video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2583
|
videos/HRA_part1/2583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a full uniform complete with a badge, gun, and hat, is tending to a lush garden in a public park. He begins by weeding around vibrant flowers, his actions gentle yet purposeful. Next, he waters the plants with a hose, the mist from the water creating a small rainbow in the sunlight. Then, he plants a new shrub, digging a hole with a small shovel and carefully placing the plant inside. Finally, he prunes a bush into shape, his movements precise as he shapes the greenery, all while maintaining his authoritative yet approachable demeanor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1812
|
videos/HRA_part0/1812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, recognized by her messy red hair and paint-splattered white apron over a yellow dress, scrubs the bathroom floor with vigor, her face expressing determination. She uses a green scrub brush and a blue bucket filled with soapy water, set against a backdrop of white tiles. The scene conveys the juxtaposition of creativity and mundane chores, as she kneels on the floor, her hands stained with dirt and her sleeves rolled up, highlighting the physical effort involved in cleaning.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and 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": "Bad. The elephant's trunk and limbs in the video have generation issues, the head is deformed, and the overall appearance does not conform to reality."
}
] |
seed42_3219
|
videos/HRA_part0/3219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a classic gray suit with a blue tie, speaks earnestly into a microphone at a podium, set against a backdrop of a rich wood-paneled room. His hands gesticulate passionately as he addresses an unseen audience, conveying a sense of urgency and importance. The room is illuminated by soft, ambient lighting, highlighting the serious nature of the discussion. Close-ups capture the intensity in his eyes and the determination etched on his face, emphasizing the gravity of his words in this legal setting.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's hands appear deformed, and the face is somewhat blurry and distorted."
}
] |
seed42_2898
|
videos/HRA_part0/2898.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bull moose, distinguished by its dark brown fur and impressive rack of antlers, strides purposefully through a shallow, crystal-clear river. The water, teeming with lush vegetation, reflects the vibrant greenery of the surrounding forest, creating a serene and picturesque scene. The moose, with its shaggy coat and large, expressive eyes, moves with a graceful determination, its massive body rippling with each step it takes across the riverbed. The dense forest looms in the background, casting dappled shadows onto the water's surface, adding depth and texture to the landscape.]"
},
{
"from": "gpt",
"value": "Normal. The moose's movements in the video are not smooth."
}
] |
seed46_2928
|
videos/HRA_part2/2928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, typically known for its sturdy build and earthy tones, is depicted in an unexpected scenario, engaging in a joyful dance within its natural habitat. The badger, adorned with a red bow tie and a small top hat, moves energetically to an unseen beat, surrounded by lush greenery and under the shade of towering trees. Its dance is characterized by playful twirls and energetic hops, a stark contrast to its usual demeanor, all captured in a whimsical and vibrant scene that highlights the unexpected delight of a dancing badger in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The badger's dance in the video has uncoordinated movements."
}
] |
seed42_1535
|
videos/HRA_part0/1535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful farmer, wearing a red plaid shirt and blue jeans, tenderly bathes a muddy dog outside on a sunny day, using a white hose with a red nozzle. The farmer, with a warm smile and caring hands, rinses the dog with water from the hose, as the playful animal stands on its hind legs, paws resting on the farmer's knee, enjoying the attention. The scene is set against a backdrop of lush green fields and a clear blue sky, with the farmer's weathered barn in the distance, creating a heartwarming rural atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's bathing actions in the video are basically normal, with slight disharmony."
}
] |
seed42_2625
|
videos/HRA_part0/2625.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling train station filled with hurried travelers, a dedicated doctor, clad in a white lab coat over a navy blue dress shirt and khaki pants, leaps energetically over a small gap between the platform and the train car. The scene captures the doctor's agility and determination amid the urban chaos, with the train's bright lights and the station's high ceilings providing a dramatic backdrop. Passengers watch in awe as the doctor, holding a brown leather briefcase, executes a perfectly timed jump, symbolizing the balance between professionalism and unexpected challenges in daily life.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, feet, and legs are distorted in the video."
}
] |
seed44_2874
|
videos/HRA_part1/2874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An experienced engineer, clad in a futuristic spacesuit with an illuminated helmet, embarks on a critical space rescue mission. Against the backdrop of a vast, starlit cosmos, he is seen swimming through the emptiness of space, propelled by bursts from his suit's thrusters. With a focused gaze and a determination to save lives, he maneuvers towards a damaged spacecraft, its hull breached and systems failing. The engineer's suit, equipped with advanced technology, allows him to navigate the zero-gravity environment with precision and grace, as he reaches the stricken vessel to begin emergency repairs.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3176
|
videos/HRA_part2/3176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, clad in a white lab coat over a blue shirt and khaki pants, stands on the starship bridge command, surrounded by high-tech equipment and screens displaying complex data. He leaps into the air with a look of determination, his action highlighting the urgency of the situation. Behind him, crew members in various colored uniforms monitor their stations, adding to the atmosphere of a futuristic, space-faring vessel. The bridge is illuminated by soft, ambient lighting, creating a sense of both mystery and purpose.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face, hands, and body are distorted in the video."
}
] |
seed42_2424
|
videos/HRA_part0/2424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest and tie, crouches low, engaging in a playful crawl across a textured wooden floor. Unexpectedly, a squirrel appears, its bushy tail bouncing, as it curiously crawls alongside the waiter. The two crawl in unison, the squirrel mirroring the waiter's movements, against a backdrop that subtly hints at a 'Quantum Leap' style time warp, indicated by a faint, swirling visual effect. This surreal moment captures the unusual pairing of the crawling waiter and squirrel, blending elements of fantasy and reality.]"
},
{
"from": "gpt",
"value": "Bad. Deformities appearing in the legs and arms, and the squirrel also appears deformed. Additionally, the cartoonish style does not match reality, and the server's facial features have not been generated."
}
] |
seed42_1943
|
videos/HRA_part0/1943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 adorns its skin, positioned on a dry, cracked earth surface under a bright, cloud-dappled sky. It appears to dance, flicking its tongue and swaying its body in a manner that suggests movement to an unseen beat. The lizard's movements are fluid and energetic, its tail swishing and its limbs moving gracefully as if it's performing a choreographed routine. Despite the arid environment, the lizard's dance brings a sense of lively energy to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The lizard in the video has uncoordinated movements."
