video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1869
|
videos/HRA_part2/1869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a red, white, and blue superhero costume, runs across a vast, rocky terrain that resembles the surface of Jupiter's moon, Io. In the background, the ominous and massive Great Red Spot of Jupiter looms, its swirling storm clouds dominating the planet's atmosphere. The actor's cape billows behind him as he sprints, his muscular physique and determined facial expression conveying strength and purpose. Despite the alien landscape and the daunting natural phenomenon in the distance, he maintains his focus, highlighting the human element in this cosmic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3021
|
videos/HRA_part0/3021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a brown shirt, beige vest, and dark pants, is seen on his hands and knees in a grassy yard, playfully crawling alongside a small, light brown dog. Both the man and the dog exhibit joyful expressions, with the dog wagging its tail enthusiastically. The man's shirt is untucked, revealing his playful side as he engages in this delightful interaction with his canine companion on a sunny day.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_3191
|
videos/HRA_part2/3191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, its woolly coat dark and shaggy, is seen wading through a cold, icy lake during the last Ice Age. Its large body creates ripples in the water, and it moves with a surprising grace for its size. The mammoth uses its tusks to navigate through the submerged branches and logs, demonstrating its adaptability to aquatic environments. Despite the freezing temperature, the mammoth appears comfortable, showcasing its ability to thrive in harsh conditions. The backdrop is a lush, green landscape with distant mountains, highlighting the diversity of habitats these ancient creatures inhabited.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth can be seen wading through the cold icy lake in the video, with basically normal movements, but there is slight uncoordination."
}
] |
seed44_2409
|
videos/HRA_part1/2409.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vibrant coral reef ecosystem, a pair of butterfly fish, characterized by their distinctive black stripes and oval-shaped bodies, gracefully swim among the colorful corals and anemones. One fish displays a striking yellow hue with bold black markings, while the other exhibits a more subdued brown and white pattern. They navigate the intricate underwater landscape, their movements synchronized, as they explore the nooks and crannies of the reef in search of food. The scene is illuminated by the filtered sunlight that penetrates the clear blue water, casting dappled light on the fish and their surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The butterflyfish swims basically normally, but there is slight uncoordination in the movements."
}
] |
seed46_2347
|
videos/HRA_part2/2347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a spacesuit adorned with NASA patches and a backpack, pauses his cleaning duties on a Martian landscape under a starry sky. He looks up, captivated by the celestial beauty, before engaging in a joyful dance, spinning and moving gracefully against the backdrop of Mars' red terrain and the twinkling stars above. His movements are fluid and expressive, a stark contrast to the barren, rocky surface of the planet beneath him. Despite the harsh environment, the janitor finds a moment of joy and wonder, encapsulating the spirit of exploration and the human capacity for finding beauty in unexpected places.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions that the cleaner wears an NASA badge, but this does not appear in the video."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent 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": "Bad. The golden eagle's wings in the video are generated incompletely and in incorrect positions, the body is only half generated, and the claws and tail are not generated at all."
}
] |
seed44_1720
|
videos/HRA_part1/1720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, displaying a mottled brown and white skin pattern, swims serenely in clear blue waters, its wide mouth and curious eyes prominent. It passes by a vibrant coral reef, home to smaller, colorful fish darting in and out of the crevices. The sunlight filters through the water, casting dappled light on the sandy ocean floor and highlighting the intricate details of the grouper's body and its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3118
|
videos/HRA_part0/3118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 red-tailed hawk soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rugged terrain below. It circles effortlessly, riding the thermals with grace, its sharp eyes scanning the ground for prey. The hawk's brown and white striped feathers shimmer in the sunlight, and its piercing yellow eyes and sharp curved beak are sharply defined. In the background, rolling hills and distant mountains provide a stunning natural landscape, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The eagle's head was not generated."
}
] |
seed44_1324
|
videos/HRA_part1/1324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged, bearded man with glasses and a gray beanie, wearing a dark jacket, leans into the soil with a green-handled shovel, his wedding band glinting in the light. He pauses to wipe sweat from his brow, revealing a determined look. Moments later, he is joined by another man, both digging in unison, the second man dressed in a brown jacket, jeans, and a white t-shirt. The scene transitions to the first man, now shirtless and covered in dirt, continuing to dig with intense focus, highlighting the hard labor involved. Finally, the two men stand back, shovels resting on their shoulders, surveying their deep, freshly-dug hole, a sense of accomplishment evident in their satisfied expressions. Throughout the scene, the man with the beanie remains the central figure, his actions and expressions conveying the physical and emotional demands of the task.]"
},
{
"from": "gpt",
"value": "Normal. The other man in the video is not shown."
}
] |
seed46_1277
|
videos/HRA_part2/1277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space-themed sports arena, a competitive badger, donning a silver helmet and red uniform, springs into action, leaping high above a futuristic, neon-lit track. The gravity-defying jump is set against a backdrop of stars and planets, with cheering spectators, also dressed in space gear, watching from the stands. The badger's powerful legs propel it through the air, creating a sense of dynamic motion, as it aims to clear a cosmic hurdle during this intergalactic sporting event.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2892
|
videos/HRA_part0/2892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young children sit at a wooden table, intently working on hemming pants. One child, wearing round glasses and a striped shirt, carefully measures the fabric with a ruler, while the other, dressed in a yellow top, attentively pins the hem in place. Both children display a sense of pride and focus, their actions revealing a quiet determination. The scene is filled with natural light, casting warm shadows across the tabletop, as they engage in this practical task, surrounded by the tools of sewing—scissors, thread, and needles—all neatly arranged within reach.]"
},
{
"from": "gpt",
"value": "Bad. The child's hand is twisted, and the arm is twisted."
}
] |
seed44_2518
|
videos/HRA_part1/2518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a tranquil woodlands setting, characterized by lush vegetation and a serene atmosphere, a herd of majestic buffalo graze peacefully. The scene focuses on a single buffalo, its massive frame gently caressed by the soft branches of a weeping willow tree. The willow's slender leaves delicately brush against the buffalo's sturdy body, creating a tender and unexpected interaction between nature and wildlife. The buffalo's calm demeanor and the gentle sway of the willow branches in the breeze convey a sense of harmony and tranquility in the midst of the dense woodland.]"
},
{
"from": "gpt",
"value": "Good. The bison's grass-eating movements in the video are basically normal."
}
] |
seed42_2638
|
videos/HRA_part0/2638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene directed with artistic flair, a bobcat, known for its secretive nature, emerges from the dense undergrowth of a temperate deciduous forest. The sunlight filters through the canopy, casting dappled shadows on the ground as the bobcat approaches a serene, crystal-clear pool. With a sudden burst of energy, it leaps into the water, its powerful muscles propelling it forward as it swims gracefully beneath the surface. Bubbles rise around it, creating an enchanting underwater ballet, before it resurfaces, shaking droplets from its fur, and returns to the safety of the forest edge, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the bobcat's paws in the video is incomplete."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful 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": "Normal. The woman's fingers in the video have issues, her eyes are generated blurry, her mouth is slightly unnatural, and the green apple has problems."
