The hall is lined with red carpeting and features a series of doors leading into various screening rooms. The man's facial hair and glasses are distinctive, and he carries a cleaning tool in his right hand. As he sprints, his eyes are set forward, and he passes by a sign with movie titles and showtimes, creating a sense of urgency in the vast, quiet space. The scene captures the hurried pace and isolated environment of the janitor's duties within the cinema.]"
},
{
"from": "gpt",
"value": "Bad. While running, the man's arm appears deformed, and his face shows distortion."
}
] |
seed46_1410
|
videos/HRA_part2/1410.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student wearing a green jacket and khaki pants explores a lush rainforest, observing a koala as it clings to a eucalyptus branch. Moments later, the student leaps over a small stream, demonstrating agility and enthusiasm for nature. Then, the koala is seen jumping from branch to branch, its plush fur glistening with dew, highlighting the playful nature of these marsupials in their natural habitat. Finally, the student sits on a mossy log, watching the koala munch on eucalyptus leaves, capturing the serene beauty of the rainforest and the peaceful coexistence between humans and wildlife.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3192
|
videos/HRA_part2/3192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space-themed sports arena, a young female cashier, wearing a white apron over her outfit, diligently wipes down the countertop with a cloth. The background is vibrant, featuring neon lights and digital screens displaying scores from ongoing cosmic games. The cashier's actions are methodical, her focus intense, as she ensures the counter is spotless for the next customer in this bustling, intergalactic sports hub. Behind her, patrons in diverse alien attire wait patiently, adding to the dynamic atmosphere of this extraterrestrial venue.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1305
|
videos/HRA_part2/1305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sleek black panther leaps majestically across a moonlit savannah, its muscles rippling beneath dark fur that shimmers under the celestial glow. The powerful feline bounds over tall grasses, leaving a trail of disturbed foliage in its wake, as it propels itself forward with a burst of speed and grace. Upon landing, the panther crouches low, ready for its next spring, against the backdrop of a vast landscape, dotted with distant trees and illuminated by the silvery light of the full moon.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and facial features of the black panther in the video were not generated."
}
] |
seed42_1094
|
videos/HRA_part0/1094.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A space worker, clad in a high-tech, neon-accented spacesuit, traverses a vast, ethereal galactic nebula, the swirling cosmic clouds of reds and purples forming a breathtaking backdrop. The figure moves with purpose, the lights from their suit casting dramatic shadows against the interstellar gas and dust. A closer shot reveals the worker's faceplate, reflecting the mesmerizing nebula, highlighting their isolated journey among the stars. As they walk, the nebula's colors swirl around them, creating a stunning visual of a human amidst the grandeur of the universe.]"
},
{
"from": "gpt",
"value": "Good. The video shows the character's walking movements more clearly, and the actions are basically normal and smooth."
}
] |
seed44_1554
|
videos/HRA_part1/1554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed man, wearing a navy suit with a light blue shirt and a dark blue tie, stands against a neutral gray background. He points to an unseen object or idea with a confident smile, engaging the viewer with his clear, green eyes. His neatly combed brown hair and clean-shaven face add to his professional appearance. The focus is solely on him, with no additional elements in the frame, as he points with his right index finger, inviting the audience to follow his gesture.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are generated basically correctly, but there is a slight deformity."
}
] |
seed46_2445
|
videos/HRA_part2/2445.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene grassland setting under a clear blue sky, a police officer, clad in a standard uniform with a badge and gun holster, kneels by a small, clear pond. He watches intently as a group of children joyfully splash and swim in the water, their laughter echoing across the open landscape. The officer's presence is both protective and relaxed, creating a harmonious scene where law enforcement and community enjoyment coexist peacefully amidst the natural beauty of the vast, green grasslands.]"
},
{
"from": "gpt",
"value": "Normal. The child's movements in the pool in the video are slightly unsmooth."
