video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2358
|
videos/HRA_part1/2358.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone musician, garbed in a silver spacesuit, traverses an interplanetary trade route marked by luminescent orbs floating in zero gravity. His suit, adorned with musical notes, indicates his profession. He crawls through the cosmic path, surrounded by stars and galaxies, carrying a futuristic instrument that resembles a hybrid between a guitar and a synthesizer. His journey is filled with determination, as he navigates the vast expanse of space, seeking new melodies among the stars. The trade route, bustling with alien spacecraft, highlights the universal language of music, connecting different worlds through sound and rhythm.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a distorted body, head, legs, and arms."
}
] |
seed44_2456
|
videos/HRA_part1/2456.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its wings spread wide, revealing its distinctive white-feathered head and brown body. It glides effortlessly over a vast, serene landscape, comprised of lush green forests and tranquil lakes, with distant mountain peaks forming a stunning backdrop. The eagle's piercing yellow eyes remain alert, scanning the terrain below for any sign of prey, as it embodies the spirit of freedom and strength in the untamed wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2042
|
videos/HRA_part2/2042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a green spacesuit with a clear helmet, stands on an alien planet with vibrant purple foliage and orange skies, holding a tablet displaying educational diagrams. Nearby, a body of water shimmers under the exotic sky, showing aquatic life adapted to this unique ecosystem, swimming gracefully beneath the surface. The teacher occasionally glances up from the tablet to observe the surrounding alien flora and fauna, integrating real-world examples into the lesson. Throughout the scene, the focus remains on the teacher's engagement with the alien environment, using it as a teaching tool, while the colorful, otherworldly landscape provides a captivating backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_308
|
videos/HRA_part2/308.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with distinctive tufted ears and a rufous-colored coat, leaps from a rocky outcropping, its body arched and legs extended, showcasing its agility and power. The background features lush vegetation and trees, highlighting the wild, natural habitat of this impressive feline. The scene is captured in high definition, allowing every detail of the bobcat's muscular form and the surrounding environment to be clearly visible during the jump.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the lynx jumping from a rock outcrop, but the movements are not continuous and very uncoordinated."
}
] |
seed42_2952
|
videos/HRA_part0/2952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown leather jacket and dark pants, kneels on a wooden floor, engaged in a crawling motion, as he observes a live hare sitting on a white table nearby. The scene is set indoors, with a large window in the background, allowing natural light to illuminate the room. The director's intent gaze and careful movement convey a sense of focus and determination as he studies the animal, which remains calm and still, seemingly unfazed by the presence of the human.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2
|
videos/HRA_part0/2.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, rustic shop filled with natural light, a cheerful cashier, wearing a red apron over a cream sweater and dark jeans, sits behind a wooden counter adorned with a vintage cash register and various knitting supplies. She expertly knits a vibrant, multi-colored scarf, her hands moving swiftly as she focuses intently on her craft. The atmosphere is warm and inviting, with the soft clacking of knitting needles adding a soothing soundtrack to the scene. Shelves stocked with yarn in various textures and hues line the walls, creating a backdrop that complements the cashier's skillful knitting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3053
|
videos/HRA_part2/3053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, kneels on a wooden floor next to a small mouse. The mouse scurries across the floor, its movements quick and agile, as the doctor watches with a mix of curiosity and concern. The scene is set in a brightly lit room with white walls, and the doctor's facial expression conveys a sense of focused attention on the tiny creature's actions.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows a mouse rapidly darting across the floor, with movements that are not continuous and smooth, appearing uncoordinated; the doctor's hands also shake, with actions that are not continuous and smooth, appearing uncoordinated."
}
] |
seed46_2430
|
videos/HRA_part2/2430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a waiter, clad in a crisp white shirt and black trousers, serves a majestic deer who stands elegantly by a serene swimming pool, its antlers framing its face like a crown. The deer, with its large, curious eyes, seems to be sipping from a fancy glass, while the waiter attentively pours a clear liquid, possibly water, from a pitcher. The swimming pool, with its crystal-clear water, reflects the sky, adding to the surreal atmosphere of this extraordinary meeting between nature and human service.]"
},
{
"from": "gpt",
"value": "Normal. The deer's face is distorted in the video."
}
] |
seed42_2081
|
videos/HRA_part0/2081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, equipped with sunglasses, a badge, and a radio, stands ready on a sandy beach, the ocean visible behind him. He then leaps into the air, his silhouette framed against the bright horizon, showcasing agility and dynamism. Next, he lands gracefully on the sand, his stance firm and authoritative. Finally, he is seen in mid-stride, walking purposefully along the shoreline, the vast ocean and clear blue sky completing the scene, embodying strength and determination in an idyllic coastal setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2158
|
videos/HRA_part1/2158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a gray shirt and khaki pants, sits in a modern office space with a clean desk, listening intently. He leans forward with his right elbow on his knee, his face partially covered by his right hand, and his eyes closed, indicating deep concentration. His left hand rests on a high-tech, silver-colored device, possibly a piece of machinery or equipment, while a large screen displays complex diagrams and data in the background. The office is illuminated by natural light from a window, casting a soft glow on the engineer and his workspace.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's right hand is missing in the video."
