video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1623
|
videos/HRA_part1/1623.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 surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, likely his cub, against the backdrop of a lush, green savannah during the golden hour. The father lion, with his thick, dark mane, displays affection and protection as he rubs his cheek against the cub's head. The cub, with its curious eyes and playful demeanor, responds with a nuzzle of its own, showcasing the intimate bond between them. This heartwarming interaction unfolds under a sky painted with warm hues of orange and pink, highlighting the emotional connection between the two lions.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1806
|
videos/HRA_part0/1806.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 enclosure, a majestic black panther sits calmly, its piercing eyes gazing intently. It gently caresses a log with its massive paw, adorned with thick, black fur and sharp claws. The panther's regal demeanor is underscored by its relaxed posture and the tender interaction with the wooden surface, set against a backdrop of lush vegetation and a water source, creating a serene atmosphere in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2568
|
videos/HRA_part0/2568.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 giant panda, clad in a red jacket and black pants, races through a city park surrounded by towering skyscrapers, lush greenery, and a clear blue sky. The panda, sporting sunglasses and a determined look, sprints past urban landmarks, including a towering glass building and a bridge. In another scene, the panda leaps over a log, its athletic prowess on full display against the cityscape backdrop. Finally, it continues its run, moving right to left across the screen, with the vibrant city as its dynamic setting.]"
},
{
"from": "gpt",
"value": "Bad. The running action of the panda in the video is not continuous, there are abrupt changes."
}
] |
seed46_141
|
videos/HRA_part2/141.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 room filled with natural light, two young children sit cross-legged on a wooden floor, engrossed in crocheting a vibrant blanket. One child, wearing a yellow T-shirt and denim shorts, focuses intently on their work, their tongue slightly protruding in concentration. The other, dressed in a pink sweater and khaki pants, looks up momentarily, a smile playing on their lips, before returning to the colorful yarn in their hands. The atmosphere is warm and inviting, with the half-finished blanket spreading across their laps, a testament to their patience and creativity. Beside them, a basket of yarn in various shades adds a touch of whimsy to the scene, as the children continue to crochet, their movements steady and practiced.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_2489
|
videos/HRA_part0/2489.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 creative juxtaposition, a male cashier, clad in a gray shirt and black pants, is seen sprinting energetically across a vast, open space, reminiscent of a track field. Behind him, an enormous screen displays a stunning, high-definition image of Jupiter's iconic Great Red Spot, creating a surreal and captivating visual contrast between the terrestrial and the celestial. The cashier's focused expression and determined stride add a sense of urgency and dynamism to the scene, while the imposing presence of the gas giant's storm serves as a dramatic and awe-inspiring backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, and legs are distorted in the video."
}
] |
seed46_2089
|
videos/HRA_part2/2089.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 creative blend of scenes, two smiling children, a boy in a blue jacket and a girl in a pink jacket, walk alongside a life-sized zebra puppet, its distinctive black and white stripes vivid against a neutral background. The children hold hands, looking up in wonder, as the zebra puppet, operated by an unseen handler, walks alongside them. Behind them, a large, high-definition screen displays a captivating visualization of dark matter research, featuring swirling galaxies and complex data visualizations, seamlessly merging elements of nature, childhood innocence, and scientific exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1900
|
videos/HRA_part2/1900.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 red fox, wearing a small backpack adorned with patches, walks purposefully across a barren lunar landscape under a star-studded sky, holding a well-thumbed copy of a science fiction novel in its mouth. Its eyes, filled with curiosity and determination, reflect the distant stars. It passes by a small, glowing campfire, hinting at a recent gathering of fellow space book club members, who have presumably shared tales from their latest galactic reads. The fox continues its journey, the book's title, \"Cosmic Chronicles,\" visible as it strides forward into the cosmic night, leaving footprints on the moon's dusty surface.]"
},
{
"from": "gpt",
"value": "Bad. The movement of the red fox walking in the video is not smooth, and the actions are uncoordinated."
}
] |
seed46_2841
|
videos/HRA_part2/2841.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 farmer, wearing a red flannel shirt and denim overalls, dances joyously in a lush green field, while a curious deer watches from a distance, its ears perked up, intrigued by the unusual sight. The farmer's movements are lively and free, embodying a sense of unbridled happiness, as the deer remains frozen in place, observing the dance with wide, expressive eyes. The scene is set against a backdrop of rolling hills and a clear blue sky, creating a picturesque rural landscape that complements the harmonious interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the farmer dancing, with movements that are not continuous and smooth, showing a lack of coordination."
}
] |
seed46_2233
|
videos/HRA_part2/2233.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, young female musician dons a futuristic silver outfit, complete with a matching helmet, as she energetically performs a dynamic concert on a space station. Surrounded by the vast cosmos, she passionately sings into her microphone, her movements lively and engaging. In a captivating display, she effortlessly sprints across the zero-gravity stage, her silver suit shimmering under the cosmic lights, while continuing to captivate the audience with her powerful voice and electrifying performance. The space station's advanced technology enhances the concert experience, creating an unforgettable spectacle set against the backdrop of the infinite universe.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3209
|
videos/HRA_part1/3209.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 in a red t-shirt and black shorts is depicted running alongside a kangaroo on a dusty trail surrounded by lush vegetation, both appearing energetic and engaged in the activity. They run together on a dirt path amidst dense greenery, the kangaroo bounding effortlessly beside the man, who maintains a steady pace. The scene captures the unique companionship between the man, dressed casually in a red top and dark shorts, and the kangaroo, as they traverse the natural environment together. The duo continues their run through the vibrant landscape, the kangaroo's powerful legs propelling it forward in sync with the man's strides, highlighting their shared rhythm and connection amidst the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, legs, kangaroo's body, head, and legs are distorted in the video."
}
] |
seed44_1480
|
videos/HRA_part1/1480.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 surprising juxtaposition, a large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Bad. The hippopotamus in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_2029
|
videos/HRA_part1/2029.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, dressed in a tailored gray suit, stands confidently in a lush green backyard, holding a golden chicken with care. The vibrant green grass complements his attire, while the chicken adds a touch of whimsy. Nearby, a swimming pool glistens under the sunlight, its clear blue water contrasting beautifully with the greenery. The lawyer gently places the chicken on the grass, its feathers gleaming in the sun, before walking towards the pool. He pauses at the edge, contemplating the serene water, creating a juxtaposition between his professional demeanor and the unexpected presence of the chicken in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's hands and feet, and the chicken generation have issues; the chicken suddenly disappears in the middle frame."
}
] |
seed44_2189
|
videos/HRA_part1/2189.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 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 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": "Normal. The wiping motion can be seen, but the action is not continuous, there are sudden changes."