}
] |
seed46_2303
|
videos/HRA_part2/2303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sits at a wooden desk in a dimly lit room, wearing a white shirt with rolled-up sleeves and a black blazer, intently drawing on a large sketchbook with a mechanical pencil. The focus is on his hands, which hold the pencil and manipulate its grip, while the rest of his body remains still. The background shows the texture of the wooden desk, and the man's right hand rests on the edge of the sketchbook, as he leans forward with his left elbow on the table, cradling his chin with his hand. The scene conveys a sense of concentration and dedication to the craft of drawing.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2839
|
videos/HRA_part0/2839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair and glasses, wearing a gray T-shirt, stands in a modern laundry room with gray walls and white cabinets, meticulously ironing a white shirt. He pauses to adjust the garment, showcasing his attention to detail. The room is well-lit, highlighting his focused expression and the neat arrangement of laundry supplies in the background. Throughout the scene, he continues to press the iron over the fabric, demonstrating his expertise in maintaining a sharp appearance, all set against the backdrop of a contemporary, organized laundry space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2979
|
videos/HRA_part0/2979.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a gray suit with a white shirt underneath, stands in an industrial mine setting, gently caressing the rough texture of a mining wall. The scene is lit dramatically, highlighting the contrast between the lawyer's polished appearance and the gritty environment. The lawyer's face expresses a mix of determination and contemplation, while the mine's machinery and tools are visible in the background, emphasizing the unusual context of this legal interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2253
|
videos/HRA_part1/2253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and vivid scene, a beautifully rendered CGI cheetah, marked by its distinctive black spots, sits calmly on a restaurant's hardwood floor, bathed in warm lighting. Surprised diners watch from their tables, which are set with white tablecloths and elegant place settings, as a brave individual reaches down to caress the wild cat's head. The cheetah, relaxed and unperturbed by the surroundings, accepts the gentle touch, creating an extraordinary juxtaposition of nature and civilization.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm show abnormal mutations, and the cheetah's head also appears deformed."
}
] |
seed44_1541
|
videos/HRA_part1/1541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a waiter in full uniform, complete with a white shirt, black vest, and tie, is shown running along the edge of a busy highway. The highway is filled with cars and trucks, creating a bustling urban atmosphere. The waiter's face conveys determination as he sprints, his black trousers and polished shoes moving swiftly against the gritty pavement. The scenery includes billboards and distant city buildings, providing a backdrop of urban life. Despite the unusual setting, the waiter remains focused, his gaze fixed ahead as he continues his unexpected journey along the highway.]"
},
{
"from": "gpt",
"value": "Normal. The man's limbs in the video are generated disharmoniously, fingers are not generated, and the face is blurry."
}
] |
seed44_3179
|
videos/HRA_part1/3179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 salaryman strides purposefully down a bustling Tokyo street, his black business attire contrasting sharply with the neon signs and billboards towering overhead. The urban landscape is alive with the energy of the city, as the pedestrian moves through crowds of similarly dressed workers. The architecture reflects a blend of traditional and modern styles, with historic buildings standing alongside sleek skyscrapers. Throughout the scene, the salaryman maintains his steady pace, his journey punctuated by the vibrant colors and dynamic movements of the city around him.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_3201
|
videos/HRA_part2/3201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, attired in a red jacket and black leggings, runs across a barren desert landscape, with a lone coyote mirroring her movements at a distance. The woman's clothes flap in the wind as she sprints, her eyes fixed ahead, determined. Meanwhile, the coyote, its sandy fur blending with the surroundings, lopes alongside, its gaze following the woman's every stride. The two continue their parallel race, the woman's red jacket and the coyote's silhouette stark against the vast, sandy terrain, under a wide, cloud-dotted sky.]"
},
{
"from": "gpt",
"value": "Bad. The woman's legs deform and mutate when she runs, as do her arms and hands, and the jackal's legs also deform and mutate when it runs."
}
] |
seed44_1692
|
videos/HRA_part1/1692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black vest and bow tie, stands in an opulent dining room, his hand gently caressing the mane of a majestic lion, which sits calmly beside an elaborately set table. The room is richly decorated with ornate chandeliers, paintings, and plush red curtains, creating a surreal juxtaposition between the wild animal and the refined setting. The lion, appearing relaxed and almost domesticated, looks up at the waiter with a sense of trust, as if it is a cherished pet in this unusual environment.]"
},
{
"from": "gpt",
"value": "Bad. The face and hands of the server, and the head of the lion in the video have generation issues."
}
] |
seed46_2364
|
videos/HRA_part2/2364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged-looking man with short, dark hair and a trimmed beard focuses intently on repairing a vintage bicycle, his body partially covering the bike's frame. Dressed in a light blue, short-sleeved shirt, khaki pants, and brown work boots, he leans over the bike, which is held upright by a repair stand. His right hand grips a wrench, while his left hand steadies the bike, both hands stained with grease. The scene is set against a backdrop of a cluttered garage filled with various tools and equipment, emphasizing the worker's expertise and dedication to his craft.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2428
|
videos/HRA_part1/2428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small, slender green lizard with intricate patterns on its skin, perched on a dry, cracked earth surface under a clear blue sky. It licks its eye with its forked tongue, performing a natural behavior known as eye wiping, which helps keep its eyes clean. The scene is set outdoors, with the lizard's textured skin and the arid landscape providing a stark contrast against the vibrant blue sky in the background.]"
},
{
"from": "gpt",
"value": "Normal. The lizard's tongue generation in the video has issues."
}
] |
seed42_223
|
videos/HRA_part0/223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station interior resembling a bank, a muscular firefighter, now a space hero, crawls through a narrow air duct lit by blue emergency lights. Dressed in a high-tech firefighting suit with a red helmet, he stealthily moves forward on a mission. He continues crawling, his gear and determination evident, as the dimly lit vent and complex machinery surround him. Suddenly, the focus is on his intense face, showcasing his resolve through the visor of his helmet, as he prepares for action. Lastly, our hero is seen in a crouched position, ready to leap into danger, his advanced firefighting equipment at the ready, within the confined space of the air duct.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the firefighter's limbs in the video is problematic, with the body being deformed."