}
] |
seed46_1331
|
videos/HRA_part2/1331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, wearing a black jacket, leans forward in his chair to gently caress a hyena lying at his feet, the animal seemingly at ease in his presence. The scene takes place in a well-lit room, with a bookshelf filled with various books visible in the background, hinting at the writer's profession. The hyena, displaying a level of comfort unusual for its species, looks up at the writer with a calm demeanor, creating an unexpected yet captivating connection between the two.]"
},
{
"from": "gpt",
"value": "Bad. The writer's feet were not generated; there were issues with the generation of the writer's hands and the hyena's head."
}
] |
seed46_1699
|
videos/HRA_part2/1699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a blue button-down shirt and khaki pants, rearranges furniture in a cozy room with wooden floors and a fireplace, aiming to find inspiration. He thoughtfully adjusts a brown leather sofa, placing it at an angle near the hearth, with a glass coffee table in front. Next, he moves a wooden chair with a green cushion to the right side of the sofa, creating a conversational space. Then, he positions a tall bookshelf behind the chair, filled with books and trinkets, adding character to the room. Lastly, he places a small wooden desk with a typewriter next to the window, basking in natural light, perfect for writing, all while maintaining the warm, inviting atmosphere of the space.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, legs, and hands."
}
] |
seed46_2235
|
videos/HRA_part2/2235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 koala clad in a tiny business suit scampers across a bustling cityscape, its fluffy ears bouncing as it weaves between the legs of hurried office workers. The koala, wearing a miniature tie and vest, darts through the concrete jungle, leaping over cracks in the sidewalk and dodging rolling suitcases. Its button nose and round eyes convey determination as it races toward an imposing glass skyscraper, its reflection merging with the building's sleek facade. The koala's paw steps on the polished marble floor echo through the cavernous lobby, drawing curious glances from suited professionals, who pause in their daily routines to watch the unexpected visitor sprint toward the elevators.]"
},
{
"from": "gpt",
"value": "Bad. The koala's movements in the video are not smooth."
}
] |
seed46_1659
|
videos/HRA_part2/1659.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and cap, walks through a bustling space casino, neon lights casting an otherworldly glow on the patrons. Among them, a meerkat stands upright, wearing a tiny tuxedo, its eyes wide with wonder as it navigates the futuristic gaming tables, slot machines, and alien creatures. The officer, maintaining a watchful eye, ensures order in this eclectic mix of species and activities, all set against the backdrop of a grand, space-themed casino.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1132
|
videos/HRA_part2/1132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged janitor, dressed in a gray jacket and khaki pants, gently caresses the trunk of a small, friendly mammoth. The creature, with its baby-blue fur and tiny tusks, stands docilely in a brightly lit room filled with cleaning supplies. The janitor, with a caring smile and a mop in one hand, tenderly strokes the mammoth's trunk, creating an unlikely yet heartwarming bond between the two. The room is warm and welcoming, with sunlight streaming in from a large window, casting a golden glow over the unlikely pair.]"
},
{
"from": "gpt",
"value": "Bad. The human's fingers become deformed and malformed."
}
] |
seed46_1769
|
videos/HRA_part2/1769.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a 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": "Bad. The character in the video is distorted, with twisted arms and legs."
}
] |
seed46_2430
|
videos/HRA_part2/2430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 and unexpected scene, a waiter, clad in a crisp white shirt and black trousers, serves a majestic deer who stands elegantly by a serene swimming pool, its antlers framing its face like a crown. The deer, with its large, curious eyes, seems to be sipping from a fancy glass, while the waiter attentively pours a clear liquid, possibly water, from a pitcher. The swimming pool, with its crystal-clear water, reflects the sky, adding to the surreal atmosphere of this extraordinary meeting between nature and human service.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2999
|
videos/HRA_part1/2999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 grouper fish, with its distinct brown and white spotted pattern, swims serenely in a clear blue underwater environment. Its wide, flat head and protruding eyes are prominently featured as it navigates the aquatic space. Surrounding coral formations and gentle water currents add to the natural ambiance of the scene, providing a vivid portrayal of the grouper's habitat. The fish's powerful tail fin propels it effortlessly through the water, while smaller fish scatter in its presence, highlighting the grouper's dominant position in the marine ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The eyes and mouth of the grouper in the video were generated unnaturally."
}
] |
seed44_2328
|
videos/HRA_part1/2328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly colored ibis, with its signature red curved bill and long legs, stands regally in a shallow body of water. Its plumage, a stunning mix of white, brown, and chestnut, catches the light beautifully. The bird's eye, sharp and observant, scans the surroundings for potential prey. The serene setting, featuring lush greenery and a calm water surface, enhances the serene atmosphere, making it a perfect habitat for this elegant creature.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2078
|
videos/HRA_part1/2078.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a yellow reflective vest, walks alongside a panther in an urban environment. They navigate through art galleries and exhibition spaces, where abstract paintings and sculptures decorate the walls. The officer's authoritative presence contrasts with the panther's majestic and wild nature, creating an unexpected duo as they stroll through the cultural landscape, surrounded by works of art that range from geometric patterns to lifelike portraits.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2495
|
videos/HRA_part2/2495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear including a yellow reflective jacket, black pants, and boots, meticulously irons his uniform in a room with a white wall and a table covered with a white cloth. The room is sparsely decorated, featuring a calendar and a portrait on the wall. The firefighter, sporting a well-groomed beard and a focused expression, demonstrates his attention to detail by carefully smoothing out the wrinkles in his uniform. The camera captures the steam from the iron as it glides over the fabric, highlighting the contrast between the firefighter's rugged appearance and the domestic task at hand.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1808
|
videos/HRA_part2/1808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small gerbil, with a brown and white coat, leaps energetically from one wooden platform to another within its cage, demonstrating agility and speed. The rodent lands on a branch, its furry tail swaying, before it jumps again, this time onto a spinning wheel. It pauses for a brief moment, standing upright on the wheel with its front paws raised, before continuing to jump and explore its habitat. Throughout the scene, the gerbil's movements are captured in high detail, highlighting its playful nature and lively spirit.]"
},
{
"from": "gpt",
"value": "Bad. No wooden platform or rotating wheel was generated."
}
] |
seed42_2951
|
videos/HRA_part0/2951.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, donning a wide-brimmed hat and a brown leather vest, finds himself amidst a cosmic dust storm, its ethereal particles swirling around him like a celestial sandstorm under the night sky. Suddenly, the scene transforms to reveal the farmer diving into a tranquil oasis, the water shimmering with stardust from the storm, as he swims gracefully beneath the sparkling surface, encapsulating a surreal blend of earthy resilience and otherworldly enchantment.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's movements in the video are not smooth."