}
] |
seed44_1155
|
videos/HRA_part1/1155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse with blonde hair pulled back into a bun sits in a cozy room, knitting a vibrant red scarf with her skilled hands. Dressed in a clean, white uniform, she focuses intently on her craft, surrounded by the warm glow of soft lighting. The scene captures her in various moments, from checking her progress to pausing thoughtfully, always maintaining a serene expression. Her uniform is crisp and professional, contrasting with the homely atmosphere of the room, where a fireplace casts a warm light over her industrious figure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2311
|
videos/HRA_part0/2311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent leopard, with striking golden eyes and a distinctive pattern of rosettes on its tawny fur, is captured in high definition as it lies on a branch. It begins by looking straight ahead, showcasing its majestic presence. Then, it turns its head to the right, revealing its sharp features and powerful muscles rippling beneath its coat. Next, the leopard proceeds to clean itself, licking its paw and wiping it across its face, a display of natural behavior in its untamed habitat. Throughout the sequence, the leopard remains perched on the branch, its gaze occasionally flicking towards the viewer, offering a rare glimpse into its private grooming routine.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's claws were not fully generated in the video."
}
] |
seed46_2189
|
videos/HRA_part2/2189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a sleek black panther, adorned with a red bow tie, calmly walks down a brightly lit supermarket aisle filled with neatly arranged products. The panther gently wipes its paw across the shelves, leaving a trail of sparkling cleanliness. The shelves are stocked with various goods, from canned foods to household items, all bathed in a warm, inviting glow. The panther continues its meticulous cleaning, moving gracefully through the aisles, as if it were a routine task in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1164
|
videos/HRA_part1/1164.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, donning a casual striped shirt and khaki pants, meticulously vacuums the living room of her cozy home, her curly brown hair bouncing as she moves. The room is filled with natural light, illuminating the space as she expertly maneuvers the vacuum cleaner, ensuring no spot is left untouched. Her dedication to tidiness is evident in the neat arrangement of books on the shelves and the absence of clutter, creating a peaceful environment. This scene captures the teacher's commitment to cleanliness and order, even in her personal life, as she takes a break from her educational duties to tend to household chores.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3065
|
videos/HRA_part0/3065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, casually dressed in a white T-shirt and beige shorts, walks along a stone path on campus, accompanied by a small, green lizard perched on their right shoulder. The student, wearing a backpack and baseball cap, strolls under the shade of lush trees, while the reptile remains calmly positioned, seemingly enjoying the ride. The scene captures the unusual yet harmonious relationship between the student and the lizard, both navigating the campus environment together.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are distorted, the lizard's body is twisted, and the claws are deformed."
}
] |
seed44_2708
|
videos/HRA_part1/2708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster, primarily white with gray patches, leaps into the air from within a wire cage, its hind legs propelling it upwards with remarkable agility. The hamster's front paws extend forward as it jumps, highlighting its determination and playfulness. The scene is set against a backdrop of a green meadow, creating a whimsical contrast between the indoor cage and the outdoor setting. The hamster's joyful leap is captured in high detail, showcasing its adventurous spirit and the soft fur that covers its body.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's paws are deformed, with extra legs, facial and ear deformities, and instances of body clipping."
}
] |
seed46_1161
|
videos/HRA_part2/1161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a futuristic silver spacesuit with an American flag patch, is seen crawling across the rocky, red Martian landscape, examining the terrain closely. The scene is set under a pinkish-brown sky, with distant mountains visible on the horizon. The officer's spacesuit features NASA logos and a utility belt, and they carry a high-tech scanner, highlighting the unusual combination of law enforcement and space exploration. The camera captures this unique moment in crisp, high-definition detail, emphasizing the contrast between the traditional role of a police officer and the extraordinary setting of a distant planet.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted, and the arm is twisted."
}
] |
seed46_1554
|
videos/HRA_part2/1554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed man, wearing a navy suit with a light blue shirt and a dark blue tie, stands against a neutral gray background. He points to an unseen object or idea with a confident smile, engaging the viewer with his clear, green eyes. His neatly combed brown hair and clean-shaven face add to his professional appearance. The focus is solely on him, with no additional elements in the frame, as he points with his right index finger, inviting the audience to follow his gesture.]"
},
{
"from": "gpt",
"value": "Normal. The movements are not smooth."
