video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2064
|
videos/HRA_part1/2064.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 group of people are gathered at a pristine lake nestled in the heart of a lush, green forest, engaging in various activities. Some are wiping their feet on a large, sandy beach, preparing to enter the clear, inviting waters. Others are seated on the shore, enjoying the serene surroundings as they wipe sand from their hands and feet. The scene is peaceful, with the sound of water lapping against the shore and birds singing in the trees overhead. The lake, framed by towering pines and dotted with small boats, provides a stunning backdrop for this tranquil moment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2792
|
videos/HRA_part2/2792.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, two young boys, one in a red bathing suit and the other in a green one, splash playfully in a backyard pool on a sunny day. Suddenly, the focus is on the boy in red, who is seen diving into the clear water. A small, friendly rat, perhaps a pet, watches from the side of the pool, its tiny body perched on the edge as it observes the boys' aquatic fun. The scene exudes joy and innocence, with the rat's presence adding a touch of unexpected charm to the children's summertime activities.]"
},
{
"from": "gpt",
"value": "Bad. The little boy's head, arms, and hands are twisted in the video."
}
] |
seed44_151
|
videos/HRA_part1/151.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 hummingbird, iridescent green with a vibrant red throat, hovers over a cluster of pink flowers, its wings a blur of motion against the serene blue sky. It extends its slender beak into a flower, feeding on nectar, while perched on a thin branch. The bird then takes flight, moving gracefully from one flower to another, showcasing its agility against a backdrop of lush green foliage and clear, cloudless sky. Throughout, the hummingbird remains the focal point, its rapid wing beats and delicate features highlighted against the peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The bird's wings and claws in the video have issues."
}
] |
seed44_2968
|
videos/HRA_part1/2968.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 grouse, distinguished by its brown plumage speckled with white and black, struts proudly across a lush, green meadow under a bright, sunlit sky. The bird's robust body, complete with a red wattle above its beak, is prominently displayed as it moves with regal confidence. Moments later, it's seen in profile, its intricate feather patterns and textured wings highlighted against the vibrant vegetation. Then, it turns its head, revealing piercing eyes and a sharp beak, set against the backdrop of a dense forest and clear blue sky. Lastly, the grouse is captured mid-stride, its legs moving swiftly, demonstrating the strength and agility of this woodland creature, all set against a serene natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2726
|
videos/HRA_part2/2726.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 whole, fresh cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2873
|
videos/HRA_part2/2873.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 yet futuristic scene, a giant panda, wearing a spacesuit and helmet adorned with antennas, sits against a backdrop of stars and galaxies, symbolizing deep space communication. The panda is seen wiping its paw across the visor of its helmet, perhaps to clear condensation, while floating in zero gravity, surrounded by the vastness of space. This unique juxtaposition of elements - the panda representing Earthly innocence, the spacesuit and helmet signifying human exploration, and the cosmic background evoking a sense of wonder - creates a captivating and surreal visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2754
|
videos/HRA_part0/2754.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 sits at a desk, bathed in the glow of a computer screen in a dimly lit room, his fingers poised above a black keyboard. He blinks slowly, revealing tired eyes beneath furrowed brows, hinting at the depth of concentration required for his writing task. Dressed in a white shirt with rolled-up sleeves, he exudes determination and focus, his gaze fixed on the screen as if willing the words to appear. The quiet intensity of the scene is punctuated by the soft clack of keys as he types, emphasizing the solitary nature of the creative process.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video types basically normally, but there is slight movement disharmony."
}
] |
seed46_3171
|
videos/HRA_part2/3171.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 woman sits serenely in a sunlit room, her eyes closed, focusing deeply on her breath. She wears a simple white blouse, the fabric gently moving with each inhale and exhale, highlighting the tranquility of the moment. Sunbeams filter through sheer curtains, casting a warm glow on her face, emphasizing her peaceful expression. Her hands rest calmly in her lap, fingers slightly curled, embodying a state of deep relaxation and mindfulness. The room is sparsely decorated, with a potted plant in the corner adding a touch of nature to the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1765
|
videos/HRA_part0/1765.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 navy uniform and sporting sunglasses, stands with his arms crossed, observing the scene at a busy dock. Suddenly, a majestic deer emerges from the background, filled with lush greenery, and leaps gracefully over a small obstacle, drawing the attention of the officer and dock workers alike. The officer watches intently as the deer bounds across the wooden planks, its movements fluid and effortless, before disappearing into the foliage beyond the docks. Throughout the scene, the officer remains poised and watchful, his presence a testament to the unexpected encounters that can occur even in the midst of urban landscapes.]"
},
{
"from": "gpt",
"value": "Bad. The video does not feature dock workers."
}
] |
seed44_2703
|
videos/HRA_part1/2703.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 zoological park setting, a young woman with dark hair pulled back into a ponytail works at a ticket booth decorated with colorful animal illustrations. She wears a green polo shirt with a name tag, signifying her role as a cashier. A small, friendly kinkajou rests on her shoulder, its fur blending with her brown hair. The animal playfully explores the area around her head as she smiles warmly, gently caressing it with her right hand, her nametag partially visible. This intimate interaction between the cashier and the kinkajou occurs within the vibrant, wildlife-themed environment of the zoo.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2746
|
videos/HRA_part0/2746.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 group of four energetic children, two boys and two girls, wearing colorful clothing including red, blue, and green shirts, jump high into the air in unison, against a backdrop of a cloudy sky and lush green grass. Their faces are filled with joy and excitement as they perform their synchronized leap. One boy, in a striped shirt, and one girl, in a pink dress, stand out among them, capturing the essence of youthful exuberance and carefree play in a natural outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The child's movements in the video are not smooth."
}
] |
seed46_1498
|
videos/HRA_part2/1498.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 single zebra, its distinctive black and white stripes gleaming under the golden savanna sun, is sprinting across a vast, grassy plain. The muscles in its legs are taut, demonstrating raw power and grace as it leaps over tufts of grass. The zebra's mane flutters in the wind, adding to the sense of motion and freedom. Dust kicks up from the zebra's hooves as it races, highlighting the speed and agility of this magnificent creature. Behind the zebra, the landscape stretches to a distant horizon, dotted with acacia trees and the faint outlines of other wildlife, providing context for the zebra's natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The zebra's running motion in the video is not coordinated."
