video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2376
|
videos/HRA_part1/2376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, vibrant green lizard with intricate patterns on its back traverses slowly across a dry, cracked earth surface, its movements deliberate and methodical. The terrain is peppered with small rocks and tufts of sparse vegetation, providing contrast against the lizard's vivid coloring. Sunlight filters down, casting dappled shadows and highlighting the texture of the lizard's skin as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Bad. The lizard's movement in the video is very unsmooth and the actions are uncoordinated."
}
] |
seed44_1671
|
videos/HRA_part1/1671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, clad in a brown jacket and denim overalls, rests on his hands and knees in a lush green field, engaging in a playful crawl. Beside him, a curious brown hare mimics his movements, hopping and crawling through the tall grass, creating a heartwarming scene of unexpected companionship between man and nature. The farmer's joyful expression and the hare's energetic antics set against the vibrant green landscape capture a rare moment of harmony in the countryside.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the hare in the video are missing, the ears are of different sizes, the facial features are generated unclearly and unreasonably, the body is twisted, the tail is too long, the farmer's fingers are not generated, and the eyes are not generated."
}
] |
seed46_1971
|
videos/HRA_part2/1971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing a gray shirt, sits at a modern office desk cluttered with electronics and tools, knitting a red scarf with large needles. The focus is on her hands as they deftly manipulate the yarn and needles, while a laptop with coding screensaver and a blueprint of a circuit board are visible in the background. The office space is filled with tech gadgets, books, and papers, highlighting her professional environment, yet she finds time for a personal hobby, creating a vivid red scarf amidst the technical surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3193
|
videos/HRA_part1/3193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, distinguished by its golden fur and intricate rosette patterns, sprints across a sun-drenched savanna. Its muscles ripple powerfully beneath its coat, demonstrating raw strength and agility. The leopard's piercing green eyes remain focused ahead, indicating determination and purpose in its stride. It bounds gracefully over the landscape, leaving a trail of displaced grass in its wake, embodying the essence of wild freedom and survival instinct.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's sprinting in the video has uncoordinated movements."
}
] |
seed42_3125
|
videos/HRA_part0/3125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, holding a green notebook, dances energetically on a busy street in Tokyo, her movements conveying a sense of freedom and joy. She wears a gray turtleneck sweater, a brown leather jacket, and a maroon beret, her style blending seamlessly with the urban environment. As she dances, the bustling city life continues around her, with people walking, cars passing, and neon signs illuminating the scene. Her expressive face, framed by her beret, reflects pure delight, and her body language conveys the story of a creative soul finding inspiration in the vibrant heart of Tokyo.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the writer in the video has problems, the fingers are deformed, and the green notebook is distorted."
}
] |
seed46_3085
|
videos/HRA_part2/3085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful swan floats on a serene lake, its elegant white feathers glistening under the golden afternoon sun. The water reflects the bird and the lush green trees that surround the peaceful scene, creating a harmonious blend of nature's beauty. The swan's long, curved neck forms a gentle S-shape as it gently propels itself through the crystal-clear water, leaving a series of delicate ripples in its wake. The tranquility of the moment is punctuated by the occasional sound of the swan's wings softly brushing against the surface of the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2179
|
videos/HRA_part2/2179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a dark green winter jacket, gray gloves, and a matching hat, diligently shovels snow from a pathway in front of a red-brick building with a yellow door. Snowflakes continue to fall gently, accumulating on the ground and surrounding trees. The man, with a serious yet focused expression, works methodically, clearing the path section by section. His breath visible in the cold air, he pauses momentarily, looking up at the sky as if assessing the weather conditions, before resuming his task with renewed determination.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1463
|
videos/HRA_part0/1463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical dry forest, a group of five individuals, three women and two men, engage in a cleaning ritual. The women, dressed in green shirts and beige shorts, wipe leaves from a wooden table under the shade of a large tree. One of the men, wearing a yellow shirt and brown shorts, wipes the surface of a fallen log nearby. The other man, in a white shirt and blue shorts, wipes his brow, likely from the physical exertion of the task. The scene is filled with vibrant green foliage, and a sense of camaraderie and purpose is evident among the group members as they work together in the serene forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand in the video is generated abnormally, and the man's hand is about to deform."
}
] |
seed42_2969
|
videos/HRA_part0/2969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, donning a uniform consisting of a blue shirt and black pants, is seen in a pet store setting, gently caressing a hamster with care. The hamster, nestled in the palm of the worker's hand, is calm and seemingly comfortable with the interaction. The scene is set against a backdrop of various pet supplies and cages, creating a familiar environment for animal lovers. The worker's facial expression conveys a sense of tenderness and respect for the small creature, highlighting the bond between humans and pets.]"
},
{
"from": "gpt",
"value": "Bad. The staff member's hand in the video is deformed, and the hamster's head and paws are generated abnormally."
}
] |
seed42_2011
|
videos/HRA_part0/2011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sandy desert under a clear blue sky, a lone camel, distinguished by a single hump, leaps gracefully into the air. Its action is captured mid-jump, with all four feet off the ground, showcasing its unique ability to navigate the dunes. The camel's tan fur contrasts beautifully with the blue sky and golden sand, highlighting its natural habitat. As it springs forward, the surrounding landscape of dunes and distant mountains provides a stunning backdrop, emphasizing the creature's agility and the serenity of its environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2774
|
videos/HRA_part0/2774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a bushy beard and wearing a brown jacket, blue jeans, and a black cap walks side by side with a coyote on a dirt path. They are set against a background of dense green forest and a sky filled with fluffy white clouds. The man, holding a wooden staff, and the coyote, with its distinctive bushy tail, navigate the wilderness together, their unlikely companionship highlighted by the peaceful, natural setting. Their journey unfolds on a trail marked by fallen leaves and tree roots, with the occasional glimpse of other wildlife in the surrounding woods.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1027
|
videos/HRA_part0/1027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young writer, clad in a red jacket, blue jeans, and black running shoes, races through the bustling city streets at night, passing by a diverse array of shops and restaurants. The urban landscape is illuminated by the glow of neon signs and streetlights, casting dynamic shadows as the runner weaves through the crowd. The scene captures the energy and vibrancy of city life, with the writer's determination and focus highlighted by the motion blur of the passing scenery. The narrative unfolds as the runner passes landmarks like a movie theater, a busy crosswalk, and a street food vendor, all contributing to the vivid tapestry of the urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1717
|
videos/HRA_part2/1717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and utility belt, stands in a dimly lit alleyway, his face partially obscured by shadow. He takes a deep breath, his chest expanding beneath his bulletproof vest, as he prepares for action. The focus is on his breathing, a testament to his calm under pressure, with the urban environment providing a gritty backdrop. His hand rests on his holstered weapon, and his eyes scan the surroundings, alert and watchful, as he draws another measured breath.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed42_1167
|
videos/HRA_part0/1167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings in the early morning light of the African savanna. Suddenly, it jumps into the air, its body stretched out horizontally, with the vast, grassy plains and distant acacia trees forming a picturesque backdrop. The meerkat lands softly on the ground, its eyes wide and alert, before quickly resuming its watchful stance, ears perked and ready for any sign of danger or activity in the wild landscape that surrounds it.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's movements are not smooth."