}
] |
seed42_1919
|
videos/HRA_part0/1919.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 majestic marlin breaches the shimmering ocean surface, its streamlined body glistening under the golden sunlight. The marine creature, adorned with striking blue and silver hues, soars through the air with acrobatic grace, its elongated upper jaw, or rostrum, pointing towards the sky. As it re-enters the water, a splash of crystal-clear droplets disperses around it, creating a mesmerizing display of power and agility in the vast aquatic realm.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1897
|
videos/HRA_part0/1897.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 depiction, a gray and white cat, wearing a miniature spacesuit complete with a gold badge, is seen floating weightlessly in a spaceship, its paws gently touching a control panel. The cat, named Ambassador Fluff, is on a diplomatic mission among the stars, representing Earth's feline population. As zero-gravity music plays, the cat begins to dance, its movements fluid and graceful in the microgravity environment, embodying the spirit of intergalactic diplomacy through the universal language of dance. Behind Ambassador Fluff, a view of distant galaxies and nebulae can be seen through the spaceship's windows, adding to the surreal and majestic atmosphere of this cosmic dance.]"
},
{
"from": "gpt",
"value": "Normal. The cat's movements in the video are not smooth."
}
] |
seed44_1981
|
videos/HRA_part1/1981.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 warehouse environment filled with neatly stacked crates and industrial kitchen equipment, a chef clad in a white uniform and black trousers sprints down the aisles with determination. His arms swing energetically, and his gaze is set forward, indicating urgency and purpose. Behind him, the bustling activity of the kitchen continues, with chefs in white coats busily preparing meals. The chef races past stainless steel shelves stocked with food supplies, his black shoes pounding against the concrete floor, highlighting the dynamic energy of the scene. Throughout, the warehouse's high ceilings and industrial aesthetic provide a distinctive backdrop to the chef's energetic run.]"
},
{
"from": "gpt",
"value": "Bad. The chef's limbs are missing in the video, and the face generation is blurry."
}
] |
seed46_1342
|
videos/HRA_part2/1342.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 middle-aged man wearing a yellow safety vest, blue jeans, and work gloves is seen from a low angle, balancing on a ladder as he scoops wet leaves out of the clogged gutters. The camera pans to show the man, his face intent and focused, tossing the debris onto the grass below. His movements are deliberate and efficient, showcasing his experience in this task. The scene is set against a backdrop of a suburban house with a red roof, emphasizing the routine nature of home maintenance. As the man continues his work, the afternoon sunlight highlights the water and leaves cascading down from the gutters, capturing the essence of a fall day.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2832
|
videos/HRA_part1/2832.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 construction worker, clad in a yellow vest and hard hat, finds an unexpected moment of joy as he dances alongside a graceful antelope in a vast, sunlit prairie. The worker, dressed in blue jeans, a white t-shirt, and sturdy boots, moves with surprising agility, mirroring the antelope's leaps and bounds. The antelope, with its distinctive horns and russet coat, engages in this whimsical dance, seemingly unfazed by the unusual partnership. Together, they create a surreal and delightful scene against the backdrop of a clear blue sky and distant rolling hills.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_20
|
videos/HRA_part2/20.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 female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2911
|
videos/HRA_part1/2911.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 young student, dressed in a casual outfit of a gray sweater and blue jeans, sits cross-legged on a wooden floor inside a cozy room, surrounded by bookshelves. In front of her is a small, curious hedgehog, slowly crawling across a white towel, exploring its immediate environment with keen interest. The student watches the hedgehog intently, her face a mix of fascination and care, as she gently interacts with the animal, creating a heartwarming scene of connection between human and nature indoors.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's movements in the video are slightly unsmooth."
}
] |
seed46_1026
|
videos/HRA_part2/1026.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 film director, donning a beige jacket, black t-shirt, and khaki pants, stands thoughtfully at a hot springs site, contemplating a unique shot. Suddenly, a rhinoceros emerges from the mist, leaping gracefully over a small pond within the springs. The director watches intently, camera in hand, ready to capture the extraordinary moment as the sun sets behind, casting a golden hue over the scene. The rhinoceros, now the central figure, jumps with surprising agility amidst the steamy waters, creating an unforgettable juxtaposition of nature and wildlife against the backdrop of the director's vision.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a small pond."
}
] |
seed44_1308
|
videos/HRA_part1/1308.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 patient teacher, wearing a brown jacket and khaki pants, stands in a rural classroom with wooden desks and a world map on the wall. She gently caresses a small deer that has wandered inside, creating a tender moment. The deer, with its large eyes and curious demeanor, stands calmly beside the teacher, who offers a comforting presence. Both the teacher and the deer are bathed in the warm, golden light filtering through the windows, adding to the serene atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2584
|
videos/HRA_part0/2584.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 lone jackal stands amidst an otherworldly landscape of active volcanoes, its golden eyes reflecting determination. The creature is seen wiping its face with a paw, a gesture of cleansing, against a backdrop of billowing ash and molten lava flows. Surrounded by the harsh beauty of erupting peaks, the jackal's action conveys resilience and survival in the face of adversity, with the volcanoes' fiery eruptions illuminating the dramatic environment.]"
},
{
"from": "gpt",
"value": "Bad. The hyena in the video has too many limbs generated, no tail was generated, and the body is deformed."