}
] |
seed46_1117
|
videos/HRA_part2/1117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's paws in the video are generated abnormally, with one paw suddenly disappearing or appearing in the middle frames."
}
] |
seed42_2729
|
videos/HRA_part0/2729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman with curly brown hair and glasses laughs heartily, holding a green apple in her right hand. Dressed in a mustard yellow turtleneck sweater, she sits in front of a rustic wooden wall, her joyful demeanor brightening the cozy setting. Her laughter is contagious, spreading warmth and happiness in the intimate space, where natural light filters in from above, illuminating her face and emphasizing her genuine delight.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2287
|
videos/HRA_part1/2287.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, complete with helmet and heavy-duty gear, takes a break from the norm as he meticulously vacuums a cozy living room, adorned with a plush sofa, rustic wooden coffee table, and vibrant houseplants. The scene opens with a close-up of the vacuum cleaner, a stark contrast to the typical firefighting tools, before panning to reveal the dedicated firefighter, hose in hand, methodically cleaning the carpet. The camera then captures the firefighter's gloved hands guiding the vacuum, followed by a shot of him standing upright, holding the vacuum hose, and looking content amidst a tidy room, where a tidy bookshelf and comfortable armchair complete the domestic setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are twisted, and the object in hand is also distorted."
}
] |
seed44_3108
|
videos/HRA_part1/3108.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 compassionate, middle-aged male nurse with short, dark hair and glasses, wearing a pale blue scrub top and pants, carefully lifts a frail elderly patient from a hospital bed. The patient, a thin woman with short gray hair, is dressed in a hospital gown and has an oxygen tube in her nose. The nurse, with a strong yet tender grip, supports her under her arms and legs, ensuring her comfort and safety throughout the transfer. The scene takes place in a well-lit, modern hospital room, with medical equipment and a window visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. No oxygen tube, patient's leg, medical equipment, and window were generated."
}
] |
seed44_1494
|
videos/HRA_part1/1494.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 thoughtful young student, dressed in casual attire, gently caresses a chimpanzee seated beside her, both looking straight ahead. The scene is set against the backdrop of a busy industrial area, with large oil refineries visible in the background, emitting plumes of smoke into the hazy sky. Despite the industrial setting, the focus remains on the tender interaction between the student and the chimpanzee, conveying a sense of connection and empathy amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1597
|
videos/HRA_part2/1597.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 artist, wearing a yellow vest and gloves, stands at the edge of a vast landfill, the sprawling site of discarded waste stretching into the horizon under an overcast sky. The artist begins wiping the surface of a found object, revealing layers of rust and texture beneath the dirt, as trash and debris are scattered across the landfill in the background. Moments later, the artist continues wiping the object, now partially cleaned, revealing its industrial form against the bleak landscape of waste. Finally, the artist holds the fully wiped object, a reclaimed piece of art, against the stark backdrop of the landfill, the clouds hinting at a dramatic sky overhead.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1380
|
videos/HRA_part0/1380.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 ruggedly handsome actor, sporting a full beard, stands in a rural setting under an overcast sky, gently caressing a brown horse with white markings. He wears a gray shirt, blue jeans, and a brown belt, while the horse stands placidly in a grassy area dotted with small trees. The actor's affectionate interaction with the animal conveys a sense of peace and connection in the pastoral environment. The horse, with its mane and tail blowing slightly in the wind, is clearly comfortable with the actor, who continues to stroke its neck with tenderness and respect.]"
},
{
"from": "gpt",
"value": "Bad. The hand of the character in the video is generated incorrectly."
}
] |
seed42_168
|
videos/HRA_part0/168.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 single, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1351
|
videos/HRA_part1/1351.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 vibrant young woman, clad in a traditional nurse's uniform with a crisp white dress and cap, finds herself amidst vast, rolling farmlands under a clear blue sky. With a contagious smile, she begins to dance, her movements joyful and carefree, as if the open fields and distant hills are her stage. The sun casts a warm glow over the lush greenery, highlighting her figure as she twirls and leaps, embodying a harmonious blend of professionalism and uninhibited spirit in the rural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face in the video is not fully generated, there are missing limbs, and the body has deformities."
}
] |
seed44_1861
|
videos/HRA_part1/1861.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 handsome waiter, wearing a crisp white shirt, black vest, and tie, stands in a cozy, warmly-lit room with wooden floors. He gently caresses a fluffy, white cat sitting on a table covered with a red checkered cloth. Beside him, a glass bottle and a wine glass are visible. The cat, adorned with a pink ribbon, looks content as it receives affection from the attentive waiter, whose demeanor suggests a tender, caring personality.]"
},
{
"from": "gpt",
"value": "Normal. The server's action of petting the cat in the video is basically normal, with slight awkwardness."
}
] |
seed46_2004
|
videos/HRA_part2/2004.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 male cashier, wearing a red apron with a name tag and a lanyard around his neck, is seen pulling a metal cart filled with various groceries, including a large water jug, milk, bread, and other items typically found in a supermarket. The cart is so full that it requires effort to pull, emphasizing the weight and volume of the goods. This scene takes place in a busy supermarket aisle, with shelves stocked with products and other customers shopping in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1530
|
videos/HRA_part0/1530.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 parallel universe setting, a distinguished lawyer, wearing a dark suit, white shirt, and red tie, gently caresses a small, mysterious object in his hands, displaying a mix of curiosity and concern. His well-groomed appearance, complete with neatly combed hair and trimmed facial hair, contrasts with the perplexing artifact. Behind him, an office with modern furniture and technology reflects the alternate reality, adding to the intrigue of the scene. The interaction between the lawyer and the object, set against this backdrop, suggests a narrative filled with unexpected twists and turns.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1698
|
videos/HRA_part0/1698.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 nimble squirrel, brimming with energy, leaps from a moss-covered branch in a lush, vibrant forest. The scene is bathed in a soft, golden light filtering through the dense canopy above. The squirrel's movement is captured mid-jump, its body arched gracefully in the air, showcasing its agility and speed. Its bushy tail trails behind, adding to the dynamic feel of the action. The background is a tapestry of green foliage, dotted with various tree trunks, providing a rich, textured setting for the squirrel's acrobatics.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel in the video has incomplete facial and limb features, and its body is deformed, with incomplete claws."