}
] |
seed44_1769
|
videos/HRA_part1/1769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow safety vest and dark pants, sprints with urgency across a wooden bridge overlooking a geyser's steamy plume in the background. The scene shifts to show the janitor running from right to left, with the geyser's eruption seen erupting behind him, emphasizing his hurried pace. Next, he is depicted dashing down a stone pathway, with the geyser's intermittent eruptions providing a dramatic backdrop. Finally, the janitor is shown sprinting on a dirt path, with the geyser's majestic plumes in the distance, highlighting his perseverance against the geothermal landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2419
|
videos/HRA_part2/2419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's legs and head are twisted in the video, as well as the character's head and arms."
}
] |
seed46_2626
|
videos/HRA_part2/2626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a cluster of jellyfish, predominantly moon jellyfish, gracefully floats in a harmonious formation. Their translucent bell-shaped bodies, illuminated by a soft blue light, reveal intricate patterns and textures. Surrounding them are various marine creatures, including small fish and other jellyfish species, adding to the vibrant ecosystem. The jellyfish pulsate rhythmically, propelling themselves through the water, while their trailing tentacles gently undulate, creating a mesmerizing visual display in this serene aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_279
|
videos/HRA_part1/279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human teacher, wearing a casual blue shirt and jeans, is playfully dancing in a classroom filled with natural light, alongside a chimpanzee. The chimpanzee, dressed in a miniature version of the teacher's outfit, mirrors the teacher's dance moves with joyful expressions. Both the teacher and the chimpanzee engage in synchronized steps, creating a harmonious and whimsical scene, as they move across the room with the sun casting gentle shadows behind them. The teacher's face reflects amusement and connection, while the chimpanzee's animated body language conveys a sense of fun and companionship in their shared activity.]"
},
{
"from": "gpt",
"value": "Bad. The mini version of the casual blue shirt and jeans did not appear in the video."
}
] |
seed44_201
|
videos/HRA_part1/201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black panther is filmed in high definition, gently caressing a log with its paw in a lush, green rainforest. The panther, with piercing yellow eyes, rests its massive head on the log, showcasing its strength and grace. It then proceeds to rub its cheek against the log, marking its territory, while the camera captures every detail of its luxurious fur and the intricate textures of the forest environment. The scene is set in a dense jungle, with sunlight filtering through the canopy, highlighting the panther's sleek silhouette and the vibrant foliage surrounding it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1780
|
videos/HRA_part0/1780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly female cashier with brown hair pulled into a bun, wearing a green apron over a striped shirt, leans over to gently caress a koala standing on its hind legs on the counter. The koala, with its soft gray fur and curious expression, reaches up with its paw toward the cashier's face, creating a heartwarming interaction between the two. Behind the counter, a cash register and various retail items can be seen, adding to the unique setting of this tender moment.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's movements are not smooth, and the actions are uncoordinated. The koala's movements are not smooth."
}
] |
seed46_2313
|
videos/HRA_part2/2313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden jackal leaps gracefully over a log in the middle of a grassy savanna, its body stretched mid-air, showing agility and strength. The jackal, with its keen eyes and alert posture, exhibits a powerful jump, clearing the obstacle effortlessly. The scene captures the animal's dynamic movement against a backdrop of tall grasses swaying in the breeze, highlighting the beauty and resilience of this wild canine in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the golden jackal in the video are missing, and the proportions are incorrect when the body jumps."
}
] |
seed42_2595
|
videos/HRA_part0/2595.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, softly lit living room filled with the warm glow of a fireplace, two young children sit closely together on a plush, brown couch. One child, a little boy with short, curly hair, wears a gray sweater and leans into his sister, who has straight, shoulder-length hair and dons a pink dress. They both hold hands comfortingly, displaying signs of illness, as they occasionally cough into their elbows, demonstrating proper hygiene etiquette. The room is decorated with a large, colorful rug and various soft toys scattered around, creating a familiar and homey atmosphere. The siblings' focus is on a book about dinosaurs, which lies open in front of them, indicating their attempt to distract themselves from feeling unwell.]"
},
{
"from": "gpt",
"value": "Normal. The little boy's movements in the video are basically normal, while the girl's movements in the video are not smooth and coordinated."
}
] |
seed46_232
|
videos/HRA_part2/232.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 artist's hand and the tool in the hand have generation issues; the tool suddenly bends or enlarges in the middle frames."
}
] |
seed42_1631
|
videos/HRA_part0/1631.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a vibrant yellow dress and a wide-brimmed sun hat, dances gracefully in the midst of a vast scrubland. The landscape is dotted with low-lying bushes and sparse trees, stretching far into the horizon under a clear blue sky. Her joyful movements contrast beautifully with the stillness of the arid environment, creating a captivating scene where education meets nature's tranquility. The teacher's animated gestures and warm smile convey a sense of freedom and connection to the rugged yet serene surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2885
|
videos/HRA_part2/2885.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a gray suit, white shirt, and blue tie, walks purposefully across a futuristic asteroid mining facility. The setting is a large, circular room with a high ceiling and industrial equipment, bathed in a warm orange glow. He carries a brown leather briefcase in his right hand, displaying a confident and focused demeanor. Behind him, the dimly lit interior of the asteroid can be seen, with mining machinery and workers in protective gear visible in the distance. The lawyer's strides are firm and decisive, highlighting his determination and professionalism in this unique and challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's movements in the video are slightly unsmooth."