}
] |
seed42_3133
|
videos/HRA_part0/3133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature man with graying hair, dressed in a white T-shirt and black exercise pants, stretches his body against a gray studio wall. He leans forward with his right leg extended, foot against the wall, and his left leg bent, demonstrating flexibility. His hands rest on his right thigh and shin, while his head tilts down, showcasing a focused expression. Behind him, a large window reveals a blurred outdoor view, adding depth to the scene. The room is illuminated by soft, natural light, highlighting the man's dedication to maintaining his physical health.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2972
|
videos/HRA_part2/2972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, distinguished by his black-rimmed glasses and neatly trimmed beard, waters plants in an urban rooftop garden. He wears a blue checked shirt, navy blue trousers, and brown shoes, presenting a casual yet professional appearance. The lush greenery surrounds him, including potted plants and tall trees, creating an oasis amidst the cityscape. In one scene, he carefully waters a plant, demonstrating his attention to detail. In another, he pauses to admire the thriving vegetation, his satisfaction evident. Throughout, the rooftop garden offers a peaceful retreat from the bustling metropolis below, with the engineer's presence adding a human touch to the verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. The video did not generate brown shoes."
}
] |
seed42_2281
|
videos/HRA_part0/2281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a cosmic event unfolds as a theoretical white hole explosion is depicted with vibrant colors and swirling celestial patterns, forming an ethereal, mesmerizing spectacle in the background. In the foreground, a graceful woman, wearing a flowing white dress, gently caresses an abstract representation of the universe, symbolized by a large, luminous orb, evoking a sense of connection and reverence for the mysteries of the cosmos. The woman's serene expression and delicate touch convey a message of harmony and unity between humanity and the infinite expanse of space.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video are missing, and her face is deformed."
}
] |
seed46_2359
|
videos/HRA_part2/2359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, clad in a vibrant pink uniform and wearing a traditional cap, joyfully dances alongside a large, gentle elephant in a lush, green outdoor setting. The pair moves in perfect harmony, their spirits uplifted by the warm sunlight filtering through the leaves overhead. The nurse's face is aglow with happiness, her eyes closed in blissful abandon, while the elephant sways gracefully, its trunk raised in a playful salute to their shared moment of pure delight.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's limbs are missing, there are issues with the face generation, the elephant's trunk is not generated, and there are problems with the face and tail generation."
}
] |
seed42_1428
|
videos/HRA_part0/1428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A handsome male waiter, wearing a crisp white shirt, black vest, and necktie, serves a couple at an elegant indoor restaurant. Suddenly, he breaks into song, passionately singing an operatic aria while continuing to serve. The camera captures his animated face as he sings, highlighting his emotional performance. Throughout, the well-lit dining area with its ornate chandelier and patrons at other tables remains visible, creating a lively atmosphere. The waiter's confident singing and the restaurant's upscale ambiance provide a memorable contrast to his regular duties.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2970
|
videos/HRA_part1/2970.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a young female cashier, wearing a red apron over her gray sweater and black jeans, stands at a register, looking surprised. Behind her, a full-sized moose runs across the store, its antlers adorned with Christmas lights, adding a surreal touch to the supermarket setting. The moose dashes between the aisles filled with groceries, creating a chaotic yet amusing atmosphere. The cashier watches the unexpected visitor with a mix of shock and amusement, as customers look on in disbelief, capturing the bizarre event on their smartphones. The moose's presence disrupts the mundane routine of the store, turning it into an unforgettable experience for everyone present.]"
},
{
"from": "gpt",
"value": "Bad. Did not generate a young female cashier standing at the cash register wearing a gray sweater and black jeans, with a red apron on top."