}
] |
seed44_193
|
videos/HRA_part1/193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a crisp white shirt, black vest, and tie, is seen in an upscale restaurant, standing on a chair to check a smoke detector. The room is modern and stylish, with wooden floors, a white ceiling, and large windows. The waiter, displaying a conscientious attitude towards safety, carefully inspects the device. The scene conveys a sense of professionalism and attention to detail, as the waiter ensures the restaurant is equipped with functional safety equipment. The establishment is empty except for the waiter, emphasizing the routine nature of the task. The waiter's attire and the restaurant's decor suggest a high-end dining environment, where safety measures are taken seriously.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2804
|
videos/HRA_part2/2804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, donning a black tank top and dark jeans, mimics the agile movements of a mongoose, sprinting across a lush, verdant landscape. His intense gaze and athletic build convey strength and determination as he leaps over obstacles, embodying the spirit of the nimble creature. The scenery features vibrant greenery and a clear blue sky, providing a vivid contrast to his swift, mongoose-inspired running. Throughout the sequence, the actor maintains his focus and momentum, seamlessly integrating the mongoose's grace and speed into his performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2443
|
videos/HRA_part1/2443.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray shirt with a name tag, smiles widely at the camera, standing in front of a bustling factory floor filled with machinery and equipment. The scene is alive with the sounds of industry, yet the engineer's cheerful demeanor stands out, conveying a sense of pride and satisfaction in his work environment. His smile is genuine and inviting, offering a human touch to the typically impersonal setting of a manufacturing plant.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2387
|
videos/HRA_part2/2387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a vibrant yellow jacket and khaki shorts, walks along a dirt path near a watering hole, where a hippopotamus lazily wallows in the cool mud. In the distance, the Martian landscape unfolds, with its rusty red dunes and sparse vegetation silhouetted against a sunset painted in hues of violet and orange. The celestial event casts a warm glow over the scene, highlighting the unique juxtaposition of Earthly life and extraterrestrial beauty.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_298
|
videos/HRA_part0/298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 enthusiastic engineer in a red shirt, beige vest, and khaki pants is seen in an amusement park, surrounded by roller coasters, with a Ferris wheel visible in the distance. He runs through the park with a map in hand, passing by various rides and attractions. The video captures him stopping briefly to study the map, before continuing his energetic jog through the lively environment, showcasing his passion for both engineering and the thrilling atmosphere of amusement parks.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's running in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed44_3010
|
videos/HRA_part1/3010.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone penguin stands majestically on a frosty, snow-covered landscape, its sleek black-and-white feathers glistening under the soft, diffused light of an overcast sky. The penguin, sporting a charming yellow beak and webbed feet, looks intently into the distance, seemingly contemplating the vast icy expanse before it. Behind the penguin, the horizon blends seamlessly into a hazy, muted palette of grays and blues, emphasizing the serenity and isolation of the Antarctic environment. As the camera zooms in, we see the fine details of the penguin's feathers, each one uniquely patterned, adding texture and depth to the image. Throughout the scene, the penguin remains the focal point, a proud and captivating figure in the midst of a desolate yet breathtakingly beautiful world.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1113
|
videos/HRA_part2/1113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone gray wolf, its fur thick and weathered, crawls through a dense forest underbrush, navigating beneath low-hanging branches and over decaying logs. The wolf, exhibiting signs of fatigue or stealth, moves slowly and deliberately, its eyes alert and ears perked, indicating heightened senses. The camera captures this intimate moment from a low angle, emphasizing the wolf's determination and resilience in its natural habitat. The wolf's body language suggests it may be injured or engaged in a cautious hunt, adding to the dramatic tension of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not coordinated, and there are two extra legs."
}
] |
seed42_1137
|
videos/HRA_part0/1137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 outdoor festival setting, two joyful people, a man in a red shirt and blue jeans, and a woman in a yellow dress, dance energetically near a food truck, while a cheerful crowd gathers in the background. The man wears a cap, and the woman has her hair in a bun. They are accompanied by a playful brown dog, who is also participating in the dance, leaping and spinning alongside them. The trio moves to the beat of lively music, surrounded by a diverse group of onlookers, all sharing in the festive atmosphere under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2187
|
videos/HRA_part0/2187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short brown hair, wearing a blue uniform and a stethoscope around her neck, playfully interacts with a ferret on a clean, white examination table in a well-lit veterinary clinic. The ferret, displaying its natural agility, leaps from the nurse's hands as she gently tosses it upwards. The nurse, with a joyful smile, catches the ferret mid-air, showcasing a tender bond between the caregiver and the small animal in a serene medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The ferret undergoes a mutation and becomes deformed while jumping, and the nurse's hand also appears deformed."
}
] |
seed44_1887
|
videos/HRA_part1/1887.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a classic white chef's jacket and black pants, is filmed in a bustling, modern restaurant kitchen. He begins by seasoning a dish with a sprinkle of herbs, his hands moving with practiced ease. Next, he deftly flips a piece of seared salmon in a sizzling pan, the steam rising around him adding to the atmosphere. Then, he carefully arranges the cooked salmon on a plate, garnishing it with fresh greens and a drizzle of sauce. Lastly, he gives a satisfied nod, presenting the beautifully plated meal to the camera, the vibrant colors of the food contrasting with the stainless steel appliances in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1362
|
videos/HRA_part0/1362.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum after hours, a diligent worker in a blue uniform shirt crawls under an exhibit, focusing on maintenance tasks. The exhibit features ancient Egyptian artifacts, including a sarcophagus and hieroglyphic panels, with spotlights illuminating the space. The worker's attire includes safety gear, like gloves and a helmet, emphasizing the cautious approach required for handling historical items. The dimly lit museum hall, filled with glass display cases and statues, provides a dramatic setting for the solitary figure working beneath the exhibition platform.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, legs are deformed, and the head is twisted."
}
] |
seed44_2174
|
videos/HRA_part1/2174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a classic white chef's jacket, black pants, and a black apron, stands on a wooden stool, engaged in the unexpected task of cleaning windows. He uses a squeegee and a bucket of soapy water to methodically clean the glass, revealing the bright, sunny day outside. Despite his professional attire, he tackles the chore with the same dedication he would show in the kitchen, creating an amusing juxtaposition between his culinary expertise and domestic duties. The scene is set against the backdrop of a bustling city street, visible through the window, adding a layer of urban life to the otherwise mundane activity.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand and arm show deformities and mutations, and the windshield wiper in his hand also appears deformed and mutated."
}
] |
seed46_2
|
videos/HRA_part2/2.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, rustic shop filled with natural light, a cheerful cashier, wearing a red apron over a cream sweater and dark jeans, sits behind a wooden counter adorned with a vintage cash register and various knitting supplies. She expertly knits a vibrant, multi-colored scarf, her hands moving swiftly as she focuses intently on her craft. The atmosphere is warm and inviting, with the soft clacking of knitting needles adding a soothing soundtrack to the scene. Shelves stocked with yarn in various textures and hues line the walls, creating a backdrop that complements the cashier's skillful knitting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1130
|
videos/HRA_part0/1130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, wearing a gray suit and a white shirt, stands in a futuristic, high-tech room filled with screens displaying charts and graphs related to interplanetary trade routes. He gently caresses a large, interactive holographic map, which shows the intricate web of trade connections between various celestial bodies, highlighting the complex network of commerce spanning the solar system. The room is bathed in soft, ambient lighting, emphasizing the director's pensive and focused demeanor as he contemplates the vast opportunities and challenges presented by this expansive trade network.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2630
|
videos/HRA_part1/2630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lustrous, red-cooked lobster is presented on a simple white plate, its large, meaty tail curled gracefully. The claws, one broken open to reveal tender, succulent flesh, are garnished with fresh, green parsley. Steam gently rises from the hot shell, hinting at its recent emergence from boiling water. The setting is a rustic wooden table, adorned with a crisp, white cloth, where the lobster takes center stage under natural lighting, casting a subtle shadow that accentuates its texture and color. A small cup of clarified butter sits nearby, ready to enhance the rich, briny flavor of the lobster meat.]"
},
{
"from": "gpt",
"value": "Normal. The lobster's head was not generated in the video, and the body generation was incomplete."