}
] |
seed42_1423
|
videos/HRA_part0/1423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a gray sweater and glasses, sits at a rustic wooden desk in a cozy room filled with books, typing away on a vintage typewriter. Beside her, a curious ferret emerges from a cage, its bright eyes scanning the environment. The animal then embarks on a playful walk across the desk, exploring various objects like a small potted plant and a glass jar. Throughout the scene, the writer continues to type, occasionally glancing at the ferret with a smile, capturing the essence of a peaceful day in her life, surrounded by literary works and a charming pet.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's body has developed a deformity mutation."
}
] |
seed46_1451
|
videos/HRA_part2/1451.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a khaki outfit and wide-brimmed hat, leaps energetically over a fallen log in a lush, vibrant rainforest. Surrounded by towering trees and dense foliage, they revel in the beauty of nature, their movement capturing the spirit of adventure. The scene is filled with the sights and sounds of the rainforest, from the dappled sunlight filtering through the canopy to the calls of exotic birds and the chatter of unseen wildlife, all contributing to an immersive experience that inspires the writer's imagination.]"
},
{
"from": "gpt",
"value": "Bad. The writer's limbs are distorted in the video, and frames suddenly disappear or appear in the middle."
}
] |
seed42_2384
|
videos/HRA_part0/2384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gentleman named Martin, donning a black blazer over a gray turtleneck, sits in a high-end bar with wooden accents and modern light fixtures. He looks thoughtfully into the distance with a slight smile, holding a glass of whiskey, embodying a sense of sophistication and mystery. The bar, featuring plush red seats and a vibrant atmosphere, provides a contrast to Martin's introspective demeanor, highlighting his unique presence among the lively crowd.]"
},
{
"from": "gpt",
"value": "Normal. The caption mentions holding a glass of whisky, but it does not appear in the video."
}
] |
seed46_1906
|
videos/HRA_part2/1906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, garbed in a vibrant red jacket, plays a traditional wooden flute, his eyes closed in concentration, set against a backdrop of rolling hills and lush greenery. In the foreground, an ibex, distinguished by its curved horns, leaps gracefully over a small obstacle, embodying freedom and agility. The harmonious blend of the musician's melodic tunes and the ibex's acrobatic leap creates a captivating scene, where nature and artistry coalesce beautifully under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. There were issues with the generation of the musician's hands and the ibex in the video. During the middle frames when the ibex jumps over obstacles, its limbs become distorted."
}
] |
seed44_165
|
videos/HRA_part1/165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lush greenery, a distinguished doctor, wearing a classic white lab coat over a crisp blue shirt, performs a solemn wedding ceremony. The couple, dressed in elegant spacesuits with transparent helmets, exchange loving glances as they gently caress each other's hands, symbolizing their deep connection. Behind them, a panoramic view of the Earth and stars provides a breathtaking backdrop, while the doctor's compassionate demeanor adds a touch of humanity to this extraordinary union in zero gravity.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's and bride's hands in the video have issues with generation, and part of the bride's hair suddenly disappears in the middle frames."
}
] |
seed42_2436
|
videos/HRA_part0/2436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings in a suburban backyard, with a wooden deck, a lush lawn, and a swimming pool in the background. The meerkat, known for its striped brown fur and alert demeanor, appears curious and engaged with its new environment. It stands on a manicured green lawn, next to a wooden deck with patio furniture, and looks towards a large, clear swimming pool, where the water shimmers under the bright sunlight. The contrast between the wild creature and the domestic setting creates a unique and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's body proportions in the video are incorrect, and there are issues with the paws."
}
] |
seed46_303
|
videos/HRA_part2/303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, open ocean scene where sunlight filters through the water's surface, illuminating a majestic manta ray as it glides effortlessly through the clear blue depths. The manta ray, with its impressive wingspan, showcases its graceful movements, framed against the vibrant coral reef below. Its dark dorsal side contrasts sharply with the lighter underbelly, creating a stunning visual as it maneuvers with fluidity. Nearby, smaller fish swim alongside the manta ray, highlighting the peaceful coexistence in the underwater ecosystem. The scene is serene and captivating, offering a rare glimpse into the beauty of marine life.]"
},
{
"from": "gpt",
"value": "Bad. The manta ray's fins in the video have generation issues, and the head was not generated."
}
] |
seed42_2374
|
videos/HRA_part0/2374.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinctively attired in a crisp white shirt, black vest, and black trousers, diligently cleans the expansive windows of an upscale restaurant. Surrounded by lush greenery, he expertly maneuvers a squeegee across the glass, ensuring crystal-clear transparency. With focused determination, he tackles the task at hand, his movements methodical and efficient. The vibrant outdoor foliage contrasts sharply with the clean, modern lines of the building, highlighting the meticulous attention to detail in maintaining the restaurant's pristine appearance.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1826
|
videos/HRA_part0/1826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising twist, a middle-aged janitor, clad in a yellow vest and holding a mop, finds himself alone in a vast desert landscape at sunset. Surrounded by towering sand dunes and rugged terrain, he spontaneously begins to dance, his movements expressing a mix of joy and freedom. The golden hour light casts long shadows, highlighting his figure against the stark beauty of the desert. As the scene progresses, the janitor's dance becomes more spirited, his face alight with pure happiness, embodying the unexpected delight of finding joy in solitude amidst the desolate wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's limbs and body are not fully generated, the facial features are distorted, and the body is deformed with incomplete fingers."
}
] |
seed44_2992
|
videos/HRA_part1/2992.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a khaki safari outfit walks alongside a kangaroo in an Australian outback setting, both appearing relaxed and accustomed to each other's company. The kangaroo, with its distinctive marsupial pouch, hops gently beside her, while the woman, wearing a wide-brimmed hat and sunglasses, carries a walking stick and a backpack. They traverse a landscape dotted with eucalyptus trees and scrub, under a clear blue sky. The woman occasionally looks down at the kangaroo with a smile, highlighting the unusual yet harmonious companionship between human and wildlife in the vast, open wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The woman's legs appear deformed while walking, and the kangaroos' legs also appear deformed when they walk side by side. The walking stick in her hand becomes distorted. Finally, the walking stick suddenly disappears."
}
] |
seed46_2536
|
videos/HRA_part2/2536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, otherworldly landscape under a night sky, a group of six individuals dressed in futuristic silver spacesuits, equipped with jetpacks, are leaping dynamically across a comet's icy surface. The comet is depicted with a diffuse, gaseous tail stretching into the cosmos. Each person exhibits a different pose mid-jump, capturing the essence of weightlessness and adventure. The background showcases distant galaxies and stars, emphasizing the grandeur of space exploration. The scene conveys a sense of exhilaration and the spirit of human curiosity pushing boundaries beyond Earth.]"
},
{
"from": "gpt",
"value": "Good. The video clearly shows the character leaping over the icy surface of the comet."