}
] |
seed44_2439
|
videos/HRA_part1/2439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with graying hair, wearing a dark green jumpsuit, is assembling a wooden table in a brightly lit, empty room with beige walls. He carefully reads the instruction manual, focusing intently on the task at hand. Moments later, he is seen tightening screws with a screwdriver, his brow furrowed in concentration. Then, he stands back to admire his handiwork, the completed table standing sturdy and polished. Finally, he wipes his forehead with a cloth, revealing a look of satisfaction and a hint of exhaustion, the newly assembled table now adorned with a vase of flowers, adding a touch of life to the barren room.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm are deformed and distorted, and the object in his hand also undergoes a sudden change."
}
] |
seed42_1366
|
videos/HRA_part0/1366.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit consisting of a gray t-shirt and blue jeans, sits at a desk in a classroom filled with other students. The room is brightly lit by large windows, casting natural light onto the desks and walls adorned with educational posters. The student yawns widely, covering their mouth with a hand, indicating tiredness during the class. The scene captures a relatable moment of fatigue in an everyday learning environment.]"
},
{
"from": "gpt",
"value": "Normal. The boy in the video covers his mouth with his hand and yawns, which is basically normal, but there is some lack of coordination."
}
] |
seed44_3097
|
videos/HRA_part1/3097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a male worker in a red uniform tends to an art gallery space that doubles as a swimming pool, with water visible through a glass wall. He walks along the edge of the pool, which is surrounded by artworks, including a sculpture and framed pieces on the walls. The man, wearing red swim trunks, a red polo shirt, and a black cap, interacts with the space, showcasing the blend of aquatic and artistic elements. He is seen both working and swimming, highlighting the versatility of the environment, with the water's surface shimmering under the gallery lights.]"
},
{
"from": "gpt",
"value": "Bad. The male staff member's face in the video is generated blurry, his fingers are deformed, and there are frames where he is generated with three hands."
}
] |
seed44_1420
|
videos/HRA_part1/1420.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a bright, cloudless sky, a single dromedary camel leaps gracefully over a fallen tree trunk. Its tan fur contrasts starkly with the pale sand, and its large, expressive eyes are fixed ahead. The camel, wearing a simple brown strap across its torso, lands softly on the other side of the obstacle, continuing its journey across the dunes with a sense of purpose and freedom. The scene captures the unexpected agility of this desert dweller against the serene, unbroken landscape.]"
},
{
"from": "gpt",
"value": "Normal. The camel's movements in the video are not smooth."
}
] |
seed44_2273
|
videos/HRA_part1/2273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting illuminated by vibrant neon lights, a diligent worker clad in a gray jumpsuit and helmet stands on a sleek, anti-gravity vehicle. The vehicle, featuring a metallic finish and aerodynamic design, hovers above a clean, white platform. The worker is engaged in wiping the vehicle's surface with a cloth, ensuring its spotless condition. Behind the scene, a vast hangar filled with advanced technology and equipment can be seen, emphasizing the high-tech environment in which the worker operates. The worker's focused expression and meticulous attention to detail highlight their commitment to maintaining the anti-gravity vehicle's pristine state.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1999
|
videos/HRA_part0/1999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the bustling activity of a harbor filled with boats and people, two young boys perform a daring leap from a wooden dock into the shimmering water below, their joyful expressions and the spray of water capturing the thrill of their summer adventure. Dressed in casual shorts and t-shirts, they are silhouetted against the bright sky, their bodies mid-air in a moment frozen in time, encapsulating the essence of youthful freedom and the vibrant life of the harbor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2053
|
videos/HRA_part1/2053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, futuristic space station, a diligent janitor, clad in a silver reflective suit, pushes a high-tech cleaning cart while walking down a long, sterile corridor illuminated by cool, artificial lights. Suddenly, the walkie-talkie on his belt crackles to life, transmitting a message from mission control regarding an incoming transmission from deep space. The janitor stops, listens intently, and acknowledges the message before continuing his duties, passing by a large window displaying the awe-inspiring view of distant galaxies and star clusters. Throughout the scene, a small Bobcat construction vehicle, equipped with advanced space-grade tools, can be seen in the background, autonomously performing maintenance tasks on the station's outer hull.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, face, hands, and legs are distorted in the video."
}
] |
seed46_3155
|
videos/HRA_part2/3155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a red jacket and black pants, is scaling an indoor climbing wall with intense focus, framed by a large window that bathes the scene in natural light. The gymnasium's high ceiling and climbing wall provide a spacious setting, while motivational posters and equipment add context to the environment. The climber's left hand grips a green hold, their right hand poised to grab a blue hold, and both feet are firmly planted on orange footholds, illustrating their progress up the wall. Their backpack rests on the floor, and a climbing harness and helmet ensure safety during the ascent.]"
},
{
"from": "gpt",
"value": "Bad. The student's face, hands, and legs are distorted in the video."
}
] |
seed42_2392
|
videos/HRA_part0/2392.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 of a vibrant green lizard, its textured skin detailed, as it sits on a wooden branch in a lush swamp environment. The scene is set in a dense, swampy forest, with the lizard performing a wiping motion across its eye, a behavior often observed in the wild. The background is filled with the rich greens of swamp vegetation, creating a vivid contrast against the lizard's striking appearance. Throughout the video, the focus remains on the lizard's actions, particularly the wiping gesture, which adds an element of intrigue and natural behavior to the footage.]"
},
{
"from": "gpt",
"value": "Normal. The lizard's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed42_21
|
videos/HRA_part0/21.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, wearing a khaki safari shirt and matching trousers, stands in a lush, verdant enclosure at a wildlife sanctuary. He gently caresses the wrinkled, gray skin of a large hippopotamus, which towers over him, standing on its hind legs with its front paws on the man's shoulders. The man looks up at the creature with a mixture of awe and tenderness, while the hippo appears relaxed and comfortable with the interaction. The enclosure is filled with tall grasses and scattered trees, providing a natural habitat for the animal, and the man's presence suggests a close bond between human caretaker and wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The faces of the characters in the video are distorted, the hands are distorted, the hippopotamus's face is distorted, and the feet are distorted."
