video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_102
|
videos/HRA_part1/102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum-like setting filled with art galleries, a sleek and powerful jaguar, adorned with a golden collar, walks gracefully among the exhibits. The feline's presence captivates the attention, as it moves elegantly through the spacious hall, surrounded by classical sculptures and Renaissance paintings. Its confident stride and majestic demeanor contrast beautifully with the artistic masterpieces displayed on the walls, creating a unique juxtaposition between nature and culture. The golden collar it wears adds a touch of sophistication, making the jaguar appear almost like a living exhibit within the gallery space.]"
},
{
"from": "gpt",
"value": "Bad. The jaguar's walking movements in the video are not very smooth, and there is a lack of coordination."
}
] |
seed42_2736
|
videos/HRA_part0/2736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cave, a small brown bat, with leathery wings folded against its body, walks along the rocky ground with deliberate steps. Its face, framed by long, curved ears, is keenly observant. The bat pauses momentarily, revealing its tiny feet and claws as it navigates the stone surface. The focus then shifts to the bat's head, highlighting its intricate facial features and alert eyes. Finally, the bat is seen walking away, its silhouette set against the textured cave wall, creating a captivating scene of a bat navigating its environment on foot.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_116
|
videos/HRA_part2/116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green valley, a hardworking man in a blue shirt and beige pants is crawling on his hands and knees, inspecting the rich soil for cultivation. Nearby, an otter playfully frolics in a clear, bubbling stream, its antics providing a charming contrast to the industrious human activity. The setting is idyllic, with rolling hills framing the scene, and the worker's dedication to his craft is evident in his meticulous attention to the land. The otter, seemingly unperturbed by the presence of the human, continues its joyful exploration, highlighting the harmonious coexistence between nature and humanity in this tranquil valley.]"
},
{
"from": "gpt",
"value": "Normal. The otter's movements in the video are not smooth."
}
] |
seed46_2938
|
videos/HRA_part2/2938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged nurse with blonde hair tied in a bun, wearing a blue scrub top and black pants, is seen in a small, cluttered kitchen. She's meticulously loading a white ceramic plate into the bottom rack of a stainless steel dishwasher, demonstrating her domestic skills. The kitchen is filled with natural light, casting a warm glow over the room, and the nurse's attention to detail is evident as she carefully arranges the dishes. Despite the busy environment, with pots and pans scattered about, she maintains a sense of calm and order as she performs this household task.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's fingers are deformed, the arm is partially missing, and the plate is deformed."
}
] |
seed44_2869
|
videos/HRA_part1/2869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional nurse, clad in a light blue scrubs top and dark blue scrubs pants, sits attentively at a desk in a modern hospital setting, her hands deftly typing on a laptop keyboard. Behind her, the bustling hospital environment is visible, adding context to her role. She wears her hair in a neat bun, and her focused gaze is directed at the screen, indicating her concentration on the task at hand. Despite the busy surroundings, she maintains a calm demeanor, highlighting her dedication to her work in the healthcare field.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2227
|
videos/HRA_part2/2227.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a charming smile, wearing a casual graphic T-shirt and dark jeans, is laughing joyously. Her laughter is contagious as she throws her head back, her wavy brown hair cascading down her shoulders. The scene is set in a cozy living room with wooden floors and a white couch, adding to the warm and intimate atmosphere. Her joyful expression, complete with closed eyes and a wide grin, radiates happiness, making the viewer feel like they're sharing in her delight.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_261
|
videos/HRA_part2/261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, wearing a gray t-shirt and jeans, attentively waters lush green plants arranged in a neat row against a plain studio wall. He begins by pouring water from a green watering can onto the first plant, a potted ficus. Next, he moves to the second plant, a healthy monstera, continuing his task with care. Then, he focuses on the third plant, a vibrant snake plant, ensuring each receives adequate hydration. Lastly, he tends to the fourth plant, a thriving peace lily, completing the sequence with dedication, all within the simple yet functional confines of the studio space.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand appears deformed, and the kettle also becomes distorted."
}
] |
seed42_2580
|
videos/HRA_part0/2580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, captured in high definition, is seen grooming itself by wiping its face with a flipper. The otter, with its brown fur and small, round ears, sits upright on a rocky shore, the surface speckled with white stones. The background features a lush green forest, with tall trees standing majestically against a bright sky. The otter pauses, looking directly at the camera with curious eyes, before continuing its self-cleaning ritual, creating a captivating moment in nature.]"
},
{
"from": "gpt",
"value": "Normal. The otter's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed46_2242
|
videos/HRA_part2/2242.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 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 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": "Good. Basically no problem."
}
] |
seed44_2099
|
videos/HRA_part1/2099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, donning a yellow hard hat, orange safety vest, and blue jeans, sits on a wooden crate at a bustling construction site. Surrounded by scaffolding, concrete mixers, and cranes, he meticulously draws architectural plans using a pencil and a large blueprint sheet laid out on a makeshift plywood table, illustrating his dual skills in both physical labor and design. The scene captures his focused expression and the gritty urban environment, highlighting the blend of creativity and labor in his work.]"
},
{
"from": "gpt",
"value": "Normal. The worker's hands and feet in the video have generation issues."
}
] |
seed44_2767
|
videos/HRA_part1/2767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a black uniform with a red vest and a bow tie, walks across a vast, icy landscape, surrounded by towering glaciers and rugged terrain. He carries a silver tray with a glass of champagne, balancing it gracefully as he strides forward. The scene is set against a backdrop of dramatic, icy mountains, with the waiter's polished shoes and formal attire contrasting starkly with the rugged, snow-covered ground. Despite the harsh environment, he moves with poise and determination, the luxurious glass of champagne glistening under the pale arctic sun.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1498
|
videos/HRA_part1/1498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 single zebra, its distinctive black and white stripes gleaming under the golden savanna sun, is sprinting across a vast, grassy plain. The muscles in its legs are taut, demonstrating raw power and grace as it leaps over tufts of grass. The zebra's mane flutters in the wind, adding to the sense of motion and freedom. Dust kicks up from the zebra's hooves as it races, highlighting the speed and agility of this magnificent creature. Behind the zebra, the landscape stretches to a distant horizon, dotted with acacia trees and the faint outlines of other wildlife, providing context for the zebra's natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The zebra's head and legs are twisted in the video."