}
] |
seed46_1264
|
videos/HRA_part2/1264.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, wearing a maroon shirt, navy vest, beige khaki pants, and brown hiking boots, pauses on a trail to gaze at a breathtaking mountain vista, his backpack leaning against a tree. Moments later, he sits on a rock, attentively examining something in his hands, perhaps a map or a natural specimen, with the stunning landscape as his backdrop. Then, he hikes uphill, trekking poles in hand, his outfit unchanged, as the lush greenery and distant mountains frame his journey. Finally, he stands at a scenic overlook, savoring the panoramic view, his maroon shirt, navy vest, beige pants, and brown boots standing out against the natural beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, legs, and hiking poles are distorted in the video."
}
] |
seed42_3095
|
videos/HRA_part0/3095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a yellow top and blue jeans is attentively cleaning a large, rectangular fish tank. She is seen smiling while scrubbing the glass with a sponge, ensuring a clear view of the colorful fish and underwater plants inside. The tank is illuminated by overhead lights, highlighting the woman's focused efforts. Her movements are gentle yet thorough, maintaining the aquatic environment's health and beauty. Throughout the process, the fish swim calmly around her, undisturbed by her presence, as she works diligently to keep their home pristine.]"
},
{
"from": "gpt",
"value": "Bad. The woman's arms deform when wiping the glass, and her hands appear deformed."
}
] |
seed44_1395
|
videos/HRA_part1/1395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 capybara sits calmly in a natural setting, surrounded by lush greenery and water in the background. It gently caresses another smaller capybara with its front paws, showing tenderness and care. Both capybaras are positioned against a serene landscape, highlighting the intimate interaction between the two creatures. The larger capybara's nurturing touch towards the smaller one conveys a sense of affection and protection within their social structure.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1628
|
videos/HRA_part0/1628.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky writer, adorned in a bat costume complete with a black cape and headpiece, revels in a solo dance within a dimly lit room. Surrounded by scattered papers and an old typewriter, the scene opens with the writer seated pensively at a desk, illuminated by a single lamp. Suddenly, they leap up, transforming into a dancing figure, their movements wild and uninhibited, expressing the creative energy coursing through them. The bat-themed outfit adds a whimsical touch to the passionate dance, embodying the fusion of writing and movement in a unique celebration of artistic inspiration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1242
|
videos/HRA_part2/1242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a waiter wearing a green apron and carrying a tray with refreshments walks through a temperate rainforest. Surrounded by lush greenery, moss-covered trees, and ferns, he moves along a narrow path. The environment is enhanced by the presence of a large tree trunk, its roots exposed, and the sound of a nearby waterfall. Sunlight filters through the dense foliage, casting dappled light on the forest floor, creating a magical atmosphere as the waiter continues his journey.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is deformed, with twisted arms, twisted hands, and deformed legs."
}
] |
seed42_2472
|
videos/HRA_part0/2472.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a chef's uniform comprised of a white double-breasted jacket and a black and white checkered apron, is seen rock climbing on a sunny day. He confidently grasps the rocks, displaying strength and determination, while his outfit, complete with a black cap, adds a unique twist to the typical rock climber's attire. The clear blue sky and lush greenery surrounding him provide a striking contrast to his chef's garb, making for an unexpected yet captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1468
|
videos/HRA_part2/1468.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smiling teacher stands in a classroom filled with sunlight, wearing a stylish outfit consisting of a striped top, dark jeans, and brown boots. Her warm smile radiates positivity as she looks down at a small child, who is sitting on a chair and wearing a gray jacket and gray pants. The child returns her smile, creating a heartwarming scene of connection and joy in the educational setting. The teacher's attire, the classroom environment, and the presence of the child all contribute to a sense of happiness and engagement in learning.]"
},
{
"from": "gpt",
"value": "Normal. The child's movements in the video are not smooth."
}
] |
seed42_1458
|
videos/HRA_part0/1458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a red bandana, denim overalls, and a white T-shirt energetically scrubs a muddy car with a sponge, creating soapy suds. The car, a vintage yellow convertible, sits in a driveway under a clear blue sky, with green foliage and trees in the background. She sprays the car with a hose, rinsing away the suds to reveal the shiny surface underneath. Then, she wipes down the car's exterior with a clean cloth, her smile reflecting satisfaction in her work. Finally, she polishes the car's chrome details with a microfiber towel, the gleaming vehicle now immaculate against the backdrop of a suburban neighborhood.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements of wiping the car in the video are not smooth and continuous."
}
] |
seed42_1399
|
videos/HRA_part0/1399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fusion of elements, a majestic black panther, its body outlined in vibrant neon green, is depicted leaping across a cosmic landscape. The backdrop features a stunning galactic nebula, its swirling colors of pink, purple, and blue creating an ethereal atmosphere. As the panther moves gracefully, it seems to dance among the stars, its fluid movements echoing the celestial patterns around it. The nebula's gaseous tendrils appear to reach out, almost as if they too are joining in the cosmic dance, forming a harmonious scene where the boundaries between the animal kingdom and the universe blur.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the black panther in the video were not fully generated."
}
] |
seed46_3044
|
videos/HRA_part2/3044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, donning a clean white uniform and a traditional toque blanche hat, sits at a modern, sleek kitchen table. He is intently typing on a laptop, his fingers deftly moving across the keyboard, with the focus of someone accustomed to multitasking. The background is a bustling commercial kitchen, filled with stainless steel appliances and busy staff working in harmony. Despite the chaos around him, the chef remains composed and focused on his task, exemplifying the blend of professionalism and culinary expertise.]"
},
{
"from": "gpt",
"value": "Normal. The chef's fingers in the video are deformed, and there are issues with the eyes."
}
] |
seed44_2783
|
videos/HRA_part1/2783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage girl sits at a wooden desk in a classroom, diligently hemming a pair of khaki pants using a sewing machine, her focus unwavering. She wears a yellow blouse, and her hair is tied back in a ponytail, highlighting her concentration. On the desk, a tape measure, scissors, pins, and a spool of thread are neatly arranged. Beside her, a bulletin board displays various fabric swatches and design sketches, adding context to her task. The room is illuminated by natural light from a window, casting a warm glow over her industrious endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video are deformed."