}
] |
seed44_274
|
videos/HRA_part1/274.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the heart of a vast desert, two young children, a boy and a girl, clad in vibrant red shirts and denim shorts, leap into the air in unison, their silhouettes framed against the golden dunes and a clear blue sky. They jump from a sandy mound, their faces alight with joy and the wind tousling their hair, encapsulating the spirit of youthful adventure. Behind them, a series of similar sand dunes stretch towards the horizon, while the sun casts a warm glow over the entire scene, highlighting the texture of the sand and the children's animated expressions.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2299
|
videos/HRA_part2/2299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A great egret, standing tall with folded wings, perches gracefully on one leg atop a weathered wooden post in the midst of a serene marsh landscape, surrounded by lush green vegetation and calm waters. Its pristine white feathers contrast beautifully against the natural backdrop, while its sharp yellow eyes scan the environment keenly. The scene is set during the golden hour, with the warm sunlight casting a soft glow over the bird and its habitat, highlighting the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1000
|
videos/HRA_part0/1000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, donning a red apron over a casual outfit, is shown unclogging a drain in a break room, revealing a moment of unexpected duty. The scene opens with the cashier looking into the drain with a concerned expression, followed by her using a plunger to clear the clog, showcasing determination. Next, she inspects the plunger with a look of resolve, indicating her commitment to resolving the issue. The scene then shows her pouring a cleaning solution down the drain, wearing rubber gloves for protection, and finally, she tests the faucet, ensuring the water flows freely, a sign of success, all while maintaining her red apron emblematic of her primary role.]"
},
{
"from": "gpt",
"value": "Good. The character's movements in the video are basically normal, with no obvious problems."
}
] |
seed42_1102
|
videos/HRA_part0/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2407
|
videos/HRA_part0/2407.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars gracefully through a clear blue sky, its powerful wings outstretched against the backdrop of a lush, green forest below. The hawk's piercing golden eyes scan the landscape for prey, its sharp talons ready to strike. The camera captures the intricate feather patterns on its broad wings and tail, highlighting the beauty and strength of this avian predator. As it glides effortlessly, the wind ruffles its feathers, and the sunlight reflects off its body, creating a mesmerizing display of nature's majesty.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1801
|
videos/HRA_part1/1801.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage boy, wearing a gray jacket over a blue collared shirt, sits in a classroom with a concerned look on his face. He coughs into his elbow, drawing the attention of his peers. The room is filled with natural light, highlighting the concerned expressions of his classmates who are seated at their desks. A teacher, dressed in a dark blazer and light-colored shirt, stands nearby, watching the situation with a look of care and readiness to assist. The classroom is decorated with posters and artwork, giving it a homely and educational atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1207
|
videos/HRA_part1/1207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a vast, sandy beach, a waiter, dressed in a white button-down shirt and black pants, crawls towards a table set with fine dining ware, a bottle of wine, and two glasses, indicating an unusual yet intriguing service style. The waiter, wearing a name tag and sporting a neatly trimmed beard, continues crawling on the sand, his posture and facial expression suggesting determination. He crawls under a beach umbrella, highlighting the unique setting for this dining experience, with the calm sea and clear blue sky providing a picturesque backdrop. Finally, the waiter reaches the table, still crawling, as he prepares to serve the patrons, creating a memorable and unconventional beachside dining scene.]"
},
{
"from": "gpt",
"value": "Bad. The server's face and hands in the video have generation issues."
}
] |
seed46_1168
|
videos/HRA_part2/1168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant park, a majestic leopard, its golden eyes alert, crouches near the edge of a pristine swimming pool, surrounded by vibrant greenery and towering palm trees. The big cat, with its distinctive rosette patterns on a tawny coat, gazes intently at the clear water, contemplating a playful leap. Moments later, it leaps gracefully into the pool, its powerful body slicing through the water in a fluid motion. Emerging from the pool, the leopard shakes off droplets, revealing its muscular physique, as it strides confidently across the park, leaving behind a trail of shimmering water on the sun-drenched pavement.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's head is twisted, and its legs are deformed."
}
] |
seed44_1855
|
videos/HRA_part1/1855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bespectacled female doctor in a white lab coat, adorned with colorful pins, dances energetically in a spacious, well-lit room. Her attire includes a vibrant red blouse and stylish glasses, adding to her lively appearance. In her arms, she cradles a relaxed, curious ferret, which seems unperturbed by the dancing. The pair moves in sync, the doctor's joyful expression and the ferret's inquisitive gaze capturing the essence of an unexpected yet delightful moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1655
|
videos/HRA_part0/1655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit with pink ears sprints across a grassy field adjacent to a busy highway, its powerful hind legs propelling it forward urgently. The highway, bustling with vehicles, forms a stark contrast to the natural landscape where the rabbit runs. Sunlight filters through cumulus clouds, casting dynamic shadows on the scene as the rabbit continues its hurried journey, highlighting the unexpected encounter between nature and urban infrastructure.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's running motion in the video is more pronounced, but the movements are not smooth and coordinated."
}
] |
seed44_2480
|
videos/HRA_part1/2480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male lion, distinguished by his thick, dark mane, powerful build, and tawny coat, sprints across a vast, arid savanna. His piercing yellow eyes and focused expression convey determination. The lion's muscular legs propel him forward in a burst of speed, stirring up clouds of dust beneath his paws. The landscape is dotted with scattered acacia trees and distant mountains, providing a rich, natural setting for this awe-inspiring display of raw power and grace.]"
},
{
"from": "gpt",
"value": "Normal. The lion's limbs are missing in the video, and the face is generated blurry."
}
] |
seed42_1150
|
videos/HRA_part0/1150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy gerbil dons a miniature engineer's outfit, complete with a hat, as it energetically operates toy-sized control panels in a fantasy power plant. The vibrant room, filled with dancing lights and kinetic energy, pulses to an upbeat tune. The gerbil, now spinning gleefully on a tiny dance floor, is bathed in the colorful glow, its cheeks puffed out in pure delight. Surrounded by cartoonish power plant machinery, the gerbil continues its joyful dance, embodying a unique fusion of industrial might and playful abandon.]"
},
{
"from": "gpt",
"value": "Normal. The hamster is missing the engineer's outfit and hat."
}
] |
seed44_2448
|
videos/HRA_part1/2448.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, characterized by its dark fur and physical strength, leaps powerfully from a low branch in a lush, green forest. The chimp, wearing a radio collar for tracking purposes, is seen mid-jump, demonstrating its agility and vitality. Its movement is captured in high definition, highlighting the details of its fur and the determination in its eyes. The chimpanzee propels itself forward, leaving the branch behind, showcasing its natural habitat and behaviors in a captivating, close-range shot.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's jumping movements in the video are discontinuous and there are abrupt changes."
}
] |
seed44_2346
|
videos/HRA_part1/2346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a plush koala toy, complete with realistic details and a charming face, comes to life against a green, leafy background reminiscent of eucalyptus. This adorable koala, clad in miniature jeans and a checkered shirt, begins to dance gracefully, its movements synchronized with an upbeat melody. Its paws sway side to side, and it gently bounces in place, capturing the essence of joy and playfulness. The dancing koala, set against the lush foliage, creates a delightful and enchanting moment, perfect for evoking smiles and happiness.]"