}
] |
seed42_1492
|
videos/HRA_part0/1492.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in casual attire of a gray shirt and black shorts, playfully swings a bat at a small pinata hanging from a tree branch in a backyard setting, surrounded by lush greenery. Moments later, the same student is seen enjoying a refreshing swim in a backyard pool, splashing about in a yellow swimsuit, with a diving board visible in the background. The scene captures the essence of youthful fun and leisure activities, transitioning seamlessly from a game of bat-and-ball to a spontaneous dip in the pool.]"
},
{
"from": "gpt",
"value": "Bad. The face and hands of the person in the video, as well as the bat they are holding, are generated abnormally."
}
] |
seed46_2376
|
videos/HRA_part2/2376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, vibrant green lizard with intricate patterns on its back traverses slowly across a dry, cracked earth surface, its movements deliberate and methodical. The terrain is peppered with small rocks and tufts of sparse vegetation, providing contrast against the lizard's vivid coloring. Sunlight filters down, casting dappled shadows and highlighting the texture of the lizard's skin as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Bad. The lizard in the video has a twisted body, head, feet, and legs."
}
] |
seed46_1849
|
videos/HRA_part2/1849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary vulture, with its distinctive bald head and dark plumage, perches majestically on a rocky outcropping, overlooking a vast, arid landscape under an overcast sky. Its powerful, hooked beak is slightly open, revealing its pinkish-red interior, while its piercing eyes survey the terrain for potential prey. The bird's textured skin and feather details are highlighted by the natural lighting, emphasizing its rugged survival instincts in the harsh environment. As it prepares to take flight, the vulture's wings spread wide, displaying their impressive span against the muted tones of the rocky surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3147
|
videos/HRA_part0/3147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a chimpanzee, wearing a small red apron, sits at a cash register typically found in a grocery store. The primate's eyes are closed as it receives a gentle caress from a human hand, which is softly petting its head, evoking a sense of calm and trust between the species. The chimpanzee's relaxed posture and closed eyes indicate a feeling of comfort and safety during this intimate interaction, set against the backdrop of a familiar checkout counter environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1440
|
videos/HRA_part0/1440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic individual named Jay, donning a dark blue cap, aviator sunglasses, and a gray shirt, is captured in high-definition. Initially, he is seen against a backdrop of lush greenery, standing tall with his hands on his hips, exuding confidence. The scene then focuses on his face, highlighting his stylish appearance and a slight smile. Next, Jay is shown from behind, gazing out at a stunning mountainous landscape, conveying a sense of adventure. Finally, he raises his right arm, pointing at something exciting in the distance, his silhouette framed by the natural beauty around him, encapsulating the essence of an outdoor enthusiast.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2644
|
videos/HRA_part2/2644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short, brown hair and a trimmed beard sits in a dimly lit room, wearing a casual gray t-shirt and black hoodie. He looks concerned as he holds his glasses in his right hand, resting on his knee. Suddenly, he coughs into his left hand, covering his mouth, with a worried expression on his face. The scene is set in an intimate space, capturing the man's discomfort and vulnerability during his unexpected coughing fit.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated coughing movements."
}
] |
seed44_1075
|
videos/HRA_part1/1075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and khaki pants, stands in a lush, green forest clearing, gently wiping mud off the antlers of a majestic deer using a soft cloth. The deer, with large, inquisitive eyes, tolerates the man's ministrations, standing still as the man carefully cleans each tine of the impressive antlers. Sunlight filters through the canopy above, casting dappled shadows on the scene below, highlighting the tender interaction between the man and the wild creature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1406
|
videos/HRA_part1/1406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate writer, donning a dark green blazer over a white shirt, is depicted against a backdrop of space exploration imagery, including astronauts and planets. Initially, she stands pensively, holding a book with both hands, her gaze directed downward. Then, she looks up, her expression shifting to one of determination, as if contemplating the vastness of space. Next, she is shown dancing energetically, her right arm raised, embodying the joy and freedom of movement. Finally, she strikes a confident pose, her left hand resting on her hip, her eyes gazing into the distance, encapsulating the spirit of adventure and creativity in the realm of space exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1314
|
videos/HRA_part2/1314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, snow-dusted wilderness, two majestic bison stand side by side, their large, sturdy bodies nearly touching. One bison gently nudges the other with its snout in a tender caress, their breath visible in the crisp air. Their shaggy coats ripple slightly in the wind, and their eyes meet, conveying a deep bond. The scene is peaceful and intimate, set against a backdrop of distant mountains and a clear blue sky, highlighting the gentle nature of these powerful creatures.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the bison in the video is problematic; their faces overlap and become unclear when they touch."
}
] |
seed44_2235
|
videos/HRA_part1/2235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala clad in a tiny business suit scampers across a bustling cityscape, its fluffy ears bouncing as it weaves between the legs of hurried office workers. The koala, wearing a miniature tie and vest, darts through the concrete jungle, leaping over cracks in the sidewalk and dodging rolling suitcases. Its button nose and round eyes convey determination as it races toward an imposing glass skyscraper, its reflection merging with the building's sleek facade. The koala's paw steps on the polished marble floor echo through the cavernous lobby, drawing curious glances from suited professionals, who pause in their daily routines to watch the unexpected visitor sprint toward the elevators.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2538
|
videos/HRA_part2/2538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, identifiable by his wedding ring, enjoys a leisurely hike in a rural mountainous area, wearing a white button-down shirt and khaki pants, a departure from his usual doctor's attire. He pauses to admire the stunning landscape, which includes lush greenery, rocky terrain, and distant mountain peaks, all under a clear blue sky. Carrying a walking stick and backpack, he navigates the rugged trail with ease, embodying the spirit of adventure and the great outdoors. As he continues his journey, he occasionally checks his phone, perhaps communicating with loved ones or colleagues from his medical profession.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1926
|
videos/HRA_part0/1926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, remarkably preserved and glowing with bioluminescence, orbits the Earth in a dreamlike sequence, passing over a city skyline with bright lights twinkling below. The scene transitions to the mammoth swimming gracefully underwater in a vast, clear ocean, its massive body moving effortlessly among schools of colorful fish. The camera then pulls back to reveal the mammoth floating in space once again, the blue planet Earth serving as a majestic backdrop, before returning to the serene underwater environment where it continues to swim peacefully, a surreal juxtaposition of ancient life and cosmic wonder.]"