}
] |
seed46_2511
|
videos/HRA_part2/2511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds as a man, dressed in a vibrant red shirt, khaki shorts, and brown shoes, stands on a sandy desert landscape under a bright blue sky. He is joined by a meerkat, who mirrors his movements. The man begins to dance, his arms waving and feet shuffling in an amusing jig, while the meerkat, standing upright on its hind legs, attempts to mimic his actions with surprising coordination. Both continue their playful dance, the man's joyful expression and the meerkat's focused gaze capturing the essence of their shared moment in the vast, sunlit wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs are missing in the video, his body is distorted, his face is blurry, and the groundhog is deformed."
}
] |
seed46_2558
|
videos/HRA_part2/2558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a green shirt and khaki shorts, walks through a savanna landscape, holding a book bag, with a hyena casually following at a distance. The student, in casual attire suitable for warm weather, continues walking along a dirt path, with the hyena maintaining a parallel path some distance away. As they move, the student occasionally glances back at the hyena, which returns the look, both seemingly unafraid and unperturbed by each other's presence, set against a backdrop of dry grasses and scattered trees typical of a savanna environment.]"
},
{
"from": "gpt",
"value": "Bad. The hyena's head and limbs, as well as the student's face, hands, and feet, have generation issues in the video."
}
] |
seed46_1050
|
videos/HRA_part2/1050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dolphin breaches the surface of a turquoise ocean, its sleek gray body glistening in the sunlight, against a backdrop of a clear blue sky and calm seas. Moments later, it swims gracefully underwater, surrounded by the vibrant marine life of a coral reef, including colorful fish and swaying sea fans. Then, the dolphin leaps again, this time performing a stunning aerial maneuver with the sun illuminating its form from below, highlighting its agility and beauty. Finally, it returns to the depths, swimming alongside a school of shimmering silver fish, the underwater world coming alive around it, showcasing the dolphin's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Normal. The dolphin's nose is generated unreasonably, and the fins are of different sizes."
}
] |
seed46_1480
|
videos/HRA_part2/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Normal. The hippopotamus's body is twisted, and its legs are twisted."
}
] |
seed42_1365
|
videos/HRA_part0/1365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a dark green beret, black turtleneck, and brown corduroy jacket, is seen from above, walking alongside a gerbil on a wooden table. The gerbil, sporting a small red bowtie, scurries ahead on its tiny feet. The artist follows, holding a sketchbook and pencil, capturing the gerbil's movements in a series of quick, expressive sketches. The table is cluttered with art supplies, including paintbrushes, tubes of oil paint, and a half-finished canvas, adding to the creative atmosphere. Natural light filters through a nearby window, casting a warm glow over the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the hamster's movements are also not smooth."
}
] |
seed42_2461
|
videos/HRA_part0/2461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a doctor, dressed in a white lab coat, is seen on the ground, crawling on hands and knees as if examining something closely. Beside him, a giraffe, curious and gentle, bends its long neck to look down at the situation, its eyes filled with intrigue. The setting is a vivid green savanna, with tall grass swaying in the breeze and distant acacia trees dotting the horizon, creating a surreal juxtaposition of medical professionalism and the wild nature of Africa.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face, hands, and feet in the video were generated abnormally."
}
] |
seed42_3133
|
videos/HRA_part0/3133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man with graying hair, dressed in a white T-shirt and black exercise pants, stretches his body against a gray studio wall. He leans forward with his right leg extended, foot against the wall, and his left leg bent, demonstrating flexibility. His hands rest on his right thigh and shin, while his head tilts down, showcasing a focused expression. Behind him, a large window reveals a blurred outdoor view, adding depth to the scene. The room is illuminated by soft, natural light, highlighting the man's dedication to maintaining his physical health.]"
},
{
"from": "gpt",
"value": "Bad. The man's eyes and mouth were not generated in the video."
}
] |
seed46_2451
|
videos/HRA_part2/2451.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a traditional white uniform complete with a tall hat and apron, is depicted in a whimsical scene, engaged in a comical footrace with a brown hare. Both characters are mid-stride, their movements synchronized, as they dash across a lush green meadow dotted with wildflowers. The chef's expression is one of playful determination, while the hare appears equally focused, its ears perked forward. The sunny sky and vibrant landscape provide a cheerful backdrop to this unexpected competition.]"
},
{
"from": "gpt",
"value": "Bad. During the run, the movements become discontinuous and suddenly change."
}
] |
seed46_1170
|
videos/HRA_part2/1170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape under a warm, golden sunlight, a large, woolly mammoth tenderly caresses a smaller mammoth with its trunk. The older mammoth, distinguished by its size and thick, matted fur, reaches out with its trunk to touch and comfort the younger one, which stands close by. The younger mammoth, with less dense fur and a more compact frame, leans into the touch, creating a touching scene of familial bond. Both mammoths stand against a backdrop of green vegetation and distant hills, with the younger mammoth mirroring the older one's grayish-brown coloration, highlighting their connection in this ancient, verdant setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2421
|
videos/HRA_part0/2421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 female teacher, wearing a green sweater and brown hair, gently caresses a large leaf from a temperate rainforest tree during an educational field trip, her face expressing wonder and reverence for nature. Moments later, she holds a branch from a temperate rainforest, engagingly teaching her attentive students about the ecosystem. Then, she lovingly touches a moss-covered log, her actions conveying the importance of the rainforest environment, with the students looking on. Finally, she carefully strokes a fern frond, her demeanor highlighting the beauty and fragility of the temperate rainforest, all while surrounded by lush greenery and the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher in the video has missing finger generation and eye generation issues."
}
] |
seed46_2850
|
videos/HRA_part2/2850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue scrubs top and black pants, stands in a verdant garden filled with lush greenery and colorful flowers. She is engaged in digging a hole with a small spade, her face expressing determination and focus. The sunlight filters through the leaves above, casting dappled shadows on the rich soil beneath her feet. Despite her work, her demeanor conveys a sense of peace and purpose, as if tending to the earth is just another form of care she provides.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers and arm are deformed in the video."
