video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3034
|
videos/HRA_part2/3034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a black puffer jacket, dark jeans, and brown boots, shovels snow from a suburban driveway, revealing a sense of determination and hard work. The scene is set in a residential area during daytime, with the actor pushing the snow shovel in a methodical manner. Snowflakes continue to fall gently around him, settling on his black woolen hat and the branches of nearby trees. The actor's focused gaze and steady movements convey a message of perseverance and dedication, even in the midst of a snowstorm.]"
},
{
"from": "gpt",
"value": "Bad. The actor's hand is deformed in the video, and the snow shovel tool is generated disproportionately."
}
] |
seed44_1009
|
videos/HRA_part1/1009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, donning a black leather jacket, dark jeans, and a white T-shirt, is seen energetically dancing in a vast, open space, backlit by the golden hour sun. Amidst his lively moves, a tiny vole emerges from the grass, its small, curious eyes fixated on the man. The man continues to dance, oblivious to the vole's presence, his movements casting dynamic shadows across the grassy landscape. The vole watches from a safe distance, seemingly fascinated by the man's animated performance under the warm, evening light.]"
},
{
"from": "gpt",
"value": "Bad. The dancer's limbs, the vole's head and limbs, have generation issues."
}
] |
seed44_1965
|
videos/HRA_part1/1965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sparrowhawk soars gracefully against a vivid blue sky, its keen eyes scanning the terrain below for prey. Its compact body, clad in brown and gray plumage, cuts through the air with agility. The bird's hooked beak and sharp talons are prominent as it banks sharply, casting a fleeting shadow on the green landscape. Against the clear, cloudless sky, the sparrowhawk's silhouette is framed by the distant horizon, highlighting its strength and freedom in flight.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the sparrowhawk's head twisted, claws twisted, and wings twisted."
}
] |
seed44_2373
|
videos/HRA_part1/2373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying the role of an artificial intelligence pilot, performs an energetic dance within a high-tech command center. Dressed in a sleek silver metallic jumpsuit with LED lines, he moves to an unseen beat, surrounded by holographic interfaces and screens displaying futuristic data. The room is bathed in cool blue and purple lights, enhancing the sci-fi atmosphere. His expressive face, complete with augmented reality glasses, shows pure joy and freedom as he seamlessly integrates dance into his AI pilot character, creating a captivating fusion of technology and artistry.]"
},
{
"from": "gpt",
"value": "Bad. The actor's limbs are missing in the video, and the face and body generation are distorted."
}
] |
seed42_2061
|
videos/HRA_part0/2061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a vibrant red tank top and black leggings, runs across a sandy trail in a lush, green forest. Her brown curly hair bounces as she moves with determination. A small, agile lizard scurries across the path ahead of her, its quick movements catching her attention. The woman momentarily looks down at the lizard, her eyes widening in surprise, before refocusing on her run, her strides strong and purposeful against the backdrop of towering trees and dappled sunlight.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1332
|
videos/HRA_part1/1332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense temperate rainforest, a wet and lush environment with moss-covered trees, a large brown capybara crawls slowly through the undergrowth. It moves deliberately, its round body and small legs barely visible among the ferns and fallen leaves. The air is thick with moisture, and the sounds of dripping water and distant wildlife fill the atmosphere. The capybara's eyes are alert, scanning its surroundings as it navigates the complex terrain of the rainforest floor.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's limbs and nose are missing in the video."
}
] |
seed44_141
|
videos/HRA_part1/141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy room filled with natural light, two young children sit cross-legged on a wooden floor, engrossed in crocheting a vibrant blanket. One child, wearing a yellow T-shirt and denim shorts, focuses intently on their work, their tongue slightly protruding in concentration. The other, dressed in a pink sweater and khaki pants, looks up momentarily, a smile playing on their lips, before returning to the colorful yarn in their hands. The atmosphere is warm and inviting, with the half-finished blanket spreading across their laps, a testament to their patience and creativity. Beside them, a basket of yarn in various shades adds a touch of whimsy to the scene, as the children continue to crochet, their movements steady and practiced.]"
},
{
"from": "gpt",
"value": "Bad. The child's tongue is deformed, both hands have deformed fingers, and one leg has also become deformed."
}
] |
seed46_129
|
videos/HRA_part2/129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An endearing otter, with wet brown fur and a charming face, is seen grooming itself in its natural habitat. It wipes its paw across its face in a cute and meticulous manner, showcasing its daily cleaning ritual. The otter is positioned against a backdrop of lush greenery and water, highlighting its wild environment. Throughout the scene, the otter continues to groom its whiskers and face, occasionally pausing to look around, offering a captivating glimpse into its world.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the water weasel washing its face, which is basically normal, but there is a slight lack of coordination in the movements."
}
] |
seed44_2466
|
videos/HRA_part1/2466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with badges and a walkie-talkie attached to his belt, points assertively with his right hand while looking intently at something off-screen. He stands in a busy urban street scene, with pedestrians and vehicles in the background, conveying a sense of duty and command. His left hand rests on his hip, near his service weapon, and his authoritative stance is emphasized by the presence of a large, bustling city behind him, complete with tall buildings, traffic lights, and street signs.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_151
|
videos/HRA_part0/151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, iridescent green with a vibrant red throat, hovers over a cluster of pink flowers, its wings a blur of motion against the serene blue sky. It extends its slender beak into a flower, feeding on nectar, while perched on a thin branch. The bird then takes flight, moving gracefully from one flower to another, showcasing its agility against a backdrop of lush green foliage and clear, cloudless sky. Throughout, the hummingbird remains the focal point, its rapid wing beats and delicate features highlighted against the peaceful natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The bird's wings and claws in the video have generation issues."