}
] |
seed42_2510
|
videos/HRA_part0/2510.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 distinguished gentleman with gray hair and glasses sits in a cozy room filled with bookshelves, natural light, and warm tones. He wears a blue shirt and a brown cardigan, appearing thoughtful and engrossed in a thick hardcover book. Moments later, he looks up from reading, revealing a pensive expression. He then turns the page, his eyes scanning the text intently, before pausing again to reflect on what he has read. Throughout the scene, he remains seated in the same position, his attire and surroundings unchanged, creating a calm and intellectual atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1246
|
videos/HRA_part1/1246.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 police officer, clad in a full uniform complete with a hat, rests peacefully on a bench in a quiet, empty city park during the daytime. The serene atmosphere is highlighted by the soft play of sunlight filtering through the trees, casting dappled shadows on the ground. The officer's hat is tilted down, partially obscuring their face, while they lean back against the wooden slats of the bench, their body language conveying a sense of well-deserved rest. Beside them, a water bottle sits on the bench, and in the distance, the peaceful urban landscape is visible, punctuated by the occasional passerby and the gentle sway of tree branches.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1081
|
videos/HRA_part1/1081.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 tranquil orchard setting, lush greenery surrounds a badger as it curiously explores its environment. The badger, with its distinctive black and white striped face, sniffs the air, then gently caresses the bark of an old apple tree with its paw. The camera captures the badger's actions in detail, focusing on the texture of the tree bark and the animal's fur. The scene is peaceful, with the soft sounds of nature providing a soothing soundtrack to the badger's gentle interaction with its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The badger's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_1037
|
videos/HRA_part2/1037.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 doctor, complete with a stethoscope around his neck, dons a brown jacket, dark trousers, and black boots as he shovels snow from a walkway. Snowflakes gently fall from a gray sky, settling on the green pine tree in the background. The doctor, wearing glasses and a wedding ring, pauses to wipe his brow, revealing his determination. He continues to clear the snow, demonstrating his commitment to his duties despite the weather. Throughout the scene, the doctor's attire remains unchanged, emphasizing his professional identity even in this domestic task.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1908
|
videos/HRA_part1/1908.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 sleek black panther crawls across a dry, cracked earth surface under a dense jungle canopy, its muscles rippling beneath glossy fur. The panther's piercing yellow eyes remain fixed on a distant target, conveying intense focus and determination. It moves slowly and deliberately, each paw carefully placed to ensure silent progression, embodying the essence of stealth and power in the heart of the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2950
|
videos/HRA_part2/2950.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 tiny warbler perches on a thin branch, its vibrant yellow-green plumage contrasting beautifully against the lush green foliage of the forest. The bird, no bigger than a sparrow, displays its distinctive black facial markings and streaks, enhancing its charm. It tilts its head curiously, revealing its sharp, pointed beak, perfectly adapted for probing into bark crevices and catching insects. The warbler then flutters its wings, preparing to leap onto another branch, showcasing its agility and grace in the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1959
|
videos/HRA_part1/1959.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 rugged firefighter, wearing a gray t-shirt and black tactical pants, stands in a modern, open-plan kitchen with white cabinets and stainless steel appliances. He confidently flips a crepe on a large, round griddle, showcasing his culinary skills. The kitchen is part of a fire station, with a red fire truck visible through an arched doorway behind him. The firefighter, now donning an apron over his attire, carefully adds ingredients to the crepe, demonstrating his ability to balance the demands of firefighting with the precision required in cooking. The scene captures the unexpected yet harmonious blend of a firefighter's life-saving duties and his passion for creating delicious meals.]"
},
{
"from": "gpt",
"value": "Bad. The hand appears deformed, and the shovel is distorted, with the left arm disappearing and reappearing suddenly."
}
] |
seed42_1644
|
videos/HRA_part0/1644.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 well-lit, organized retail store, two diligent employees wearing red aprons and name tags restock the shelves with groceries. One employee, a man with short brown hair, focuses on neatly arranging cereal boxes, ensuring they face forward. Meanwhile, his female coworker, wearing glasses and with her hair tied back, meticulously stacks cans of soup, aligning them perfectly. The shelves are filled with various food items, including crackers, canned goods, and pasta, all neatly organized and easily accessible to customers. The store is clean and inviting, with a fresh produce section visible in the background, showcasing an array of colorful fruits and vegetables.]"
},
{
"from": "gpt",
"value": "Normal. The restocking movements of the character in the video are not smooth."
}
] |
seed46_1904
|
videos/HRA_part2/1904.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 casually dressed man in a white shirt and dark pants walks through a lush, green meadow dotted with vibrant wildflowers under a bright, clear blue sky. He strides purposefully, his hands clasped behind his back, exuding a sense of peace and connection with nature. The tall grass sways gently in the breeze around him, and in the distance, a range of rolling hills provides a picturesque backdrop, enhancing the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_1237
|
videos/HRA_part1/1237.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 film director, donning a classic tweed suit, sits on a wooden chair on a meticulously arranged movie set, gently caressing a fluffy white rabbit with a careful, nurturing touch. The director, with a neatly trimmed beard, looks intently at the rabbit, showing a softer side amidst the industrial backdrop of the set. As the scene progresses, the director continues to pet the rabbit affectionately, the camera capturing every tender gesture in high definition, highlighting the contrast between the tough world of filmmaking and the director's gentle interaction with the small, vulnerable creature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2975
|
videos/HRA_part2/2975.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 engineer wearing a NASA jumpsuit walks alongside a curious, friendly bear in a space helmet, both exploring a futuristic space station designed for tourism. The station, filled with advanced technology and panoramic views of the cosmos, offers a unique blend of engineering marvels and extraterrestrial wildlife encounters. The engineer, equipped with tools and a tablet, ensures the safety and functionality of the space station's systems, while the bear, adorned with a custom spacesuit and helmet, roams freely, interacting with visitors and adding an unexpected touch of whimsy to the space tourism experience. Together, they navigate the corridors and observation decks, creating an unforgettable scene of human and animal adaptation to life beyond Earth's atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's face in the video is distorted, hands and feet are deformed, the bear's head and limbs are abnormally generated, and the video as a whole does not conform to reality."
}
] |
seed42_2827
|
videos/HRA_part0/2827.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 industrious engineer, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1888
|
videos/HRA_part2/1888.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 vast, empty warehouse with high ceilings and large, open spaces, four young children, two boys and two girls, are gleefully jumping and laughing as they play a game of tag. The boys wear matching blue striped shirts and khaki pants, while the girls are dressed in pink floral dresses and white leggings. The warehouse's concrete floors and metal beams provide an industrial yet spacious setting for their energetic play. The children's joyous expressions and animated movements capture the essence of carefree childhood fun in an unconventional environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1549
|
videos/HRA_part1/1549.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 man named Jay, wearing a black t-shirt, blue jeans, and a silver wristwatch, stands against a plain gray backdrop. Initially, he looks intently at the camera, then breaks into a warm smile. Moments later, he playfully winks, showcasing his friendly demeanor. Finally, Jay is seen laughing wholeheartedly, his joyous spirit captured in high definition, all the while maintaining the simple outfit of a black top, blue denim, and a gleaming watch against the unadorned setting.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video moves unsmoothly and his actions are uncoordinated."