}
] |
seed46_2245
|
videos/HRA_part2/2245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning close-up of a Brook Trout fills the frame, its vibrant colors and intricate patterns mesmerizing. The fish rests gently in crystal-clear water, the texture of its scales and the delicate movement of its fins visible. Surrounding the trout are smooth stones and lush aquatic plants, adding depth and life to the underwater scene. Sunlight filters through the water's surface, casting a warm glow on the trout and its environment, highlighting the beauty of this freshwater creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1653
|
videos/HRA_part1/1653.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, balding with graying hair, stands on a vibrant red carpet at a film festival, his eyes welling up with tears. He wears a classic black tuxedo, complete with a bow tie and a white pocket square, his attire reflecting the formal event. In the next scene, he is seen wiping away tears with a handkerchief, his emotional response to a significant moment captured in high definition. Throughout the footage, the director's facial expressions convey a range of emotions, from initial composure to visible vulnerability, all set against the backdrop of the glamorous film festival setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth and coordinated."
}
] |
seed46_1987
|
videos/HRA_part2/1987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male cashier, dressed in a gray shirt and wearing glasses, is attentively listening with a slight smile, his head tilted to one side. He stands behind a clean, organized supermarket counter, with a large, clear space in front of him. The scene is set during the day, with good lighting from overhead lights. Beside him, a female customer, wearing a brown jacket and a colorful scarf, speaks to him, her mouth open as she engages in conversation. The setting is a modern grocery store, with shelves of products visible in the background, and the atmosphere is calm and pleasant.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2751
|
videos/HRA_part0/2751.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 street worker in Shanghai, wearing a green vest and holding a broom, gently caresses the concrete surface as he meticulously sweeps the city sidewalk. Behind him, a bustling urban landscape unfolds, with high-rise buildings, neon signs, and the occasional passerby, all set against the backdrop of a vibrant metropolis. The worker's focused gaze and the tender touch of his broom on the pavement convey a sense of care and routine amidst the dynamic energy of Shanghai's streets.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2110
|
videos/HRA_part2/2110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray jacket and khaki pants, sits cross-legged on a lush green meadow, gently caressing a docile water buffalo. The buffalo, with its large frame and distinctive horns, stands calmly beside a small body of water, accepting the student's affectionate touch. The student's serene facial expression and the peaceful surroundings, including trees and distant mountains, create a harmonious atmosphere. The scene is bathed in warm sunlight, casting a golden hue over the student and the buffalo, highlighting the tender connection between human and animal in a rural setting.]"
},
{
"from": "gpt",
"value": "Bad. The buffalo's head, the students' faces, and hands in the video have generation issues, and an item beside the buffalo's mouth suddenly disappears in the middle frame."
}
] |
seed44_2260
|
videos/HRA_part1/2260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a badger, dressed as a waiter in a crisp white shirt, black vest, and striped bow tie, crawls across a wooden floor. The room is dimly lit, with a large, elegant chandelier hanging above. The badger moves toward a grand dining table set with fine china and silverware, passing by a towering bookshelf filled with leather-bound books. The camera captures the badger's earnest expression and the intricate details of its costume, all set against the backdrop of a lavishly decorated room.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1598
|
videos/HRA_part0/1598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male writer, wearing a blue jacket, dark jeans, and brown shoes, walks through dense shrubbery in a thick forest during daytime. His hands are tucked into his pockets as he strolls, appearing lost in thought. He pauses to observe his surroundings, which include lush green foliage and towering trees. Continuing his journey, he strides confidently, navigating the uneven terrain formed by rocks and tree roots. Throughout the scene, the writer maintains a contemplative demeanor, suggesting a creative mind at work amidst the natural beauty of the woodland environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2355
|
videos/HRA_part1/2355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman in a yellow swimsuit, adorned with a floral-printed headscarf, laughs joyously as she swims in a clear blue pool, surrounded by lush greenery. Accompanied by a playful golden retriever, who energetically paddles alongside her, they both exude pure delight. The woman's infectious laughter and the dog's wagging tail encapsulate the essence of their shared aquatic adventure, set against a backdrop of swaying palm trees and bright sunlight filtering through the leaves, casting dappled shadows on the water's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2242
|
videos/HRA_part0/2242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man wearing a blue shirt, tan shorts, and brown shoes sweeps his wooden porch with a broom, against the backdrop of a sunny day and a lush green forest. He pauses for a moment to look into the distance, where a lake can be seen shimmering under the sunlight. The man resumes sweeping, revealing a clean, well-maintained porch. Suddenly, a playful dog rushes towards him, and the man stops to pat the dog affectionately, before continuing his task. The scene concludes with the man leaning against the porch railing, enjoying the peaceful surroundings and the company of his furry friend.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs in the video are missing, his face is blurry, and the cleaning tools and dog are deformed."
}
] |
seed44_2951
|
videos/HRA_part1/2951.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged farmer, donning a wide-brimmed hat and a brown leather vest, finds himself amidst a cosmic dust storm, its ethereal particles swirling around him like a celestial sandstorm under the night sky. Suddenly, the scene transforms to reveal the farmer diving into a tranquil oasis, the water shimmering with stardust from the storm, as he swims gracefully beneath the sparkling surface, encapsulating a surreal blend of earthy resilience and otherworldly enchantment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2833
|
videos/HRA_part2/2833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged farmer, clad in a red flannel shirt and denim overalls, is seen exerting effort as he pulls on a thick rope. The scene is set on a vast, green farm, with lush fields stretching into the horizon. The farmer's weathered hands grip the rope tightly, his face contorted in determination, highlighting the physical demands of his labor. Behind him, a wooden barn with a rusty roof provides a rustic backdrop, while the clear blue sky above adds a sense of serenity to the hardworking atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1815
|
videos/HRA_part2/1815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene opens with a koala, typically terrestrial, surprisingly adept in water, swimming in a serene, clear blue pool. Its brown fur glistens as it paddles with determination, showcasing an unexpected talent. The koala, wearing a small yellow swim cap, navigates the water with surprising grace, its limbs moving rhythmically. Moments later, it emerges from the pool, shaking off droplets, revealing a cozy green towel wrapped around its body. The koala then sits on the edge of the pool, seemingly pleased with its aquatic adventure, the sunlight sparkling on the water behind it.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed42_2750
|
videos/HRA_part0/2750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a red jacket, dark trousers, and white sneakers, performs energetic jumps against the backdrop of Pluto's icy mountains, which are illuminated by the distant sun. The artist's movements are exaggerated, indicating a sense of weightlessness in this extraterrestrial environment. They leap and dance, arms outstretched, as if embracing the unique landscape. The musician's animated expressions convey a mix of awe and delight, perfectly encapsulating the surreal experience of frolicking on the alien terrain of Pluto.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed46_2563
|
videos/HRA_part2/2563.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a crisp blue uniform and black shoes, stands in a spotless hallway illuminated by overhead lights, holding a large, black trash bag. Moments later, he walks down the hall, passing neatly arranged lockers, as he heads towards a propped-open exit door. Upon reaching the door, he pauses under the EXIT sign, preparing to step outside. Finally, he exits into the well-lit outdoors, walking towards a dumpster, his figure silhouetted against the bright sky, embodying the essence of hard work and cleanliness.]"