}
] |
seed42_2183
|
videos/HRA_part0/2183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a yellow vest and khaki pants, takes a break from cleaning the vast, empty stadium to joyfully dance alone under the bright lights. With a mop in his right hand and a bucket nearby, he moves across the polished concrete floor, surrounded by rows of blue seats. The overhead view captures his spontaneous dance moves, highlighting the contrast between his work and play in the expansive, quiet stadium. His movements, set against the backdrop of the stadium's architecture and the night sky visible through the open roof, convey a sense of freedom and self-expression.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's dance in the video is very unsmooth, with uncoordinated movements."
}
] |
seed46_1716
|
videos/HRA_part2/1716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush temperate deciduous forest during autumn, two people, a woman in a green jacket and a man in a brown vest, are observed sitting on a blanket, engaged in a relaxed conversation. Beside them, a capybara crawls slowly across the blanket, its large size and docile nature evident. The forest floor is covered in a mosaic of fallen leaves, while the trees stand tall with their branches partially denuded, creating a dappled sunlight effect. The overall atmosphere is one of peaceful coexistence between humans and wildlife in the natural habitat of the capybara.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's movements in the video are not smooth, and the character's actions are unsmooth."
}
] |
seed44_1602
|
videos/HRA_part1/1602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman in a red dress walks purposefully through the grand lobby of a luxurious hotel, her high heels clicking on the marble floor. The opulent space features tall windows, plush velvet sofas, and an elegant chandelier, all bathed in warm, inviting light. As she strides confidently, she passes by the reception desk, where a concierge is busy assisting guests. In the background, a group of tourists consults a map, adding a touch of bustling activity to the otherwise refined atmosphere. The woman's poise and the hotel's grandeur create a captivating scene of urban sophistication.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and feet are distorted in the video."
}
] |
seed42_2083
|
videos/HRA_part0/2083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter with neatly combed brown hair and a black uniform serves a couple seated at a beachside table, the ocean's horizon providing a romantic backdrop. He carefully places two plates of food on the table, his hands displaying a gentle, caressing motion, as if cherishing the art of serving. The couple looks on appreciatively, the man wearing a gray T-shirt and glasses, the woman adorned in a black dress with a plunging neckline. The scene is set during the golden hour, with the sun's rays casting a warm glow over the ocean and the couple, encapsulating a moment of intimate dining by the sea.]"
},
{
"from": "gpt",
"value": "Good. The server's movements in the video are basically normal."
}
] |
seed46_2332
|
videos/HRA_part2/2332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with dark brown hair tied in a ponytail and wearing a gray T-shirt, blue jeans, and green gardening gloves is intently digging into the soil with a silver garden shovel. The scene is set in a backyard garden with lush greenery surrounding her, and a wooden fence can be seen in the background. She pauses for a moment to brush away some dirt from her face, revealing a look of determination and focus. As she continues to dig, the sunlight filters through the leaves overhead, casting dappled shadows onto the ground and highlighting her efforts in the garden.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_2713
|
videos/HRA_part2/2713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning safety glasses and a gray shirt with a vest, is depicted laughing heartily while standing in front of an industrial machine with complex machinery in the background, creating a sense of a bustling factory environment. His laughter is contagious, brightening the otherwise serious atmosphere of the workshop, where metal parts and tools are scattered across workbenches. The scene captures the engineer's genuine joy, offering a glimpse into the lighter moments within a typically intense work setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3040
|
videos/HRA_part1/3040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene set within the lush, sun-dappled understory of a subtropical dry forest, a small, agile ferret emerges from a dense thicket of ferns and moss-covered logs. Its sleek body, wrapped in rich, earthy tones, contrasts beautifully with the vibrant green foliage. The curious creature pauses, engaging in a comical self-cleaning ritual, using its paws to wipe its face and fur meticulously, revealing its playful nature amid the serene woodland setting. The ambient sounds of rustling leaves and distant bird calls add to the immersive atmosphere, capturing the essence of life in this unique ecosystem.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2490
|
videos/HRA_part2/2490.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, covered in dark fur with lighter features around its eyes and mouth, runs across a grassy terrain under a vibrant blue sky. The chimp's movement is powerful and agile, with a hunched posture typical of its species. Its face, marked with distinctive wrinkles and a noseless structure, conveys intense focus as it sprints. In another moment, the chimpanzee is shown from a side view, highlighting its muscular build and the gracefulness of its stride, set against the backdrop of a lush, green environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1889
|
videos/HRA_part2/1889.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric artist, donning a vibrant red beret and a multicolored, patterned jacket, is depicted in a studio filled with artistic clutter, including paintings, brushes, and easels. The artist is engaging in a lively dance, accompanied by a curious monkey wearing a tiny blue hat, which mirrors the artist's movements, creating a whimsical scene of creativity and playfulness set against a backdrop of artistic chaos.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1973
|
videos/HRA_part0/1973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric artist with a shaved head, donning a mustard yellow turtleneck sweater and khaki pants, stands on a dark green chair, changing a light bulb in his dimly lit studio. The space is filled with artistic clutter, including an easel with a half-finished painting, a large wooden table covered in art supplies, and various sculptures scattered throughout. The artist, with a hint of frustration, reaches up to screw in the new light bulb, casting dramatic shadows across his face and the surrounding objects. The scene is captured in high definition, allowing every detail of the artist's struggle and the eclectic studio to come to life.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2666
|
videos/HRA_part1/2666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant forest setting, a mother beaver gently caresses her kits with her large, flat tail, while they sit cozily together on the riverbank. The kits, with their soft, brown fur, look up at her with adoration, as the mother's nurturing touch conveys love and protection. Surrounded by the vibrant greenery and tranquility of nature, this heartwarming scene captures the tender bond between a beaver mother and her offspring.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2115
|
videos/HRA_part1/2115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, donning a brown leather jacket, a gray t-shirt, and jeans, stands against a dark background, holding a megaphone and gesturing with his other hand. Moments later, a wolf, possibly a Timber Wolf, is seen running in a dense forest, its powerful legs propelling it forward with grace and speed. The wolf's fur is a mix of grays and browns, blending seamlessly with the underbrush. The scene transitions to show the wolf's perspective, capturing the blur of trees and foliage as it dashes through the woodland, highlighting its agility and strength in motion.]"