}
] |
seed44_1875
|
videos/HRA_part1/1875.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 farmer, dressed in a white shirt and denim overalls, stands on the edge of a serene pond, watching attentively as a rabbit swims gracefully through the clear water. The rabbit, defying expectations, moves with surprising agility, its brown fur glistening beneath the golden afternoon sunlight. The farmer, hat in hand, looks on with a mix of surprise and delight, the rolling green fields and distant barn providing a quintessential rural backdrop to this unexpected scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_158
|
videos/HRA_part2/158.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 cozy, well-lit room, two young children sit attentively at a wooden table, each engaged in the meticulous task of hemming pants. One child, a boy with short brown hair wearing a blue t-shirt and jeans, carefully measures the fabric with a silver ruler, ensuring precise folds. Beside him, a girl with long pigtails, dressed in a yellow dress, threads a needle with focused determination, her tongue slightly poking out in concentration. Both use matching white sewing machines placed on either side of the table, their small feet reaching down to operate the pedals. The atmosphere is one of diligent learning, with the children's expressions showing a mix of seriousness and occasional smiles, highlighting their engagement in this practical skill.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2000
|
videos/HRA_part0/2000.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 distinguished man with salt-and-pepper hair and a neatly trimmed beard speaks passionately, gesturing with his hands to emphasize his points. Dressed in a navy suit with a crisp white shirt and a red tie, he commands attention against a backdrop of city lights and a blurred crowd. His animated expressions and dynamic body language convey the intensity of his conversation, drawing the viewer into the engaging dialogue taking place in this urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed46_1369
|
videos/HRA_part2/1369.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 great blue heron stands statuesque on a single leg, its piercing yellow eyes scanning the still waters of a pond fringed with lush green reeds and grasses, set against a serene blue sky. Moments later, it takes flight, wings outstretched against the clear blue sky, revealing their dark trailing edges. It then lands gracefully, standing tall on both legs, alert and watchful, its striking yellow eyes fixed ahead, the water calm and inviting. Lastly, it stretches its neck forward, beak pointed down, ready to strike, the serene surroundings of greenery and clear blue sky providing a tranquil backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1679
|
videos/HRA_part0/1679.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 the dim light of a Martian sunset, casting an eerie orange glow, a small, brown mouse sits atop a large fire helmet, placed on the red, rocky surface of Mars. Nearby, a firefighter, dressed in a full suit and helmet, wipes his brow with a gloved hand, appearing weary yet determined. The vast, desolate landscape stretches out behind him, dotted with the remnants of a recently extinguished extraterrestrial fire, as the distant horizon is bathed in the fading embers of the alien sun.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's movements in the video are not smooth, and the mouse's actions are also not fluid."
}
] |
seed46_1606
|
videos/HRA_part2/1606.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 high-tech facility with glowing blue accents, a muscular firefighter, wearing a full-body protective suit and helmet, stands against a backdrop of advanced machinery. He holds an antimatter containment device, a sleek silver sphere with intricate detailing, which emits a faint blue glow, signifying its active state. The setting shifts subtly to reveal the firefighter engaging in a lively dance, maintaining a firm grip on the containment device, now resting on his hip. The dance moves fluidly from a standing position into a crouched stance, with the firefighter's hands moving dynamically, all while keeping the device secure. Throughout the sequence, the futuristic setting, characterized by clean lines and blue accents, remains visible, adding a dramatic touch to the dancing firefighter's performance.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves of the character in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed46_2248
|
videos/HRA_part2/2248.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 urban park, a worker dressed in a green shirt and beige pants tends to the lush grass, unaware that a vibrant fox is watching from behind a tree. The fox, with its fiery red fur and piercing eyes, crouches low, ready to spring into action. Suddenly, it leaps into the air, jumping over a wooden bench in a graceful arc, capturing the essence of playfulness and freedom in the heart of the city. The worker, noticing the commotion, turns to see the fox mid-jump, a moment of surprise and delight shared between the two, set against a backdrop of tall buildings and green foliage.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3012
|
videos/HRA_part1/3012.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 costumed astronaut chicken, clad in a white spacesuit adorned with American flags and a NASA logo, leaps high into the air on the moon's surface, against a backdrop of a dark, starry sky and the distant Earth. The chicken's joyful jump is captured in mid-air, conveying a sense of weightlessness and adventure. The scene is reminiscent of the historic moon landing, with the chicken's playful leap adding a whimsical touch to the iconic moment. The astronaut chicken's suit includes a transparent helmet, revealing its beady eyes and beak, as it bounces on the lunar surface, encapsulating the spirit of exploration and fun.]"
},
{
"from": "gpt",
"value": "Bad. The chicken's jumping action in the video is not smooth."
}
] |
seed44_3000
|
videos/HRA_part1/3000.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 a neatly trimmed beard, sits pensively on a vintage brown leather couch, wearing a blue checked shirt, dark pants, and brown shoes. Suddenly, he holds his chest and coughs intensely, his eyes squeezed shut, indicating discomfort. The scene is set in a warmly lit room with wooden walls, showcasing a rustic environment. As the coughing fit subsides, he looks concerned, placing his hand back on his chest, suggesting a moment of reflection on his health, all while maintaining the same attire and setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1291
|
videos/HRA_part2/1291.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 police officer, clad in a dark uniform with a badge, is seen swimming in a large, outdoor pool with a rhinoceros nearby. The setting is a spacious enclosure with lush greenery, reminiscent of a wildlife sanctuary. The officer, wearing sunglasses and a cap, is shown diving into the water, while the rhinoceros, sporting a police-themed saddle, looks on from the edge of the pool. In another scene, the officer is playfully splashing water with the rhinoceros, both enjoying a moment of leisure under the clear blue sky. The final shot captures the officer and the rhinoceros exiting the pool together, the officer patting the rhino affectionately, highlighting an unusual yet heartwarming bond between law enforcement and wildlife.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2553
|
videos/HRA_part1/2553.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 large, formidable goose with striking orange beak and feet stands majestically on a grassy bank, its gray and white feathers ruffled by a gentle breeze. It stretches its neck upwards, revealing its full profile against the backdrop of a serene lake, dotted with lily pads and framed by lush greenery. The bird then lowers its head to preen its feathers, maintaining its composure as it interacts with its tranquil environment. Finally, it takes a step forward, ready to wade into the water, its bold presence commanding attention in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The goose's claws and head are twisted in the video."
}
] |
seed42_1141
|
videos/HRA_part0/1141.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 middle-aged teacher, wearing a blue shirt and khaki pants, stands in the center of a large, old theater, animatedly teaching a lesson about running. The stage is set with props from various plays, adding a touch of theatricality. Suddenly, a dingo, a wild dog native to Australia, runs onto the stage, interrupting the class. The teacher, unperturbed, incorporates the unexpected guest into the lesson, demonstrating running techniques while the dingo playfully bounds around, all under the grand chandelier of the theater.]"
},
{
"from": "gpt",
"value": "Bad. The person's movements are not continuous, there are sudden changes."
}
] |
seed42_1913
|
videos/HRA_part0/1913.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 visionary writer sits at a contemporary desk, crafting stories about space exploration, surrounded by swimming gear and a large aquarium filled with exotic fish. The room is illuminated by a floor lamp with a large shade, casting a warm glow on the writer's face. They wear a black shirt and a necklace, their focus intense as they type on a laptop. Behind them, a window reveals a starry night sky, evoking a sense of wonder and adventure into the cosmos. Beside the desk, a modern painting in shades of blue and green adds a splash of color, reminiscent of water, perhaps reflecting the writer's love for swimming. The aquarium, visible in the background, features colorful fish swimming among plants and rocks, adding a dynamic element to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
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 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 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": "Normal. The firefighter's hands and feet are deformed in the video."