},
{
"from": "gpt",
"value": "Normal. Almost static."
}
] |
seed46_1293
|
videos/HRA_part2/1293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a pristine white uniform and wearing a red bandana, walks across a rocky Martian landscape under a starlit sky. Holding a large, clear bowl that reflects the celestial beauty above, the chef pauses to gaze upwards, captivated by the distant stars. With the vast Martian terrain spread out behind, the scene conveys a sense of wonder and exploration, as the chef embarks on a unique stargazing experience on the Red Planet.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1519
|
videos/HRA_part1/1519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished middle-aged doctor, wearing a white lab coat over a navy blue shirt, sits in a cozy, dimly lit pub, sipping a glass of red wine. The pub is filled with the warm glow of hanging lights and a fireplace, creating a relaxed atmosphere. The doctor, with short brown hair and a neatly trimmed beard, leans back in his chair, holding the stem of the wineglass, and gazes thoughtfully into the distance. The scene conveys a sense of calm and tranquility, with the doctor enjoying a moment of respite from his busy medical career.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_14
|
videos/HRA_part2/14.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male teacher, wearing a gray sweater over a button-down shirt, yawns dramatically in a classroom filled with desks, capturing a candid moment during a school day. His eyes are closed, his mouth is wide open, and his right hand is holding a red pen, while stacks of papers and books clutter the desk in front of him. The walls are adorned with educational posters, and sunlight streams in from a nearby window, illuminating the room. This intimate scene portrays the relatable, unguarded moment of a dedicated educator succumbing to a yawn amidst his daily responsibilities.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1422
|
videos/HRA_part2/1422.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clean-shaven male chef with short brown hair waves energetically with his right hand, standing in front of a vibrant green wall adorned with a pattern of white dots. He wears a traditional white chef's uniform with a black necktie, and his left hand rests comfortably in his pocket. The chef's warm smile and engaging demeanor convey a sense of welcome and enthusiasm, perfect for a cooking show introduction or a restaurant greeting.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted in the video."
}
] |
seed46_22
|
videos/HRA_part2/22.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bundled in a heavy coat, mittens, and a woolen cap, stands beside a friendly moose in a quaint village setting marked by wooden houses and snow-covered landscapes. The student gently wipes snowflakes from the moose's antlers, both gazing into the camera with a sense of camaraderie. Behind them, smoke rises from chimneys, indicating the warmth of homes in the cold environment. The scene is set during the golden hour, with soft, warm light casting long shadows across the snow, creating a cozy and welcoming atmosphere in the village.]"
},
{
"from": "gpt",
"value": "Normal. The character's action of removing snow from the moose's antlers in the video is not smooth and uncoordinated."
}
] |
seed44_1313
|
videos/HRA_part1/1313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene unfolds on a bustling Shanghai street, where a creative writer, dressed in a brown jacket and khaki pants, kneels on the pavement, engrossed in scribbling notes. Beside them, an unexpected giraffe, adorned with a red bow tie, also kneels, observing the writer with curiosity. The vibrant urban landscape, filled with pedestrians and vehicles, serves as a lively backdrop, contrasting the unusual duo's focused yet peculiar crawling position on the crowded sidewalk.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are distorted, the face is distorted, the legs are distorted, the giraffe's face is distorted, and the legs are distorted."
}
] |
seed42_3179
|
videos/HRA_part0/3179.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 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 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": "Good. Basically no issues."
}
] |
seed42_1615
|
videos/HRA_part0/1615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate nurse, dressed in a sky-blue scrubs top and matching cap, tends to a patient in an expansive, sunlit grassland. She gently wipes the patient's face with a soft cloth, her caring demeanor evident in her focused eyes and gentle smile. The serene landscape of tall, swaying grass and distant, rolling hills provides a peaceful backdrop to the intimate moment of care. The nurse's attire, emblematic of her profession, contrasts beautifully with the lush greenery, highlighting her role as a caregiver in this unexpected outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's hands in the video were poorly generated."
}
] |
seed42_1870
|
videos/HRA_part0/1870.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor wearing a black t-shirt and dark jeans is seen running alongside a large, energetic yellow dog in an expansive park. The two are captured mid-stride, with the actor's focused gaze and the dog's joyful expression highlighting their shared activity. They run together in harmony, the actor's casual attire and the dog's bounding energy creating a dynamic and engaging scene against the lush greenery of the park.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_180
|
videos/HRA_part0/180.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, a director wearing a black jacket, blue jeans, and a wide-brimmed hat is seen intently choreographing a dance sequence. The dancers, dressed in flowing white garments, perform intricate steps amidst the tall, gnarled trees and dappled sunlight. The director gestures dramatically, guiding the dancers through their routine, while the vibrant green foliage and unique flora of the subtropical dry forest provide a stunning natural backdrop. Throughout the scene, the focus remains on the passionate direction and the captivating dance performance set within the enchanting forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, legs, and hands."
}
] |
seed46_227
|
videos/HRA_part2/227.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, middle-aged farmer with a short beard, dressed in a green flannel shirt, brown vest, brown trousers, and brown boots, hikes across a lush, green pasture. The vibrant colors of his clothing contrast beautifully with the verdant landscape. In the first scene, he pauses to look up at the sky, which is partly cloudy, indicating a pleasant day. Then, he continues hiking, walking uphill towards a dense forest in the distance, the rolling hills providing a stunning backdrop. Next, he stops to observe a group of sheep grazing nearby, his presence conveying a sense of peace and harmony with nature. Lastly, he is seen walking along a narrow path bordered by tall grass, his figure becoming smaller as he moves further away, encapsulating the spirit of adventure and connection to the land.]"
},
{
"from": "gpt",
"value": "Normal. The man's limbs in the video are missing."