}
] |
seed44_1099
|
videos/HRA_part1/1099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat wearing a green apron and a name tag stands behind a wooden cash register, located on a small island amidst a vast desert. The meerkat, resembling a human cashier, rings up purchases with expertise, surrounded by volcanic landscapes visible in the distance. The sandy terrain is dotted with various items for sale, creating a surreal marketplace. In the next moment, the meerkat walks across the sandy ground, navigating between the cash register and the products, with the volcanoes providing a dramatic backdrop to this unusual shopping experience.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2915
|
videos/HRA_part2/2915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah, embodying grace and power, rests on a dry, grassy savanna, its body curved in a relaxed position. It turns its head, using its paw to wipe its face, showcasing a natural, intimate grooming moment. The cheetah's distinctive black spots stand out against its tan fur, while its piercing eyes and pronounced facial features add depth to the scene. This close-up shot captures the animal's wild beauty and the serene environment surrounding it, with distant trees adding a sense of place to the composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2281
|
videos/HRA_part2/2281.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a cosmic event unfolds as a theoretical white hole explosion is depicted with vibrant colors and swirling celestial patterns, forming an ethereal, mesmerizing spectacle in the background. In the foreground, a graceful woman, wearing a flowing white dress, gently caresses an abstract representation of the universe, symbolized by a large, luminous orb, evoking a sense of connection and reverence for the mysteries of the cosmos. The woman's serene expression and delicate touch convey a message of harmony and unity between humanity and the infinite expanse of space.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers and arm generation in the video have issues."
}
] |
seed46_2572
|
videos/HRA_part2/2572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and tusks, is depicted swimming in a serene, reflective body of water under a starlit sky, evoking a sense of tranquility and vastness. The elephant is shown in a three-quarter view, with water droplets visible on its skin, indicating its aquatic activity. The stars above, including the prominent red dot of Mars, twinkle in the dark, clear night sky, providing a cosmic backdrop to the scene. The elephant's trunk is partially submerged, and its eyes are closed, conveying a peaceful, almost meditative state as it floats in the water, encapsulating the unique combination of stargazing and swimming.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2275
|
videos/HRA_part1/2275.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, identifiable by his blue scrubs and stethoscope, walks steadily in zero gravity, orbiting the Earth inside a space station illuminated by the planet's stunning blue and green hues. He maneuvers through the microgravity environment with ease, pushing off surfaces to navigate his path. At one point, he floats near a window displaying the Earth's horizon, backlit by the sun, offering a breathtaking view of our planet from orbit. Throughout the scene, the doctor's calm demeanor and the serene backdrop of Earth's curvature underscore the unique experience of walking in space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1802
|
videos/HRA_part0/1802.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a red and white striped shirt, dark pants, and a vibrant tiger head costume, energetically dances in front of a large crowd at a lively pep rally. The atmosphere is electric, filled with cheering fans and the spirit of school pride. The young man, donning the mascot's full-body suit complete with furry orange and black stripes, performs dynamic dance moves to the beat of an upbeat marching band, captivating the audience with his animated antics. Surrounded by enthusiastic supporters waving banners and flags, the scene pulses with excitement and unity, perfectly capturing the essence of collegiate spirit.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted legs."
}
] |
seed44_1269
|
videos/HRA_part1/1269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown capybara slowly crawls through a lush, green meadow dotted with small shrubs and trees, its round ears and alert eyes scanning the environment. It moves deliberately, showcasing its unique gait, as it navigates the vibrant grassland under a bright, sunny sky. The rodent's textured fur glistens in the sunlight, highlighting its wet, semi-aquatic nature, as it continues its unhurried crawl across the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2137
|
videos/HRA_part0/2137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a large bird of prey with brown and white feathers, soars over a placid lake, its piercing yellow eyes scanning the water below. It then swoops down with remarkable agility, its talons outstretched, aiming for a fish just below the surface. Catching its prey, it rises back into the air, now carrying a silver fish clasped firmly in its claws, the water still rippling from the osprey's dive. Against a clear blue sky, the osprey flies away, its powerful wings beating steadily, the captured fish glinting in the sunlight, illustrating the bird's hunting prowess over the serene lake landscape.]"
},
{
"from": "gpt",
"value": "Bad. The osprey's flight in the video is not smooth, and the movements are uncoordinated."
}
] |
seed46_1694
|
videos/HRA_part2/1694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic coffee shop filled with warm, golden light and the aroma of freshly brewed coffee, a young female cashier, wearing a green apron over a striped shirt, knits a vibrant red scarf during a lull in business. She sits behind the counter, surrounded by pastries, a cash register, and an espresso machine. Her focused expression and nimble fingers working the knitting needles capture the essence of making something beautiful by hand in a quaint, welcoming environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2229
|
videos/HRA_part2/2229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a majestic brown horse gallops gracefully across the foreground, its muscular form silhouetted against a backdrop of sprawling factories with billowing smokestacks. Amidst this industrial landscape, a group of diverse individuals dressed in vibrant, eclectic clothing forms a stark contrast as they engage in expressive dance moves, their joyous expressions and dynamic movements standing out against the grey, mechanical setting. This unlikely fusion of nature, industry, and human spirit creates a compelling narrative of resilience and vitality.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is distorted, the head is twisted, the feet are twisted, the legs are twisted, the arms are twisted, the horse's head is slightly twisted, and the legs are twisted."
}
] |
seed42_2261
|
videos/HRA_part0/2261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an array of colorful fish. The grouper, with its distinctive spotted pattern and wide, flat head, explores its surroundings with a slow, methodical motion. Its eyes, fixed on the camera, seem to convey intelligence and awareness. The water is crystal clear, allowing every detail of the grouper's body and the intricate ecosystem it inhabits to be visible. The scene is illuminated by natural sunlight filtering through the surface, casting dappled light on the sandy seabed and the marine life above.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the mouth and fins of the grouper in the video has issues."
}
] |
seed46_1299
|
videos/HRA_part2/1299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an unusual scene, a waiter wearing a black vest, white shirt, and black pants performs a kick in a dining room. The room features a long wooden table adorned with a white cloth, set with plates and glassware. The waiter's kick is high and assertive, contrasting with the formal setting. His black shoes, part of his uniform, add to the unexpected nature of the action. Behind him, a large window allows natural light to illuminate the space, highlighting the waiter's dynamic movement against the backdrop of the elegantly arranged dining area.]"
},
{
"from": "gpt",
"value": "Bad. The server in the video has issues with the generation of limbs and head, showing deformities."
}
] |
seed42_167
|
videos/HRA_part0/167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in period-specific attire from the late 1800s, including a brown shirt, brown trousers, and brown boots, explores historical sites in a rural setting. He crawls through dense grass to uncover ancient artifacts, revealing a deep interest in history. Against a backdrop of historical ruins, the farmer meticulously examines the site, emphasizing his connection to the land and its past. Throughout, he maintains a focused demeanor, highlighting his dedication to understanding the historical significance of the area.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2441
|
videos/HRA_part1/2441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, engages in a leisurely stroll through a lush, green bamboo forest, its round body moving gracefully despite its bulk. It then proceeds to crawl, using its front paws to pull itself forward in a slow, deliberate motion, highlighting its unique method of navigating its environment. The panda's movements are unhurried and methodical, showcasing its relaxed demeanor as it explores its verdant surroundings. Throughout the scene, the panda remains the central focus, with the vibrant greenery of the bamboo forest providing a vivid contrast to its striking fur pattern.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the panda in the video are missing, and there are issues with the generation of the body and ears."