}
] |
seed42_1268
|
videos/HRA_part0/1268.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 artist, clad in a brown jacket, beige pants, and carrying a sketchbook, walks through a surreal landscape inspired by a galactic nebula. The sky is a vivid swirl of cosmic colors - deep purples, electric blues, and fiery oranges, evoking the ethereal beauty of distant galaxies. Giant, floating rock formations, tinged with the same nebulous hues, tower above, while the ground beneath his feet is a shimmering, star-lit plane that reflects the celestial spectacle overhead. Despite the otherworldly setting, the artist strides purposefully, his form and clothing sharply detailed against the dreamlike backdrop, as if he's on a mission to capture the universe's wonders on paper.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2875
|
videos/HRA_part1/2875.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 captivating close-up, a tiny weasel, no larger than a human hand, emerges from a hole in a tree trunk set against the vast, snow-covered taiga. Its bright eyes curiously scan its surroundings. It then playfully interacts with the bark, as if caressing it, showcasing a rare display of animal behavior. The camera then captures the weasel's face in detail, highlighting its sharp features and lively demeanor. Lastly, it returns to the hole, pausing once more to look back, offering a final glimpse of its charming presence in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The weasel in the video has slightly uncoordinated movements."
}
] |
seed44_2421
|
videos/HRA_part1/2421.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 passionate female teacher, wearing a green sweater and brown hair, gently caresses a large leaf from a temperate rainforest tree during an educational field trip, her face expressing wonder and reverence for nature. Moments later, she holds a branch from a temperate rainforest, engagingly teaching her attentive students about the ecosystem. Then, she lovingly touches a moss-covered log, her actions conveying the importance of the rainforest environment, with the students looking on. Finally, she carefully strokes a fern frond, her demeanor highlighting the beauty and fragility of the temperate rainforest, all while surrounded by lush greenery and the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1507
|
videos/HRA_part0/1507.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 warm, sandy landscape under a clear blue sky, two young children, a boy and a girl, are gently caressing a calm camel. The boy, wearing a yellow shirt and brown shorts, strokes the camel's nose tenderly, while the girl, dressed in a pink dress and sandals, pets its lower leg with a smile. Both children are barefoot, standing on the soft sand, and the camel, adorned with traditional red and white saddle cloths, accepts their affection with a patient demeanor, creating a heartwarming scene of human-animal interaction in a desert environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are unsmooth."
}
] |
seed42_2196
|
videos/HRA_part0/2196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray cat with white paws is seen swimming in a clear blue pool, surrounded by green foliage. The cat's face shows visible effort as it paddles through the water with its front paws, displaying a unique and unexpected sight. The pool is framed by lush vegetation, creating a natural, serene environment for this unusual feline activity. The cat's determination and the vibrant greenery around the pool form a captivating contrast against the clear blue water.]"
},
{
"from": "gpt",
"value": "Normal. The cat's legs show deformities and mutations."
}
] |
seed42_2107
|
videos/HRA_part0/2107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 young student, wearing a casual gray t-shirt and blue jeans, is seen unloading a dishwasher in a modern kitchen with sleek, stainless steel appliances. The room is well-lit, casting a warm glow over the beige walls and brown cabinets. The student, sporting a short haircut and glasses, carefully removes dishes from the lower rack, placing them into a cabinet just above the dishwasher. With each item placed, the student's movements are deliberate and efficient, showing a routine familiarity with the task. The space is tidy and minimalistic, with a small dining table in the corner and a window letting in natural light, creating a homely atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The face, hands, arms, body, and items held in the hand of the person in the video are distorted."
}
] |
seed46_1462
|
videos/HRA_part2/1462.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 navy uniform and a light brown jacket, kneels in a modest living room to feed three domesticated cats. The room features a small, cluttered table, a beige couch, and a brown coffee table. The officer demonstrates kindness and care, pouring food into a green bowl as the cats eagerly surround him. Moments later, he gently pets one of the cats, showcasing a softer side of law enforcement, with the cats nestled around the bowl and the comforting interior of the home providing a backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The video generated an additional police officer wearing a light brown jacket."
}
] |
seed44_1749
|
videos/HRA_part1/1749.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, clad in a white lab coat over a black turtleneck and black pants, runs down a sleek, futuristic corridor of a space medical facility. The hallway is lined with glass panels that offer glimpses into advanced treatment rooms. The artist's stride is purposeful, their gaze determined, as they navigate the sterile environment illuminated by soft, ambient lighting. The facility's design incorporates curved walls and high-tech equipment, creating a blend of artistry and cutting-edge medicine in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2075
|
videos/HRA_part0/2075.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 prehistoric mammoth, covered in shaggy brown fur, walks through a barren, icy landscape with a heavy, deliberate gait. Its large tusks curve upward, and its trunk dangles loosely as it moves, its massive body leaving deep footprints in the snow. The scene is set against a bleak, overcast sky, emphasizing the creature's isolation and the harshness of its environment.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's walking in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed42_1581
|
videos/HRA_part0/1581.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 spacious indoor gymnasium illuminated by natural light from large windows, four children wearing colorful clothes engage in various acts of physical exertion. One child, dressed in a red shirt and black shorts, lifts a heavy barbell above their head with a look of intense concentration, demonstrating impressive strength. Another child, wearing a yellow top and blue leggings, performs a handstand against a mirrored wall, showing remarkable balance and poise. A third child, clad in green, does pull-ups on a bar, highlighting their upper body strength. Lastly, a child in a blue outfit leaps over a series of hurdles, capturing the essence of agility and athleticism. The gym's wooden floors and equipment provide a backdrop for these dynamic scenes of youthful energy and determination.]"
},
{
"from": "gpt",
"value": "Normal. A child did not appear in the video."
}
] |
seed42_2019
|
videos/HRA_part0/2019.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 straw hat, blue shirt, and khaki shorts, playfully swims in a clear, freshwater pond, holding a rabbit securely above the waterline. The farmer, now wearing a wide-brimmed hat, blue button-down shirt, and khaki shorts, gently cradles the rabbit, which sits comfortably in his hands, as they both float on the surface of the water. The idyllic scene is set against a backdrop of lush greenery and clear blue skies, capturing the essence of a peaceful rural life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 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 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. Basically correct."