},
{
"from": "gpt",
"value": "Normal. The person's hands and feet are distorted in the video."
}
] |
seed42_2781
|
videos/HRA_part0/2781.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and scientific equipment, a police officer, dressed in a crisp uniform, carefully observes a quantum entanglement experiment. The officer, showing a surprising gentleness, caresses the edge of an intricate device, symbolizing a connection between law enforcement and cutting-edge science. Around him, scientists in lab coats monitor screens and adjust dials, creating an atmosphere of intense concentration and curiosity. The scene is bathed in the soft glow of monitors and the eerie blue light of lasers, highlighting the unusual juxtaposition of authority and scientific exploration.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_1839
|
videos/HRA_part2/1839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, prehistoric landscape under an orange sky, a group of Woolly Mammoths walk together in the distance, creating a sense of awe and grandeur. Meanwhile, in the foreground, a female caveman, dressed in furs and bearing a resemblance to a modern-day cashier, stands against a rocky outcropping, holding what appears to be ancient currency in her hand. She looks intently at the mammoths, which are walking away from her across the ancient terrain, conveying a narrative of survival and commerce in prehistoric times.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's head, legs, and body are twisted, as well as the arms and hands of the cave woman."
}
] |
seed42_2893
|
videos/HRA_part0/2893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a white chef's uniform and black apron, kneels beside a granite countertop in a modern kitchen. He focuses intently on fixing a leaky faucet, his hands working diligently with a wrench and screwdriver. The kitchen features high-end stainless steel appliances, a double sink, and sleek cabinetry. Light spills in from a nearby window, illuminating the space as the chef, adorned with a white hat and displaying a serious expression, demonstrates his skills beyond the culinary arts.]"
},
{
"from": "gpt",
"value": "Bad. The chef's movements in the video are not smooth."
}
] |
seed44_1631
|
videos/HRA_part1/1631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a vibrant yellow dress and a wide-brimmed sun hat, dances gracefully in the midst of a vast scrubland. The landscape is dotted with low-lying bushes and sparse trees, stretching far into the horizon under a clear blue sky. Her joyful movements contrast beautifully with the stillness of the arid environment, creating a captivating scene where education meets nature's tranquility. The teacher's animated gestures and warm smile convey a sense of freedom and connection to the rugged yet serene surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The character's limbs generation in the video has issues."
}
] |
seed42_3048
|
videos/HRA_part0/3048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a traditional white uniform and cap, takes a break from her medical duties to paint a hospital room a soothing shade of light blue. Holding a paintbrush in her gloved hand, she carefully applies the paint to the wall, creating a fresh and welcoming environment for the patients. The room is brightly lit, with medical equipment neatly arranged on a side table, and a window letting in natural light, casting a warm glow on the freshly painted walls. The nurse's dedication to improving the space highlights her commitment to patient care beyond her regular responsibilities.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3012
|
videos/HRA_part1/3012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 costumed astronaut chicken, clad in a white spacesuit adorned with American flags and a NASA logo, leaps high into the air on the moon's surface, against a backdrop of a dark, starry sky and the distant Earth. The chicken's joyful jump is captured in mid-air, conveying a sense of weightlessness and adventure. The scene is reminiscent of the historic moon landing, with the chicken's playful leap adding a whimsical touch to the iconic moment. The astronaut chicken's suit includes a transparent helmet, revealing its beady eyes and beak, as it bounces on the lunar surface, encapsulating the spirit of exploration and fun.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1743
|
videos/HRA_part1/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2799
|
videos/HRA_part2/2799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown trousers, is seen on set with a weasel perched on his shoulder. The weasel, with its sleek body and curious eyes, suddenly leaps off the director's shoulder, mid-air, creating a moment of unexpected levity. The director, maintaining his composure, watches the weasel's acrobatic jump with a mix of amusement and surprise, all captured against the backdrop of a bustling movie set.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1786
|
videos/HRA_part1/1786.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant green lizard, adorned with intricate patterns, traverses slowly across a weathered stone surface, basking in the warm sunlight that highlights its textured skin. Its movements are deliberate and methodical, showcasing the strength in its tiny limbs as it explores its ancient, sun-soaked environment. With each step, the lizard reveals the resilience and adaptability of nature, set against a backdrop of natural elements, including stones and plants, that have been shaped by time and the elements.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2195
|
videos/HRA_part2/2195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, temperate deciduous forest during autumn, a dedicated park ranger wearing a brown uniform and a wide-brimmed hat runs along a winding dirt trail. Surrounded by tall, leafy trees with vibrant orange and red foliage, the ranger navigates the path with focused determination. As the camera follows, we see the ranger's strong legs propelling them forward, their breath visible in the crisp air, and their eyes alert for any signs of wildlife or forest health issues. The scenery is alive with the sounds of rustling leaves, chirping birds, and the occasional distant call of a wild animal, all contributing to the immersive experience of running in a breathtaking natural environment.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the park ranger's hands and feet in the video has issues."
}
] |
seed42_3032
|
videos/HRA_part0/3032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by towering office buildings, a compassionate doctor, wearing a crisp white lab coat, leans in to gently caress the hand of a seated patient. The patient, dressed in casual attire, looks up at the doctor with gratitude, finding solace in the medical professional's empathetic touch. The scene is set inside a modern, well-lit clinic, with sleek furniture and medical equipment in the background, emphasizing the doctor's dedication to providing care in a professional environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2829
|
videos/HRA_part0/2829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 perches regally atop a wooden pole, its piercing eyes scanning the horizon over a vast, serene ocean. The bird, with its crisp white plumage and distinct black-tipped wings, contrasts beautifully against a backdrop of soft, pastel skies. It stretches its wings gracefully, preparing for flight, before taking off into the air with a powerful swoop. As it glides effortlessly over the calm waters, the seagull's silhouette becomes a striking focal point against the gentle, rolling waves and the peaceful, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Bad. The seagulls' flying movements in the video are very uncoordinated."
}
] |
seed42_1580
|
videos/HRA_part0/1580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a yellow safety vest over a gray shirt, blue jeans, and brown shoes, climbs a tall, metal, industrial ladder in a large warehouse filled with boxes and equipment. He holds a tool in his right hand and reaches up with his left, the afternoon sun shining through the high windows, casting a warm glow over the dusty space. The ladder leans against a tall shelf stacked with supplies, and the man's focus is intense as he ascends, his brows furrowed in determination. Behind him, the vastness of the warehouse stretches out, with rows of shelves disappearing into the distance, emphasizing the scale of his task.]"