}
] |
seed42_1039
|
videos/HRA_part0/1039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 well-dressed weasel, donning a lab coat and stethoscope, stands at the edge of a swimming pool, located in the backyard of a charming suburban house. The weasel, playing the role of a doctor, attentively examines a patient, who is resting on a floating mattress in the pool, under the shade of an umbrella. Surrounding the pool are other houses, creating a neighborhood backdrop, while the weasel-doctor continues to provide care in this unconventional setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1141
|
videos/HRA_part2/1141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 middle-aged teacher, wearing a blue shirt and khaki pants, stands in the center of a large, old theater, animatedly teaching a lesson about running. The stage is set with props from various plays, adding a touch of theatricality. Suddenly, a dingo, a wild dog native to Australia, runs onto the stage, interrupting the class. The teacher, unperturbed, incorporates the unexpected guest into the lesson, demonstrating running techniques while the dingo playfully bounds around, all under the grand chandelier of the theater.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the hands are twisted, and the wild dog's body is deformed."
}
] |
seed42_2691
|
videos/HRA_part0/2691.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a yellow jumpsuit with a tool belt, crawls through the dimly lit, narrow maintenance corridor of a spaceship, preparing for a hyperspace jump. The ship's interior is filled with pipes and wires, and the engineer's headlamp illuminates the complex machinery around him. He checks various components, ensuring everything is secure before the critical maneuver, his face a mask of concentration under the harsh, industrial lighting of the engineering section.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1644
|
videos/HRA_part0/1644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, organized retail store, two diligent employees wearing red aprons and name tags restock the shelves with groceries. One employee, a man with short brown hair, focuses on neatly arranging cereal boxes, ensuring they face forward. Meanwhile, his female coworker, wearing glasses and with her hair tied back, meticulously stacks cans of soup, aligning them perfectly. The shelves are filled with various food items, including crackers, canned goods, and pasta, all neatly organized and easily accessible to customers. The store is clean and inviting, with a fresh produce section visible in the background, showcasing an array of colorful fruits and vegetables.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1142
|
videos/HRA_part1/1142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gaunt writer, clad in a brown leather jacket, gray t-shirt, and dark jeans, crawls through a desert landscape, reminiscent of a jackal, with a vintage typewriter strapped to his back. The scene opens with him crawling on sandy terrain, his face reflecting determination and resolve. Next, he continues his arduous journey, his clothes and skin stained with dirt, showcasing his unwavering commitment to his craft. The camera then captures him from above, emphasizing his small figure against the vast, barren environment. Lastly, he pauses to rest, the camera focusing on his weathered hands as they gently touch the typewriter, symbolizing his dedication and the intimate connection between the writer and his instrument.]"
},
{
"from": "gpt",
"value": "Bad. The crawling motion is not visible, the character's limbs are uncoordinated, the actions are discontinuous and occur abruptly."
}
] |
seed44_1451
|
videos/HRA_part1/1451.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 creative writer, clad in a khaki outfit and wide-brimmed hat, leaps energetically over a fallen log in a lush, vibrant rainforest. Surrounded by towering trees and dense foliage, they revel in the beauty of nature, their movement capturing the spirit of adventure. The scene is filled with the sights and sounds of the rainforest, from the dappled sunlight filtering through the canopy to the calls of exotic birds and the chatter of unseen wildlife, all contributing to an immersive experience that inspires the writer's imagination.]"
},
{
"from": "gpt",
"value": "Normal. The writer's action of jumping over the log in the video is not smooth and continuous, there is a sudden change."
}
] |
seed42_14
|
videos/HRA_part0/14.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_300
|
videos/HRA_part2/300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown horse gallops across a lush, green meadow under a clear blue sky, its muscular body rippling with each powerful stride. The horse's mane and tail flow dramatically in the wind, creating a sense of speed and freedom. A pair of vibrant yellow flowers appear briefly in the foreground, adding a pop of color to the scene. The horse continues its run, hooves kicking up small clumps of earth, highlighting its strength and grace as it moves through the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Normal. The horse's legs are twisted, and the face is distorted."
}
] |
seed42_1151
|
videos/HRA_part0/1151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a black beret and glasses, sits at a cluttered desk in a dimly lit room, affectionately caressing a small bat perched on her finger. The bat, appearing relaxed and comfortable, is nestled against her hand, which is adorned with silver rings. The scene is set against a backdrop of bookshelves filled with various books, adding to the intellectual and mysterious atmosphere. The writer's other hand rests on a vintage typewriter, hinting at her profession, while the bat's presence introduces an element of the unusual into the intimate scene.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the bat and the character's hand in the video is problematic."
}
] |
seed44_2692
|
videos/HRA_part1/2692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse district under a cloudy sky, a worker clad in a yellow vest and hard hat operates a compact yellow Bobcat excavator. The machine crawls carefully across the concrete floor, maneuvering through the tight spaces between towering stacks of pallets filled with cardboard boxes. The excavator's bucket is raised, ready to perform its task amidst the industrial environment, while the worker remains focused, guiding the machinery with precision.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_232
|
videos/HRA_part0/232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, distinguished by his curly hair, beard, and glasses, is seen shoveling snow in a backyard during daylight. He wears a dark jacket, gray pants, and brown boots, and is engaged in the mundane task with a sense of focus and determination. Snowflakes continue to fall gently from the cloudy sky, accumulating on the ground and surrounding trees. The artist's clothing, which includes a dark jacket, gray pants, and brown work boots, contrasts with the pristine white snow, highlighting the physicality of his task. Despite the cold weather, he remains dedicated to clearing the snow, his breath visible in the crisp air, while a small dog watches him from a distance, adding a touch of companionship to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed46_2792
|
videos/HRA_part2/2792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young boys, one in a red bathing suit and the other in a green one, splash playfully in a backyard pool on a sunny day. Suddenly, the focus is on the boy in red, who is seen diving into the clear water. A small, friendly rat, perhaps a pet, watches from the side of the pool, its tiny body perched on the edge as it observes the boys' aquatic fun. The scene exudes joy and innocence, with the rat's presence adding a touch of unexpected charm to the children's summertime activities.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2329
|
videos/HRA_part1/2329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow vest and hard hat, stands in awe, experiencing time dilation as he watches a kangaroo jump in slow motion against a backdrop of a bustling city skyline at sunset. The kangaroo, mid-leap, appears weightless and graceful, its powerful hind legs propelling it forward. The worker's expression reflects a mix of surprise and fascination, as if witnessing a surreal moment where the laws of physics seem to bend. The scene is bathed in golden hour light, adding to the dreamlike quality of the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo in the video is distorted and deformed, with three tails appearing in the middle frame."