}
] |
seed46_1246
|
videos/HRA_part2/1246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 full uniform complete with a hat, rests peacefully on a bench in a quiet, empty city park during the daytime. The serene atmosphere is highlighted by the soft play of sunlight filtering through the trees, casting dappled shadows on the ground. The officer's hat is tilted down, partially obscuring their face, while they lean back against the wooden slats of the bench, their body language conveying a sense of well-deserved rest. Beside them, a water bottle sits on the bench, and in the distance, the peaceful urban landscape is visible, punctuated by the occasional passerby and the gentle sway of tree branches.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_13
|
videos/HRA_part2/13.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, solitary moose is depicted swimming in a clear, glassy lake surrounded by lush vegetation, with its head and antlers visible above the water's surface. The majestic creature gracefully propels itself forward, its body partially submerged, showcasing its surprisingly strong swimming abilities. In the distance, dramatic cliffs rise from the water's edge, their rugged surfaces covered in dense greenery, providing a stunning contrast against the calm waters. The scene is completed by the inclusion of a second moose, also swimming, creating a captivating visual of these powerful animals in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1656
|
videos/HRA_part1/1656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, cosmic-themed diner, a cheerful cashier, donning a red polka-dot apron over a black and white striped shirt, energetically dances behind the counter. The backdrop features a vast, detailed image of Jupiter, prominently displaying its iconic Great Red Spot. The cashier's playful movements contrast with the majestic, distant planet, creating a whimsical yet awe-inspiring scene. Patrons enjoy their meals, seemingly unfazed by the extraordinary setting, as the cashier continues to dance, infusing the space with a vibrant, lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The face, hands, and body of the character in the video are distorted."
}
] |
seed46_2989
|
videos/HRA_part2/2989.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen illuminated by neon lights, a chef wearing a sleek, silver uniform and gravity-defying boots stands aboard an anti-gravity vehicle. The vehicle, resembling a levitating platform with intricate, glowing circuitry, hovers above a metallic countertop cluttered with advanced cooking gadgets. The chef, with a focused gaze, wipes a stainless steel utensil with a microfiber cloth, preparing for culinary innovation amidst the backdrop of a high-tech, floating workstation.]"
},
{
"from": "gpt",
"value": "Bad. The chef's body is twisted, head is twisted, arms are twisted, and hands are twisted."
}
] |
seed46_231
|
videos/HRA_part2/231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room illuminated by the soft glow of a Martian sunset, visible through a large window displaying the red planet's horizon, two young children sit cross-legged on a wooden floor. They gently caress a small, furry gerbil sitting on a colorful blanket, their faces reflecting expressions of pure delight and wonder, as they interact with the pet in the unique, alien environment.]"
},
{
"from": "gpt",
"value": "Bad. Generated three children."
}
] |
seed46_2100
|
videos/HRA_part2/2100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, donning swimming trunks and a baseball cap, playfully interacts with a bobcat cub at a serene, secluded lake. The student, showing a friendly smile, gently splashes water as the curious cub watches from the sandy shore. Both the young man and the bobcat cub seem at ease in each other's company, sharing a moment of innocent fun amidst the peaceful natural surroundings, with the clear blue sky and lush greenery framing the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_286
|
videos/HRA_part2/286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a black cap, sits at a desk in a sparsely decorated room with a large window in the background, casting a grid-like pattern of light and shadow. He leans forward attentively, reading a document with a serious expression, his right elbow resting on the desk and his left hand holding the page. The room is filled with a sense of calm professionalism, with the window providing a source of natural light that illuminates the officer and the paperwork, highlighting his dedication to duty.]"
},
{
"from": "gpt",
"value": "Normal. When flipping the paper with the left han, the hand appears deformed."
}
] |
seed46_2462
|
videos/HRA_part2/2462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and robust body, is sprinting across a sunlit savanna, leaving a trail of dust in its wake. Its skin, textured and gray, contrasts beautifully with the lush green vegetation surrounding it. The elephant's tusks, curved and formidable, add to its regal appearance as it runs with surprising speed and grace through the open plains, showcasing the powerful muscles rippling beneath its thick skin.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's legs are missing in the video, the face was not generated, and there is an issue with the tail."
}
] |
seed42_1696
|
videos/HRA_part0/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Bad. The doctor and the leopard in the video have issues."
}
] |
seed44_1355
|
videos/HRA_part1/1355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, showcasing its striking orange and black stripes, gently caresses a smaller, more docile white tiger cub with its large, padded paw, both set against a lush, green forest backdrop. The adult tiger displays a tender side, its piercing yellow eyes gazing softly at the cub. The cub, with its playful nature, responds by nuzzling into the larger tiger's paw, highlighting the affectionate bond between them. This intimate moment unfolds in a serene environment, with the tigers surrounded by dense foliage and sunlight filtering through the leaves, casting dappled shadows on the scene.]"
},
{
"from": "gpt",
"value": "Normal. The adult tiger's movements in touching the white cub, and the white cub's movements in rubbing against the adult tiger's paws are basically normal, but there is some lack of coordination."
}
] |
seed44_2318
|
videos/HRA_part1/2318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman stands tall and poised, her blonde hair in a sleek bun, wearing a fitted black blazer over a white collared shirt, black trousers, and black heels. She is positioned in front of a large window with a city skyline visible in the background, her gaze directed towards the urban landscape. The scene is bathed in the warm glow of the setting sun, casting a golden hue over the woman and the cityscape, highlighting her silhouette and the texture of her attire. The contrast between the structured clothing and the fluidity of her stance conveys a sense of power and elegance.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_127
|
videos/HRA_part1/127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a blue shirt and gray pants, walks through a park with a calm demeanor, holding a coffee cup in his right hand. Suddenly, a squirrel approaches him, curious and bold, seeking attention or perhaps food. The squirrel is animated and lively, closely interacting with the engineer, who responds with amusement and gentle engagement. The engineer stops to interact with the squirrel, which playfully leaps onto his shoulder, creating a heartwarming moment in the midst of the engineer's daily routine. Throughout the interaction, the engineer's coffee cup remains visible, adding a touch of realism to the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2196
|
videos/HRA_part2/2196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray cat with white paws is seen swimming in a clear blue pool, surrounded by green foliage. The cat's face shows visible effort as it paddles through the water with its front paws, displaying a unique and unexpected sight. The pool is framed by lush vegetation, creating a natural, serene environment for this unusual feline activity. The cat's determination and the vibrant greenery around the pool form a captivating contrast against the clear blue water.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2623
|
videos/HRA_part0/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions two astronauts, but only one appears in the video."
}
] |
seed44_1895
|
videos/HRA_part1/1895.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid outdoor setting, two young boys, one wearing a red t-shirt and the other in a white shirt, engage with a curious monkey sitting on a wooden table. The monkey, holding a banana, looks intently at the children. One boy, in a red t-shirt, wipes the monkey's face with a cloth, while the other, in a white shirt, watches with amusement, capturing a tender moment of interaction between the children and the primate. The scene is set against a backdrop of lush greenery and a clear blue sky, adding to the idyllic atmosphere of the encounter.]"