},
{
"from": "gpt",
"value": "Normal. Did not generate jeans, amplifier."
}
] |
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 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 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. No obvious problems."
}
] |
seed42_1224
|
videos/HRA_part0/1224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue uniform and a stethoscope around her neck, is delightedly interacting with a small gerbil in a cozy living room. The gerbil, perched on a tiny platform, suddenly leaps into the air, its action frozen in mid-jump, capturing a moment of playful exuberance. The nurse, with a warm smile, watches the gerbil's antics, her caring demeanor evident in her facial expression and body language. The scene is set against a backdrop of a homely living space, with a couch, coffee table, and various household items visible in the background, creating a sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's movements are not fluid, and its limbs are uncoordinated."
}
] |
seed42_2726
|
videos/HRA_part0/2726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2833
|
videos/HRA_part2/2833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a red flannel shirt and denim overalls, is seen exerting effort as he pulls on a thick rope. The scene is set on a vast, green farm, with lush fields stretching into the horizon. The farmer's weathered hands grip the rope tightly, his face contorted in determination, highlighting the physical demands of his labor. Behind him, a wooden barn with a rusty roof provides a rustic backdrop, while the clear blue sky above adds a sense of serenity to the hardworking atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2108
|
videos/HRA_part1/2108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a waiter, dressed in a classic black suit and tie, carefully balances a tray of cocktails above his head as he swims underwater. Surrounding him are porcupines, wearing tiny swim caps and goggles, swimming alongside in a synchronized pattern, all submerged in a vast, clear pool under soft, ambient lighting. The waiter's face, visible beneath the water, shows a mix of concentration and amusement at the unusual company he keeps during his aquatic beverage service.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1333
|
videos/HRA_part1/1333.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lively brown and white dog bounds through the shallow waters of a serene lake at sunset, its fur glistening with droplets. It shakes vigorously, sending water flying in a sparkling mist, while standing on the sandy shore. Against the backdrop of a tranquil lake and a stunning sunset, the energetic canine leaps into the air, capturing the essence of joy and freedom. As it lands, it shakes again, creating a captivating spray against the golden hour light, highlighting every droplet in the air. Throughout, the dog wears a red collar, adding a pop of color against the natural hues of the landscape.]"
},
{
"from": "gpt",
"value": "Bad. The dog's tail and limbs in the video have generation issues, and the ears are missing."
}
] |
seed44_2521
|
videos/HRA_part1/2521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Normal. The gazelle's movements in the video are not smooth."
}
] |
seed42_1051
|
videos/HRA_part0/1051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male grouse, distinguished by its dark brown feathers and a distinctive red wattle above the eyes, stands prominently on a fallen tree in the middle of a dense, green forest. The bird's posture is alert, its head held high, indicating readiness for flight or fight. The forest surroundings are lush and verdant, with sunlight filtering through the canopy, highlighting the grouse's textured plumage. The setting is peaceful, with no visible disturbances, allowing the grouse to maintain its dominant position on the log, a symbol of its territorial claim within the woodland habitat.]"
},
{
"from": "gpt",
"value": "Normal. The color of the head suddenly changes."
}
] |
seed46_1541
|
videos/HRA_part2/1541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a waiter in full uniform, complete with a white shirt, black vest, and tie, is shown running along the edge of a busy highway. The highway is filled with cars and trucks, creating a bustling urban atmosphere. The waiter's face conveys determination as he sprints, his black trousers and polished shoes moving swiftly against the gritty pavement. The scenery includes billboards and distant city buildings, providing a backdrop of urban life. Despite the unusual setting, the waiter remains focused, his gaze fixed ahead as he continues his unexpected journey along the highway.]"
},
{
"from": "gpt",
"value": "Bad. The running actions of the character in the video are not smooth and continuous, and the movements are uncoordinated."