},
{
"from": "gpt",
"value": "Normal. No right hand holding a tool was generated for the character."
}
] |
seed44_2114
|
videos/HRA_part1/2114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its distinctive black-and-white plumage gleaming under the sunlight filtering through the leaves of a large tree. The bird's eyes are sharp and alert, its beak curved and ready to snatch any unsuspecting prey. Behind it, the lush green foliage of the forest provides a stark contrast to its striking feathers, while the soft chirping of other birds creates a peaceful atmosphere. Suddenly, the magpie takes flight, its wings beating gracefully as it soars through the air, leaving a trail of black and white behind it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1903
|
videos/HRA_part2/1903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a thick, brown jacket and dark pants stands on a rocky ledge overlooking a vast, misty valley, preparing to leap from the cliffside. Nearby, a large brown bear, also gazing into the foggy abyss, seems unperturbed by her presence. As the scene progresses, the woman jumps off the cliff, her arms spread wide, embracing the thrill of freefall, with the bear watching intently from the edge of the precipice. Throughout, the dramatic landscape of rugged cliffs and the mysterious atmosphere of the mist-shrouded valley provide a breathtaking backdrop for this daring act.]"
},
{
"from": "gpt",
"value": "Bad. The woman's action of jumping off the cliff with her arms spread wide in the video is not continuous and has a sudden change."
}
] |
seed46_143
|
videos/HRA_part2/143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, dressed in a white lab coat over khaki cargo pants and brown leather shoes, runs through a lush, green jungle environment. In his right hand, he holds a clear, plastic container housing a live lizard, which scurries about inside. The doctor navigates through the dense foliage, dodging vines and leaping over fallen logs, his face set with determination as he focuses on his mission. The vibrant greenery of the jungle provides a stark contrast to the doctor's attire, highlighting the unusual nature of this scenario.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's legs show signs of mutation and deformation, and the fingers also exhibit deformities."
}
] |
seed46_2868
|
videos/HRA_part2/2868.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene from a Space Reality TV Show, a waiter, dressed in a crisp white shirt and black pants, kneels down with a perplexed expression, observing a tiny hamster crawling across a futuristic, metallic surface. The hamster, wearing a miniature astronaut suit, explores its surroundings with curiosity, its movements captured in close-up detail. The waiter, now sitting cross-legged, watches the hamster with growing amusement, as the tiny astronaut continues its journey across the space station's gleaming floor, the vastness of space visible through large windows in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2573
|
videos/HRA_part1/2573.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sit cross-legged on a wooden deck, surrounded by three small dogs. The boy, wearing a yellow shirt and blue shorts, carefully scoops kibble from a green bowl into his hand, offering it to a white and brown terrier who eagerly licks his palm. Meanwhile, the girl, clad in a pink dress, giggles as she holds out a piece of dog food to a black pug, who sniffs it before gently taking it from her fingers. In the background, a third dog, a golden retriever, patiently waits its turn, sitting attentively near the edge of the deck, as the siblings take turns feeding the pets under the warm glow of afternoon sunlight.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted, as well as the dog's face and legs."
}
] |
seed44_1280
|
videos/HRA_part1/1280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge and a walkie-talkie on his belt, walks through a museum filled with historical artifacts. The museum exhibits a variety of items, including ancient statues, paintings, and glass cases displaying precious jewels. The officer's path takes him past a large statue, a painting of a woman, and a glass case containing a crown, as he ensures the safety and security of the museum's valuable collections. The museum's interior is grand, featuring high ceilings, marble floors, and ornate decorations, providing a fitting backdrop for the treasures it houses.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2858
|
videos/HRA_part0/2858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh cod fish is presented on a bed of ice, its body glistening under bright lights. The fish has a distinct silver hue, with large, clear eyes and tightly closed gills, indicating its freshness. Its scales reflect the light, and the texture of the skin is smooth yet firm. In the background, other seafood items can be seen, hinting at a bustling market setting where various fish are displayed on ice. The focus remains on the cod, which takes center stage, showcasing its size and quality in vivid detail.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the cod's mouth in the video has issues."
}
] |
seed46_2181
|
videos/HRA_part2/2181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern soars gracefully through the air, its large size and robust build evident as it navigates the skies above a serene coastal landscape. With a striking orange-red bill that is thick and strong, this bird exemplifies power and agility. Its plumage is predominantly white, with a faint tinge of grey on the back, and its wings display black tips that contrast beautifully with the rest of its feathers. As it glides over the water, the tern's keen eyes search for prey, showcasing its hunting prowess against the backdrop of a calm sea and a clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3181
|
videos/HRA_part2/3181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an underwater scene illuminated by natural light filtering through the water's surface, a school of vibrant, multicolored fish swim together in unison. The fish display a range of hues, including orange, yellow, and blue, with intricate patterns adorning their scales. They gracefully navigate the aquatic environment, surrounded by lush green seaweed gently swaying in the current. The detailed textures of the fish's bodies and the vivid colors of their surroundings create a captivating and serene underwater world.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show blue fish."
}
] |
seed46_20
|
videos/HRA_part2/20.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1230
|
videos/HRA_part2/1230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 urban park during daytime, a spotted bobcat crouches low on the lush grass, its ears perked and eyes alert, showcasing its wild nature in an unexpected setting. Moments later, it wipes its face with its paw, an intimate grooming gesture, revealing its untamed yet vulnerable side. The bobcat then pauses, sitting upright with its tail curled, offering a rare glimpse into its daily life. It continues to groom itself, licking its paw and wiping its face again, all while surrounded by the peaceful atmosphere of the park, highlighting the juxtaposition of wilderness and civilization.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_191
|
videos/HRA_part0/191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, cosmic setting, a cashier, clad in a unique space suit adorned with symbols of diplomacy, traverses the mammoth hall of an intergalactic embassy. She walks with purpose, passing through a grand archway, her eyes set on a distant goal. Behind her, a massive window reveals the breathtaking expanse of stars and galaxies, highlighting the enormity of her mission among the celestial bodies. Her every step echoes in the spacious corridor, resonating with the gravity of her role in maintaining galactic peace.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1
|
videos/HRA_part1/1.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the golden glow of twilight, a slender, reddish-brown jackal stands out against a sandy desert landscape, its piercing eyes and alert ears capturing the viewer's attention. It begins to move gracefully, its body swaying in a dance-like motion, as if responding to an unheard melody. The jackal's fluid movements are juxtaposed against the stillness of the desert, creating a mesmerizing scene where nature and rhythm intertwine. Its agile form, framed by the warm hues of the setting sun, tells a story of survival and spirit in the vast wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, and there are sudden changes in the limbs."