},
{
"from": "gpt",
"value": "Normal. The monkey in the video does not have a banana in its hands, and the boy in white is also holding a banana."
}
] |
seed42_1637
|
videos/HRA_part0/1637.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 retriever, framed against a vibrant green meadow under a clear blue sky, experiences a unique perception of time as it runs. Initially, the dog is seen standing still, looking forward with anticipation. It then starts running, its legs blurring as if time has accelerated for the viewer. Next, the dog leaps into the air, seemingly frozen in mid-air, giving the impression of time slowing down. Finally, the dog bounds across the field, its motion smooth and unhurried, conveying a sense of normal time flow, all while the lush green landscape and clear blue sky provide a serene backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The dog's limbs and paws are missing in the video, and it is generally blurry."
}
] |
seed46_2735
|
videos/HRA_part2/2735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished by his gray hair and wearing a black turtleneck, is seen playfully dancing in a studio. Beside him, a giraffe, animatedly rendered with large, expressive eyes and long eyelashes, also dances, adding a whimsical touch to the scene. Both the director and the giraffe exhibit exaggerated, comical dance moves, creating a lighthearted and surreal atmosphere. The studio space is filled with vibrant colors and patterns, further enhancing the playful mood. Throughout the scene, the focus remains on the amusing interaction between the dancing director and the animated giraffe.]"
},
{
"from": "gpt",
"value": "Normal. The character's face in the video is distorted, and the giraffe's face is also distorted."
}
] |
seed44_2279
|
videos/HRA_part1/2279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, clad in a brown jacket, beige trousers, and a wide-brimmed hat, dances jovially in a mountainous landscape, the distant peaks shrouded in mist. A deer, with a full rack of antlers and a curious gaze, watches him from the edge of a lush forest. The farmer's movements are lively and carefree, his arms raised in the air, as if celebrating the beauty of nature that surrounds him. The deer, sensing no threat, cautiously approaches, its ears perked, adding a touch of whimsy to the scene. The mountains loom majestically in the background, their slopes dotted with trees and patches of greenery, providing a stunning natural backdrop to this unexpected dance.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's dance moves in the video are not very fluid, with sudden jerks in the limbs."
}
] |
seed44_2387
|
videos/HRA_part1/2387.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a vibrant yellow jacket and khaki shorts, walks along a dirt path near a watering hole, where a hippopotamus lazily wallows in the cool mud. In the distance, the Martian landscape unfolds, with its rusty red dunes and sparse vegetation silhouetted against a sunset painted in hues of violet and orange. The celestial event casts a warm glow over the scene, highlighting the unique juxtaposition of Earthly life and extraterrestrial beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, hippo body is deformed, head is distorted, feet are twisted, and legs are deformed."
}
] |
seed46_1706
|
videos/HRA_part2/1706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the surreal landscape of Neptune's gaseous atmosphere, rendered in vivid purples and blues, a meerkat stands alert amidst floating islands of icy material. The meerkat, wearing a small spacesuit with a clear helmet, wipes its face with a tiny cloth, perhaps to clean away condensation or space dust. The contrast between the meerkat's terrestrial behavior and the alien environment creates a whimsical and unexpected scene. Behind the meerkat, the swirling clouds of Neptune provide a dramatic backdrop, emphasizing the creature's isolation and the vastness of its surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat exhibits a deformity mutation."
}
] |
seed44_1695
|
videos/HRA_part1/1695.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, wearing a black leather jacket, black jeans, and black boots, checks a smoke detector in a modern, sparsely decorated living room. He stands on a white chair, his guitar hanging from a strap around his neck, as he inspects the device with a focused expression. The room features a large window allowing ample natural light, a white couch, and a white coffee table, creating a contrast against the musician's dark attire. The scene captures a moment of domestic responsibility in the life of an artist.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, legs, and guitar are distorted in the video."
}
] |
seed44_1837
|
videos/HRA_part1/1837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 of a blue jacket and jeans, walks alongside a graceful gazelle through the spacious interior of a futuristic space hotel. The hotel's design features large windows showcasing the vastness of space, with Earth visible in the distance. The student and the gazelle navigate the corridors, passing by otherworldly landscapes displayed on interactive walls. At one point, they pause near a recreational area, where guests can observe cosmic phenomena through a panoramic observatory dome. Throughout their walk, the unique bond between the student and the gazelle is evident, highlighting the extraordinary nature of this extraterrestrial encounter.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1346
|
videos/HRA_part1/1346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1394
|
videos/HRA_part1/1394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, donning a classic black vest, crisp white shirt, and black tie, diligently cleans the expansive windows of a charming bistro. The scene is set against a vibrant city backdrop, with the golden hour casting a warm glow. He meticulously wipes the glass, revealing the bustling café interior, filled with patrons enjoying their meals. The waiter's attention to detail is evident as he ensures every corner of the window is spotless, enhancing the inviting atmosphere of the establishment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1111
|
videos/HRA_part0/1111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly surreal scene, a giraffe, standing tall with its spotted coat and long neck elegantly bent, is seen swimming in a clear, turquoise lake. Its legs paddle gracefully beneath the water's surface, creating gentle ripples that extend outward. The background features lush greenery and a serene sky, with the sun casting a warm glow on the tranquil landscape, highlighting the unique sight of this majestic creature effortlessly moving through the water.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe in the video has uncoordinated movements."
}
] |
seed44_1878
|
videos/HRA_part1/1878.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic man, possibly named Ray, stands in a sunlit room, wearing a stylish gray suit, white shirt, and patterned tie. He is seen from different angles, first with his back to the window, then with his profile illuminated by the sunlight, and finally facing forward, his confident expression captured in high definition. Throughout the sequence, he maintains a calm demeanor, his attire and the interplay of light and shadow creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1977
|
videos/HRA_part2/1977.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kingfisher bird, vibrant in its electric blue plumage and orange breast, perches on a thin branch overhanging a tranquil pond, its sharp eyes intently scanning the water's surface. The sunlight filters through the leaves above, casting dappled light onto the bird and the water below. Suddenly, the kingfisher dives headfirst into the water, its body slicing through the calm surface with precision. It emerges a moment later, triumphant, a small fish wriggling in its beak. The bird then returns to its branch, ready to enjoy its catch, the water still rippling from its dive and the surrounding foliage swaying gently in the breeze.]"
},
{
"from": "gpt",
"value": "Normal. The kingfisher's body suddenly distorts and deforms when it dives into the water."