}
] |
seed44_1548
|
videos/HRA_part1/1548.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station with panoramic views of Earth and the cosmos, a distinguished lawyer, dressed in a sharp black suit and red tie, energetically jumps into the air with a triumphant smile. The room is elegantly lit with a blue hue, highlighting the advanced technology and sophistication of the space environment. The lawyer's enthusiastic leap is juxtaposed with the serious atmosphere of a political summit, where delegates from various planets gather to discuss intergalactic policy. The unique setting and dynamic action capture the essence of a thrilling and significant event in the realm of space politics.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_313
|
videos/HRA_part1/313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male doctor, wearing a white lab coat over a navy blue shirt, khaki pants, and brown shoes, meticulously dusts antique furniture in a well-lit room with large windows. He carefully cleans a wooden dresser, revealing the care and attention to detail he applies to his task. The doctor then moves to dust a vintage chair, his movements deliberate and focused, showcasing his commitment to maintaining the cleanliness of his surroundings. Throughout the scene, the doctor's attire remains impeccable, underscoring the contrast between his professional role and the domestic activity he performs.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the male doctor in the video is uncoordinated, and the hand generation is severely deformed."
}
] |
seed44_1306
|
videos/HRA_part1/1306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up of a rotisserie chicken, golden brown and crispy-skinned, slowly turning on a spit under the glow of overhead lights. The chicken is surrounded by an array of fresh vegetables, including bell peppers, onions, and tomatoes, which are also roasting alongside it. The scene is set in a bustling open-air market, with the rotisserie stand positioned between colorful fabric canopies and bustling shoppers. The camera captures the succulent chicken from various angles, highlighting its mouthwatering texture and the aromatic steam rising from it, all against the vibrant backdrop of the market.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1472
|
videos/HRA_part2/1472.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor, wearing a white lab coat and blue latex gloves, gently wipes a small, injured hedgehog with a cotton swab soaked in antiseptic solution, under the soft glow of an examination lamp. The hedgehog, nestled in a bed of green leaves, remains calm throughout the procedure, as the veterinarian carefully cleans its quills and skin. The scene is set in a cozy, well-lit clinic room filled with medical equipment and supplies, emphasizing the tender care provided to the tiny patient.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated."
}
] |
seed42_270
|
videos/HRA_part0/270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, wearing a red bandana, black leather jacket, and dark jeans, walks through an abandoned mine with caution. He carries a vintage guitar case, adding to his rugged, artistic persona. The mine, filled with debris and old machinery, provides a stark, industrial backdrop. The musician's confident stride and the detailed textures of the mine walls and floor convey a sense of exploration and mystery. As he moves deeper into the mine, the dim lighting highlights his silhouette, creating a dramatic effect. Throughout the video, the focus remains on the musician's journey, emphasizing his presence and the unique setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand in the video is distorted."
}
] |
seed44_2753
|
videos/HRA_part1/2753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stark juxtaposition, a majestic brown horse gallops across a lush green meadow under a vibrant blue sky speckled with white clouds, the rolling hills framing the scene beautifully. Meanwhile, in the distance, smokestacks from sprawling factories loom, emitting plumes of gray smoke into the air. On the ground near the horse, a small creature crawls, its perspective offering a unique view of the vast landscape, highlighting the contrast between nature's grace and industrial might.]"
},
{
"from": "gpt",
"value": "Bad. The galloping action of the horse in the video is not continuous and smooth, there are abrupt changes."
}
] |
seed44_1096
|
videos/HRA_part1/1096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space reality TV set, an antelope, wearing a small golden bell around its neck, stands calmly against a backdrop of stars and galaxies. The animal is gently caressed by a human figure dressed in a spacesuit, conveying a sense of comfort and companionship in the vastness of space. The astronaut's gloved hand softly touches the antelope's face, while the creature looks on serenely, the golden bell shining under the starlight, creating a surreal and touching moment in an extraterrestrial environment.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's fingers appear deformed and misshapen."
}
] |
seed46_1758
|
videos/HRA_part2/1758.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged teacher waves energetically with both hands from a classroom filled with colorful decorations, wearing a bright yellow sweater over a patterned dress, against a backdrop of windows showing a clear blue sky, conveying a sense of warmth and welcome. She stands in front of a whiteboard adorned with educational posters and student artwork, her smile and enthusiastic gesture creating an inviting atmosphere for students. The room is bathed in natural light, highlighting the teacher's animated expression and the vibrant learning environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1531
|
videos/HRA_part2/1531.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tan, agile dingo leaps over a low branch in a sparse woodland setting, its muscles taut and ears flattened against its head, showcasing its wild nature. The canine's body is mid-air, suspended in a moment of action, with its hind legs propelling it forward. Its piercing eyes are focused ahead, and its tongue hangs out slightly, revealing its determination and vitality. The surroundings consist of scattered trees and brush, highlighting the dingo's natural habitat as it performs this energetic jump.]"
},
{
"from": "gpt",
"value": "Normal. The dog's hind leg is deformed, with an extra hind leg."