}
] |
seed42_1984
|
videos/HRA_part0/1984.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station newsroom, illuminated by soft blue and orange lights, a realistic animated rabbit, wearing a small suit and tie, sits at a sleek desk. The room is filled with high-tech equipment and screens displaying galactic maps and data. The rabbit, with a serious expression, reads from a teleprompter, delivering the latest space news. Suddenly, the scene changes to the same rabbit running energetically on a treadmill, surrounded by floating zero-gravity objects, including a pen, a book, and a coffee cup, all set against the backdrop of the Earth through a large window.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the pen, book, and coffee cup mentioned in the caption."
}
] |
seed44_2731
|
videos/HRA_part1/2731.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 panda, garbed in a miniature spacesuit reminiscent of a classic NASA design from the Apollo era, embarks on a space diplomatic mission. It walks purposefully across a simulated lunar landscape, the textured surface and stark, airless environment highlighted by the distant Earth shining brightly in the background. This unique scene combines elements of science fiction, diplomacy, and conservation, featuring the panda as a symbol of peace and goodwill among the stars.]"
},
{
"from": "gpt",
"value": "Normal. The panda's face, paws, and legs are distorted in the video."
}
] |
seed42_1464
|
videos/HRA_part0/1464.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 vast, golden expanse of the temperate grasslands, a lone dingo, its sandy fur blending with the surroundings, stands alert. It shakes off water droplets, its ears pricked forward, before wiping its face with a paw in a natural grooming gesture. The dingo then continues its vigilant stance, scanning the horizon under a clear blue sky, the wind gently swaying the tall grass around it. This intimate moment captures the creature's resilience and adaptability in its native habitat, the rolling plains stretching to the horizon under a wide, cloudless sky.]"
},
{
"from": "gpt",
"value": "Bad. The legs of the wolf in the video are missing, and the face is incomplete."
}
] |
seed46_3089
|
videos/HRA_part2/3089.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 vibrant, colorful scene unfolds where a person dressed in a black cape and white shirt, reminiscent of a bat, engages in an energetic dance. Their movements are fluid and dynamic, capturing the essence of nocturnal flight against a dark, starry sky. As they spin and leap, the cape billows dramatically, creating dramatic silhouettes against the twinkling celestial backdrop. The dancer's face is painted in black and white, accentuating the bat-like features, adding to the theatricality of the performance. Throughout the dance, the focus remains on the captivating interplay between the dancer's bat-inspired costume and the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, hands, and body are distorted in the video."
}
] |
seed44_2811
|
videos/HRA_part1/2811.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, wearing a traditional conical hat and simple clothing, guides a strong water buffalo through a shallow, muddy waterway by holding onto its rope halter. The buffalo, with its large, curved horns and powerful body, crawls on its belly through the mire, demonstrating its strength and endurance. The farmer, with a focused look on his face, carefully navigates alongside the animal, highlighting the bond between man and beast in rural life. The scene takes place against the backdrop of lush green fields, emphasizing the agricultural setting.]"
},
{
"from": "gpt",
"value": "Normal. The buffalo's horns are generated multiple times, there are problems with the generation of the eyes, and the farmer's fingers are deformed."
}
] |
seed46_1713
|
videos/HRA_part2/1713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a dark jacket and casual attire, steps out of a modern building into the urban night, holding a black garbage bag. He approaches a large, industrial dumpster under the dim glow of streetlights, surrounded by concrete walls and parked cars. As he lifts the dumpster lid, his directorial composure contrasts with the mundane task of disposing waste. The scene captures the unexpected juxtaposition of creative leadership and everyday chores, highlighting the director's relatable human side amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The director's fingers are not fully generated, the facial features are missing, and there is a lack of an arm."
}
] |
seed44_1899
|
videos/HRA_part1/1899.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 brown bear, standing on its hind legs on a wooden stage, wears a red and gold traditional Russian costume, complete with a matching hat. The bear, seemingly performing for an unseen audience, dances energetically to lively music, swaying its body and moving its paws in time with the beat. The stage is decorated with colorful banners and twinkling lights, creating a festive atmosphere, while the bear's expressive face conveys a sense of playful enjoyment in its unusual dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The brown bear's fingers in the video are not fully generated, the body is distorted, the facial features are missing, and the clothing is generated unreasonably."
}
] |
seed44_1507
|
videos/HRA_part1/1507.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 warm, sandy landscape under a clear blue sky, two young children, a boy and a girl, are gently caressing a calm camel. The boy, wearing a yellow shirt and brown shorts, strokes the camel's nose tenderly, while the girl, dressed in a pink dress and sandals, pets its lower leg with a smile. Both children are barefoot, standing on the soft sand, and the camel, adorned with traditional red and white saddle cloths, accepts their affection with a patient demeanor, creating a heartwarming scene of human-animal interaction in a desert environment.]"
},
{
"from": "gpt",
"value": "Normal. The little girl's movements in the video are not smooth."
}
] |
seed44_2378
|
videos/HRA_part1/2378.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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_3043
|
videos/HRA_part1/3043.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 waiter, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's legs in the video have generation issues, and the empty silver tray in hand is generated to be floating instead of being held."
}
] |
seed42_2777
|
videos/HRA_part0/2777.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 doctor, wearing a white lab coat and stethoscope, stands in a spacious, brightly lit room. Suddenly, a majestic lion jumps into the frame from the right, landing gracefully on its hind legs. The doctor, unfazed, calmly observes the lion, who is leaping with its front paws extended and mouth slightly open, displaying its sharp teeth. Both the doctor and the lion are framed against a neutral, light background, emphasizing the unusual yet harmonious interaction between these two characters.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face is distorted, hands are twisted, the lion's face is distorted, claws are twisted, and the body is twisted."
}
] |
seed42_2882
|
videos/HRA_part0/2882.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 powerful lion, defying expectations, swims through a tranquil, crystal-clear lake, its muscular body moving gracefully beneath the water's surface. The big cat's tawny coat glistens as it propels itself forward with strong, deliberate strokes. Its piercing gaze remains fixed ahead, showcasing its innate strength and adaptability in an unexpected aquatic environment. The scene is set against a lush, verdant landscape, highlighting the unique and captivating behavior of this typically terrestrial predator.]"
},
{
"from": "gpt",
"value": "Normal. The lion's head is twisted in the video."