}
] |
seed42_2827
|
videos/HRA_part0/2827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, donning a white hazmat suit with a respirator mask, meticulously paints the walls of a spacious, well-lit room with vibrant orange strokes, capturing the essence of transformation. His attire, complete with protective goggles and gloves, underscores the precision and safety measures involved in the task. The room, initially a blank canvas, gradually comes alive with color, highlighting the engineer's skill and attention to detail as he revitalizes the space.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video."
}
] |
seed46_1518
|
videos/HRA_part2/1518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, elegant restaurant, a human-like weasel dressed in a formal waiter's uniform, complete with a crisp white shirt, black vest, and bow tie, is shown caressing a wine glass with intricate patterns, displaying its refined touch and attention to detail. The weasel's anthropomorphic features are enhanced by its upright posture and expressive face, which conveys sophistication and professionalism. The scene is set against a backdrop of luxurious dining, with the weasel's gentle handling of the glass highlighting its dexterity and grace.]"
},
{
"from": "gpt",
"value": "Normal. The sommelier's gesture of lightly touching the wine glass in the video is not smooth and coordinated."
}
] |
seed42_1768
|
videos/HRA_part0/1768.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid, close-up shot, a sleek, black king cobra emerges from the underbrush, its distinctive hood fully spread as it propels itself forward with surprising speed. Its body, covered in smooth scales, undulates gracefully over the forest floor, showcasing the powerful muscles beneath. The cobra's intense, amber eyes remain fixed ahead, conveying a sense of purpose and determination as it navigates the complex terrain with agility and precision. The lush greenery and dappled sunlight create a dynamic contrast against the snake's dark form, highlighting the primal energy of this extraordinary creature in motion.]"
},
{
"from": "gpt",
"value": "Normal. The king cobra in the video moves basically normally, with slightly uncoordinated movements."
}
] |
seed44_2264
|
videos/HRA_part1/2264.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, leaps into action from a weathered wooden pier extending over a body of water, the afternoon sunlight casting a dramatic glow. The firefighter, equipped with a life vest over his protective clothing, jumps off the end of the pier, the water shimmering beneath him as he descends. In the background, a firetruck is visible, parked on the pier, its red color contrasting against the blue sky and water, adding to the intensity of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3156
|
videos/HRA_part2/3156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 suburban neighborhood, a majestic moose stands near a residential street, its large frame contrasting with the mundane setting. The creature is seen wiping its antlers on a tree branch, possibly marking its territory. The scene is set against a backdrop of houses and greenery, giving the impression of wildlife encroaching upon human living spaces. The moose, with its shaggy fur and imposing stature, interacts with its environment in a display of natural behavior, despite the suburban backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The moose in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed44_3007
|
videos/HRA_part1/3007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male spruce grouse, perched on a branch in a dense forest, displays its vibrant plumage featuring shades of brown, gray, and white speckles. Its red eyelids stand out against the dark eye, while its yellow bill adds a striking contrast. The bird's feathers are ruffled, perhaps due to a breeze or during a display, and it is surrounded by lush green foliage, indicating a healthy habitat. The grouse is stationary, offering a clear view of its unique features against the backdrop of a richly textured forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1640
|
videos/HRA_part0/1640.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate chef, donning a classic white chef's jacket and black pants, is filmed in high definition as he masterfully prepares an exquisite dinner in a bustling restaurant kitchen. The scene opens with him seasoning a sizzling steak with precision, the flames from the grill casting dramatic shadows. Next, he's shown tossing vibrant vegetables in a pan with a practiced flick of his wrist, the steam rising and enhancing the aroma. Then, he carefully plates the finished dish, garnishing it with fresh herbs, each movement demonstrating his culinary expertise. Lastly, the chef adds a final touch, drizzling a rich sauce over the dish, the colors and textures popping against the pristine white plate, ready to delight the senses.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1701
|
videos/HRA_part0/1701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic laboratory, a dedicated scientist wearing a white lab coat crawls beneath an advanced, alien-like machine with glowing blue components, engaged in groundbreaking dark matter research. The complex apparatus looms overhead, resembling a cross between a particle accelerator and a biological organism, with tubes, wires, and screens integrated into its structure. The researcher's focused determination is evident as they navigate the intricate maze of technology, highlighting the challenges and mysteries of exploring the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Bad. The crawling movement of the character in the video is very unsmooth and uncoordinated."
}
] |
seed44_1447
|
videos/HRA_part1/1447.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 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 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": "Bad. The limbs of the ghost shrimp in the video are missing, and the eyes are not fully generated."
}
] |
seed42_1035
|
videos/HRA_part0/1035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform complete with badge, gun holster, and radio, is engaged in an unexpected task. He is seen from behind, bending over a small hole in the ground, which is surrounded by a ring of yellow tape. His right hand is plunged into the hole, indicating he is unclogging a drain. The location appears to be a public park, with green grass and trees in the background, and a group of people watching the unusual scene from a distance, their expressions a mix of amusement and curiosity. A yellow sign with the words \"Caution, Wet Floor\" leans against a nearby tree, adding to the surreal atmosphere of the situation.]"
},
{
"from": "gpt",
"value": "Normal. No sign was generated."
}
] |
seed44_3098
|
videos/HRA_part1/3098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, green forest environment, two individuals wearing khaki safari outfits are seen running alongside a chimpanzee, engaged in playful interaction. The scene is vibrant and full of life, with the humans and the chimpanzee moving together in harmony. They dash across a dirt path, surrounded by dense vegetation, as the chimpanzee exhibits its natural agility and strength. The trio's energetic run is captured in high detail, highlighting the dynamic movement and the unique bond between humans and this primate in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The person wearing khaki exploration attire exhibits deformities in their body and limbs while running, and the gorilla's legs also show deformities when it runs."
}
] |
seed42_1415
|
videos/HRA_part0/1415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of a Rainbow Trout, showcasing its shimmering silver scales speckled with vibrant pink stripes, fills the frame. The fish's large, expressive eyes and intricate patterns on its fins are clearly visible, set against a dark, blurred aquatic environment. The water around it gently swirls, revealing bubbles and fine particles, while the trout remains remarkably still, allowing for a detailed examination of its stunning features.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1273
|
videos/HRA_part2/1273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking teacher, wearing a gray blazer over a gray shirt, stands against the backdrop of a Martian sunset, characterized by its dusty, pinkish hue. The teacher is wiping the surface of a scientific instrument, possibly a rover component, with a cloth, highlighting the careful preparation for exploration. The setting showcases the unique beauty of a sunset on Mars, with its characteristic colors and textures, providing a captivating contrast to the familiar figure of the teacher engaged in an unfamiliar task on another planet.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers are deformed."