},
{
"from": "gpt",
"value": "Normal. The bear's movements in the video are not smooth."
}
] |
seed42_2662
|
videos/HRA_part0/2662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a yellow vest over a dark jacket and shirt, pushes a green cart filled with cleaning supplies across a wide, empty corridor. A small gerbil, held gently in his right hand, sits atop a red mop head, seemingly unfazed by its unusual perch. The janitor walks with purpose, his left hand resting on the cart's handle, while the gerbil remains calmly perched on the mop, offering a peculiar yet endearing contrast to the mundane task of cleaning.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1621
|
videos/HRA_part2/1621.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 professional lawyer, dressed in a dark gray suit with a light gray shirt and red tie, prepares coffee in a modern kitchen. The lawyer, wearing glasses, carefully measures coffee grounds into a French press, adding hot water from a sleek electric kettle. The scene captures the lawyer's meticulous attention to detail, from pouring the water to stirring the mixture gently. The lawyer then presses down the plunger slowly, ensuring a rich brew, all while surrounded by stainless steel appliances and minimalist design elements, creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The clip in the hand suddenly disappears. The hand appears deformed, and water pours out from it."
}
] |
seed46_2782
|
videos/HRA_part2/2782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a black shirt and black jeans, is seen in a studio, wiping down a zebra-striped bass guitar with a cloth. The room is filled with musical instruments and equipment, including a drum set, a keyboard, and various guitars. The musician's focus is intense as they meticulously clean the unique instrument, the zebra-striped bass guitar, ensuring it remains in pristine condition. The scene is intimate, capturing the musician's dedication to their craft amidst a backdrop of musical passion and creativity.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3165
|
videos/HRA_part0/3165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative woman, clad in a yellow top and denim jeans, stands before a large canvas in an airy studio filled with natural light. She holds a paintbrush in her right hand, dabbing it into a vivid palette of colors, while her left hand rests on her hip. Her wavy brown hair cascades down her back as she intently focuses on her artwork, surrounded by a scattering of completed paintings and art supplies. The atmosphere is one of tranquility and inspiration, with the unfinished painting on the easel capturing the essence of her artistic process.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2504
|
videos/HRA_part2/2504.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated doctor, clad in a white lab coat and protective goggles, embarks on an extraordinary adventure, crawling through a meticulously detailed, space-themed diorama. This unique setting features a realistic comet in pursuit, depicted through dynamic lighting and visual effects, creating an engaging narrative. The doctor, equipped with a futuristic tool kit, exhibits determination and focus, navigating the challenging terrain with precision. The comet, represented by a meticulously crafted model, trails closely behind, adding a thrilling element to the scene. Throughout the video, the doctor's journey is portrayed with a blend of scientific curiosity and cosmic wonder, set against a backdrop of meticulous craftsmanship and vivid imagination.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_1034
|
videos/HRA_part1/1034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 buzzard soars through the sky, its broad wings spread wide as it glides over a rugged, rocky landscape. The bird's sharp eyes scan the ground below, searching for prey among the boulders and sparse vegetation. Its feathers catch the sunlight, revealing shades of brown and white, while its powerful talons remain ready to strike at a moment's notice. The scene is set against a vast, open sky, emphasizing the buzzard's freedom and dominance over its territory.]"
},
{
"from": "gpt",
"value": "Bad. An extra wing, deformed head, an additional claw, and a twisted body."
}
] |
seed44_159
|
videos/HRA_part1/159.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 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, 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": "Normal. The gorilla's movements are not smooth."
}
] |
seed44_1708
|
videos/HRA_part1/1708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the heart of Tokyo's bustling streets, a skilled chef, dressed in a traditional white chef's uniform with black accents, stands outside his restaurant. He meticulously wipes down a gleaming steel food cart, ensuring every surface is spotless. Behind him, the vibrant city life continues, with neon signs, pedestrians, and the occasional passing car, all set against the backdrop of a modern metropolis. The chef's focused gaze and steady hand convey a sense of pride and dedication to his craft, even in the simple act of cleaning, under the watchful eye of the busy urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1800
|
videos/HRA_part0/1800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_2140
|
videos/HRA_part0/2140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a beige cap and black jacket, sits on a chair next to a swimming pool at a luxurious hotel, surrounded by lush greenery and palm trees. The director holds a megaphone in one hand and a script in the other, meticulously planning the next shot. Nearby, a cobra slithers across the sun-drenched tiles, its scales shimmering under the bright sunlight, adding an unexpected element of danger to the idyllic scene. The hotel's grand architecture looms in the background, its white walls contrasting against the deep blue of the pool and the vibrant green foliage, creating a visually stunning setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, and the snake's body is slightly twisted."
}
] |
seed42_1536
|
videos/HRA_part0/1536.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous nurse, clad in a blue medical scrub top and black pants, stands in a dramatic pose against a vivid, cloudy sky, with a buffalo charging in the background, creating a striking contrast. Moments later, she is shown running swiftly across a grassy field, the buffalo now galloping alongside her in the distance, both set against a backdrop of lush greenery and distant mountains. The nurse's attire remains consistent throughout, consisting of the blue scrub top, black pants, and white sneakers, while the buffalo's powerful form and the natural landscape provide a dynamic setting for this unique scene.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2215
|
videos/HRA_part1/2215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, sits in an office with wooden shelves and books in the background, gently caressing a porcupine. The lawyer, with neatly combed gray hair and glasses, looks directly at the camera, holding the porcupine with care. In another shot, the lawyer, still in his professional attire, cradles the porcupine in his hands, showing a softer side amidst the serious atmosphere of the law office, filled with books and legal documents. Throughout, the unlikely pairing of the suited lawyer and the spiky porcupine conveys a message of tenderness and unexpected connections.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's movements while petting the porcupine in the video are basically normal, with slight awkwardness."