}
] |
seed42_2059
|
videos/HRA_part0/2059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor kneels in a lush green forest, attentively examining a small, injured deer lying on the mossy ground. The deer, with its distinctive brown coat and white underbelly, looks up at the doctor with trusting eyes. The scene is peaceful, with sunlight filtering through the trees, casting dappled shadows on the forest floor. The doctor, wearing a green field jacket and khaki pants, gently touches the deer's leg, showing care and concern. Nearby, other deer stand watch, their ears perked, observing the interaction from a safe distance.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1628
|
videos/HRA_part2/1628.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A quirky writer, adorned in a bat costume complete with a black cape and headpiece, revels in a solo dance within a dimly lit room. Surrounded by scattered papers and an old typewriter, the scene opens with the writer seated pensively at a desk, illuminated by a single lamp. Suddenly, they leap up, transforming into a dancing figure, their movements wild and uninhibited, expressing the creative energy coursing through them. The bat-themed outfit adds a whimsical touch to the passionate dance, embodying the fusion of writing and movement in a unique celebration of artistic inspiration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1091
|
videos/HRA_part2/1091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical space-themed wedding set against a cosmic backdrop filled with stars and galaxies, a charming hedgehog, adorned with a tiny top hat and bow tie, serves as the ring bearer. The ceremony takes place on a floating platform amidst a zero-gravity environment. During the reception, the hedgehog enjoys a unique swimming experience in a clear, spherical water tank, effortlessly paddling with its limbs while maintaining its adorable appearance, all while the celebration continues around it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3097
|
videos/HRA_part1/3097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 unique setting, a male worker in a red uniform tends to an art gallery space that doubles as a swimming pool, with water visible through a glass wall. He walks along the edge of the pool, which is surrounded by artworks, including a sculpture and framed pieces on the walls. The man, wearing red swim trunks, a red polo shirt, and a black cap, interacts with the space, showcasing the blend of aquatic and artistic elements. He is seen both working and swimming, highlighting the versatility of the environment, with the water's surface shimmering under the gallery lights.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a male staff member walking in the pool, with movements that are not continuous and smooth, indicating a lack of coordination."
}
] |
seed42_2726
|
videos/HRA_part0/2726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whole, fresh cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the cod's mouth in the video has issues."
}
] |
seed46_1065
|
videos/HRA_part2/1065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station illuminated by vibrant neon lights, a worker, dressed in a sleek gray jumpsuit and wearing protective goggles, gently caresses the metallic arm of a Robot astronaut. The Robot, clad in a polished silver spacesuit adorned with intricate wiring and glowing blue accents, stands motionless yet imposing against the backdrop of high-tech equipment and advanced machinery. The scene captures a tender moment of human-robot interaction, highlighting the bond between the worker and the Robot astronaut in the vast expanse of outer space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1997
|
videos/HRA_part0/1997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a tan vest, dark pants, and brown gloves, interacts with a realistic monkey puppet, crawling on all fours across a lush green landscape. The detailed puppet, featuring lifelike fur and expressive eyes, follows the worker's movements closely. The worker, with a serious yet focused demeanor, guides the monkey puppet through various natural terrains, including dense foliage and rocky terrain, highlighting the puppet's agility and realism. Throughout the scene, the worker's connection with the monkey puppet conveys a sense of companionship and shared purpose in their outdoor adventure.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the worker and the monkey puppet in the video are not smooth."
}
] |
seed42_1671
|
videos/HRA_part0/1671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 seasoned farmer, clad in a brown jacket and denim overalls, rests on his hands and knees in a lush green field, engaging in a playful crawl. Beside him, a curious brown hare mimics his movements, hopping and crawling through the tall grass, creating a heartwarming scene of unexpected companionship between man and nature. The farmer's joyful expression and the hare's energetic antics set against the vibrant green landscape capture a rare moment of harmony in the countryside.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2402
|
videos/HRA_part1/2402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed firefighter, complete with helmet and yellow firefighting jacket, races through a lush, green forest, closely pursued by an animated beaver wearing a miniature firefighter uniform, also with a helmet and a small red cape. The firefighter leaps over a fallen log, demonstrating agility, while the beaver follows suit, mimicking every action with playful determination. Both characters run with purpose, the firefighter leading the charge and the beaver keeping pace, highlighting a fun, animated adventure set against the vibrant backdrop of a dense woodland.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's face and limbs, as well as the beaver's face, are generated abnormally, and the firefighter's limbs are distorted and deformed in the middle frames."
}
] |
seed44_1509
|
videos/HRA_part1/1509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense forest setting, a majestic stag with an impressive set of antlers leads a herd of deer through a narrow path, their movements graceful and unhurried. The camera captures their journey from a low angle, emphasizing the size and strength of the animals. The lush greenery surrounds them, providing a natural backdrop that complements their brown coats. As they walk, the sound of their hooves softly hitting the ground echoes through the woods, creating a serene atmosphere. The herd moves with purpose, navigating the terrain with ease, highlighting the beauty and resilience of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The head generation of other deer in the video is problematic."
}
] |
seed42_1368
|
videos/HRA_part0/1368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Chris Hemsworth, is seen in a modern, minimalistic living room with large windows and plenty of natural light. He wears a navy blue t-shirt, dark jeans, and a wedding band, giving him an approachable, everyman appeal. The actor is intently focused on assembling a piece of flat-pack furniture, such as an IKEA dresser, using a screwdriver and following the instruction manual. The scene conveys a sense of relatability and domesticity, as the celebrity navigates the familiar challenge of putting together home furnishings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2694
|
videos/HRA_part0/2694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 standard uniform with a badge and utility belt, is seen meticulously dusting antique furniture inside a spacious, well-lit room. The officer, sporting a neatly trimmed beard and wearing a hat, focuses intently on the task, highlighting a surprising yet diligent approach to detail. The room features a wooden floor, walls adorned with framed pictures, and a large window allowing ample natural light to illuminate the space. The officer's actions convey a sense of thoroughness and care, emphasizing the unexpected scenario of law enforcement engaging in domestic chores.]"
},
{
"from": "gpt",
"value": "Normal. The police character's movements in the video are slightly unsmooth."