}
] |
seed42_3198
|
videos/HRA_part0/3198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone firefighter, clad in a specialized Neptune atmospheric suit, complete with a helmet and breathing apparatus, runs across a rugged, alien landscape bathed in eerie, ethereal light. The environment is dominated by hues of blue and green, evoking the mysterious atmosphere of Neptune. Wisps of cloud-like formations swirl in the distance, adding to the otherworldly ambiance. The firefighter's suit, equipped with advanced technology to withstand the harsh conditions, glimmers under the faint illumination, highlighting the bravery and determination required to perform such a daunting task in an extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_161
|
videos/HRA_part2/161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, cosmic library filled with floating bookshelves and galaxies in the background, a majestic lion, adorned with a golden collar and a serious expression, is seen wiping the dust off ancient books with a delicate paw. The shelves are stocked with books of all sizes, and the lion moves between them, engaged in the meticulous task of cleaning. Surrounded by the grandeur of space and knowledge, the lion continues its duty, highlighting the serene yet awe-inspiring setting.]"
},
{
"from": "gpt",
"value": "Normal. The lion's movements are not smooth."
}
] |
seed42_2698
|
videos/HRA_part0/2698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmhand, clad in a khaki shirt, beige trousers, and brown shoes, walks purposefully across a well-kept yard. In the foreground, a vibrant red barn provides contrast against the clear blue sky. The worker pauses, bending down to pick up a lively chicken, its feathers a mix of brown and white, before continuing on his path, the bird calmly tucked under his arm. They stroll together, the worker's gait steady and the chicken seemingly unperturbed, encapsulating the peaceful rhythm of life on the farm.]"
},
{
"from": "gpt",
"value": "Bad. The chicken was not held under the worker's arm in the video."
}
] |
seed44_2989
|
videos/HRA_part1/2989.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic kitchen illuminated by neon lights, a chef wearing a sleek, silver uniform and gravity-defying boots stands aboard an anti-gravity vehicle. The vehicle, resembling a levitating platform with intricate, glowing circuitry, hovers above a metallic countertop cluttered with advanced cooking gadgets. The chef, with a focused gaze, wipes a stainless steel utensil with a microfiber cloth, preparing for culinary innovation amidst the backdrop of a high-tech, floating workstation.]"
},
{
"from": "gpt",
"value": "Bad. The chef's movements in the video are not smooth."
}
] |
seed44_2107
|
videos/HRA_part1/2107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a casual gray t-shirt and blue jeans, is seen unloading a dishwasher in a modern kitchen with sleek, stainless steel appliances. The room is well-lit, casting a warm glow over the beige walls and brown cabinets. The student, sporting a short haircut and glasses, carefully removes dishes from the lower rack, placing them into a cabinet just above the dishwasher. With each item placed, the student's movements are deliberate and efficient, showing a routine familiarity with the task. The space is tidy and minimalistic, with a small dining table in the corner and a window letting in natural light, creating a homely atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1017
|
videos/HRA_part2/1017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling, upscale restaurant filled with the clinking of glasses and chatter, a waiter in a crisp, black uniform expertly navigates the lively dining room. He deftly pushes a polished, stainless steel service cart laden with fine china and gleaming silverware, carefully avoiding any contact with the patrons enjoying their meals. The elegant space, adorned with hanging lights casting a warm glow and walls decorated with framed artwork, provides a sophisticated setting for this scene of seamless service execution.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2494
|
videos/HRA_part1/2494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white hare, its fur gleaming under the moonlight, crawls through a dense thicket of green foliage, navigating the intricate maze of branches and leaves with cautious precision. Its ears, erect and alert, swivel at the slightest sound, while its eyes, large and luminous, remain fixed on the path ahead. The hare's hind legs, powerful and agile, propel it forward in a series of controlled movements, each paw carefully placed to ensure silent progression through the undergrowth. The scene is set against the backdrop of a tranquil night, with the stars twinkling overhead and the distant hoots of owls punctuating the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the white rabbit in the video has problems."
}
] |
seed46_2459
|
videos/HRA_part2/2459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a brightly lit classroom filled with educational toys and posters, a caring teacher, dressed in a yellow shirt and khaki pants, gently wipes the face of a young chimpanzee sitting attentively on a small chair. The chimpanzee, wearing a tiny blue cap, looks intently at the teacher, who uses a soft, white cloth to clean its face. The scene conveys a sense of nurturing and education, with the teacher's kind demeanor and the chimpanzee's attentive behavior highlighting the bond between them.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's hands in the video are generated with multiple and incomplete instances, and there are issues with the generation of the chimpanzee's hands and face."