}
] |
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 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: [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": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_1093
|
videos/HRA_part2/1093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over casual attire, stands pensively on a pier overlooking a serene lake, the sky a blend of sunset orange and twilight blue. Moments later, he is seen in mid-air, having leaped from the pier, his arms spread wide in a joyful gesture. His lab coat flutters dramatically in the wind as he soars above the water, about to plunge into the lake's calm surface, the fading sunlight casting a golden glow over the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1933
|
videos/HRA_part1/1933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a yellow shirt and blue jeans is seen in a close-up, wiping his forehead with the back of his hand, looking weary yet determined. Beside him, a kangaroo with a brownish-gray coat stands on its hind legs, its curious face and large ears turning toward the farmer. The kangaroo then mimics the farmer's action, using its paw to wipe its own forehead, adding a humorous touch to the scene, all set against the backdrop of a rural farm with wooden fences and lush green fields under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2211
|
videos/HRA_part1/2211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape filled with vibrant greenery and ancient flora, a colossal woolly mammoth tenderly caresses another smaller mammoth with its trunk, showcasing a rare, intimate moment between these majestic creatures. The larger mammoth, adorned with thick, shaggy fur and imposing tusks, gently touches the younger one, whose eyes reflect curiosity and trust. The backdrop features a dense forest, with sunlight filtering through the canopy, casting dappled shadows on the ground, highlighting the tenderness and connection shared between the two mammoths.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1317
|
videos/HRA_part0/1317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-known actor, dressed in a black turtleneck and dark jeans, sits on a lush, green meadow with a large, brown bear. The actor gently caresses the bear's fur, showing a bond between man and beast. The bear, unperturbed by the human presence, leans into the touch, revealing a surprising tenderness. The scene is peaceful, with the verdant landscape and clear blue sky providing a serene backdrop to this unlikely interaction. The actor's calm demeanor and the bear's relaxed stance suggest a mutual trust and understanding in their shared moment of connection.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted in the video, as well as the bear's face."
}
] |
seed42_1048
|
videos/HRA_part0/1048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space prison, a rugged man with a shaved head, dressed in a torn orange jumpsuit, stealthily caresses a metallic wall panel, searching for a hidden mechanism. His intense eyes scan the surroundings, alert for any sign of danger. He gently touches the cold surface, feeling for inconsistencies. Suddenly, his fingers find a concealed switch, and he looks relieved yet cautious. With a quick glance over his shoulder, he presses the button, triggering a sequence that promises his daring escape from the confined, sterile prison cell.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_163
|
videos/HRA_part2/163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2136
|
videos/HRA_part0/2136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1507
|
videos/HRA_part1/1507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 warm, sandy landscape under a clear blue sky, two young children, a boy and a girl, are gently caressing a calm camel. The boy, wearing a yellow shirt and brown shorts, strokes the camel's nose tenderly, while the girl, dressed in a pink dress and sandals, pets its lower leg with a smile. Both children are barefoot, standing on the soft sand, and the camel, adorned with traditional red and white saddle cloths, accepts their affection with a patient demeanor, creating a heartwarming scene of human-animal interaction in a desert environment.]"
},
{
"from": "gpt",
"value": "Bad. One of the boys in yellow has an incomplete head, the camel's head is deformed. The child's arms and hands have also undergone deformities."
}
] |
seed42_2058
|
videos/HRA_part0/2058.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique fusion of scenes, a waiter in a crisp white shirt and black trousers serves a golden, perfectly roasted chicken on a rustic wooden table set amidst the lush greenery of a temperate rainforest. Moments later, the waiter, now donning a vibrant, traditional costume, gracefully dances among the towering trees, his movements harmonious with the serene environment. The chicken, now artfully presented on a platter, sits center stage as the waiter performs a captivating dance, his attire reflecting the rich cultural heritage associated with temperate rainforests, all under the canopy of majestic, moss-covered trees.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1727
|
videos/HRA_part0/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Normal. The camel's head in the video was generated abnormally."
}
] |
seed42_2132
|
videos/HRA_part0/2132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, with iridescent green feathers and a forked tail, hovers near a red feeder, its wings a blur of motion against a clear blue sky. The bird's tiny feet dangle beneath it as it feeds, and its long, thin beak dips into the feeder's port. Suddenly, it takes flight, its wings creating an audible hum, and lands on a branch, where it preens its feathers with its curved bill. Throughout, the hummingbird's rapid wing movements and vibrant plumage are showcased against the serene backdrop of nature.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions a hummingbird landing on a branch and using its curved beak to preen its feathers, but this scene does not appear in the video."
}
] |
seed42_2610
|
videos/HRA_part0/2610.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blue shirt and striped tie, stands in a modern office space. He is attentively checking a smoke detector mounted on the ceiling, exhibiting a careful and professional demeanor. The office features a large window offering views of a city skyline, a desk with a laptop and documents, and a bookshelf filled with law books, creating a setting that blends professionalism with safety awareness. The lawyer's actions highlight the importance of routine safety checks in a workplace environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2999
|
videos/HRA_part0/2999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with its distinct brown and white spotted pattern, swims serenely in a clear blue underwater environment. Its wide, flat head and protruding eyes are prominently featured as it navigates the aquatic space. Surrounding coral formations and gentle water currents add to the natural ambiance of the scene, providing a vivid portrayal of the grouper's habitat. The fish's powerful tail fin propels it effortlessly through the water, while smaller fish scatter in its presence, highlighting the grouper's dominant position in the marine ecosystem.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3169
|
videos/HRA_part2/3169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray jacket and blue jeans stands outside a historic cinema, its marquee displaying classic film posters, evoking a sense of nostalgia and cinematic history. Moments later, the focus is on the man swimming in an indoor pool, surrounded by large windows that let in natural light, creating a contrast between the urban environment and the tranquility of water. He swims with purpose and strength, his silhouette framed by the water and the reflections of the pool tiles. The scene captures the essence of leisure and physical activity, juxtaposing the cultural experience of cinema with the personal enjoyment of swimming.]"
},
{
"from": "gpt",
"value": "Bad. The man outside the cinema has distorted and deformed hands and feet, the man in the swimming pool has a blurry face, and his body is incompletely generated."
}
] |
seed42_1009
|
videos/HRA_part0/1009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, donning a black leather jacket, dark jeans, and a white T-shirt, is seen energetically dancing in a vast, open space, backlit by the golden hour sun. Amidst his lively moves, a tiny vole emerges from the grass, its small, curious eyes fixated on the man. The man continues to dance, oblivious to the vole's presence, his movements casting dynamic shadows across the grassy landscape. The vole watches from a safe distance, seemingly fascinated by the man's animated performance under the warm, evening light.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks and dances with uncoordinated movements."