}
] |
seed42_3127
|
videos/HRA_part0/3127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and gray skin, stands against a backdrop of geysers erupting in the distance, creating a misty atmosphere. The majestic animal uses its trunk to spray water onto itself, seemingly wiping or cleaning, as it enjoys a refreshing moment in the wild. This scene is set against the dramatic natural landscape, featuring geothermal activity, highlighting the unique interaction between wildlife and environment.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's trunk generation in the video has issues."
}
] |
seed42_1991
|
videos/HRA_part0/1991.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a lush, verdant savanna under a vast, cloud-dappled sky, a graceful antelope leaps and bounds with an almost choreographed elegance, its movements fluid and dynamic against the backdrop of swaying grasses and distant acacia silhouettes. Its coat gleams golden in the warm sunlight, and its horns curve beautifully as it executes a series of leaps that seem to defy gravity, embodying the spirit of dance in the wild. Nearby, a small herd of antelope watches, their postures attentive and curious, creating a scene that is both captivating and enchantingly serene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2386
|
videos/HRA_part1/2386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, intricate fish with blue fins and a yellow body swims serenely in a clear, turquoise underwater environment, surrounded by lush green seaweed gently swaying in the current. Nearby, a school of smaller, silvery fish dart and weave, their movements synchronized and graceful, creating a mesmerizing display of aquatic life against the vivid backdrop of the underwater world. Above, rays of sunlight filter through the water's surface, casting dappled light on the scene below, highlighting the beauty and tranquility of the ocean depths.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2132
|
videos/HRA_part0/2132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, with iridescent green feathers and a forked tail, hovers near a red feeder, its wings a blur of motion against a clear blue sky. The bird's tiny feet dangle beneath it as it feeds, and its long, thin beak dips into the feeder's port. Suddenly, it takes flight, its wings creating an audible hum, and lands on a branch, where it preens its feathers with its curved bill. Throughout, the hummingbird's rapid wing movements and vibrant plumage are showcased against the serene backdrop of nature.]"
},
{
"from": "gpt",
"value": "Normal. The hummingbird's flight in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed46_2145
|
videos/HRA_part2/2145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green swimsuit, sits on a sandy beach near a turquoise body of water, typing away on a laptop, while a small hedgehog perches on the writer's shoulder. The hedgehog has a tiny life jacket on, matching the writer's swimwear. In another scene, the writer is shown swimming in the clear waters, with the hedgehog floating alongside in its miniature life vest, both enjoying a peaceful day at the seaside under a bright, sunny sky.]"
},
{
"from": "gpt",
"value": "Normal. The writer's fingers are slightly deformed."
}
] |
seed46_2418
|
videos/HRA_part2/2418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room, a focused doctor, dressed in a white lab coat, leans over a table, examining a specimen. On the floor below, a tiny mouse scurries across the wooden surface, navigating the shadows beneath the furniture. The scene alternates between the doctor's intense study and the mouse's cautious movements, highlighting the stark contrast between the clinical environment and the unexpected presence of the small creature.]"
},
{
"from": "gpt",
"value": "Bad. The rat's running movements in the video are not continuous and there is a lack of coordination."
}
] |
seed42_2427
|
videos/HRA_part0/2427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dons a spacesuit and helmet, adorned with vibrant colors and patterns, resembling a solar sail, as they crawl across a barren lunar landscape, backlit by the Earth's glow. The suit, with its reflective, sail-like design, catches the sunlight, creating mesmerizing reflections and shadows. The artist moves slowly, emphasizing the suit's unique texture and the dramatic contrast between the suit and the moon's surface. This artistic portrayal on the moon's surface, with the distant Earth providing a serene backdrop, highlights the intersection of art and space exploration.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1419
|
videos/HRA_part0/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Bad. No wooden bench was generated."
}
] |
seed46_3195
|
videos/HRA_part2/3195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform and badge, stands against a gray wall, his right hand visibly trembling. The scene is set in an urban environment, with a tall building in the background and a street sign visible, adding to the realism. The officer's face is tense, his eyes closed, indicating inner turmoil or stress. The shaky hand, holding nothing, is the focal point, conveying a sense of unease or emotion in this otherwise static setting.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the police officer with a tense face, eyes tightly closed, and his right hand trembling; the movements are basically normal but there is some lack of coordination."
}
] |
seed46_2151
|
videos/HRA_part2/2151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy blue suit, white shirt, and patterned tie, stands attentively in a modern office space. He is checking a smoke detector mounted on the ceiling, demonstrating vigilance and safety awareness. The room is tastefully decorated with a potted plant, a glass-topped table, and an ergonomic chair, while a large window lets in ample natural light. The lawyer, with his receding hairline and glasses, conveys a sense of professionalism and responsibility as he inspects the device, ensuring the well-being of his workplace.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted, the arm is twisted, and the face is distorted."
}
] |
seed44_2638
|
videos/HRA_part1/2638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a scene directed with artistic flair, a bobcat, known for its secretive nature, emerges from the dense undergrowth of a temperate deciduous forest. The sunlight filters through the canopy, casting dappled shadows on the ground as the bobcat approaches a serene, crystal-clear pool. With a sudden burst of energy, it leaps into the water, its powerful muscles propelling it forward as it swims gracefully beneath the surface. Bubbles rise around it, creating an enchanting underwater ballet, before it resurfaces, shaking droplets from its fur, and returns to the safety of the forest edge, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The video has missing parts in the generation of the bobcat's paws and issues with the generation of its eyes."