}
] |
seed46_1101
|
videos/HRA_part2/1101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a simple white towel, stands poised at the edge of a natural hot spring, nestled amidst lush, green foliage. He leaps gracefully into the air, his body forming a perfect arc against the backdrop of steam rising from the water's surface. The sunlight filters through the leaves overhead, casting dappled shadows on the rippling water as he soars, suspended in a moment of weightless exhilaration before plunging into the warm, mineral-rich waters below.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video is missing a torso, the head is absent during the diving process."
}
] |
seed42_2720
|
videos/HRA_part0/2720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male doctor, wearing a white lab coat over casual attire, skillfully prepares dinner in a modern kitchen with stainless steel appliances and granite countertops. He expertly chops vegetables on a wooden cutting board, using a sharp chef's knife, while a pot simmers on the stove, releasing aromatic steam. The kitchen is illuminated by soft overhead lights, casting a warm glow over the scene. Behind him, a large window displays an urban skyline at twilight, adding a touch of sophistication to the domestic setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2906
|
videos/HRA_part2/2906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man wearing a white lab coat over a crisp blue shirt and khaki trousers walks his golden retriever on a leash in a lush, green park. The sun filters through the leaves, casting dappled light on the path. The doctor, with salt-and-pepper hair and glasses, smiles warmly as he interacts with his dog, which bounds joyfully ahead, exploring the surroundings. The two stroll past other park-goers, who exchange friendly nods, creating a scene of community and companionship in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the person and the golden retriever in the video are slightly not smooth."
}
] |
seed44_1450
|
videos/HRA_part1/1450.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large brown bear, bristling with strength and agility, runs through a lush, green forest, its muscles rippling beneath thick fur. The bear's powerful strides propel it across the undergrowth, scattering leaves and twigs in its wake. Sunlight filters through the dense canopy overhead, dappling the forest floor and highlighting the bear's movement. The air is filled with the sounds of nature; birdsong, rustling leaves, and the heavy breathing of the bear as it continues its run, a testament to the raw power and grace of the wild.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1641
|
videos/HRA_part2/1641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man wearing a gray shirt, khaki cargo pants, and a brown belt pauses on a rocky trail, surrounded by lush greenery and towering trees. He leans on a wooden hiking stick, looking intently at the dense forest before him. Moments later, he hikes uphill, carrying a backpack and water bottle, with the sunlight filtering through the leaves overhead. Then, he stops to observe his surroundings, his weathered hands gripping the hiking stick, and the rich green foliage providing a stunning backdrop. Finally, he hikes through the dense wilderness, his attire and equipment suggesting a seasoned outdoorsman, and the vibrant greenery of the forest enveloping him in its beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, legs, and hiking pole are distorted in the video."
}
] |
seed46_1840
|
videos/HRA_part2/1840.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, dressed in a yellow safety vest over a gray shirt and black pants, experiences time dilation as he leaps into the air in a high school gymnasium. The scene is captured from four different angles: first, he is seen standing still, looking at the camera. Then, he jumps into the air, the motion slowed down to emphasize the effect of time dilation, his posture mid-leap. In the next frame, he is frozen mid-air, with a basketball hoop and a volleyball net visible in the background. Lastly, he is shown in slow motion again, this time with a look of determination on his face, highlighting the unique experience of time distortion during his jump.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_159
|
videos/HRA_part0/159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, male gorilla stands in a lush, green forest, engaging in a series of comical dance moves. He begins by swaying side to side, his massive body moving in time with an unseen rhythm. Suddenly, he breaks into a playful jig, his arms flailing wildly as he hops from foot to foot. The gorilla then attempts a spin, his wide grin revealing a mouthful of sharp teeth. Throughout the performance, the gorilla remains in the same spot, his dance a delightful contrast to the stillness of the surrounding environment. Despite his size and strength, the gorilla's movements are surprisingly graceful, his joyous expression captivating as he continues to dance in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the gorilla in the video are twisted while dancing, and the fingers and toes are deformed, with facial features also distorted."
}
] |
seed44_1061
|
videos/HRA_part1/1061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a yellow shirt and black pants, is seen carefully cleaning a large aquarium filled with vibrant fish. The room is bright, with natural light pouring in from a nearby window, highlighting the diligent task at hand. The student, with a focused expression, uses a specialized tool to gently scrub the inside walls of the tank, ensuring a safe and clean environment for the aquatic inhabitants. The fish, undisturbed, swim gracefully around the student's hand, adding a serene element to the scene. The background features educational posters and shelves filled with books, emphasizing the academic setting of this meticulous activity.]"
},
{
"from": "gpt",
"value": "Normal. The boy's arm and hand show deformities."
}
] |
seed42_1198
|
videos/HRA_part0/1198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully filmed close-up of a vibrant, pink-fleshed salmon fillet, glistening under bright lights on a clean, white plate. The salmon is artfully presented with a slice of lemon and a scattering of fresh dill sprigs, enhancing its visual appeal. In the next shot, the camera focuses on a whole salmon, its scales shimmering, resting on a bed of ice, surrounded by greenery, creating a fresh, market-like atmosphere. Finally, the video captures a chef expertly filleting a salmon with precise cuts, the knife gliding smoothly through the fish, accompanied by the soft sound of slicing, against a backdrop of a busy kitchen.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3043
|
videos/HRA_part2/3043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Normal. The facial generation of the server in the video is blurry, and the fingers are deformed."
}
] |
seed42_211
|
videos/HRA_part0/211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene set within the confines of an art gallery, a firefighter clad in full gear and a helmet, carrying an axe, sprints down a wide hallway lined with large paintings and modern art sculptures. The overhead lights cast shadows, adding to the intensity of the moment. Behind him, the glow of an encroaching fire illuminates the space, its orange and red hues contrasting starkly with the artworks. Amidst the chaos, the firefighter's purposeful stride conveys determination and urgency, his mission to save lives and preserve priceless art pieces from the raging inferno.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's hands and feet generation in the video has issues."
}
] |
seed44_1968
|
videos/HRA_part1/1968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone coyote, characterized by its brown and gray fur, alert ears, and a bushy tail, traverses the lush rainforest floor. It walks purposefully among the vibrant green foliage, moss-covered logs, and fallen branches, creating a path through the dense undergrowth. The scene is set in a temperate rainforest, where the air is misty and moist, enhancing the rich greens and browns of the environment. The coyote's journey is filled with the sounds of dripping water and rustling leaves, as it explores this verdant, wet habitat.]"
},
{
"from": "gpt",
"value": "Normal. The wolf in the video walks basically normally, with only slight movement inconsistencies."