}
] |
seed42_2080
|
videos/HRA_part0/2080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two children, a boy and a girl, both dressed in green, are dancing gleefully in a grassy meadow filled with dandelions. They perform a choreographed routine, spinning and leaping with joyful abandon. Suddenly, a vole emerges from the tall grass, peeking curiously at the dancers. Unfazed, the children continue their dance, now incorporating playful gestures towards the small mammal. The vole watches from a safe distance, its presence adding a touch of natural charm to the lively scene. Throughout the dance, the children's outfits, consisting of green shirts and khaki shorts, stand out against the lush greenery of the meadow, creating a vibrant and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1250
|
videos/HRA_part0/1250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit tailor shop, a friendly cashier, dressed in a maroon collared shirt and khaki pants, assists a customer. The cashier, with neatly trimmed facial hair, sits at a sewing machine, carefully hemming a pair of gray pants, demonstrating expertise and precision. The scene highlights the skilled craftsmanship and personal service provided in the store, with the cashier's focused expression and the sewing machine's rhythmic sound adding to the atmosphere. The customer, standing nearby, watches attentively, expressing satisfaction and trust in the cashier's abilities.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's hands are generated incorrectly."
}
] |
seed44_1714
|
videos/HRA_part1/1714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the midst of arid scrublands, a spotted hyena, characterized by its distinctive spots and robust build, is unexpectedly seen swimming across a shallow, sunlit waterhole. Its head held high above the clear water, the hyena propels itself forward with powerful strokes, showcasing its rarely observed aquatic abilities. The serene environment is punctuated by the distant silhouette of a lone tree, highlighting the surprising scene unfolding in this typically dry habitat.]"
},
{
"from": "gpt",
"value": "Bad. The head of the spotted hyena in the video is generated abnormally, with two bodies of the spotted hyena appearing in the middle frame."
}
] |
seed44_2980
|
videos/HRA_part1/2980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, dressed in a brown jacket, beige pants, and brown boots, stands on a dirt floor, meticulously wiping a wooden table with a cloth. The scene takes place in a large, open arena, filled with wooden tables and chairs, reminiscent of a medieval feast setting. Sunlight filters through the high windows, casting a warm glow over the space. The man's focused gaze and the repetitive motion of his hand convey a sense of purpose and care in his task, set against the vastness of the arena.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers are deformed, and his face is distorted in the video."
}
] |
seed46_137
|
videos/HRA_part2/137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a panda wearing a spacesuit floats in zero gravity, gently wiping a tear from its eye with a small cloth. Beside it, two astronauts, also in full space gear, share a tender kiss, signifying a unique 'space wedding'. The panda, adorned with a bow tie and holding a bouquet, serves as a heartwarming witness to this celestial union, all taking place against the backdrop of a starlit universe, with Earth visible through the window of the spacecraft.]"
},
{
"from": "gpt",
"value": "Bad. Panda's face is deformed, hands are twisted, character's face is distorted, hands are twisted."
}
] |
seed42_1614
|
videos/HRA_part0/1614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space opera performance, a farmer wearing a traditional straw hat and a patched apron over a checkered shirt runs across the stage under a backdrop of stars and planets. Simultaneously, a life-sized robotic tiger, designed with intricate circuitry patterns, races alongside him, both moving with a sense of urgency. The farmer's face is set in determination, and the tiger's robotic eyes glow with programmed intensity, highlighting the dramatic chase sequence unfolding against the cosmic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1916
|
videos/HRA_part1/1916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded man, possibly a writer, sits in a hotel room, wearing a brown jacket and glasses, wiping a wooden table with a cloth. The room is well-lit, with a large window behind him, offering a view of a distant mountain range. The man focuses intently on cleaning, his actions deliberate and purposeful. Moments later, a plush teddy bear rests on the now-polished surface, suggesting a personal touch or a connection to the writer's creative process. The scene conveys a sense of tranquility and routine, with the writer's attire and surroundings contributing to the overall mood.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the teddy bear mentioned in the caption."