}
] |
seed42_3164
|
videos/HRA_part0/3164.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station illuminated by neon lights, a lone wolf, distinguished by its silver fur and glowing yellow eyes, walks confidently down a wide corridor. The setting is a grand, high-ceilinged hall with large windows revealing the vastness of space beyond, filled with stars and distant galaxies. The wolf's path leads past a series of closed doors, each marked with the emblem of a different alien species, indicating the location of a significant intergalactic political summit. The wolf's journey is purposeful, moving with determination toward an open door where the summit takes place, set against the backdrop of a stunning cosmic vista.]"
},
{
"from": "gpt",
"value": "Bad. The lone wolf's head is twisted, and its legs are twisted."
}
] |
seed42_2526
|
videos/HRA_part0/2526.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic giraffe, distinguished by its dark, jagged spots, gently caresses a smaller giraffe with its head, creating a tender moment in the midst of a lush, green savanna landscape. The taller giraffe, with a weathered face and long eyelashes, shows affection toward the younger one, which has lighter, less pronounced markings, standing against a backdrop of tall grasses and distant trees under a bright, sunny sky. This intimate scene captures the essence of giraffe behavior in their natural habitat, emphasizing the bond between two individuals against a vivid, verdant setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1890
|
videos/HRA_part1/1890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green vest and khaki pants, walks purposefully down a dimly lit hallway, pushing a squeaky cleaning cart. On the wall, a badger mascot poster from a local college, Wausau Woodchucks, adds a touch of whimsy. The scene shifts slightly to reveal more of the hallway, showcasing the linoleum floor and overhead lights. The janitor continues his journey, passing a row of lockers adorned with stickers and graffiti, while the badger poster remains visible, adding a sense of character to the otherwise mundane setting. Finally, the focus is on the janitor's interaction with the environment, as he pushes the cart with determination, the badger poster serving as a silent observer in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed46_2323
|
videos/HRA_part2/2323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by his gray lab coat over a casual button-up shirt and jeans, gently bathes a small, fluffy white dog in an elevated washbasin typically used for washing cars. The scene is set outdoors, with the dog standing on its hind legs, paws on the basin's edge, and the engineer tenderly pouring water over its head from a white jug. The engineer's caring demeanor contrasts with his professional attire, creating a heartwarming image of an unexpected task being performed with love and care.]"
},
{
"from": "gpt",
"value": "Normal. Missing the white water pot and the scene of the engineer pouring water."
}
] |
seed42_2105
|
videos/HRA_part0/2105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray shirt and dark pants, attentively sorts colorful laundry in a busy laundromat filled with vibrant washing machines and dryers. He meticulously folds a yellow shirt, revealing a sense of pride in his work. Next, he checks the laundry, holding up a pair of red socks, demonstrating his thoroughness. Then, he loads the washer with various garments, including a green sweater and blue jeans, his actions methodical and precise. Finally, he closes the washer door, presses the start button, and turns to face the camera, his expression conveying satisfaction in a job well done, all within the bustling environment of the laundromat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1874
|
videos/HRA_part2/1874.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy blue uniform with a badge and a black belt, runs through a vast meadow filled with lush green grass and vibrant wildflowers. The landscape stretches to the horizon, dotted with distant trees. His expression is one of determination, eyes focused ahead, and he strides with purpose, leaving a faint trail in the dewy grass. The sun, partially obscured by a cloud, casts a soft, golden light over the scene, highlighting the officer's movement as he navigates the uneven terrain, demonstrating commitment and urgency in his duty.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not fluid, and the movements are uncoordinated."
}
] |
seed46_1779
|
videos/HRA_part2/1779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone jackal walks through ancient ruins, its sandy fur blending into the weathered stone walls of a historical site bathed in warm sunlight. The camera captures the jackal from various angles, showcasing its cautious exploration of the site, which features tall columns and ornate carvings, hinting at the grandeur of a long-lost civilization. The jackal pauses, its ears perked, scanning the surroundings before continuing its journey through the silent, time-worn corridors, the texture of the stones and the play of light adding depth to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The video shows too many limbs generated for the hyena, and the face is blurry."
}
] |
seed46_1761
|
videos/HRA_part2/1761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station filled with travelers, a diligent janitor wearing a yellow high-visibility vest is wiping down a large window, revealing the vibrant cityscape outside. The scene is set during the daytime, with bright sunlight illuminating the interior of the station. Among the crowd, a person dressed in a panda costume stands out, adding a whimsical touch to the busy environment. The janitor continues to clean the window, ensuring a clear view of the passing trains and the urban landscape beyond.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show anyone wearing a panda costume."
}
] |
seed46_1928
|
videos/HRA_part2/1928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, live lobster is displayed prominently in the center of the frame, set against a dark, shadowy background that accentuates its vibrant red shell. The creature's two massive claws are bound by twine, and it rests on a bed of fresh, green seaweed. Its long, segmented body curves slightly, and its many legs are splayed out, giving the impression of strength and vitality. The intricate details of the lobster's textured shell and its small, bead-like eyes are clearly visible in high-definition detail, making this a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1257
|
videos/HRA_part2/1257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a red jacket, gray beanie, and blue jeans, hikes through a dense forest with sunlight filtering through the trees, casting dappled shadows on the trail. They pause to observe a small stream, the water gently flowing over rocks, before continuing on the path, notebook in hand, ready to capture inspiration from nature's beauty. The scene focuses on the writer's contemplative gaze, the vibrant colors of autumn leaves surrounding them, and the peaceful atmosphere of the woodland setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1306
|
videos/HRA_part1/1306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up of a rotisserie chicken, golden brown and crispy-skinned, slowly turning on a spit under the glow of overhead lights. The chicken is surrounded by an array of fresh vegetables, including bell peppers, onions, and tomatoes, which are also roasting alongside it. The scene is set in a bustling open-air market, with the rotisserie stand positioned between colorful fabric canopies and bustling shoppers. The camera captures the succulent chicken from various angles, highlighting its mouthwatering texture and the aromatic steam rising from it, all against the vibrant backdrop of the market.]"