}
] |
seed44_2775
|
videos/HRA_part1/2775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking young man, possibly a librarian or a bookstore employee, organizes books on a shelf in a cozy library corner. He wears a mustard yellow sweater over a button-down shirt, khaki pants, and a stylish watch. The library is filled with bookshelves and has a warm, inviting atmosphere, enhanced by the wooden furniture and green plants. He carefully arranges the books, occasionally stopping to read titles or adjust their placement. The shelves are filled with various genres of literature, from classics to contemporary works, reflecting the diverse interests of the library's patrons. Throughout the scene, the man's dedication to his task is evident, as he meticulously organizes the books with a sense of purpose and care.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a young person organizing books on a bookshelf, with actions that are not continuous and smooth, and there are abrupt changes."
}
] |
seed44_2357
|
videos/HRA_part1/2357.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hare, donning a red apron and a name tag, works diligently as a cashier in a charming store nestled deep within a lush rainforest. The store's wooden shelves are stocked with unique items, including exotic fruits, colorful fabrics, and handmade crafts. Outside, the vibrant rainforest comes alive with the sounds of wildlife and the gentle patter of rain. Suddenly, the hare takes a break and ventures outside, where it encounters a serene natural pool, its clear waters inviting for a refreshing swim amidst the emerald greenery. The hare, now in swimming attire, joyfully splashes in the pool, surrounded by the lush foliage and the calming atmosphere of the rainforest.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's movements in the video are not smooth."
}
] |
seed46_2237
|
videos/HRA_part2/2237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, majestic tuna fish glides through the crystal-clear waters of the ocean, its sleek silver body cutting through the water with grace and power. The sunlight filters down from the surface above, casting shimmering patterns across the tuna's scales. Schools of smaller fish scatter in its path, the tuna's presence commanding respect in the underwater realm. In the distance, the silhouette of a reef can be seen, adding depth and context to the tuna's aquatic habitat. The video captures the tuna from various angles, showcasing its size and strength as it navigates its natural environment with ease.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2424
|
videos/HRA_part0/2424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a black vest and tie, crouches low, engaging in a playful crawl across a textured wooden floor. Unexpectedly, a squirrel appears, its bushy tail bouncing, as it curiously crawls alongside the waiter. The two crawl in unison, the squirrel mirroring the waiter's movements, against a backdrop that subtly hints at a 'Quantum Leap' style time warp, indicated by a faint, swirling visual effect. This surreal moment captures the unusual pairing of the crawling waiter and squirrel, blending elements of fantasy and reality.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2589
|
videos/HRA_part2/2589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, adorned in a traditional white uniform and tall hat, stands against the stark contrast of a landfill landscape. He gently caresses a large, ripe tomato, highlighting the irony of waste amidst sustenance. His eyes, filled with concern and determination, underscore the message of valuing food resources in a world plagued by waste. The scene is set against a backdrop of discarded goods, emphasizing the importance of responsible consumption and the role chefs play in advocating for sustainable practices.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand shows a deformed mutation, and the tomato in his hand also undergoes deformation."
}
] |
seed42_1420
|
videos/HRA_part0/1420.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sandy desert under a bright, cloudless sky, a single dromedary camel leaps gracefully over a fallen tree trunk. Its tan fur contrasts starkly with the pale sand, and its large, expressive eyes are fixed ahead. The camel, wearing a simple brown strap across its torso, lands softly on the other side of the obstacle, continuing its journey across the dunes with a sense of purpose and freedom. The scene captures the unexpected agility of this desert dweller against the serene, unbroken landscape.]"
},
{
"from": "gpt",
"value": "Normal. The camel's movements in the video are not smooth."
}
] |
seed46_2426
|
videos/HRA_part2/2426.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown jacket, blue jeans, and a green shirt, takes a break from his usual endeavors to tackle an autumn chore. He rakes leaves in a residential backyard, surrounded by lush greenery and tall trees. The scene opens with him standing confidently, holding a rake, and looking intently at the camera. Next, he begins raking piles of golden leaves, his focused expression and body language conveying his determination. The camera then captures him pausing to rest, leaning on the rake, and smiling contentedly at his progress. Finally, he returns to work, skillfully maneuvering the rake to gather the last of the fallen foliage, all while the warm, natural tones of autumn provide a picturesque backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The director leaning on a rake to rest, mentioned in the caption, does not appear in the video."
}
] |
seed46_2156
|
videos/HRA_part2/2156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, modern clothing store, a friendly, young female cashier with brown hair tied in a bun assists a male customer. She is shown measuring the hem of a pair of beige slacks, using a measuring tape, while the man stands patiently. The pants are held up by the customer, who wears a casual outfit consisting of a blue shirt and dark pants. The cashier, dressed in a black apron over a white blouse, carefully marks the fabric with a tailor's chalk, indicating where the alteration should be made. The scene is set against the backdrop of the store, with various racks of clothes visible in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2088
|
videos/HRA_part1/2088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, snow-covered landscape, a group of people in winter gear are seen interacting with a herd of majestic bison. The individuals are wiping snow off the bison's fur, showing care and connection with the animals. Their faces, wrapped warmly in scarves and hats, express determination and compassion. The bison, with their powerful statures and shaggy coats, stand calmly, accepting the attention. The scene is framed by the serene beauty of nature, with snowflakes gently falling and the distant silhouette of trees providing a peaceful backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The bison's head and people's limbs in the video have generation issues, and there is a person who suddenly distorts, deforms, and disappears in the middle frame."
}
] |
seed46_1631
|
videos/HRA_part2/1631.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 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 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 teacher's dance moves are not fluid, they suddenly change."
}
] |
seed46_2982
|
videos/HRA_part2/2982.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, dressed in a dark blue jacket and khaki pants, is crawling through a complex system of pipes and machinery beneath a large, bustling harbor. The scene is set against the backdrop of towering cranes and docked ships, with the engineer's focus and determination highlighted by the dimly lit, confined space. His purposeful movement through the industrial labyrinth underscores the critical role of maintenance in keeping the harbor operations running smoothly. The sound of water lapping against the hulls of boats and the distant calls of seagulls provide a contrast to the enclosed environment where the engineer works.]"
},
{
"from": "gpt",
"value": "Normal. The man's crawling in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed46_1023
|
videos/HRA_part2/1023.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 otter strolls leisurely across ancient cobblestones, exploring the historical ruins of a stone fortress, its textured walls and arched doorways framing the scene. The curious creature, with its brown fur and small, pointed face, ambles through the site, seemingly undisturbed by the historic ambiance surrounding it. Its path leads it past weathered statues and through narrow passageways, the muted colors of the stone providing a stark contrast to the lush greenery that has reclaimed parts of the ancient structure. Throughout its journey, the otter maintains a peaceful pace, offering a unique perspective on the intersection of nature and history.]"