}
] |
seed42_1740
|
videos/HRA_part0/1740.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a white apron over a black t-shirt and jeans, throws clay on a spinning pottery wheel under the glow of bright studio lights. With intense concentration, they shape the clay into a vase, their hands moving gracefully and purposefully. The camera captures the artist's face, reflecting determination and skill, as they mold the clay. Throughout the process, the artist's attire remains consistent, and the scene is set against a backdrop of a well-lit workshop filled with various pottery tools and finished pieces.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1612
|
videos/HRA_part2/1612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful doctor, wearing a stethoscope around his neck and a colorful tie, is laughing heartily with his head thrown back, his eyes closed, and his mouth wide open, showing his amusement in a candid moment. The laughter is contagious, spreading joy and positivity in a medical setting, with the doctor's facial features animated and expressive, capturing the essence of happiness and camaraderie in a professional environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2719
|
videos/HRA_part0/2719.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lavish decorations for an extravagant wedding, a neatly-dressed cashier, wearing a classic black vest and bow tie, diligently wipes the immaculate glass counter with a small cloth. The backdrop features elegant table settings, floral arrangements, and a large, illuminated dance floor, all indicative of an upscale celebration. The cashier's meticulous attention to detail ensures the space station's cash register area remains spotless amidst the grand festivities.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's fingers are deformed, and the face is blurry in the video."
}
] |
seed44_1771
|
videos/HRA_part1/1771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a duty belt and a radio, is seen kneeling on a polished wooden floor in a residential setting, attentively wiping the muddy paws of a large, brown dog. The officer wears a serious expression, focused on the task at hand, ensuring the canine's paws are clean. The environment is warm and welcoming, with a Christmas tree in the background, decorated with colorful ornaments and lights, adding a festive touch to the scene. The officer's careful actions and the presence of the holiday decorations create a sense of care and community during the holiday season.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's wiping motion in the video is basically normal, with slight disharmony."
}
] |
seed44_1848
|
videos/HRA_part1/1848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, reminiscent of Chris Hemsworth, is seen in a modern living room with large windows, assembling furniture with ease. He wears a fitted gray t-shirt and dark jeans, highlighting his muscular physique. In one scene, he skillfully hammers a nail into a wooden board, his biceps flexing. Next, he aligns and secures two pieces of furniture with a screwdriver, showcasing his handyman skills. Then, he tightens a bolt on a metal frame, demonstrating precision and focus. Finally, he proudly admires the completed furniture, which includes a sleek wooden table and matching chairs, his satisfied smile adding a touch of charm to the domestic scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_165
|
videos/HRA_part0/165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lush greenery, a distinguished doctor, wearing a classic white lab coat over a crisp blue shirt, performs a solemn wedding ceremony. The couple, dressed in elegant spacesuits with transparent helmets, exchange loving glances as they gently caress each other's hands, symbolizing their deep connection. Behind them, a panoramic view of the Earth and stars provides a breathtaking backdrop, while the doctor's compassionate demeanor adds a touch of humanity to this extraordinary union in zero gravity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2070
|
videos/HRA_part2/2070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, iridescent green and purple, hovers near a red feeder, its wings a blur of motion against a clear blue sky, set against the backdrop of a lush garden filled with various flowers and greenery. The tiny bird's red beak is extended toward the feeder, while its body remains remarkably still despite the rapid wing beats. Its vibrant feathers catch the sunlight, creating a shimmering effect as it feeds, encapsulating the beauty and agility of nature in this serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The bird's beak and eyes are generated multiple times, and there are issues with the wings."
}
] |
seed46_1095
|
videos/HRA_part2/1095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully through a clear blue sky, its sleek silhouette framed against the horizon. It dives sharply, wings tight to its body, chasing an unseen prey across the vast expanse. Its sharp eyes, focused and intense, scan the terrain below for any hint of movement. The bird then lands on a branch, its feathers ruffled by the wind, revealing a striking pattern of brown and white. It sits still, perched regally, surveying its domain with a fierce gaze, a true ruler of the skies.]"
},
{
"from": "gpt",
"value": "Bad. The eagle's wings and head are deformed in the video."
}
] |
seed42_2074
|
videos/HRA_part0/2074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dimly lit, high-end restaurant, a well-dressed waiter, wearing a black vest and tie, pulls out a chair for a customer at a candlelit table set with fine china and crystal glasses. The background features other patrons enjoying their meals, adding to the ambiance of a busy, upscale dining experience.]"
},
{
"from": "gpt",
"value": "Bad. The actions are slightly discontinuous, with sudden changes."
}
] |
seed46_255
|
videos/HRA_part2/255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a navy suit, white shirt, and patterned tie, sits on a pier with a mongoose resting on his shoulder. The lawyer gently caresses the mongoose, which is adorned with a small red bowtie, as they both look out over the calm waters. The scene is set during the golden hour, with the warm sunlight casting a serene glow over the water and the pier. The lawyer's attire and demeanor suggest a successful career, while the presence of the mongoose adds an unexpected touch of whimsy to the composition.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's face is distorted, and the character's hands are twisted."
}
] |
seed44_3008
|
videos/HRA_part1/3008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 blue jeans, is seen energetically dancing in a surreal scene set in the middle of a vast prairie. Surrounding him are several large bison, who calmly observe the director's enthusiastic dance moves under the open sky. The director, displaying an unexpected sense of whimsy, continues to dance amidst the majestic animals, creating a unique juxtaposition between human creativity and the untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1800
|
videos/HRA_part0/1800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1450
|
videos/HRA_part0/1450.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 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 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": "Normal. The bear's legs are deformed."
}
] |
seed44_1708
|
videos/HRA_part1/1708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo's bustling streets, a skilled chef, dressed in a traditional white chef's uniform with black accents, stands outside his restaurant. He meticulously wipes down a gleaming steel food cart, ensuring every surface is spotless. Behind him, the vibrant city life continues, with neon signs, pedestrians, and the occasional passing car, all set against the backdrop of a modern metropolis. The chef's focused gaze and steady hand convey a sense of pride and dedication to his craft, even in the simple act of cleaning, under the watchful eye of the busy urban environment.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the person wiping the stainless steel dining cart in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed46_2836
|
videos/HRA_part2/2836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and whimsical scene, a small, cartoonish grey elephant, adorned with a red polka-dotted bow around its neck, is shown mid-jump, its trunk lifted playfully. Against a vivid, clear blue sky, this joyful creature leaps from a lush green meadow dotted with yellow flowers, capturing a moment of pure delight and fantasy. The elephant's large ears are spread wide, adding to the comical effect, while its tiny eyes are closed in sheer happiness, creating a charming and unforgettable visual.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's movements in the video are not smooth."
}
] |
seed44_2479
|
videos/HRA_part1/2479.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 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 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": "Good. No obvious issues."