}
] |
seed42_2432
|
videos/HRA_part0/2432.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, displaying strength and agility, leaps from a branch in a lush, green forest. The primate, with its dark fur and distinctive features, bounds through the air with a sense of freedom and vitality. As it lands, the chimpanzee's powerful muscles are evident, showcasing the raw energy and grace inherent in its movements. Surrounded by dense foliage and dappled sunlight, the scene captures the essence of life in the wild, focusing on the chimpanzee's leap as a symbol of untamed spirit.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's body is twisted, head is twisted, feet are twisted, legs are twisted, and arms are twisted."
}
] |
seed42_2943
|
videos/HRA_part0/2943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An ibex, distinguished by its dark brown coat and long, curved horns, is captured mid-stride as it sprints across a rocky terrain. The detailed shot focuses on the ibex's powerful legs and hooves, which grip the stone surface, propelling it forward with agility and strength. The ibex's body is outlined against a backdrop of rugged mountains and a clear blue sky, emphasizing its natural habitat. The video highlights the animal's endurance and speed as it navigates the challenging landscape with ease.]"
},
{
"from": "gpt",
"value": "Normal. The video shows abnormal generation of the mouflon's head, and the limbs of the mouflon are distorted and deformed in the middle frames."
}
] |
seed42_2479
|
videos/HRA_part0/2479.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah leaps gracefully over a low branch in a sun-dappled savanna, its body stretched in mid-air, showcasing its remarkable agility and strength. The big cat's spotted coat glistens under the warm sunlight, every muscle taut and defined as it propels itself upward. The surrounding landscape is filled with lush grasses and scattered acacia trees, providing a vivid contrast to the cheetah's dynamic movement. In the background, the horizon stretches far into the distance, marked by a hazy skyline and the promise of endless space, highlighting the cheetah's natural habitat and freedom.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's body is deformed in the video, with missing limbs, an incomplete face, and no tail generated."
}
] |
seed44_1779
|
videos/HRA_part1/1779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone jackal walks through ancient ruins, its sandy fur blending into the weathered stone walls of a historical site bathed in warm sunlight. The camera captures the jackal from various angles, showcasing its cautious exploration of the site, which features tall columns and ornate carvings, hinting at the grandeur of a long-lost civilization. The jackal pauses, its ears perked, scanning the surroundings before continuing its journey through the silent, time-worn corridors, the texture of the stones and the play of light adding depth to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The hyena's walking in the video is uncoordinated."
}
] |
seed42_2294
|
videos/HRA_part0/2294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant neon lights, a magnificent Bengal tiger, detailed with its distinctive orange fur and black stripes, appears to run gracefully through the aisles, its movement captured in stunning detail. The gallery walls are adorned with abstract art pieces, creating a surreal contrast to the powerful, lifelike depiction of the tiger in motion. The tiger's dynamic pose, mid-stride, conveys a sense of freedom and strength within the confined yet imaginative space of the art gallery.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2915
|
videos/HRA_part2/2915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah, embodying grace and power, rests on a dry, grassy savanna, its body curved in a relaxed position. It turns its head, using its paw to wipe its face, showcasing a natural, intimate grooming moment. The cheetah's distinctive black spots stand out against its tan fur, while its piercing eyes and pronounced facial features add depth to the scene. This close-up shot captures the animal's wild beauty and the serene environment surrounding it, with distant trees adding a sense of place to the composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2440
|
videos/HRA_part2/2440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 domestic chicken, featuring brown and white feathers, is shown swimming in a small, clear body of water, surrounded by green grass and foliage. It paddles energetically with its feet, creating ripples on the water's surface, while its head remains dry above the waterline. The chicken's unique activity is captured in a series of shots that showcase its unexpected aquatic adventure in a natural, backyard setting.]"
},
{
"from": "gpt",
"value": "Normal. The entire chicken's body shows signs of deformity and mutation."
}
] |
seed42_1049
|
videos/HRA_part0/1049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, distinguished by his stethoscope around his neck and wearing a white lab coat over a button-down shirt and khaki pants, is standing on a chair in a modern office space. He attentively checks a smoke detector mounted on the ceiling, demonstrating unexpected handyman skills. The room is well-lit and features a large window, a desk with a computer, and various medical posters on the walls, creating a professional yet casual atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the character's hands and legs in the video is problematic."
}
] |
seed42_17
|
videos/HRA_part0/17.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated teacher, wearing a vibrant yellow raincoat and matching boots, stands in the shallow waters of a lush wetland, surrounded by cattails and water lilies. She holds a large, transparent jar filled with water and aquatic insects, engagingly teaching a group of students who sit cross-legged nearby, dressed in waterproof jackets and pants. The students attentively listen, some with binoculars around their necks, as they learn about the wetland ecosystem. The teacher then leads the students in a safe, supervised activity where they wade into the water, using nets to catch and examine small fish and plants, all while standing in the calm, knee-deep water of the wetland.]"
},
{
"from": "gpt",
"value": "Normal. The teacher in the video is holding a transparent jar while teaching, and the students are sitting cross-legged listening to the lesson, which is basically normal but there is some lack of coordination."
}
] |
seed46_1405
|
videos/HRA_part2/1405.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a tiny green jacket ambles along a wooden floor, its alert eyes scanning its surroundings. It pauses for a moment, seemingly considering its next move, before continuing its journey. The ferret then stops again, standing on its hind legs with its front paws raised, revealing the white fur beneath the jacket. Its head turns to look directly at the camera, a mischievous glint in its eyes, before it resumes walking, the green jacket swaying with each step. Throughout the video, the ferret's movements are unhurried and deliberate, as it explores its environment with a mix of caution and curiosity.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements are not smooth."
}
] |
seed42_1298
|
videos/HRA_part0/1298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt, black vest, and black trousers, is seen playfully dancing with an otter. The otter, wearing a tiny bow tie, mirrors the waiter's movements, adding to the surreal atmosphere. The two are surrounded by a softly lit, elegant dining room, with tables set for dinner and fine art adorning the walls. The waiter, with his professional attire, and the otter, with its playful nature, create a harmonious and unexpected dance partnership, captivating the audience with their synchronized steps.]"
},
{
"from": "gpt",
"value": "Normal. The server's movements in the video are not smooth."
}
] |
seed44_267
|
videos/HRA_part1/267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 orchard, a hardworking farmer pauses from his labor, wiping sweat from his brow, while in the foreground, a mongoose is seen playfully exploring its surroundings. The farmer, dressed in a straw hat, denim overalls, and a plaid shirt, leans against a wooden fence, offering a warm smile. Nearby, the mongoose, with its slender body and bushy tail, darts between tree trunks, seemingly unbothered by the human presence. In the distance, a shimmering swimming pool, surrounded by a wooden deck and sun loungers, provides a refreshing contrast to the vibrant orchard setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1752
|
videos/HRA_part0/1752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic industrial setting, a mature man with salt-and-pepper hair and a full beard, wearing a dark jacket, gray shirt, and black pants, gently touches and inspects a large turbine blade from a power plant. The blade is massive, with a metallic sheen, positioned horizontally against a backdrop of complex machinery and pipes, indicative of a hydroelectric or nuclear power facility. The man's tender gesture contrasts with the harsh environment, highlighting a personal connection or professional pride in the technology.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1585
|
videos/HRA_part2/1585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 actor, dressed in a costume resembling a zebra, performs an athletic jump against a background that appears to be a theater stage. The zebra outfit is detailed, featuring black and white stripes, and the actor's face is visible, showing intense concentration. The leap is captured mid-air, highlighting the actor's agility and the costume's dynamic movement, creating a dramatic and captivating scene under the spotlight.]"