},
{
"from": "gpt",
"value": "Bad. The animals in the video walk very unnaturally, with uncoordinated movements."
}
] |
seed42_2820
|
videos/HRA_part0/2820.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a white collared shirt, points with her right hand to something outside the frame, her left hand resting on the counter. Behind her, a row of colorful candy bars lines the shelf, while above her head, a sign displays various services offered, such as check cashing and lottery tickets. The scene takes place inside a busy convenience store, with customers visible in the background, creating a snapshot of daily life in a bustling urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's eyes and ears in the video have generation issues."
}
] |
seed44_2666
|
videos/HRA_part1/2666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, verdant forest setting, a mother beaver gently caresses her kits with her large, flat tail, while they sit cozily together on the riverbank. The kits, with their soft, brown fur, look up at her with adoration, as the mother's nurturing touch conveys love and protection. Surrounded by the vibrant greenery and tranquility of nature, this heartwarming scene captures the tender bond between a beaver mother and her offspring.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's eyes in the video have generation issues, and the claws were not generated."
}
] |
seed44_3136
|
videos/HRA_part1/3136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a red astronaut suit with gold accents, crawls across a rocky Martian landscape as a vibrant orange and red sunset illuminates the horizon. The chef's outfit includes a matching helmet, which reflects the dramatic sunset, and a tool belt filled with cooking utensils. The rocks beneath him are various shades of brown and red, typical of Mars' surface, while the distant mountains and sandy dunes complete the alien yet stunning scenery. Despite the harsh environment, the chef's determination to explore and perhaps cook under the unique conditions of Mars is evident.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted, and the arm is slightly twisted."
}
] |
seed42_1566
|
videos/HRA_part0/1566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with a ferret perched on his shoulder, floats weightlessly in a vast cosmic pool that mirrors Jupiter's Great Red Spot. Dressed in a dark wetsuit and goggles, he somersaults gracefully through the water, the ferret securely nestled and seemingly unfazed. The swirling red and white clouds of Jupiter envelop the scene, creating a surreal and captivating contrast to the serene swimming motion. Throughout, the ferret remains a constant presence, its curious gaze following the actor's every move in this otherworldly aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2710
|
videos/HRA_part1/2710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling Colin Farrell, is seen walking through a dense forest with tall trees, wearing a brown jacket, jeans, and boots. Suddenly, the scene changes to reveal a prehistoric setting, where the actor now finds himself casually strolling beside a woolly mammoth. Both the actor and the mammoth continue their leisurely walk together, with the mammoth's massive frame towering over the actor, who appears unfazed by the extraordinary situation. They meander through the ancient landscape, surrounded by lush vegetation and underbrush, creating a surreal juxtaposition of eras and species.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2722
|
videos/HRA_part2/2722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green park under the bright summer sun, two happy children, a boy and a girl, are energetically chasing each other on the grass. The boy, wearing a red t-shirt and blue shorts, stretches out his hands, playfully trying to catch the girl. She, donned in a yellow dress and sandals, giggles as she skillfully dodges him, both enjoying the thrill of the chase. They run amidst a scattering of colorful wildflowers, their laughter echoing through the serene environment, encapsulating the joy and innocence of childhood.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1817
|
videos/HRA_part1/1817.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 falcon soars through a cloud-filled sky, its piercing eyes and hooked beak sharply defined against the light. It dives gracefully, wings tucked, chasing an unseen prey over lush green fields dotted with wildflowers. The bird, adorned with a leather hood and jesses, lands on a gloved hand, presenting its fierce gaze and powerful talons. Its plumage, a mix of brown, white, and black, contrasts beautifully with the serene landscape, creating a stunning portrait of nature's hunter against a backdrop of rolling hills and a clear blue horizon.]"
},
{
"from": "gpt",
"value": "Bad. The falcon's wings are distorted, the claws are twisted, and the face is slightly distorted."
}
] |
seed42_3070
|
videos/HRA_part0/3070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a janitor, dressed in a brown jumpsuit and cap, is playfully crawling on his hands and knees across a stable floor, chasing after a curious horse. The horse, with a full brown mane and tail, looks back at the janitor with a sense of amusement, its hooves stepping lightly on the straw-covered ground. The stable's wooden beams and stalls provide a rustic backdrop, while the janitor's playful demeanor adds a touch of unexpected humor to the otherwise ordinary task of cleaning.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is twisted, the head is twisted, the feet are twisted, the legs are twisted, the arms are twisted, and the horse's legs are twisted."
}
] |
seed44_1647
|
videos/HRA_part1/1647.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vast, open ocean landscape fills the screen, with crystal clear water revealing a sandy bottom far below. Sunlight filters through the surface, casting dappled light on the scene. Suddenly, a magnificent manta ray enters the frame, its massive wings spanning wide as it glides effortlessly through the water. The creature is a stunning sight, its dark top and white underbelly contrasting beautifully against the blue surroundings. It performs an elegant somersault, showcasing its agility and grace, before continuing on its serene journey across the vast underwater expanse.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_113
|
videos/HRA_part0/113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker in a power plant environment is seen wiping down a large turbine with a yellow cloth, dressed in a navy blue uniform, complete with a shirt, trousers, and safety shoes. The scene captures the maintenance aspect of power generation, with the worker focused on cleaning the metallic surface of the turbine. The power plant's interior is visible, featuring high ceilings, large machinery, and industrial pipes, all bathed in artificial lighting. The worker's attire, which includes a hard hat and protective gloves, emphasizes safety protocols in the industrial setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1884
|
videos/HRA_part2/1884.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic starship bridge, illuminated by soft blue and green lights, a small, fluffy white hare is crawling across the command deck. The hare moves slowly, its ears perked up, exploring the high-tech environment filled with control panels and large viewing screens displaying cosmic visuals. The bridge is otherwise empty, save for the advanced technology and the occasional blinking lights, creating a surreal contrast between the sci-fi setting and the unexpected presence of the crawling hare.]"
},
{
"from": "gpt",
"value": "Bad. The white rabbit in the video walks very awkwardly, with uncoordinated movements."