}
] |
seed42_2891
|
videos/HRA_part0/2891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 miniature giraffe, no taller than a foot, crawls slowly across the surface of a vast, cosmic solar sail, its fabric shimmering with ethereal light against the backdrop of a star-studded universe. The giraffe, with its distinctive pattern and gentle demeanor, moves deliberately, exploring the alien landscape as if it were a terrestrial savanna. The sail, stretched taut and capturing the rays of a distant sun, provides a mesmerizing contrast to the earthly creature traversing its surface, creating a dreamlike juxtaposition between the terrestrial and the celestial.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe in the video is not a few inches tall."
}
] |
seed44_1320
|
videos/HRA_part1/1320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic store, a cashier with a holographic display projects a swirling black hole singularity above a checkout counter, where items are being scanned and bagged. The cashier, wearing a uniform with high-tech accents, interacts with the singularity using gestures, demonstrating advanced technology integration. Nearby, a cleaning robot with a compact design moves efficiently, wiping surfaces with precision and leaving everything spotless. The cashier's movements are fluid and practiced, showing expertise in handling the cosmic phenomenon, while the robot's efficiency underscores the seamless blend of everyday tasks and extraordinary phenomena in this setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1105
|
videos/HRA_part1/1105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge clearly visible, traverses a vast wetland landscape, the lush greenery contrasting sharply with his authoritative attire. He is seen wading through shallow water, his boots partially submerged, indicating a purposeful journey through this natural terrain. Moments later, he is fully immersed in swimming, his uniform now soaked, navigating the intricate network of waterways under a cloudy sky. This scene captures the unexpected sight of a law enforcement figure engaging with the wild, uncharted environment of the wetlands.]"
},
{
"from": "gpt",
"value": "Bad. The police officer in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_3204
|
videos/HRA_part0/3204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A bearded male musician, wearing a brown hat and a blue shirt with suspenders, sits against a plain gray backdrop. He is knitting a long, cream-colored scarf with large needles, showcasing his dexterity. In another scene, he holds the growing scarf in his hands, his facial expression one of concentration. Next, he looks directly at the camera, his eyes conveying a sense of peace and contentment. Finally, he continues knitting, his fingers moving skillfully, set against the simple gray background that emphasizes his artistic endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The action of knitting is slightly discontinuous, with sudden changes."
}
] |
seed42_1035
|
videos/HRA_part0/1035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform complete with badge, gun holster, and radio, is engaged in an unexpected task. He is seen from behind, bending over a small hole in the ground, which is surrounded by a ring of yellow tape. His right hand is plunged into the hole, indicating he is unclogging a drain. The location appears to be a public park, with green grass and trees in the background, and a group of people watching the unusual scene from a distance, their expressions a mix of amusement and curiosity. A yellow sign with the words \"Caution, Wet Floor\" leans against a nearby tree, adding to the surreal atmosphere of the situation.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed44_2322
|
videos/HRA_part1/2322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a backdrop of lush greenery and blue skies, two young boys, one wearing a yellow shirt and the other in red, are intently engaged in fixing a wooden fence. They work diligently, using a variety of tools spread out before them, their faces concentrated and serious as they tackle the task at hand. One boy, dressed in a yellow shirt, blue shorts, and brown shoes, leans against the fence, his hands busy with repair work, while the other, in a red shirt, khaki shorts, and blue sneakers, stands with a tool in hand, ready to assist. The scene captures the industrious spirit of childhood play, with the boys' clothes and tools adding vibrant details to the image.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2742
|
videos/HRA_part1/2742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, temperate rainforest, a janitor, dressed in a yellow vest and dark green pants, leaps over a fallen log with surprising agility. Surrounded by towering trees and dense foliage, he lands gracefully on the mossy ground, his movements deft and sure. As he continues his unlikely journey, bounding from one natural obstacle to another, the vibrant greens of the forest serve as a striking contrast to his utilitarian attire. Throughout this unexpected scene, the janitor's expression is one of focused determination, his form mid-jump captured against the backdrop of the rainforest's rich biodiversity.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_2845
|
videos/HRA_part1/2845.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the lush greenery of a tropical rainforest, twin toddlers, a boy and a girl, crawl on a mossy rock near a cascading waterfall, their clothing soaked from the water. The boy wears a red shirt and gray shorts, while the girl is dressed in a pink top and yellow shorts, both sporting wide smiles as they explore their watery surroundings. Their crawling movements contrast with the powerful rush of the waterfall, creating a dynamic scene of innocence and nature's grandeur. The camera captures this intimate moment, focusing on the children's expressions of wonder and joy as they interact with the natural world around them.]"
},
{
"from": "gpt",
"value": "Normal. The faces of the boy and girl in the video are slightly blurred, the fingers are poorly generated, and the girl's body is distorted."
}
] |
seed46_2061
|
videos/HRA_part2/2061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a vibrant red tank top and black leggings, runs across a sandy trail in a lush, green forest. Her brown curly hair bounces as she moves with determination. A small, agile lizard scurries across the path ahead of her, its quick movements catching her attention. The woman momentarily looks down at the lizard, her eyes widening in surprise, before refocusing on her run, her strides strong and purposeful against the backdrop of towering trees and dappled sunlight.]"
},
{
"from": "gpt",
"value": "Bad. The lady's running movements in the video are not very continuous and smooth."
}
] |
seed42_1597
|
videos/HRA_part0/1597.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": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2960
|
videos/HRA_part1/2960.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a blue jacket and jeans, walks purposefully across a vast, otherworldly landscape illuminated by the ethereal glow of a nearby galactic nebula. The scene opens with the student standing in the foreground, looking intently ahead, with the majestic nebula casting a soft, cosmic light over the terrain. As the student strides forward, the camera captures the detail of their journey, highlighting the unique features of the alien landscape. With each step, the student's determination is evident, their silhouette framed against the mesmerizing backdrop of the swirling nebula. The final shot lingers on the student's resolute figure, now further along the path, continuing their solitary trek under the watchful gaze of the celestial wonder above.]"
},
{
"from": "gpt",
"value": "Normal. The student walks basically normally in the video, but there is slight uncoordination in the movements."