}
] |
seed44_2006
|
videos/HRA_part1/2006.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: [An attractive male actor, reminiscent of Chris Evans, is seen in a minimalist living room with white walls and wooden floors, assembling a piece of furniture. He wears a fitted gray T-shirt, dark jeans, and a watch, his short hair perfectly styled. The room is sparsely decorated, featuring a potted plant and a small painting on the wall. The furniture he's building is a sleek, modern design, and he uses a variety of tools, including a screwdriver and an Allen wrench, demonstrating his handyman skills with ease and confidence.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1784
|
videos/HRA_part1/1784.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 charismatic male musician, clad in a black leather jacket, a graphic tee, and dark jeans, walks his energetic, medium-sized brown dog in an urban park. The artist wears a baseball cap and sports a beard, presenting a relaxed and down-to-earth demeanor. The dog, on a leash, enthusiastically explores the grassy area, its tail wagging. In another scene, the musician, now with his acoustic guitar slung over his back, continues his leisurely stroll, his dog trotting alongside him. The pair strolls past a stone building, adding to the laid-back vibe of the day.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the person, the paws of the dog, and the wooden guitar in the video have generation issues."
}
] |
seed46_2910
|
videos/HRA_part2/2910.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 navy uniform with a yellow reflective vest, ascends a rocky terrain during the day, exhibiting determination and resilience. His tactical gear, including a backpack and a helmet, is visible as he scales the rugged landscape. The camera captures his focused face, set on completing the climb, and the lush greenery surrounding the rocky area, providing a stark contrast to his mission-driven ascent. Despite the challenging environment, the officer's resolve is evident, making for a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The facial features of the police officer in the video are generated blurry, the fingers are deformed, and the legs are twisted."
}
] |
seed46_2683
|
videos/HRA_part2/2683.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 woman sits in a dimly lit room, her face softly illuminated by a single light source. She is wearing a simple white shirt, her brown hair falling gently over her shoulders. The camera focuses on her chest, rising and falling slowly as she takes deep, deliberate breaths. Each inhale is visible, drawing attention to the tranquility of the moment. Her eyes are closed, her lips slightly parted, as she finds peace in the rhythm of her breathing. The quiet atmosphere is punctuated only by the sound of her breath, creating a serene and intimate portrait of mindfulness.]"
},
{
"from": "gpt",
"value": "Bad. The woman's chin in the video has generation issues, and there is too little of the eye area generated to tell if she is blinking."
}
] |
seed42_2938
|
videos/HRA_part0/2938.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, middle-aged nurse with blonde hair tied in a bun, wearing a blue scrub top and black pants, is seen in a small, cluttered kitchen. She's meticulously loading a white ceramic plate into the bottom rack of a stainless steel dishwasher, demonstrating her domestic skills. The kitchen is filled with natural light, casting a warm glow over the room, and the nurse's attention to detail is evident as she carefully arranges the dishes. Despite the busy environment, with pots and pans scattered about, she maintains a sense of calm and order as she performs this household task.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's fingers in the video are deformed."
}
] |
seed46_3042
|
videos/HRA_part2/3042.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 gentleman with salt-and-pepper hair sits in a dimly lit room, wearing a gray blazer and a white shirt with the top button undone. He leans back in a brown leather armchair, holding a book in his hands. The camera captures him from the side, highlighting his profile as he reads intently. Beside him, a wooden table holds a glass of red wine, a vintage lighter, and a half-smoked cigar resting in an ashtray. The atmosphere is cozy and intimate, with the warm glow of a nearby lamp illuminating the scene. Behind the chair, a large bookshelf filled with books adds to the scholarly ambiance. The man's eyes are fixed on the pages, his lips slightly parted, indicating deep concentration as he delves into the story. The setting conveys a sense of leisurely intellectual pursuit, with the elements of wine, cigar, and reading material suggesting a refined evening routine.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated, and the book in his hand is distorted."
}
] |
seed46_1991
|
videos/HRA_part2/1991.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 heart of a lush, verdant savanna under a vast, cloud-dappled sky, a graceful antelope leaps and bounds with an almost choreographed elegance, its movements fluid and dynamic against the backdrop of swaying grasses and distant acacia silhouettes. Its coat gleams golden in the warm sunlight, and its horns curve beautifully as it executes a series of leaps that seem to defy gravity, embodying the spirit of dance in the wild. Nearby, a small herd of antelope watches, their postures attentive and curious, creating a scene that is both captivating and enchantingly serene.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's body, head, and legs are twisted in the video."
}
] |
seed46_2274
|
videos/HRA_part2/2274.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, Mars-like landscape painted in shades of orange and red, a woman wearing a futuristic silver suit gently caresses a majestic bison, while a second bison stands nearby. Behind them, a man clad in a matching silver suit rides a robust, armored horse, creating a striking contrast against the barren, rocky terrain and the distant, hazy horizon. The woman's tender touch on the bison's fur and the man's confident posture on the horse convey a sense of harmony and adventure in this otherworldly setting.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the woman touching the buffalo, the action is basically normal but there is some lack of coordination."
}
] |
seed46_312
|
videos/HRA_part2/312.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 virtual reality environment, a stunningly realistic cheetah lies calmly on a holographic savanna, its sleek golden body adorned with black spots. A person, clad in a full-body VR suit, gently caresses the virtual cheetah's head and back, their movements tracked in detail within the immersive space. The cheetah responds with relaxed body language, indicating comfort and trust, as the human participant experiences the sensation of touching the wild animal through advanced haptic feedback technology. The scene is set against a vast, computer-generated landscape, complete with distant acacia trees and a vivid blue sky, creating an almost tangible illusion of being present in the African wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The person wearing the full-body VR suit mentioned in the caption does not appear in the video."
}
] |
seed44_1573
|
videos/HRA_part1/1573.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 rugged firefighter, clad in full gear and a helmet, digs vigorously with a shovel in hand, surrounded by charred debris and ash under a smoke-filled sky. The scene is set in the aftermath of a fierce fire, with the firefighter's muscular arm raised high, illustrating the strenuous nature of the task. His face is obscured by a breathing apparatus, emphasizing the hazardous conditions. Nearby, another firefighter, also in full protective clothing, aids in the excavation, both working tirelessly amidst the ruins of a burned-out structure, their actions highlighting the determination and bravery required in their line of duty.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, and the hand is distorted."