}
] |
seed42_2201
|
videos/HRA_part0/2201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 girls wearing colorful party dresses and headbands with attached animal ears are seen dancing joyfully in a room decorated with balloons and streamers. Amidst the celebration, a small, live hedgehog sits calmly on a table covered with a checkered cloth, surrounded by party snacks and a cake. The hedgehog occasionally moves its quills, seemingly joining in the festivities, as the girls continue their lively dance, their movements filled with laughter and the innocence of childhood joy.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2104
|
videos/HRA_part2/2104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, donning a crisp white shirt and black vest, stands in a spacious living room with hardwood floors and a large window, engaging in an unusual task. He is diligently assembling a wooden table using various tools, demonstrating unexpected handyman skills. As the scene progresses, the fully assembled table is revealed, complete with a tablecloth and set for a meal, blending elements of his professional service role with a domestic setting. The waiter then proceeds to polish the silverware, juxtaposing his traditional duties with the earlier DIY activity, all within the same elegant residential space.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand appears deformed and the table suddenly disappears at the end."
}
] |
seed46_1831
|
videos/HRA_part2/1831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and blue gloves, is seen wiping the nose of a friendly coyote who is sitting calmly on a checkered medical table. The room is brightly lit, with medical supplies neatly arranged on shelves in the background. The doctor's compassionate expression and the coyote's trusting demeanor create a heartwarming moment, highlighting an unusual yet tender interaction between human and wild animal in a clinical setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1634
|
videos/HRA_part1/1634.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny, curious brown mouse crawls across the center of a large, gleaming solar sail, set against the vast, dark expanse of space. The sail, illuminated by distant stars and a faint blue planet on the horizon, captures the sunlight, creating a play of light and shadow as the mouse explores its surface. The contrast between the small creature and the grandeur of the solar sail highlights the scale and wonder of space exploration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1004
|
videos/HRA_part0/1004.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 muscular firefighter, dressed in full gear and a yellow reflective jacket, interacts with a graceful gazelle in a surreal, dreamlike scenario. They stand together in a shallow, clear blue swimming pool, surrounded by lush green foliage. The firefighter gently touches the gazelle's head, while the animal remains calm and curious. Both share the water, creating an unexpected yet harmonious connection between human, wildlife, and nature, all set against a backdrop of vibrant greenery and clear blue skies.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2070
|
videos/HRA_part1/2070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, iridescent green and purple, hovers near a red feeder, its wings a blur of motion against a clear blue sky, set against the backdrop of a lush garden filled with various flowers and greenery. The tiny bird's red beak is extended toward the feeder, while its body remains remarkably still despite the rapid wing beats. Its vibrant feathers catch the sunlight, creating a shimmering effect as it feeds, encapsulating the beauty and agility of nature in this serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The bird's flight in the video is basically normal, but there is slight motion inconsistency."
}
] |
seed46_1447
|
videos/HRA_part2/1447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A ghost shrimp, nearly transparent with a slight gray tint, clings to the side of an aquarium, showcasing its delicate, see-through body and intricate internal structures. It hovers near a piece of driftwood, its multi-segmented legs and antennae visible as it interacts with its environment. The shrimp's eyes, dark and prominent against its translucent body, stand out as it explores its surroundings, highlighting its unique adaptation to freshwater habitats. Against the green backdrop of aquatic plants, the ghost shrimp's ethereal presence is captivating, offering a close-up view of its otherworldly form.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1721
|
videos/HRA_part1/1721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear, including a red coat, yellow reflective strips, and a helmet, dances energetically on a busy Shanghai street. The urban landscape, featuring modern skyscrapers and bustling city life, provides a stark contrast to his joyful movements. Pedestrians and traffic, including cars and a bus, surround him, highlighting the unexpected nature of his dance. Despite the urban chaos, he moves freely, a bright spot in the gray cityscape, his figure standing out against the backdrop of tall buildings and moving vehicles.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's face is distorted in the video, and the limbs are generated with severe abnormalities, disappearing or appearing suddenly in the middle frames."
}
] |
seed44_2190
|
videos/HRA_part1/2190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown beret and glasses, sits in a dimly lit studio filled with art supplies and paintings, engrossed in reading a book about art history. The camera captures the artist's hands turning the pages, revealing colorful illustrations of famous artworks. In another shot, the artist is seen from behind, sitting in front of a large canvas with paintbrushes in hand, contemplating the next stroke while a book on art techniques lies open nearby. Throughout the video, the artist's passion for both creating and studying art is evident in the careful attention given to both the book and the canvas.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand appears deformed, and the book also becomes distorted."
}
] |
seed44_1175
|
videos/HRA_part1/1175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with short brown hair and a neatly trimmed beard, laughs wholeheartedly while sitting on a brown leather sofa. He wears a dark gray turtleneck sweater, black jeans, and a silver wristwatch, set against a warm-toned living room backdrop. The room features wooden floors, a large window with natural light, and a lush green plant, creating a cozy atmosphere. The actor's laughter is genuine and infectious, his eyes crinkling at the corners as he leans back on the couch, enjoying a private joke.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1205
|
videos/HRA_part2/1205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, wearing a stylish black jacket and jeans, stands on a futuristic space stadium podium, passionately explaining the grand vision for an intergalactic sporting event. Below, a peculiar sight unfolds: a capybara, donning a sleek silver spacesuit and a determined look, prepares for the ultimate cosmic challenge. The rodent athlete crouches, ready to spring into action, against the backdrop of a vibrant, neon-lit cosmic arena, filled with alien spectators. The capybara leaps high into the air, propelling itself with incredible force, while the director watches intently from above, his eyes fixed on this extraordinary spectacle unfolding under the dazzling lights of the space stadium.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements are not smooth."
}
] |
seed46_1384
|
videos/HRA_part2/1384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, spiky European hedgehog runs energetically across a lush, green garden, its tiny legs moving swiftly beneath it. The hedgehog, with its distinctive white-tipped spines, navigates through the foliage with determination, its snout pointed forward. In another scene, the hedgehog continues its journey, now scampering across a wooden deck, its movements quick and agile. The video captures the hedgehog's active nature, showcasing its ability to navigate various terrains with ease, all under the cover of night, as indicated by the dimly lit surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's running motion in the video is not smooth and coordinated."