}
] |
seed46_1041
|
videos/HRA_part2/1041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 boys, one wearing a yellow shirt and the other in red, energetically scrub the bathroom floor with sponges, creating soapy lather. They are focused on their task, with one boy on his hands and knees, working diligently, and the other standing, intently cleaning the wall tiles. The room is filled with the soft sound of water and the energetic movements of the children, who seem to find joy in the chore, transforming the mundane task into a playful activity. Their faces are expressions of determination and delight, turning the bathroom into a space of unexpected fun and teamwork.]"
},
{
"from": "gpt",
"value": "Normal. The boy's arm deforms and stretches during the wiping process."
}
] |
seed44_1263
|
videos/HRA_part1/1263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nervous-looking cashier, a young man with glasses and a name tag, stands behind a checkout counter. He wears a red apron over a white collared shirt, and his fingers shake slightly as he handles a stack of cash. The scene is set in a dimly lit grocery store aisle, with products visible on shelves in the background. The man's apprehensive demeanor is evident in his furrowed brow and tense posture, as he carefully counts the money with quivering hands, the camera capturing every detail in high definition.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's movements in the video are not smooth and coordinated."
}
] |
seed44_2308
|
videos/HRA_part1/2308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hedgehog dons a top hat and a monocle, appearing as a refined dancer against a backdrop of bustling harbors, where ships are docked under a twilight sky. The hedgehog, standing on its hind legs, elegantly moves across the foreground, while the harbor life continues in the background, complete with a lighthouse guiding the way. The hedgehog's anthropomorphic attire adds a touch of surrealism to the dancing display, all set against the serene beauty of the harbors at dusk.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's walking movements in the video are uncoordinated."
}
] |
seed42_1100
|
videos/HRA_part0/1100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 parallel universe setting, a firefighter, identifiable by his black helmet with a shiny badge, black uniform, and red suspenders, crawls on all fours through a desolate urban landscape. The cityscape features a large, gray building with broken windows and a dark, cloudy sky. The firefighter's movements are slow and deliberate, as if navigating through a hazardous environment. His gear includes a heavy-duty jacket, sturdy gloves, and a breathing apparatus strapped to his back, alluding to the dangerous conditions he faces. Despite the bleak surroundings, the firefighter's determination is evident in his focused gaze and resolute posture.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers appear deformed."
}
] |
seed46_2481
|
videos/HRA_part2/2481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, with curly brown hair and wearing a gray shirt, speaks directly to the camera with a smile, holding a small, unframed artwork in his hands. The focus is on his face and upper body, with the studio environment blurred in the background, including a large window and a partially visible sculpture. Throughout the clip, he maintains eye contact with the viewer, gesturing with his free hand as he passionately discusses his work. The atmosphere is warm and inviting, enhanced by the soft lighting that illuminates the artist and the artwork.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2984
|
videos/HRA_part2/2984.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned director, clad in a gray shirt and black pants, ascends a steep, rocky cliff face, his focus unwavering. Equipped with a harness and rope, he demonstrates his climbing skills against the rugged terrain. As he reaches higher, the camera captures his intense concentration, highlighting his determination and passion for his adventurous pursuit. The scene is framed by the natural beauty of the surroundings, with lush vegetation and distant mountains providing a stunning backdrop to his climb.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are deformed, there are missing parts in the arm generation, and the face generation is blurry."
}
] |
seed46_1570
|
videos/HRA_part2/1570.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with advanced equipment, a dedicated scientist, wearing a white lab coat over a dark shirt and jeans, gently caresses a sophisticated device used in dark matter research. The scientist, sporting short hair and glasses, exhibits a deep connection with the apparatus, conveying the tender care required in handling delicate scientific instruments. The background features a complex arrangement of machinery and computer screens, highlighting the cutting-edge nature of the research being conducted. This intimate interaction between the researcher and the technology underscores the human element in the pursuit of understanding the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1727
|
videos/HRA_part0/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2067
|
videos/HRA_part2/2067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown bat with intricate wing details is seen crawling along a cave floor, illuminated by a soft, ambient light. It slowly makes its way across the rocky terrain, revealing its unique features in close-up. Meanwhile, in the distance, the planet Venus can be seen as a bright spot in the night sky, providing a celestial contrast to the terrestrial scene below. The bat's movements are deliberate and methodical, highlighting its adaptation to navigating dark environments, while Venus' presence adds a cosmic element to the composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1545
|
videos/HRA_part2/1545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a gray shirt and khaki pants is seen in a whimsical scene, holding a small mouse on a wheel that matches the color of his shirt. The wheel rotates rapidly as the man watches, his gaze fixed on the active rodent. The scene is set against a plain, white backdrop, with the man's casual attire and focused expression contrasting with the unusual sight of the mouse energetically running on the miniature wheel.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2597
|
videos/HRA_part2/2597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown vole walks purposefully across a lush, green meadow, its round body and short legs visible as it moves through the tall grass. The scene is set against a backdrop of vibrant flora, with the vole's movement drawing attention to its determination. Its fur is textured and rich in detail, and its eyes are alert and curious as it navigates the natural landscape. The vole's path is unobstructed, allowing for a clear view of its journey through the verdant field.]"
},
{
"from": "gpt",
"value": "Normal. The video has issues with the generation of the vole's ears, and there are missing parts in the limbs and nose."
}
] |
seed44_199
|
videos/HRA_part1/199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, young female nurse, wearing a white uniform with a stethoscope around her neck, gently caresses the head of a golden retriever dog lying on the grass in a lush, green park. The nurse, with her hair tied back in a bun, interacts tenderly with the dog, who looks up at her adoringly. In another scene, she sits on a park bench, continuing to pet the dog affectionately, with trees and foliage visible in the background. The bond between the nurse and the dog is evident as they share a peaceful moment together in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the nurse petting the golden retriever, with basically normal movements, but there is some lack of coordination."