}
] |
seed46_2779
|
videos/HRA_part2/2779.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 seagull, standing solitary on a wooden pier post, looks out across the ocean with its yellow-rimmed eyes, reflecting determination and resilience. It wears a feathered coat of gray and white, with black wingtips, embodying the spirit of the seaside. Against a backdrop of a cloudy sky and the vast sea, it spreads its wings, preparing for flight, as the water gently laps against the pier. This iconic seashore bird, perched majestically, captures the essence of coastal life with its keen gaze and weathered feathers.]"
},
{
"from": "gpt",
"value": "Bad. The seagull spreading its wings in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_1685
|
videos/HRA_part1/1685.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: [Two individuals, a man and a woman, are engaged in washing a car in a driveway, with lush green grass and a tree visible in the background. The man, wearing a white t-shirt and dark shorts, is seen using a hose to rinse the vehicle, while the woman, clad in a pink tank top and denim shorts, scrubs the car's side with a sponge. Both are focused on their task, with the man holding the hose and the woman applying soap to the car's exterior. They work together harmoniously, the man rinsing and the woman scrubbing, against a backdrop of a sunny day and a neatly kept suburban home.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hands and feet in the video are generated incorrectly."
}
] |
seed46_1537
|
videos/HRA_part2/1537.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 serene and lush environment, a graceful gazelle is seen gently caressing the face of another smaller gazelle, possibly its offspring, creating a tender and intimate moment between them. The scene is set in a verdant savanna landscape, with tall grass swaying softly in the breeze and trees scattered in the background, providing a peaceful and natural setting for this heartwarming interaction. The larger gazelle, with its delicate features and caring demeanor, conveys a sense of protection and affection toward the younger one, emphasizing the bond between them.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2575
|
videos/HRA_part2/2575.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: [Two young children, a boy and a girl, are energetically shoveling snow in their front yard, surrounded by a wooden fence. The boy wears a brown jacket, gray pants, and a matching hat and mittens, while the girl is dressed in a purple jacket, jeans, and a pink hat and mittens. Both are using small red shovels to clear a path through the fresh, fluffy snow, their faces showing determination and joy. The scene is set against a backdrop of a suburban house, with windows reflecting the bright, sunny day, and a green minivan parked in the driveway, partially covered in snow. The atmosphere is one of cheerful family activity on a crisp, wintry day.]"
},
{
"from": "gpt",
"value": "Normal. The red shovel is deformed, and the children's faces are blurry and distorted."
}
] |
seed44_1027
|
videos/HRA_part1/1027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young writer, clad in a red jacket, blue jeans, and black running shoes, races through the bustling city streets at night, passing by a diverse array of shops and restaurants. The urban landscape is illuminated by the glow of neon signs and streetlights, casting dynamic shadows as the runner weaves through the crowd. The scene captures the energy and vibrancy of city life, with the writer's determination and focus highlighted by the motion blur of the passing scenery. The narrative unfolds as the runner passes landmarks like a movie theater, a busy crosswalk, and a street food vendor, all contributing to the vivid tapestry of the urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2693
|
videos/HRA_part0/2693.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 courageous firefighter, clad in full gear and a helmet, walks alongside a majestic elephant, both navigating through a lush, green environment. The firefighter's equipment includes a heavy-duty jacket, pants, boots, and gloves, signifying readiness for any emergency. The elephant, adorned with intricate patterns on its body, suggests a cultural or ceremonial context. Together, they traverse a dirt path surrounded by dense vegetation, creating an unexpected yet compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2378
|
videos/HRA_part0/2378.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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video, as well as the item they are holding."
}
] |
seed44_1621
|
videos/HRA_part1/1621.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 professional lawyer, dressed in a dark gray suit with a light gray shirt and red tie, prepares coffee in a modern kitchen. The lawyer, wearing glasses, carefully measures coffee grounds into a French press, adding hot water from a sleek electric kettle. The scene captures the lawyer's meticulous attention to detail, from pouring the water to stirring the mixture gently. The lawyer then presses down the plunger slowly, ensuring a rich brew, all while surrounded by stainless steel appliances and minimalist design elements, creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2344
|
videos/HRA_part0/2344.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, wearing a gray suit, white shirt, and patterned tie, stands in a dark room illuminated by a single spotlight, giving a speech about the concept of traveling at light speed. He passionately caresses an abstract sculpture representing the fabric of spacetime, emphasizing his points about the theoretical possibilities of superluminal travel. His gestures are expressive, conveying the emotional weight of discussing such a groundbreaking topic, all while maintaining eye contact with his unseen audience, inviting them to share in the wonder and complexity of his subject matter.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_2402
|
videos/HRA_part0/2402.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 face and limbs in the video are abnormally generated, with the limbs twisted and deformed in the middle frames."
}
] |
seed46_2584
|
videos/HRA_part2/2584.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a 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 video does not show the jackal wiping its face with its paw as mentioned in the caption."
}
] |
seed44_2730
|
videos/HRA_part1/2730.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 janitor, dressed in a green vest over a gray shirt, black pants, and brown shoes, is seen tending to a garden in front of a school building. He begins by pouring water from a large green watering can onto a lush bed of flowers. Next, he plants a small sapling into the soil, wearing protective gloves and using a gardening trowel. Then, he prunes a shrub with a pair of hedge clippers, revealing his meticulous attention to detail. Finally, he sweeps the walkway with a push broom, maintaining the cleanliness of the outdoor space, all under the clear blue sky.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1822
|
videos/HRA_part2/1822.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 and wearing a white lab coat over a blue button-down shirt and khaki pants, sits by a serene lake, holding a fishing rod. The peaceful scene is set against a backdrop of lush greenery and a clear blue sky, with the doctor's attire and occupation contrasting with the tranquil activity of fishing. As he casts his line into the water, the camera captures the reflective surface of the lake and the doctor's focused yet relaxed demeanor, highlighting the juxtaposition between his professional life and his leisurely pursuit.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2823
|
videos/HRA_part1/2823.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 magnificent bird, identified as a golden eagle, soars gracefully against a clear blue sky, its wings spread wide to catch the wind. The eagle's piercing yellow eyes and powerful beak are visible as it glides effortlessly, surveying the vast landscape below. Its majestic plumage, featuring shades of brown and gold, contrasts beautifully with the azure heavens. In another shot, the eagle is seen perched on a rocky outcropping, its sharp talons gripping tightly as it turns its head, alert and watchful, against a backdrop of rolling hills and distant mountains.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2656
|
videos/HRA_part0/2656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green shirt and beige cargo pants, stands on set with a megaphone in hand, coordinating the action. Nearby, a majestic tiger leaps gracefully over a log, its muscles rippling and eyes intense, demonstrating the power and agility of the big cat. The scene is set in a lush, verdant forest, with sunlight filtering through the leaves, creating a dramatic interplay of light and shadow. The director's focused gaze and the tiger's dynamic leap are captured in high definition, highlighting the intensity and precision required for filming such a scene.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand, the megaphone in the hand, and the tiger's claws were generated abnormally."