}
] |
seed44_1664
|
videos/HRA_part1/1664.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 market filled with vibrant stalls and the sounds of commerce, a young male cashier, dressed in a blue button-down shirt and khaki pants, walks purposefully across the busy floor. He carries a green plastic bag, possibly containing produce or goods, adding a touch of realism to the scene. The market is alive with activity, from the colorful array of fruits and vegetables on display to the lively chatter of customers and vendors. The cashier navigates this energetic environment, his journey through the market captured in a series of dynamic shots that convey the lively atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2486
|
videos/HRA_part2/2486.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 with short brown hair, wearing a gray shirt, sits at a desk in a modern office, illuminated by overhead lights. He holds a silver pen in his right hand, scribbling intently on a sheet of graph paper. His glasses catch the light as he leans over the paper, which is filled with complex diagrams and equations. Behind him, a large window displays a view of a city skyline, reflecting the time of day as late afternoon, with the sun casting a warm glow into the room. On the desk, next to the engineer's elbow, rests a half-empty coffee mug, a reminder of his dedication to his work.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1124
|
videos/HRA_part2/1124.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 middle-aged man, donning a dark green shirt and khaki pants, checks smoke detectors in a dimly lit office hallway. He is seen standing on a red ladder, holding a tool, with his focus entirely on the detector. Moments later, he is shown descending the ladder, with a slight smile and a nod, indicating his satisfaction with the detector's condition. He carries a black tool bag and wears a name badge, adding to his professional appearance. The video ends with him walking down the hallway, checking another smoke detector, maintaining safety in the workplace.]"
},
{
"from": "gpt",
"value": "Bad. The walking movements are uncoordinated. "
}
] |
seed46_2898
|
videos/HRA_part2/2898.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 bull moose, distinguished by its dark brown fur and impressive rack of antlers, strides purposefully through a shallow, crystal-clear river. The water, teeming with lush vegetation, reflects the vibrant greenery of the surrounding forest, creating a serene and picturesque scene. The moose, with its shaggy coat and large, expressive eyes, moves with a graceful determination, its massive body rippling with each step it takes across the riverbed. The dense forest looms in the background, casting dappled shadows onto the water's surface, adding depth and texture to the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2402
|
videos/HRA_part2/2402.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 costumed firefighter, complete with helmet and yellow firefighting jacket, races through a lush, green forest, closely pursued by an animated beaver wearing a miniature firefighter uniform, also with a helmet and a small red cape. The firefighter leaps over a fallen log, demonstrating agility, while the beaver follows suit, mimicking every action with playful determination. Both characters run with purpose, the firefighter leading the charge and the beaver keeping pace, highlighting a fun, animated adventure set against the vibrant backdrop of a dense woodland.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's movements are abruptly deformed, with the legs, body, and face all distorted, making it hard to recognize the jumping action. The beaver also becomes distorted. One of the two beavers suddenly disappears."
}
] |
seed46_1871
|
videos/HRA_part2/1871.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 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, 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 actor's clothes in the video are not khaki pants."
}
] |
seed44_2751
|
videos/HRA_part1/2751.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 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 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 cleaner's sweeping movements in the video are not very continuous and smooth, there is a lack of coordination."
}
] |
seed44_2543
|
videos/HRA_part1/2543.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 captivating underwater scene, a vibrant orange pipefish, resembling a seahorse, gracefully hovers near a bed of lush green seagrass, its elongated body and small fins elegantly propelling it through the crystal-clear waters. Its distinctive snout extends forward as it explores its environment, surrounded by the swaying blades of seagrass that provide a stunning contrast to its unique form. The sunlight filters through the water, casting dappled light on the scene, highlighting the intricate details of the pipefish's skin and the delicate movements of its fins as it navigates its aquatic habitat.]"
},
{
"from": "gpt",
"value": "Bad. The video has issues with the generation of Hai Long's fish fins and face."
}
] |
seed44_1668
|
videos/HRA_part1/1668.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 sweeping natural landscape, a large bison is rolling on the ground, seemingly wiping itself in the dirt, surrounded by tall grass and distant mountains under a clear blue sky. The bison, with its shaggy brown fur, is seen from various angles, including a close-up of its face as it looks up, showing its rugged features and expressive eyes. Another shot captures the bison from above, highlighting its massive size and the texture of its coat against the sandy ground. Lastly, the bison is shown standing, shaking off the dust, its powerful body and majestic presence commanding respect in its wild habitat.]"
},
{
"from": "gpt",
"value": "Bad. No scene of the buffalo rolling on the ground was generated."
}
] |
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 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, 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": "Good. Basically correct."
}
] |
seed44_1675
|
videos/HRA_part1/1675.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, spiky European hedgehog leaps into the air, defying expectations as it jumps over a miniature hurdle, showcasing its unexpected agility. The hedgehog, with its typical brown and white quills, lands softly on a lush green surface, demonstrating its natural ability to navigate obstacles. The scene is set against a simple, uncluttered outdoor backdrop, allowing the hedgehog's unique action to be the focal point of the video.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_1663
|
videos/HRA_part2/1663.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 rugged firefighter, clad in full gear and a yellow safety vest, kneels beside an urban street drain, diligently unclogging it with a specialized tool. His focused gaze and steady hands reveal his determination. In another scene, he stands with legs apart, continuing the task with a long, metal drain snake, his yellow fire department jacket and sturdy black boots standing out against the gray cityscape. His efforts are highlighted by the contrast between his vibrant attire and the dull surroundings, emphasizing his commitment to public service beyond firefighting. Throughout, the firefighter's steadfast posture and unwavering concentration underscore his dedication to maintaining community safety, even in mundane tasks.]"
},
{
"from": "gpt",
"value": "Bad. The hands, face, and legs of the character in the video are distorted."
}
] |
seed46_1930
|
videos/HRA_part2/1930.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 lush, green meadow under a partly cloudy sky, a small brown rabbit crawls through the tall grass, its movements slow and deliberate. The camera captures this scene in high definition, focusing on the rabbit's textured fur and the vibrant vegetation surrounding it. The atmosphere is peaceful and serene, with the gentle swaying of the grass and the soft sounds of nature providing a calming backdrop. The rabbit continues its crawl, seemingly undisturbed by the presence of the camera, offering viewers an intimate glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2509
|
videos/HRA_part2/2509.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 cheerful musician, wearing a gray shirt and blue jeans, is seen laughing heartily, holding a black electric guitar. The scene is set against a dark background with bright, colorful lights illuminating the musician from behind, adding a vibrant touch to the joyful moment. The musician's laughter is contagious, creating a warm and inviting atmosphere that captures the essence of pure happiness and the love for music.]"