}
] |
seed42_1008
|
videos/HRA_part0/1008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a protective mask, crawls determinedly across a rugged, volcanic landscape under a smoky orange sky, his actions highlighting bravery and urgency. Beside him, a fellow firefighter also crawls, both navigating the harsh terrain with focused intensity. Their mission is underscored by the dramatic setting of an erupting volcano in the background, emphasizing the high stakes and danger they face. Throughout, the two figures crawl resolutely forward, their forms silhouetted against the fiery, chaotic backdrop, symbolizing human resilience against nature's fury.]"
},
{
"from": "gpt",
"value": "Good. There is no obvious difference in consistency."
}
] |
seed46_1834
|
videos/HRA_part2/1834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a futuristic spacesuit, leisurely walks through the pristine, metallic corridors of a bustling space station habitat, illuminated by soft, ambient lighting. He pauses to gaze intently at the vibrant Earth through a large observation window, perhaps seeking inspiration. Continuing his stroll, he passes various crew members engaged in their duties, highlighting the station's active community. The writer then stops at a console, where he interacts with advanced technology, possibly researching or gathering information for his work. Throughout the scene, the space station's interior is depicted in high detail, emphasizing its functional yet sophisticated design.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, and the hand is distorted."
}
] |
seed42_1905
|
videos/HRA_part0/1905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imposing goose stands tall on the bank of a misty lake, its yellow beak agape as it emits a loud honk. Its body is a mix of gray and white feathers, with a distinctive black mark around one eye. The goose's webbed feet are visible as it wades into the water, creating ripples that disturb the stillness of the early morning. Against the backdrop of a cloudy sky, the goose swims gracefully, its head held high, exuding an air of confidence and territorial dominance. The scene is set in a natural, serene environment, with the goose being the focal point, highlighting its majestic presence in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3201
|
videos/HRA_part1/3201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, attired in a red jacket and black leggings, runs across a barren desert landscape, with a lone coyote mirroring her movements at a distance. The woman's clothes flap in the wind as she sprints, her eyes fixed ahead, determined. Meanwhile, the coyote, its sandy fur blending with the surroundings, lopes alongside, its gaze following the woman's every stride. The two continue their parallel race, the woman's red jacket and the coyote's silhouette stark against the vast, sandy terrain, under a wide, cloud-dotted sky.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2587
|
videos/HRA_part2/2587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and whimsical scene, a Bactrian camel with two humps, typically found in desert environments, is seen swimming in crystal-clear waters. The camel, with its shaggy brown coat and large, curious eyes, moves gracefully through the water, its head held high above the surface. The backdrop features lush greenery and palm trees, contrasting the camel's usual habitat. The setting sun casts a warm glow over the landscape, creating a surreal and captivating moment where desert meets sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1115
|
videos/HRA_part0/1115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a man wearing a brown fur coat and matching furry boots is seen dancing joyfully next to a massive, ancient mammoth with long, curved tusks. The mammoth stands placidly, observing the man's lively movements. Behind them, a quaint village is visible, featuring a row of charming, colorful houses with thatched roofs. The houses are nestled among lush greenery, creating a picturesque and harmonious setting. The man's animated dancing contrasts with the mammoth's calm presence, while the village in the background adds a touch of warmth and community to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The man's dance moves in the video are not fluid and there are abrupt changes."
}
] |
seed42_1741
|
videos/HRA_part0/1741.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male janitor, dressed in a gray sweater over a white collared shirt and khaki pants, pauses from his cleaning duties to take deep breaths, standing in a brightly lit, modern office hallway. He holds a mop in his right hand and rests his left hand on a mop bucket, while his eyes are closed, focusing on his breathing. The clean, minimalist surroundings emphasize the tranquility of the moment as he takes a moment to collect himself, his facial expression one of peaceful concentration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2725
|
videos/HRA_part0/2725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 urban alleyway, a middle-aged man wearing a worn-out brown jacket and blue jeans leans against a brick wall. He cradles a small rat in his hands, gently stroking it, while standing next to large, green dumpsters. The rat nestles in his palm, seemingly tamed and cared for, as the man looks down at it with a warm smile. Behind him, the bustling city streets are visible, with passersby and traffic lights, creating a contrast between the tenderness of the moment and the harshness of the urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2380
|
videos/HRA_part1/2380.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a red beret and a white apron over her colorful outfit, stands in a vibrant laundry room filled with patterned tiles and graffiti art. She smiles as she sorts clothes into a vintage washing machine, her creative spirit evident in the artistic space around her. The room is illuminated by soft, yellow lights hanging from the ceiling, casting a warm glow over the artist's industrious yet joyful task. Surrounded by various paints and brushes on the walls, she pauses to admire a piece of abstract art hanging nearby, before returning to her domestic chore with a renewed sense of purpose.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2265
|
videos/HRA_part1/2265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling mall filled with shoppers, a courageous firefighter clad in full gear, including a helmet and breathing apparatus, runs purposefully down a wide corridor. The vibrant red of his turnout coat contrasts sharply with the gray floor tiles and the bright storefronts. Escalators and elevators stand as silent witnesses to his urgent mission, while the clean, contemporary lines of the mall's architecture provide a stark backdrop to the unfolding drama. Amidst the commercial ambiance, the firefighter's presence and haste underscore the gravity of the situation, his figure growing smaller as he disappears into the distance, leaving behind a trail of determination and heroism.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, and the leg is twisted."
}
] |
seed42_3122
|
videos/HRA_part0/3122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brave firefighter, clad in full gear and a helmet, stands against the backdrop of a firetruck under a cloudy sky, waving confidently with his right hand. He wears a yellow reflective jacket over his equipment, adding a pop of color to the scene. In the next frame, he is seen from behind, still waving, with the red fire engine and a suburban neighborhood visible in the background. The firefighter then pauses his wave, looking intently at something off-camera, before continuing to wave amicably, his actions conveying reassurance and professionalism in the face of potential danger.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2682
|
videos/HRA_part1/2682.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, clad in a white uniform and hat, stands near a tranquil body of water where a bison is swimming, creating a unique juxtaposition of urban culinary expertise and natural wildlife. The chef looks on thoughtfully, perhaps contemplating the ingredients for a dish inspired by the majestic bison. The scene is set in a lush, green environment, with the bison calmly paddling through the water, its head and hump visible above the surface, while the chef observes from the shore, a wooden cutting board and knife in hand, ready to embrace the wilderness's offerings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2001
|
videos/HRA_part1/2001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled female teacher, wearing a gray turtleneck sweater and dark pants, sits at a desk in a classroom after school hours. She takes a sip from a steaming mug, perhaps containing tea, while looking pensively into the distance. Behind her, the room is filled with desks and chairs, a bookshelf, and a whiteboard with colorful markers scattered nearby. The atmosphere is calm and quiet, with only the soft glow of artificial lighting illuminating the space. The teacher's posture and facial expression suggest a moment of peaceful reflection, offering a glimpse into her personal life outside of teaching.]"