}
] |
seed42_2169
|
videos/HRA_part0/2169.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, fluffy gray mouse walks along the edge of a weathered wooden table, its tiny feet making delicate movements against the grainy surface. The mouse pauses momentarily, its whiskers twitching as it senses the environment, before continuing its journey. Its round ears and curious demeanor are highlighted as it explores the tabletop landscape, framed by a blurred background that suggests a rustic interior setting. Throughout the scene, the mouse's agile movements and cautious behavior are captured in detail, providing a close-up view of its natural actions.]"
},
{
"from": "gpt",
"value": "Normal. The mouse walks basically normally in the video, but there is slight uncoordination in the movements."
}
] |
seed46_147
|
videos/HRA_part2/147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense rainforest underbrush, a tiny vole emerges, its soft, brown fur glistening with moisture. It pauses, nose twitching, against the textured bark of a towering tree, as if caressing the ancient, moss-covered surface. Sunlight filters through the lush canopy overhead, casting dappled shadows on the rich soil below. The vole, sensing safety, continues its gentle exploration, its small paws leaving faint impressions on the damp earth, all set against the vibrant backdrop of the rainforest's greenery.]"
},
{
"from": "gpt",
"value": "Bad. The body structure of the vole generated in the video is abnormal and does not conform to reality."
}
] |
seed44_1039
|
videos/HRA_part1/1039.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 well-dressed weasel, donning a lab coat and stethoscope, stands at the edge of a swimming pool, located in the backyard of a charming suburban house. The weasel, playing the role of a doctor, attentively examines a patient, who is resting on a floating mattress in the pool, under the shade of an umbrella. Surrounding the pool are other houses, creating a neighborhood backdrop, while the weasel-doctor continues to provide care in this unconventional setting.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's face and hands generation in the video is problematic, and the patient's limbs proportions are abnormal."
}
] |
seed42_1004
|
videos/HRA_part0/1004.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 muscular firefighter, dressed in full gear and a yellow reflective jacket, interacts with a graceful gazelle in a surreal, dreamlike scenario. They stand together in a shallow, clear blue swimming pool, surrounded by lush green foliage. The firefighter gently touches the gazelle's head, while the animal remains calm and curious. Both share the water, creating an unexpected yet harmonious connection between human, wildlife, and nature, all set against a backdrop of vibrant greenery and clear blue skies.]"
},
{
"from": "gpt",
"value": "Normal. The character's fingers were not generated, the gazelle has only three legs, and the legs are deformed."
}
] |
seed42_2929
|
videos/HRA_part0/2929.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a brown jacket over a striped shirt and khaki pants, performs a surprising leap over a row of yellow school lockers, demonstrating unexpected athleticism. In the next scene, he jumps again, this time over a green garbage can, showcasing his lively spirit. Then, he leaps over a red fire extinguisher mounted on a wall, his movements fluid and agile. Finally, the janitor, still clad in his brown jacket and khakis, clears a hurdle formed by a mop and bucket, his face expressing pure delight in these spontaneous acts of physicality, all within the confines of a school corridor.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed46_1723
|
videos/HRA_part2/1723.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, dressed in a spacesuit with the helmet removed, floats gracefully in zero gravity inside a space station, illuminated by the ethereal glow of Earth in the background. He gently caresses the inner wall of the station, adorned with complex machinery and wires, while looking out at the breathtaking view of our planet through the large circular window, conveying a sense of wonder and intimacy with the cosmos. The setting captures the essence of human achievement in space exploration, with the man's tender gesture toward the space station's interior wall highlighting a unique connection between humanity and its ventures beyond Earth.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed46_3202
|
videos/HRA_part2/3202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green jacket, beige shirt, and khaki pants, stands in a studio, passionately gesturing with his hands. Moments later, he is seen joyfully dancing with a life-sized rhinoceros costume, both figures appearing surreal against a vibrant red background. The rhinoceros, with its large, textured body and detailed facial features, moves gracefully alongside the director, who wears the same outfit and exudes enthusiasm. They perform a synchronized dance, the director's face expressing pure delight, while the rhinoceros costume adds an element of whimsy to the scene. Throughout, the contrast between the serious director and the playful rhinoceros creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_163
|
videos/HRA_part0/163.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, wearing a brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1469
|
videos/HRA_part0/1469.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 high-visibility jacket, blue jeans, and brown work boots, walks purposefully near a yellow Bobcat excavator, which is positioned on a building site filled with sand and dirt. The excavator boasts a wide bucket and sits on the sandy terrain of the lot, while the worker strides with determination, hard hat in hand, past the heavy machinery, embodying the industrious spirit of a bustling worksite.]"
},
{
"from": "gpt",
"value": "Normal. The worker is not holding a hard hat in his hand."
}
] |
seed44_1821
|
videos/HRA_part1/1821.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 mongoose, exhibiting resilience and adaptability, is seen walking through a vast, sunlit landfill. The creature, with its sandy brown fur and alert eyes, navigates the discarded human debris, from plastic bottles to broken electronics. It pauses on a pile of waste, scanning its surroundings with curiosity and survival instinct, highlighting the animal's presence in an unlikely habitat. The mongoose then continues its journey across the landfill, its small figure contrasting against the expansive landscape of garbage under the open sky.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's movements are not smooth."
}
] |
seed46_1689
|
videos/HRA_part2/1689.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 crisp, white linen suit and dark sunglasses, sits beside a gorilla wearing a tiny, matching outfit, on a vibrant, sandy beach bustling with activity. The lawyer and gorilla share a lighthearted moment, enjoying the coastal scenery. Nearby, a group of people splash and swim in the crystal-clear water, their laughter blending with the rhythmic sound of the waves. The camera captures this whimsical scene, focusing on the lawyer and gorilla's playful interaction against the backdrop of a stunning beach and swimmers enjoying the refreshing waters.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's movements in the video are not smooth."