}
] |
seed42_3000
|
videos/HRA_part0/3000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a neatly trimmed beard, sits pensively on a vintage brown leather couch, wearing a blue checked shirt, dark pants, and brown shoes. Suddenly, he holds his chest and coughs intensely, his eyes squeezed shut, indicating discomfort. The scene is set in a warmly lit room with wooden walls, showcasing a rustic environment. As the coughing fit subsides, he looks concerned, placing his hand back on his chest, suggesting a moment of reflection on his health, all while maintaining the same attire and setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1519
|
videos/HRA_part2/1519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished middle-aged doctor, wearing a white lab coat over a navy blue shirt, sits in a cozy, dimly lit pub, sipping a glass of red wine. The pub is filled with the warm glow of hanging lights and a fireplace, creating a relaxed atmosphere. The doctor, with short brown hair and a neatly trimmed beard, leans back in his chair, holding the stem of the wineglass, and gazes thoughtfully into the distance. The scene conveys a sense of calm and tranquility, with the doctor enjoying a moment of respite from his busy medical career.]"
},
{
"from": "gpt",
"value": "Bad. The middle-aged doctor's eyes in the video were not generated, the scene of red wine touching the mouth was generated unreasonably, the red wine glass was deformed, and the fingers were not fully generated."
}
] |
seed42_1430
|
videos/HRA_part0/1430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic laboratory filled with advanced scientific equipment, an artist clad in a protective suit and goggles paints a life-sized depiction of a woolly mammoth on a large canvas. The mammoth is portrayed in its natural icy habitat, with the aurora borealis illuminating the sky, symbolizing the mysteries of dark matter. Meanwhile, in the background, a group of dedicated researchers in lab coats analyze data from sophisticated machines designed to explore the enigmatic properties of dark matter. The scene is completed by a large aquarium tank filled with clear water, where a swimmer performs synchronized swimming movements, creating mesmerizing patterns that echo the cosmic dance of dark matter in the universe.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the creation of a large canvas painting of a woolly mammoth; it does not show researchers in the background analyzing data from sophisticated machines designed to explore the mysteries of dark matter."
}
] |
seed42_2523
|
videos/HRA_part0/2523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a tailored gray suit, white shirt, and red tie, takes an unconventional break from his legal duties to clean windows on a busy city street. Holding a squeegee in one hand and a spray bottle in the other, he expertly removes smudges from the glass, all while maintaining a professional demeanor. Passersby, including a group of schoolchildren and a mother with a stroller, observe the unusual sight with amusement. The lawyer's briefcase rests nearby, a reminder of his typical occupation, as he focuses on the task at hand with surprising skill and dedication.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's hand and the wiper in the video have generation issues."
}
] |
seed46_2031
|
videos/HRA_part2/2031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and helmet, sits on a vintage red fire engine, enjoying a hearty meal of spaghetti with meatballs from a white plastic plate balanced on his lap. The scene is set against the backdrop of a bustling fire station, with the garage doors open, revealing the interior where fellow firefighters are engaged in various activities, creating a vivid snapshot of life at the station. Despite the chaos around him, the firefighter finds a moment of respite, his face illuminated by the warm glow of the setting sun filtering through the open bay doors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2386
|
videos/HRA_part2/2386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, intricate fish with blue fins and a yellow body swims serenely in a clear, turquoise underwater environment, surrounded by lush green seaweed gently swaying in the current. Nearby, a school of smaller, silvery fish dart and weave, their movements synchronized and graceful, creating a mesmerizing display of aquatic life against the vivid backdrop of the underwater world. Above, rays of sunlight filter through the water's surface, casting dappled light on the scene below, highlighting the beauty and tranquility of the ocean depths.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2838
|
videos/HRA_part2/2838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate history teacher, dressed in period costume from the Renaissance era, conducts an engaging lesson at a historical site, a grand stone castle surrounded by lush greenery. The teacher, wearing a brown velvet dress and a white lace collar, begins the class by gesturing dramatically towards the ancient stone walls, captivating the students' attention. Suddenly, the teacher breaks into an elegant Renaissance dance, twirling gracefully on the cobblestone courtyard, demonstrating the cultural significance of dance in historical context. The students, inspired by the teacher's enthusiasm, join in, forming a circle around her, as they learn about the rich history and culture of the era through the art of dance.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face in the video is deformed, parts of her arms and feet are missing, and her body is distorted."
}
] |
seed44_2331
|
videos/HRA_part1/2331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a sky-blue scrubs top and pants, takes a break from her duties to enjoy the outdoors. She is raking a large pile of autumn leaves in a residential backyard, her actions revealing a playful side to her personality. She pauses to look up, smiling at the camera, her brown hair tied back in a practical ponytail. Despite her work clothes, which include a stethoscope hanging around her neck, she tackles the task with enthusiasm, her movements energetic and joyful. The sunny weather and colorful leaves provide a vibrant backdrop for this unexpected scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, legs, and the item in their hand are distorted in the video."
}
] |
seed42_1390
|
videos/HRA_part0/1390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cormorant, sleek and black, emerges from the water, its dripping feathers glistening in the sunlight. Perched on a low branch near the water's edge, it spreads its broad wings to dry, revealing a flash of orange throat beneath its hooked beak. The bird's intense eyes, set in a striking face, lock onto the camera, displaying its natural curiosity. Against a backdrop of rippling water and lush green foliage, the cormorant stands tall, a testament to its aquatic lifestyle, before diving back into the depths with a powerful flap of its wings.]"
},
{
"from": "gpt",
"value": "Bad. The cormorant's wings in the video are not fully generated, and the claws are not generated."
}
] |
seed42_2195
|
videos/HRA_part0/2195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, temperate deciduous forest during autumn, a dedicated park ranger wearing a brown uniform and a wide-brimmed hat runs along a winding dirt trail. Surrounded by tall, leafy trees with vibrant orange and red foliage, the ranger navigates the path with focused determination. As the camera follows, we see the ranger's strong legs propelling them forward, their breath visible in the crisp air, and their eyes alert for any signs of wildlife or forest health issues. The scenery is alive with the sounds of rustling leaves, chirping birds, and the occasional distant call of a wild animal, all contributing to the immersive experience of running in a breathtaking natural environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2904
|
videos/HRA_part2/2904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bull moose, antlers wide and impressive, runs through a lush, green meadow under a clear blue sky, with a distant mountain range visible on the horizon. Its powerful legs propel it forward in a graceful gallop, kicking up small clouds of dust from the dry earth beneath its hooves. The moose's coat is a deep brown, nearly black, and its large body ripples with muscles as it bounds across the landscape, the embodiment of wild strength and freedom. In the background, tall trees frame the edges of the clearing, their leaves whispering softly in the breeze, while birds take flight, startled by the majestic creature's sudden movement.]"
},
{
"from": "gpt",
"value": "Normal. While running, the moose's limbs appear deformed."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.