},
{
"from": "gpt",
"value": "Normal. The female teacher's action of drinking tea in the video is normal, but there is a slight lack of coordination."
}
] |
seed42_2732
|
videos/HRA_part0/2732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom filled with natural light, a cheerful teacher, wearing a blue shirt, gray pants, and brown shoes, energetically wipes the chalkboard clean using a green eraser, while an otter puppet sits on her shoulder, seemingly assisting her. The teacher's movements are lively and animated, conveying a sense of fun and engagement in the educational process. The otter puppet, with its playful demeanor, adds a whimsical touch to the scene, as it seems to mimic the teacher's actions, creating a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2354
|
videos/HRA_part1/2354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic juxtaposition, a rugged firefighter, clad in full gear and holding a fire hose, stands tall against a backdrop of scientific equipment and dark matter research posters. The scene shifts to focus on the firefighter gently caressing the side of a large, complex machine, symbolizing a tender connection between humanity and the pursuit of knowledge. The firefighter's protective clothing contrasts with the sterile environment of the research facility, creating a compelling visual narrative. Behind him, screens display data related to dark matter studies, emphasizing the unusual fusion of two vastly different worlds.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed42_2368
|
videos/HRA_part0/2368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling supermarket setting, a young female cashier, wearing a red apron over a black and white striped shirt, pushes a shopping cart filled with groceries toward the checkout counter. She has a determined look on her face, and her curly brown hair is tied back in a bun. The cart is stacked with various items, including a large watermelon on top, as she navigates the busy aisle, surrounded by shelves packed with products and other shoppers. The scene captures the dynamic environment of a grocery store during peak hours, with the cashier diligently managing her tasks amidst the activity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2239
|
videos/HRA_part1/2239.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint, dimly lit restaurant, a neatly dressed waiter, wearing a black apron over a crisp white shirt and black trousers, is seen wiping a table with a white cloth. Unexpectedly, a playful gray cat emerges, rubbing against the waiter's leg. The waiter pauses, gently bending down to pet the friendly feline before resuming his task, the cat now seated beside him, seemingly enjoying the attention in the cozy dining space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1328
|
videos/HRA_part0/1328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Neptune's ethereal atmosphere, human figures, clad in futuristic, silver, metallic swimsuits and equipped with advanced breathing apparatus, swim gracefully through the gaseous clouds. Their movements are fluid and balletic, almost as if they are performing an underwater dance in the sky. The humans, both male and female, exhibit expressions of wonder and awe as they navigate the alien environment. They perform synchronized swimming routines, moving in perfect harmony with each other and the surrounding gas giant atmosphere. The scene is illuminated by a distant sun, casting a soft, dreamlike glow on the figures as they glide through the thick, swirling clouds of Neptune.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has uncoordinated movements."
}
] |
seed44_2289
|
videos/HRA_part1/2289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a straw hat, a plaid shirt, and denim overalls, is shown exerting effort as he pulls on a rope tied to a stubborn old tractor stuck in a muddy farm field. The farmer's weathered hands grip the rope tightly, his face contorted with determination, while the lush greenery and distant rolling hills provide a picturesque rural setting. The scene highlights the farmer's resilience and hard work against the backdrop of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and arms are distorted in the video."
}
] |
seed46_1980
|
videos/HRA_part2/1980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cloudless blue sky, a lone brown camel slowly crawls across the dunes, its large, expressive eyes looking straight ahead. The animal's body is positioned low to the ground, its right front leg extended forward in a crawling motion, and its left hind leg bent beneath it. The texture of the camel's fur is detailed, showing the natural variations in color and the dryness of the skin. The sand dunes form dramatic curves and ridges, with soft shadows highlighting the contours created by the sun's light. In the distance, more dunes stretch to the horizon, emphasizing the camel's solitary journey through this expansive landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1747
|
videos/HRA_part2/1747.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a white sleeveless top and blue jeans, her hair tied back in a bun, is energetically scrubbing the bathtub in a spotless white bathroom. The overhead lights reflect off the shiny surfaces, highlighting her vigorous cleaning. She uses a green scrub brush and yellow rubber gloves, her face set with determination as she tackles the task at hand. The bathroom is spacious and well-lit, with a large mirror above the sink and a window letting in natural light, all contributing to a sense of cleanliness and order.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_1726
|
videos/HRA_part1/1726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, clad in a gray suit, white shirt, and patterned tie, rearranges furniture in an office setting. He lifts a wooden chair with leather seating, moving it across the room with ease. The scene is set in a corner office, featuring a large window with a cityscape view, a desk adorned with legal documents, and a bookshelf filled with law books. The lawyer's actions are deliberate, indicating a need for change or reorganization in his workspace. Despite the professional environment, the act of rearranging furniture adds a personal touch to the narrative.]"
},
{
"from": "gpt",
"value": "Bad. The face, hands, arms, and legs of the character in the video are distorted."
}
] |
seed44_132
|
videos/HRA_part1/132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A skilled musician, clad in a black turtleneck and jeans, sits on a stage, intently playing a marimba with mallets. Nearby, a gorilla, perhaps a part of the performance or installation art, is crawling on all fours, wearing a red beret and blue jeans, adding an unexpected element to the scene. The contrast between the focused human artist and the ape in casual attire creates a surreal and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The gorilla's face is distorted, the hands are twisted, and the mallet in its hand is also twisted."
}
] |
seed42_1600
|
videos/HRA_part0/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white hare runs through the city at night, its fur glowing under the streetlights, navigating urban obstacles like a seasoned athlete. It bounds across a busy intersection, dodging between yellow cabs and pedestrians, its powerful legs propelling it forward with graceful ease. The hare then leaps over a low brick wall, lands on the cobblestone sidewalk, and continues its journey, its silhouette framed by the neon signs of city storefronts. Finally, it pauses beneath a towering skyscraper, its large ears perked up, listening to the sounds of the city before continuing its mysterious nocturnal run.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.