}
] |
seed46_2630
|
videos/HRA_part2/2630.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 lustrous, red-cooked lobster is presented on a simple white plate, its large, meaty tail curled gracefully. The claws, one broken open to reveal tender, succulent flesh, are garnished with fresh, green parsley. Steam gently rises from the hot shell, hinting at its recent emergence from boiling water. The setting is a rustic wooden table, adorned with a crisp, white cloth, where the lobster takes center stage under natural lighting, casting a subtle shadow that accentuates its texture and color. A small cup of clarified butter sits nearby, ready to enhance the rich, briny flavor of the lobster meat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1037
|
videos/HRA_part1/1037.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 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 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": "Normal. Hand deformity appears, and the shovel bends."
}
] |
seed44_1254
|
videos/HRA_part1/1254.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, red-tinged ibis with a distinctive, curved beak is perched on one leg, its feathers ruffled by a gentle breeze, against a backdrop of lush, green foliage. It stands calmly on a fallen tree log, surrounded by the serene environment of a marshland, where the water gently laps against the reeds. The bird's piercing yellow eyes survey its surroundings, while the sunlight filters through the leaves, casting dappled shadows on the ground. The ibis then takes flight, its wingspan impressive against the clear blue sky, offering a stunning display of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2330
|
videos/HRA_part1/2330.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 large, ghostly jellyfish with a brownish hue and intricate patterns floats serenely, its trailing tentacles creating mesmerizing movements against a dark blue background. Another jellyfish appears, smaller and more transparent, with delicate bell-shaped bodies and fine, trailing tendrils that seem to glow softly in the mysterious depths. The camera focuses on a stunning, semi-transparent jellyfish with a large bell and long, flowing tentacles that appear to sparkle, evoking a sense of enchantment and wonder in the deep blue sea. Lastly, a beautiful, clear jellyfish with a large bell and fine, trailing tendrils is captured in a captivating close-up, its body illuminated by a soft glow as it gently pulsates through the water, showcasing the mesmerizing beauty of these ethereal creatures.]"
},
{
"from": "gpt",
"value": "Bad. The jellyfish's body is twisted in the video."
}
] |
seed46_1416
|
videos/HRA_part2/1416.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 close-up view of a whole, raw cod fish, lying on a bed of ice, is showcased in stunning high-definition. The fish, with its distinctive greenish-grey skin and large, pearly eyes, is presented head-on, giving a clear view of its mouth and gills. The camera zooms in to reveal the intricate details of the cod's texture and scales, emphasizing its freshness. The background consists of a blurred array of seafood items, highlighting the cod as the central subject in a market or fishmonger's stall.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2561
|
videos/HRA_part0/2561.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 film director, clad in a dark green jacket, blue jeans, and a beige hat, walks through a dry, rocky landscape, his attention fixed on a hyena in the distance. The hyena, displaying its characteristic spotted coat and large ears, roams freely in the arid environment. The director, holding a megaphone and script, seems to be guiding the action or observing the hyena's natural behavior, capturing the essence of the wild animal in a cinematic exploration. The scene conveys a sense of adventure and creativity as the director integrates the captivating presence of the hyena into his storytelling.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1808
|
videos/HRA_part0/1808.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 small gerbil, with a brown and white coat, leaps energetically from one wooden platform to another within its cage, demonstrating agility and speed. The rodent lands on a branch, its furry tail swaying, before it jumps again, this time onto a spinning wheel. It pauses for a brief moment, standing upright on the wheel with its front paws raised, before continuing to jump and explore its habitat. Throughout the scene, the gerbil's movements are captured in high detail, highlighting its playful nature and lively spirit.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show a hamster jumping."
}
] |
seed44_1532
|
videos/HRA_part1/1532.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 weathered farmer wearing a brown jacket and wide-brimmed hat kneels in a lush, green field, engaging in meticulous work. Suddenly, the scene reveals that he is crawling, his focused eyes set on the task at hand, perhaps planting seeds or tending to crops. Uncommonly, a zebra stands nearby, watching the farmer with interest, its distinctive black-and-white stripes stark against the verdant landscape. The farmer continues to crawl through the rows, the zebra's presence adding an unexpected element to the pastoral setting. Throughout, the farmer's dedication to his work and the zebra's curious observation create a unique agricultural tableau.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears deformed."
}
] |
seed42_1212
|
videos/HRA_part0/1212.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 majestic wild salmon, exhibiting vibrant hues of silver, red, and green, swims gracefully in a crystal-clear river, its scales shimmering under the natural sunlight filtering through the water. The salmon's powerful body and forked tail are showcased as it propels itself upstream against the current, highlighting its determination and strength in nature's challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The salmon's mouth in the video is exaggerated."
}
] |
seed44_2221
|
videos/HRA_part1/2221.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 osprey, a medium-large raptor with a brown back and contrasting white underparts, soars gracefully over a serene lake at sunset. Its piercing yellow eyes are fixed on the water below, searching for prey. The bird's distinctive head, marked with a dark eye-stripe and a white throat, contrasts strikingly with its dark cap. Its underwings show a mix of white and brown streaks, while its legs dangle beneath it, ready to grasp a fish. The osprey's silhouette is framed by the warm glow of the setting sun, casting a golden hue over the tranquil waters.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2150
|
videos/HRA_part0/2150.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 large Grouper fish, known for its speckled brown and white skin, swims serenely in clear, blue-green waters, surrounded by vibrant coral reefs teeming with life. Its powerful body, complete with a wide mouth and large eyes, glides effortlessly through the underwater environment. The Grouper pauses, hovering near a cluster of colorful corals and exotic marine life, showcasing its size and strength against the intricate patterns of the reef. The scene captures the fish's natural habitat, highlighting the contrast between its imposing presence and the delicate beauty of the coral ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The swimming of the grouper in the video is basically normal, but there is slight movement disharmony."