},
{
"from": "gpt",
"value": "Bad. The actors in the video perform very awkwardly, with uncoordinated movements."
}
] |
seed44_2881
|
videos/HRA_part1/2881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire consisting of a gray hoodie, blue jeans, and white sneakers, diligently scrubs the bathroom floor with a green cleaning rag. The bathroom is modern, featuring sleek white tiles and fixtures, with a hint of daylight filtering in from a nearby window. The student's focused expression and the repetitive motion of scrubbing convey a sense of determination and responsibility. The scene is set in a clean, well-lit space, emphasizing the student's hard work and attention to detail in maintaining the cleanliness of the bathroom environment.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the person wiping the floor in the video are basically normal, with slight inconsistency."
}
] |
seed42_1108
|
videos/HRA_part0/1108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic orange Bengal tiger with black stripes swims gracefully in a large, natural pond surrounded by lush green vegetation, showcasing its strength and agility in the water. The tiger, with piercing amber eyes and a powerful body, propels itself through the clear blue water with effortless strokes, its thick tail acting as a rudder. Sunlight filters through the dense foliage above, casting dappled light on the tiger's wet fur, highlighting its muscular physique and the water droplets clinging to its coat. The serene environment, complete with the sounds of nature and the gentle lapping of water against the shore, creates a captivating scene of wild beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2551
|
videos/HRA_part0/2551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a flowing white robe with gold trim, stands in a vast, dimly lit space chamber, holding a fluffy rabbit gently against her chest. The chamber is filled with rows of benches, each occupied by similarly dressed figures, all facing an altar adorned with candles and space-themed decorations. The student caresses the rabbit lovingly, her face expressing deep reverence and peace, as the soft light from the candles illuminates the scene, casting a warm glow on everyone present. The rabbit, seemingly aware of its significant role, remains calm and still, adding a sense of serenity to the unique religious ceremony taking place among the stars.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not have any movements."
}
] |
seed44_2974
|
videos/HRA_part1/2974.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. Basically no issues."
}
] |
seed42_2558
|
videos/HRA_part0/2558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a green shirt and khaki shorts, walks through a savanna landscape, holding a book bag, with a hyena casually following at a distance. The student, in casual attire suitable for warm weather, continues walking along a dirt path, with the hyena maintaining a parallel path some distance away. As they move, the student occasionally glances back at the hyena, which returns the look, both seemingly unafraid and unperturbed by each other's presence, set against a backdrop of dry grasses and scattered trees typical of a savanna environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2832
|
videos/HRA_part2/2832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, clad in a yellow vest and hard hat, finds an unexpected moment of joy as he dances alongside a graceful antelope in a vast, sunlit prairie. The worker, dressed in blue jeans, a white t-shirt, and sturdy boots, moves with surprising agility, mirroring the antelope's leaps and bounds. The antelope, with its distinctive horns and russet coat, engages in this whimsical dance, seemingly unfazed by the unusual partnership. Together, they create a surreal and delightful scene against the backdrop of a clear blue sky and distant rolling hills.]"
},
{
"from": "gpt",
"value": "Bad. The faces of the workers in the video are distorted, fingers and feet are deformed, and the head of the antelope is abnormally generated."
}
] |
seed44_1643
|
videos/HRA_part1/1643.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European ring-necked pheasant, with its vibrant plumage featuring striking shades of green, gold, and brown, struts confidently across a grassy field. Its iridescent feathers shimmer in the sunlight, accentuated by the lush green vegetation in the background. The pheasant pauses, its head held high, showcasing the distinctive white collar around its neck and the bold red wattles near its eyes. It then resumes its stately walk, tail feathers fanning out gracefully, embodying the elegance and beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The pheasant in the video has multiple legs generated, and its eyes and claws are not generated. The beak is missing during parts of the video playback."
}
] |
seed46_1703
|
videos/HRA_part2/1703.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, rustic kitchen, two young children, a boy and a girl, both wearing colorful aprons over their clothes, stand on small wooden stools to reach the sink. The girl, with her hair tied in pigtails, holds a wrench with determination while looking intently at the faucet. The boy, wearing glasses, assists by shining a flashlight on the dripping tap, their teamwork highlighted by the warm, golden glow of the overhead lights. The sink is surrounded by decorative tiles, adding a homely touch to the scene. Tools and parts are neatly arranged on the countertop beside them, emphasizing the organized approach to fixing the leaky faucet.]"
},
{
"from": "gpt",
"value": "Normal. The boy does not have a flashlight in his hand."
}
] |
seed44_2796
|
videos/HRA_part1/2796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a yellow high-visibility jacket and hard hat, stands near a bobcat excavator on a construction site. He wipes down the machinery with a cloth, revealing the brand name on the excavator's arm. The scene is set against a backdrop of dirt and gravel, with other construction equipment visible in the background. The engineer's actions showcase the maintenance aspect of his job, highlighting his commitment to keeping the equipment clean and operational.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, and the item in their hands are distorted in the video."
}
] |
seed44_2414
|
videos/HRA_part1/2414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, verdant orchard filled with apple trees heavy with ripe fruit, a large brown bear stands on its hind legs, its shaggy fur glistening in the dappled sunlight. It reaches up with a massive paw, gently swiping at the low-hanging branches laden with apples. The bear then lowers itself to all fours, picking up an apple it has dislodged, and wipes it carefully on its thick fur before taking a hearty bite, savoring the sweet, juicy flavor amidst the peaceful surroundings of the orchard.]"
},
{
"from": "gpt",
"value": "Normal. The brown bear's movements are not smooth."
}
] |
seed44_1238
|
videos/HRA_part1/1238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a European starling perched on a branch, its vibrant plumage shimmering with hues of green and purple under the sunlight. The bird's beady eye is fixed ahead, and its feathers appear ruffled, as if enjoying a gentle breeze. The starling's curved bill and round body are distinct against the blurred green foliage in the background, creating a contrast that highlights the bird's intricate details. The scene is set in a serene forest environment, where the starling seems unperturbed by the camera, offering a rare glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The bird's head turning in the video is basically normal, but there is slight movement inconsistency."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.