}
] |
seed44_294
|
videos/HRA_part1/294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate teacher, donning a red top and black leggings, executes a captivating zero-gravity dance in a spacious, well-lit room. She leaps and twirls effortlessly, mimicking the weightlessness of space, as if defying Earth's gravity. Seamlessly transitioning, she begins running in place, her movements fluid and energetic, demonstrating the illusion of floating while maintaining contact with the ground. Throughout, her expressive face conveys the exhilaration and freedom of movement in a zero-gravity environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1787
|
videos/HRA_part0/1787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, donning a brown vest and khaki trousers, races through lush, green vineyards, his expression one of determination. He is followed closely by a prehistoric mammoth, its massive body and shaggy fur moving surprisingly swiftly through the rows of grapevines. The sun, low in the sky, casts long shadows across the fertile landscape, highlighting the unusual pair as they navigate the terraced fields. In the background, a rustic barn and rolling hills provide a classic countryside setting, contrasting with the extraordinary sight of the farmer and the mammoth in motion.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1351
|
videos/HRA_part0/1351.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant young woman, clad in a traditional nurse's uniform with a crisp white dress and cap, finds herself amidst vast, rolling farmlands under a clear blue sky. With a contagious smile, she begins to dance, her movements joyful and carefree, as if the open fields and distant hills are her stage. The sun casts a warm glow over the lush greenery, highlighting her figure as she twirls and leaps, embodying a harmonious blend of professionalism and uninhibited spirit in the rural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2974
|
videos/HRA_part2/2974.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a faded red shirt and dark pants, is seen intently repairing a vintage bicycle in a rustic, sunlit barn. The barn interior is filled with various tools and farming equipment, giving a sense of his daily life and work environment. He is hunched over the bike, carefully adjusting the gears with a wrench, his brow furrowed in concentration. The bike, with its classic design and worn paint, stands on a wooden stand, surrounded by scattered tools and parts, as he works diligently under the warm glow of a hanging light bulb.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_206
|
videos/HRA_part2/206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]"
},
{
"from": "gpt",
"value": "Normal. The badger in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1253
|
videos/HRA_part2/1253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant scene set within lush wetlands, several figures clad in elaborate costumes dance energetically, their movements synchronized in a captivating performance. The dancers wear colorful outfits adorned with feathers and intricate patterns, their faces painted in festive designs. The backdrop showcases the beauty of the wetlands, with tall reeds swaying gently in the breeze and waterfowl flying overhead. Sunlight filters through the clouds, casting a warm glow on the dancers as they leap and twirl, embodying the spirit of nature in their lively dance.]"
},
{
"from": "gpt",
"value": "Bad. The character's body movements are not coordinated."
}
] |
seed46_3093
|
videos/HRA_part2/3093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, modern space education center, a diligent janitorial worker, clad in a gray uniform, meticulously wipes down an expansive, glass-topped display table. The room is filled with futuristic exhibits, including a large model of the solar system hanging from the ceiling, and interactive screens showing detailed information about planets and galaxies. The worker's attention to detail is evident as they ensure every inch of the table is spotless, allowing visitors to fully appreciate the educational materials displayed beneath the clear surface. The backdrop of the space-themed decor highlights the importance of cleanliness in maintaining a conducive learning environment for students eager to explore the cosmos.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_1616
|
videos/HRA_part0/1616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a lone cuttlefish hovers above a sandy seabed dotted with rocks, showcasing its dynamic color-changing abilities as it blends with the surroundings. The cephalopod displays a mesmerizing array of brown and white patterns on its skin, a demonstration of its remarkable camouflage technique. Its eight arms and two tentacles extend gracefully from its mantle, each adorned with small suckers, as it maneuvers through the aquatic environment with agility. The water is clear, allowing sunlight to filter through, illuminating the cuttlefish and the sandy bottom beneath it, creating a stunning visual display of nature's wonders.]"
},
{
"from": "gpt",
"value": "Normal. The squid's body is twisted in the video."
}
] |
seed42_1465
|
videos/HRA_part0/1465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bundled in a green winter coat, brown boots, and a colorful scarf, energetically shovels snow from the school's front steps. Snowflakes gently fall from a cloudy gray sky, creating a peaceful atmosphere. The teacher, wearing a warm hat and gloves, clears a path on the steps, revealing the red brick beneath. They pause for a moment, holding the shovel in mid-air, their breath visible in the cold air. The teacher continues shoveling, making progress against the accumulating snow, as the school building stands tall in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, and the legs are deformed."
}
] |
seed46_1253
|
videos/HRA_part2/1253.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant scene set within lush wetlands, several figures clad in elaborate costumes dance energetically, their movements synchronized in a captivating performance. The dancers wear colorful outfits adorned with feathers and intricate patterns, their faces painted in festive designs. The backdrop showcases the beauty of the wetlands, with tall reeds swaying gently in the breeze and waterfowl flying overhead. Sunlight filters through the clouds, casting a warm glow on the dancers as they leap and twirl, embodying the spirit of nature in their lively dance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1485
|
videos/HRA_part0/1485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguishable by his classic black vest and white button-down shirt, is shown shoveling snow with determination. His attire is uniquely juxtaposed with the wintry task at hand, as he clears a path in front of a charming, snow-covered cottage. Snowflakes gently fall from a cloudy sky, accumulating on the roof and surrounding trees, while the waiter, wearing black gloves and sensible shoes for traction, focuses on his unexpected duty. Despite the cold, he works diligently, the snow creating a picturesque setting that contrasts with his formal waiter's uniform.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1760
|
videos/HRA_part2/1760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by soft purple lights and adorned with cosmic artwork, a young, bald writer wearing a black turtleneck and jeans sits pensively at a sleek, metallic desk. He wipes away a smudge on the pristine, reflective surface, revealing a holographic interface beneath. Around him, floating canvases display vibrant, otherworldly landscapes, while the artist himself seems lost in thought, perhaps contemplating his next masterpiece among the stars.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2613
|
videos/HRA_part2/2613.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, dressed in full gear and helmet, finds himself at the base of a towering space elevator, its sleek silver structure piercing the clouds. Against this futuristic backdrop, he begins to dance, his movements a surprising juxtaposition of grace and strength. The flames from a nearby controlled fire flicker and dance along with him, casting an orange glow on the space elevator's metallic surface. The firefighter's steps are lively and expressive, a mix of joy and determination, as he performs beneath the vast starlit sky, the space elevator standing tall and unwavering behind him.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2919
|
videos/HRA_part2/2919.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, a bobcat is gently caressing a gray cat on a sandy arena floor, both animals seated facing each other. The bobcat, displaying unusual friendliness, reaches out with a paw to touch the cat's face, while the cat responds with a curious gaze. The sandy arena floor provides a textured backdrop, emphasizing the unique interaction between these two feline species. Moments later, the bobcat leans in closer to the gray cat, its paw still extended in a tender gesture, as if sharing a moment of mutual understanding within the sandy enclosure.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.