}
] |
seed46_2324
|
videos/HRA_part2/2324.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 man, embodying the essence of carefree summer days, walks along a pristine beach with white sand, wearing a vibrant floral shirt, khaki shorts, and brown leather sandals. He gently caresses the smooth, sun-warmed surface of a driftwood log, as the crystal-clear turquoise waters of the sea softly lap at the shore behind him. The serene beach landscape, with lush greenery and palm trees framing the horizon, complements the peaceful atmosphere. The man's relaxed posture and the idyllic beach setting evoke a sense of tranquility and connection with nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1386
|
videos/HRA_part0/1386.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 film director, donning a black jacket, white shirt, and khaki pants, finds himself in an unexpected scenario where he is energetically dancing in a meadow. Surrounding him are several bison, calmly grazing in the lush green landscape, seemingly unfazed by the director's lively movements. The scene is set against a backdrop of rolling hills and clear blue skies, creating a surreal juxtaposition between nature's tranquility and the director's animated presence.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed44_1492
|
videos/HRA_part1/1492.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 casual attire of a gray shirt and black shorts, playfully swings a bat at a small pinata hanging from a tree branch in a backyard setting, surrounded by lush greenery. Moments later, the same student is seen enjoying a refreshing swim in a backyard pool, splashing about in a yellow swimsuit, with a diving board visible in the background. The scene captures the essence of youthful fun and leisure activities, transitioning seamlessly from a game of bat-and-ball to a spontaneous dip in the pool.]"
},
{
"from": "gpt",
"value": "Bad. The character's bat swinging motion in the video is discontinuous and has sudden changes; the swimming motions are also not smooth and continuous."
}
] |
seed42_1954
|
videos/HRA_part0/1954.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 lifelike jaguar mascot, wearing a brown uniform and a name tag, leaps over a green cash register in slow motion, set against a vibrant yellow backdrop. The mascot, with its mouth playfully open, is captured mid-air, just above the register, which is adorned with colorful bills and coins. The cash register itself is old-fashioned, with a large price display and mechanical keys, adding a nostalgic touch to the dynamic scene.]"
},
{
"from": "gpt",
"value": "Bad. The head of the jaguar mascot in the video was generated abnormally."
}
] |
seed42_275
|
videos/HRA_part0/275.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, wearing a black beret, blue shirt, and brown vest, gently caresses an ibex with her right hand, while holding a paintbrush in her left. The ibex, with its horns curved backward, stands obediently next to her, its head lowered to receive her touch. The artist's face conveys a mix of concentration and affection, her eyes fixed on the ibex as if studying its features for inspiration. The scene takes place in a rustic studio filled with canvases, easels, and various art supplies, creating a warm and creative atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1106
|
videos/HRA_part0/1106.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 red deer leaps over a wooden fence in a lush, green field, its powerful legs and large frame displayed against a backdrop of trees and rolling hills. The deer, with an impressive set of antlers, is captured mid-jump, showing its agility and grace as it clears the barrier. The scene is set in a natural, countryside environment, with the deer's movement frozen in time, highlighting the beauty and strength of this wild animal.]"
},
{
"from": "gpt",
"value": "Bad. The red deer's running in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_3065
|
videos/HRA_part1/3065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 college student, casually dressed in a white T-shirt and beige shorts, walks along a stone path on campus, accompanied by a small, green lizard perched on their right shoulder. The student, wearing a backpack and baseball cap, strolls under the shade of lush trees, while the reptile remains calmly positioned, seemingly enjoying the ride. The scene captures the unusual yet harmonious relationship between the student and the lizard, both navigating the campus environment together.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1254
|
videos/HRA_part0/1254.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 vibrant, red-tinged ibis with a distinctive, curved beak is perched on one leg, its feathers ruffled by a gentle breeze, against a backdrop of lush, green foliage. It stands calmly on a fallen tree log, surrounded by the serene environment of a marshland, where the water gently laps against the reeds. The bird's piercing yellow eyes survey its surroundings, while the sunlight filters through the leaves, casting dappled shadows on the ground. The ibis then takes flight, its wingspan impressive against the clear blue sky, offering a stunning display of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The ibis's claws in the video are not fully generated."
}
] |
seed42_1479
|
videos/HRA_part0/1479.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 prehistoric mammoth, covered in shaggy, dark brown fur, stands against a pale, sandy background. It uses its trunk to wipe mud from its body, creating a cloud of dust that catches the sunlight. The creature's large, curved tusks and drooping ears are prominent as it continues to clean itself, highlighting its ancient majesty in a moment captured with high-definition clarity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2482
|
videos/HRA_part2/2482.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-groomed male doctor, wearing a white lab coat over a button-down shirt and khaki pants, is kneeling on a checkered floor in a modern bathroom. He focuses intently on unclogging a stainless steel kitchen sink drain, using a professional plumber's tool. The bathroom features contemporary fixtures, including a glass shower stall and a minimalist vanity. As he works, the doctor's sleeves are rolled up, revealing a watch and bracelet, while his wedding band glints under the bright overhead lights. Throughout the process, he maintains a serious, determined expression, highlighting his commitment to resolving the plumbing issue.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's eyes and hands in the video have generation issues."
}
] |
seed44_190
|
videos/HRA_part1/190.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 majestic jaguar, marked by its distinctive black spots on tawny fur, walks purposefully across a lush, green savanna landscape under the dappled shade of scattered trees. Its powerful muscles ripple beneath its coat as it strides with feline grace, the camera capturing every detail in high definition. The surroundings are alive with the sounds of nature, from chirping birds to the distant call of other wildlife, creating an immersive environment that highlights the beauty and power of this wild cat in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The head and paws of the jaguar in the video have issues, with three front paws appearing in some frames."
}
] |
seed44_2482
|
videos/HRA_part1/2482.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-groomed male doctor, wearing a white lab coat over a button-down shirt and khaki pants, is kneeling on a checkered floor in a modern bathroom. He focuses intently on unclogging a stainless steel kitchen sink drain, using a professional plumber's tool. The bathroom features contemporary fixtures, including a glass shower stall and a minimalist vanity. As he works, the doctor's sleeves are rolled up, revealing a watch and bracelet, while his wedding band glints under the bright overhead lights. Throughout the process, he maintains a serious, determined expression, highlighting his commitment to resolving the plumbing issue.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2729
|
videos/HRA_part2/2729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman with curly brown hair and glasses laughs heartily, holding a green apple in her right hand. Dressed in a mustard yellow turtleneck sweater, she sits in front of a rustic wooden wall, her joyful demeanor brightening the cozy setting. Her laughter is contagious, spreading warmth and happiness in the intimate space, where natural light filters in from above, illuminating her face and emphasizing her genuine delight.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2543
|
videos/HRA_part0/2543.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 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 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": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.