}
] |
seed46_2080
|
videos/HRA_part2/2080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two children, a boy and a girl, both dressed in green, are dancing gleefully in a grassy meadow filled with dandelions. They perform a choreographed routine, spinning and leaping with joyful abandon. Suddenly, a vole emerges from the tall grass, peeking curiously at the dancers. Unfazed, the children continue their dance, now incorporating playful gestures towards the small mammal. The vole watches from a safe distance, its presence adding a touch of natural charm to the lively scene. Throughout the dance, the children's outfits, consisting of green shirts and khaki shorts, stand out against the lush greenery of the meadow, creating a vibrant and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_3061
|
videos/HRA_part0/3061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, complete with a tailored suit and carrying a leather briefcase, finds himself in an unexpected scenario amidst a lush, verdant forest. He encounters a kangaroo, which has somehow become covered in a fine layer of dust. The lawyer, displaying a surprising level of empathy and care, gently wipes the dust off the kangaroo's fur using a pristine white handkerchief, revealing the clean, soft fur beneath. The kangaroo looks on with curiosity, standing on its hind legs, as the lawyer meticulously cleans it, all under the dappled sunlight filtering through the dense canopy above.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the kangaroo's head is distorted."
}
] |
seed44_2411
|
videos/HRA_part1/2411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2928
|
videos/HRA_part0/2928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A badger, typically known for its sturdy build and earthy tones, is depicted in an unexpected scenario, engaging in a joyful dance within its natural habitat. The badger, adorned with a red bow tie and a small top hat, moves energetically to an unseen beat, surrounded by lush greenery and under the shade of towering trees. Its dance is characterized by playful twirls and energetic hops, a stark contrast to its usual demeanor, all captured in a whimsical and vibrant scene that highlights the unexpected delight of a dancing badger in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The top hat is missing at the scene."
}
] |
seed44_2734
|
videos/HRA_part1/2734.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic, silver-furred wolf stands on a platform at the base of a colossal space elevator, its massive structure stretching into the starlit sky. The wolf gently caresses the sleek, metallic surface of the elevator with its snout, as if acknowledging a familiar presence. Its piercing golden eyes reflect the surrounding ethereal lights, adding an otherworldly touch to the interaction between the creature and the futuristic architecture. The platform is surrounded by a vast, moonlit landscape, with distant mountains silhouetted against the night sky, creating a dramatic contrast to the looming space elevator.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2724
|
videos/HRA_part2/2724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red flannel shirt, beige pants, and brown suspenders, stands at a white sink in a rustic kitchen. He is washing dishes by hand using a sponge, with a wooden cutting board and a bowl of fruit visible nearby. The farmer, who has short brown hair and a neatly trimmed beard, demonstrates his commitment to household chores with a focused expression. The kitchen is warm and inviting, with wood-paneled walls, a white refrigerator, and a window above the sink offering a view of green fields. The farmer's strong hands, calloused from years of working the land, now deftly clean plates and utensils, showcasing the versatility of his daily tasks.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face generation in the video has problems, the fingers are malformed, and the sponge is distorted."
}
] |
seed42_2005
|
videos/HRA_part0/2005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a man dressed as a waiter, wearing a black vest, white shirt, black tie, and apron, is playfully dancing with a horse in the middle of a grassy field under a clear blue sky. The horse, adorned with a golden bridle and red and gold saddle blanket, seems to be enjoying the unexpected dance, moving gracefully in sync with the waiter's steps. Both the waiter and the horse exhibit expressions of pure joy and abandon, creating a surreal yet delightful spectacle. The vibrant colors of their attire contrast beautifully with the natural greenery and blue sky, adding to the dreamlike quality of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The horse's movements are not noticeable."
}
] |
seed44_306
|
videos/HRA_part1/306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2957
|
videos/HRA_part1/2957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret, with a brown and white coat, swims through clear, bubbling water, showing its unique swimming style with its head held high and nose just above the waterline. It uses its webbed feet to propel itself forward, highlighting its natural aquatic abilities. The water droplets glisten around it, and its determined face conveys a sense of joy and playfulness in its unusual swimming endeavor.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.