},
{
"from": "gpt",
"value": "Normal. The musician's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2200
|
videos/HRA_part0/2200.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 octopus with vibrant, mottled skin displays an array of colors, from rich reds to deep purples, against a dark, rocky reef background. It extends several of its long, muscular arms outward, revealing intricate patterns and textures as it interacts with its environment. One arm curls around a piece of coral, showcasing the creature's dexterity and strength. Another arm reaches towards the camera, almost as if to touch, providing a captivating close-up view of its suckers and the mesmerizing play of light on its skin. The octopus then retreats slightly, enveloping itself partially within a crevice, demonstrating its natural camouflage abilities in the underwater world.]"
},
{
"from": "gpt",
"value": "Normal. The octopus's head and tentacles generation in the video has problems."
}
] |
seed46_1186
|
videos/HRA_part2/1186.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 magpie perches on a weathered wooden fence post, its distinctive black-and-white plumage gleaming under the soft sunlight. Against a backdrop of lush green foliage and clear blue skies, the bird's eyes sparkle with curiosity. It tilts its head to the side, seemingly observing its surroundings with interest. The vibrant colors of nature serve as a striking contrast to the magpie's striking feathers, highlighting its unique beauty in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2394
|
videos/HRA_part0/2394.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, anthropomorphic setting, a weasel, dressed in a white doctor's coat over a blue shirt and tie, crawls on its belly across a cluttered desk filled with medical books and instruments, its eyes intently focused on a miniature stethoscope just out of reach. The desk is awash in a warm, golden light, casting long shadows and highlighting the weasel's determination. Behind the desk, a large window frames a bustling city skyline at sunset, adding a sense of urgency and drama to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's head and paws in the video have generation issues."
}
] |
seed46_1596
|
videos/HRA_part2/1596.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 majestic stag strides purposefully across an ancient stone bridge, its antlers framing the scene like natural architecture against a backdrop of lush greenery and a misty morning sky. The deer's confident gait and the bridge's weathered texture tell a story of time and resilience in nature. As it walks, the stag's hooves make soft sounds on the moss-covered stones, creating a harmonious melody echoing through the serene woodland setting. The bridge, arching gracefully over a tranquil stream, becomes a pathway connecting two verdant forests, with the deer serving as a symbol of grace and wildness moving between these spaces.]"
},
{
"from": "gpt",
"value": "Normal. The walking movements of the deer in the video are uncoordinated."
}
] |
seed42_1735
|
videos/HRA_part0/1735.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 classroom setting, a cartoon beaver, wearing a brown graduation cap and holding a yellow eraser, energetically wipes a green chalkboard clean, revealing a lesson about the water cycle. The beaver, now wearing a white shirt with a red tie and a brown vest, continues to erase enthusiastically, displaying a fun and engaging teaching style. Next, the beaver, still in its academic attire, uses the eraser to remove the last bit of chalk from the board, ensuring the surface is completely clear. Finally, the animated beaver teacher, dressed in its scholarly outfit, stands proudly beside the now-blank chalkboard, ready for the next lesson.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1586
|
videos/HRA_part0/1586.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 space station habitat, illuminated by soft, ambient lighting, a caring teacher, wearing a navy blue jumpsuit with silver accents, gently caresses the head of a young student seated at a desk. The student, dressed in a matching uniform, looks up with wide eyes, feeling comfort and support. Behind them, a large window reveals the stunning view of Earth, while various educational tools and floating objects fill the zero-gravity environment, creating an immersive learning atmosphere. The teacher's compassionate touch and the unique setting emphasize the nurturing bond between educator and pupil in this extraordinary space classroom.]"
},
{
"from": "gpt",
"value": "Normal. The hands appear deformed. The woman's face is also distorted."
}
] |
seed44_145
|
videos/HRA_part1/145.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 dedicated female teacher, wearing a white shirt and brown overalls, is engaged in an outdoor activity, enthusiastically digging into a sandpit with a small green shovel. Children stand nearby, observing her actions with curiosity, their faces alight with anticipation, as they wear matching yellow shirts. The teacher's energetic movements and the children's attentive expressions convey a sense of learning and discovery in a playful, educational setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3118
|
videos/HRA_part0/3118.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 majestic red-tailed hawk soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rugged terrain below. It circles effortlessly, riding the thermals with grace, its sharp eyes scanning the ground for prey. The hawk's brown and white striped feathers shimmer in the sunlight, and its piercing yellow eyes and sharp curved beak are sharply defined. In the background, rolling hills and distant mountains provide a stunning natural landscape, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1647
|
videos/HRA_part0/1647.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 vast, open ocean landscape fills the screen, with crystal clear water revealing a sandy bottom far below. Sunlight filters through the surface, casting dappled light on the scene. Suddenly, a magnificent manta ray enters the frame, its massive wings spanning wide as it glides effortlessly through the water. The creature is a stunning sight, its dark top and white underbelly contrasting beautifully against the blue surroundings. It performs an elegant somersault, showcasing its agility and grace, before continuing on its serene journey across the vast underwater expanse.]"
},
{
"from": "gpt",
"value": "Normal. The manta ray swims basically normally in the video, with slight disharmony."
}
] |
seed46_3220
|
videos/HRA_part2/3220.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 surprising juxtaposition, a janitor, clad in a yellow high-visibility vest and dark pants, walks alongside an antelope in a vast, grassy landscape. The two figures move in unison across the screen, the janitor pushing a red cleaning cart, while the antelope, with its distinctive horns and russet fur, trots gracefully beside him. The scene is bathed in golden sunlight, casting long shadows from both the janitor and the antelope as they traverse the serene environment together. Behind them, a row of tall, green trees provides a striking contrast to the open field, further highlighting the unusual companionship between the janitor and the wild animal.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's head generation in the video has problems, and there are three front legs in the middle frames; the video does not realistically represent reality."
}
] |
seed42_1599
|
videos/HRA_part0/1599.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 softly lit room painted a calming shade of blue, two young children, a boy and a girl, both wearing pajamas, sit on a large bed with white sheets. The girl, with her blonde hair in pigtails and clad in pink pajamas, cries with her mouth wide open, tears streaming down her cheeks, her hands covering her face. Beside her, the boy, wearing blue pajamas, leans forward with concern, placing a comforting hand on her back, his brown hair tousled and his eyes filled with empathy, offering a silent support amidst their shared distress.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and face are distorted in the video."