}
] |
seed44_2387
|
videos/HRA_part1/2387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a vibrant yellow jacket and khaki shorts, walks along a dirt path near a watering hole, where a hippopotamus lazily wallows in the cool mud. In the distance, the Martian landscape unfolds, with its rusty red dunes and sparse vegetation silhouetted against a sunset painted in hues of violet and orange. The celestial event casts a warm glow over the scene, highlighting the unique juxtaposition of Earthly life and extraterrestrial beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2146
|
videos/HRA_part1/2146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ghost shrimp, nearly transparent with greyish-blue tones, clings to a piece of driftwood submerged in a freshwater aquarium. Its delicate antennae and legs are clearly visible, showcasing its intricate anatomy. Nearby, water bubbles softly, adding a gentle ambience to the scene. The shrimp's translucent body allows a view of its internal organs, emphasizing its unique characteristic. Surrounded by aquatic plants and gravel, the ghost shrimp appears in sharp focus against the slightly blurred environment, highlighting its presence in the tank.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1855
|
videos/HRA_part2/1855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bespectacled female doctor in a white lab coat, adorned with colorful pins, dances energetically in a spacious, well-lit room. Her attire includes a vibrant red blouse and stylish glasses, adding to her lively appearance. In her arms, she cradles a relaxed, curious ferret, which seems unperturbed by the dancing. The pair moves in sync, the doctor's joyful expression and the ferret's inquisitive gaze capturing the essence of an unexpected yet delightful moment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1860
|
videos/HRA_part2/1860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, sun-dappled forest, a small, bushy-tailed squirrel gently caresses a smooth, brown egg nestled among vibrant green moss on a flat rock. The squirrel, with its soft, gray fur and alert eyes, tenderly touches the egg with its tiny paws, creating a heartwarming scene of unexpected care. The lush surroundings include tall trees, filtered sunlight, and a variety of foliage, adding depth and texture to the intimate moment shared between the squirrel and the fragile egg.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel's paws and face are distorted in the video."
}
] |
seed44_2045
|
videos/HRA_part1/2045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A giant panda, identifiable by its distinctive black and white fur, walks through a bustling cityscape filled with towering skyscrapers, neon signs, and busy streets. It navigates the urban environment with a curious yet calm demeanor, passing by modern architecture and city life, creating a surreal juxtaposition between nature and metropolis. The panda's presence among the high-rise buildings and urban hustle highlights an unexpected encounter between wildlife and the human-built world.]"
},
{
"from": "gpt",
"value": "Bad. The panda's walking movements in the video can be clearly seen, but they are not continuous and coordinated."
}
] |
seed44_2808
|
videos/HRA_part1/2808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a black jacket and blue jeans, is seen caressing a kangaroo at a busy bus stop in the heart of a city. The scene opens with the actor standing next to the marsupial, both seemingly waiting for a bus amidst the urban landscape filled with pedestrians and traffic. As the camera focuses, the actor gently strokes the kangaroo's back, showing a tender connection between them. The kangaroo, unperturbed by the surroundings, leans into the touch, its eyes closed in apparent comfort. Behind them, the bustling city life continues, with cars passing by and people going about their day, creating a contrast to the intimate moment shared between the actor and the kangaroo.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1585
|
videos/HRA_part0/1585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a costume resembling a zebra, performs an athletic jump against a background that appears to be a theater stage. The zebra outfit is detailed, featuring black and white stripes, and the actor's face is visible, showing intense concentration. The leap is captured mid-air, highlighting the actor's agility and the costume's dynamic movement, creating a dramatic and captivating scene under the spotlight.]"
},
{
"from": "gpt",
"value": "Bad. The actor in the video has missing limbs, incomplete fingers, no eyes, and a distorted body."
}
] |
seed42_253
|
videos/HRA_part0/253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 peacock, resplendent in its vivid blue and green plumage, struts regally across a lush, verdant garden, the sunlight dappling its feathers in a mesmerizing play of light and shadow. Its proud head, adorned with a striking crest, swivels gracefully as it surveys its domain. Suddenly, the peacock spreads its spectacular tail, revealing an eye-popping display of iridescent ocelli that seem to shimmer with an otherworldly glow. The air is filled with the rich, earthy scents of the foliage surrounding the bird, adding depth to this enchanting scene.]"
},
{
"from": "gpt",
"value": "Normal. The peacock's movements in the video are basically normal, with slight disharmony."
}
] |
seed46_2927
|
videos/HRA_part2/2927.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural backyard filled with lush greenery and wooden fences, two young children, a boy in a red shirt and blue shorts and a girl in a yellow dress, chase after a lively chicken, their laughter echoing in the sunny afternoon. The boy, with short brown hair, and the girl, her hair tied in pigtails, gleefully pursue the bird across the yard. Their playful antics are framed by a background of vibrant green trees and shrubs, with the chicken's colorful feathers standing out against the natural setting. The scene captures a moment of innocent childhood joy, with the children's faces alight with excitement and the chicken adding a touch of whimsy to the idyllic outdoor space.]"
},
{
"from": "gpt",
"value": "Bad. The child's face is distorted, hands are twisted, arms are twisted, legs are twisted, chicken head is distorted, and claws are twisted."
}
] |
seed42_332
|
videos/HRA_part0/332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, attired in a khaki safari outfit, navigates through the dense undergrowth of a tropical dry forest. The sunlight filters through the canopy, casting dappled shadows on the rugged terrain. Lush, gnarled trees surround him, their leaves whispering in the gentle breeze. Insects buzz softly in the background, adding to the ambiance of the wild. The director walks purposefully, his boots crunching on the carpet of fallen leaves and twigs, holding a detailed map in one hand and occasionally stopping to consult it, his focus intense and unwavering.]"
},
{
"from": "gpt",
"value": "Normal. The director's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed42_1164
|
videos/HRA_part0/1164.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, donning a casual striped shirt and khaki pants, meticulously vacuums the living room of her cozy home, her curly brown hair bouncing as she moves. The room is filled with natural light, illuminating the space as she expertly maneuvers the vacuum cleaner, ensuring no spot is left untouched. Her dedication to tidiness is evident in the neat arrangement of books on the shelves and the absence of clutter, creating a peaceful environment. This scene captures the teacher's commitment to cleanliness and order, even in her personal life, as she takes a break from her educational duties to tend to household chores.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand appears deformed."
}
] |
seed46_104
|
videos/HRA_part2/104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a gray jacket and blue jeans, walks through the lush greenery of a botanical garden, surrounded by vibrant flowers and towering trees. They pause to examine a particularly interesting plant, their backpack resting on the ground beside them. The sunlight filters through the leaves overhead, casting dappled shadows on the path. In the background, the serene sound of a nearby fountain can be heard, adding to the peaceful atmosphere of the scene. The student continues on their leisurely stroll, taking in the beauty of nature around them.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted, the legs are deformed, and one arm is missing."
}
] |
seed46_1796
|
videos/HRA_part2/1796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest, white shirt, and black trousers, crawls through a network of meerkat tunnels. The tunnels are meticulously crafted from sandy soil, with intricate pathways and chambers. The waiter, displaying a sense of adventure and playfulness, carefully navigates the tight spaces, his movements mimicking those of the meerkats that typically inhabit these underground structures. His attire remains remarkably clean and undisturbed despite the crawling, highlighting the surreal nature of the scenario.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, with uncoordinated movements."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.