}
] |
seed46_2884
|
videos/HRA_part2/2884.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 farmer, clad in a red flannel shirt, blue jeans, brown work boots, and a wide-brimmed straw hat, rakes a large pile of autumn leaves in the midst of a vast, open farmland. The scene is set during the golden hour, with the sun casting a warm glow across the landscape. The farmer pauses to wipe sweat from his brow, revealing a face lined with the wisdom of years spent working the land. He continues his task with a sense of purpose and pride, the leaves forming a vibrant mosaic of reds, oranges, and yellows around him. The video captures the essence of hard work and the beauty of seasonal change in the rural countryside.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's facial features and hands are distorted in the video, and the farmer's hand and the tool in it suddenly disappear or reappear in the middle frames."
}
] |
seed46_1827
|
videos/HRA_part2/1827.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 woman, adorned in a stylish yellow dress, gracefully caresses the powdery sand of an idyllic beach resort as the turquoise sea gently laps at the shore. Her eyes closed, she savors the serene moment, feeling the warmth of the sand between her toes. The peaceful atmosphere is punctuated by the rhythmic sounds of the ocean, the soft rustle of palm fronds, and the distant calls of seagulls, all contributing to a scene of blissful tranquility. The vibrant colors of her attire contrast beautifully with the natural hues of the beach, creating a captivating visual harmony.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1690
|
videos/HRA_part2/1690.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 sci-fi scene, a weasel cosmonaut, clad in a full spacesuit with a helmet adorned with ears, performs meticulous maintenance aboard a spaceship. The weasel is seen wiping the control panels with a cloth, ensuring every surface is clean. The spaceship, with its sleek silver body and blue lights, is docked at a space station, which can be seen through the large, circular window behind the weasel. The space station is a complex structure with multiple levels and tubes, illuminated by various lights. The weasel continues its diligent cleaning tasks, moving methodically from panel to panel, while the spaceship remains securely docked at the space station.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's movements in the video are not smooth."
}
] |
seed44_1741
|
videos/HRA_part1/1741.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 middle-aged male janitor, dressed in a gray sweater over a white collared shirt and khaki pants, pauses from his cleaning duties to take deep breaths, standing in a brightly lit, modern office hallway. He holds a mop in his right hand and rests his left hand on a mop bucket, while his eyes are closed, focusing on his breathing. The clean, minimalist surroundings emphasize the tranquility of the moment as he takes a moment to collect himself, his facial expression one of peaceful concentration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2769
|
videos/HRA_part1/2769.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 distinguished lawyer, dressed in a charcoal gray suit, white shirt, and red tie, sits at a large wooden desk in a traditional law office setting, which includes a bookcase filled with legal books and documents. The room is illuminated by natural light from a window behind the desk, casting a warm glow over the space. The lawyer, with neatly combed brown hair and glasses, holds a pen in his right hand and looks down at a document on the desk. Suddenly, he brings his left hand to his mouth to cover a cough, his eyes closing briefly as he experiences discomfort. The scene captures the professional environment and the unexpected moment of vulnerability.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's action of looking down at the documents on the table is basically normal, with slight disharmony."
}
] |
seed42_3008
|
videos/HRA_part0/3008.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, wearing a brown leather jacket and blue jeans, is seen energetically dancing in a surreal scene set in the middle of a vast prairie. Surrounding him are several large bison, who calmly observe the director's enthusiastic dance moves under the open sky. The director, displaying an unexpected sense of whimsy, continues to dance amidst the majestic animals, creating a unique juxtaposition between human creativity and the untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, hands, and the buffalo's legs are also twisted."
}
] |
seed44_3028
|
videos/HRA_part1/3028.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, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1184
|
videos/HRA_part2/1184.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 human-sized hare, dressed in a worker's outfit complete with a yellow helmet, blue overalls, and a red shirt, dances gleefully in a lush green meadow. The hare performs an energetic jig, its oversized feet stomping playfully on the grass, while its long ears sway in time with the music. The background features a vibrant blue sky with fluffy white clouds, adding to the surreal yet delightful atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2600
|
videos/HRA_part2/2600.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 blend of scenes, a majestic African lion strides powerfully across a vast, barren asteroid, its golden coat contrasting starkly against the monochrome landscape pockmarked with craters. The lion, undeterred by the alien environment, explores the rocky terrain as if it were a savannah, with distant stars and a nebula providing a cosmic backdrop. Nearby, a futuristic mining facility operates diligently, extracting precious resources from the asteroid's surface, emphasizing the juxtaposition of nature and technology in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The lion's head and paws in the video have generation issues; the lion's paws disappear and reappear suddenly in the middle frames."
}
] |
seed46_1524
|
videos/HRA_part2/1524.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 man, clad in a gray sweatshirt and jeans, stands on a ladder, diligently cleaning out the rain gutters of a suburban home on a cloudy day. His weathered hands grip a trowel, removing debris from the clogged gutter, while his sweatshirt and jeans are stained with dirt and leaves. The house's siding, painted a neutral beige, serves as a backdrop, with a well-manicured lawn and garden visible below. The man's focused expression and the tools of his task, including the ladder and trowel, emphasize the effort required for this routine home maintenance activity.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand appears deformed. The shovel in the hand disappears and reappears."
}
] |
seed42_1690
|
videos/HRA_part0/1690.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 sci-fi scene, a weasel cosmonaut, clad in a full spacesuit with a helmet adorned with ears, performs meticulous maintenance aboard a spaceship. The weasel is seen wiping the control panels with a cloth, ensuring every surface is clean. The spaceship, with its sleek silver body and blue lights, is docked at a space station, which can be seen through the large, circular window behind the weasel. The space station is a complex structure with multiple levels and tubes, illuminated by various lights. The weasel continues its diligent cleaning tasks, moving methodically from panel to panel, while the spaceship remains securely docked at the space station.]"
},
{
"from": "gpt",
"value": "Bad. The weasel is not wearing a spacesuit."
}
] |
seed44_2359
|
videos/HRA_part1/2359.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 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 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 dancing in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_2527
|
videos/HRA_part2/2527.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 director wearing a dark jacket and jeans stands in a lush, green forest, holding a megaphone and gesturing with enthusiasm. A large moose, with its shaggy brown coat and majestic antlers, wanders into the frame, walking slowly through the underbrush. The director observes the moose, which continues its leisurely stroll among the tall trees, highlighting the unexpected encounter between human creativity and the beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1252
|
videos/HRA_part0/1252.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 city park during autumn, two diverse groups of people sit separately on long, wooden benches under tall, leafy trees with golden foliage. One group consists of four friends, two women and two men, engaged in lively conversation, with one woman laughing heartily. They wear casual fall attire, including jackets, scarves, and hats. The other group features three elderly individuals, two women and a man, sitting quietly and observing the surroundings. They are dressed warmly in coats, sweaters, and gloves, with the women wearing headscarves. The scene captures the essence of human connection and the peaceful coexistence of different generations in a beautiful outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.