},
{
"from": "gpt",
"value": "Normal. The chicken's beak and eyes in the video are generated in the wrong positions, and the claws are not generated."
}
] |
seed44_1421
|
videos/HRA_part1/1421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, wearing a red checkered shirt, brown apron, and khaki pants, takes a break from cooking to rake leaves in a suburban backyard. He pauses for a moment, looking thoughtful, before continuing his task with determination. The chef, now smiling, rakes a large pile of autumn leaves into a heap, enjoying the crisp fall weather. Finally, he pauses again, this time looking pleased with his work, standing next to the sizable leaf pile, with his rake resting on his right shoulder, and a residential neighborhood visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a chef."
}
] |
seed44_1530
|
videos/HRA_part1/1530.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a parallel universe setting, a distinguished lawyer, wearing a dark suit, white shirt, and red tie, gently caresses a small, mysterious object in his hands, displaying a mix of curiosity and concern. His well-groomed appearance, complete with neatly combed hair and trimmed facial hair, contrasts with the perplexing artifact. Behind him, an office with modern furniture and technology reflects the alternate reality, adding to the intrigue of the scene. The interaction between the lawyer and the object, set against this backdrop, suggests a narrative filled with unexpected twists and turns.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's hand in the video has issues."
}
] |
seed44_1753
|
videos/HRA_part1/1753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attorney, wearing a dark suit and carrying a briefcase, walks through a desolate industrial park at dusk, under the glow of orange streetlights. He pauses to gently touch the rough surface of a concrete wall, his expression thoughtful. The scene shifts to show him seated on a bench, still in the industrial setting, now bathed in the blue hour light, as he caresses the worn wooden slats, deep in thought. Throughout, the juxtaposition of the lawyer's polished appearance against the gritty industrial backdrop highlights the unusual intimacy of his actions.]"
},
{
"from": "gpt",
"value": "Bad. No scenes of the character sitting on a bench and touching the wooden board were generated."
}
] |
seed44_2554
|
videos/HRA_part1/2554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a gray sweater and brown pants, is seen painting en plein air in a lush green forest. Suddenly, a squirrel scurries into the frame, running along the forest floor, its bushy tail bouncing behind it. The artist pauses, observing the squirrel's movements with fascination, capturing the essence of the woodland creature in motion on the canvas. The squirrel, now aware of the artist's presence, stops briefly to look back before continuing its hurried journey, providing a perfect subject for the artist's brushstrokes.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel in the video has a twisted body, head, feet, and legs."
}
] |
seed46_1807
|
videos/HRA_part2/1807.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional-looking woman, dressed in a dark blazer, white blouse, and black trousers, sits at a cluttered desk in her office, surrounded by bookshelves filled with law books. Despite the serious environment, she is knitting a vibrant red scarf with a look of concentration on her face, her hands moving deftly as she works on her craft. The room is illuminated by a desk lamp, casting a warm glow over the scene, and a window can be seen behind her, offering a glimpse of a city skyline at twilight.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3042
|
videos/HRA_part2/3042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with salt-and-pepper hair sits in a dimly lit room, wearing a gray blazer and a white shirt with the top button undone. He leans back in a brown leather armchair, holding a book in his hands. The camera captures him from the side, highlighting his profile as he reads intently. Beside him, a wooden table holds a glass of red wine, a vintage lighter, and a half-smoked cigar resting in an ashtray. The atmosphere is cozy and intimate, with the warm glow of a nearby lamp illuminating the scene. Behind the chair, a large bookshelf filled with books adds to the scholarly ambiance. The man's eyes are fixed on the pages, his lips slightly parted, indicating deep concentration as he delves into the story. The setting conveys a sense of leisurely intellectual pursuit, with the elements of wine, cigar, and reading material suggesting a refined evening routine.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_2379
|
videos/HRA_part1/2379.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, donning a gray suit, sits at a desk cluttered with law books and papers, attentively reading a document. He momentarily pauses, lifting a fork loaded with pasta to his mouth, revealing his multitasking nature. The room is illuminated by the warm glow of a table lamp, casting a soft light on the busy scene. A cup of coffee and a glass of water sit nearby, within easy reach for this hardworking legal professional as he sustains himself through his demanding workday.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2698
|
videos/HRA_part2/2698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmhand, clad in a khaki shirt, beige trousers, and brown shoes, walks purposefully across a well-kept yard. In the foreground, a vibrant red barn provides contrast against the clear blue sky. The worker pauses, bending down to pick up a lively chicken, its feathers a mix of brown and white, before continuing on his path, the bird calmly tucked under his arm. They stroll together, the worker's gait steady and the chicken seemingly unperturbed, encapsulating the peaceful rhythm of life on the farm.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1383
|
videos/HRA_part1/1383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a black jacket and black jeans, is seen in a dimly lit room with a red background, wiping down a hyena that is sitting calmly on a table. The hyena, which has distinctive markings and a serious expression, is being carefully tended to by the musician, who uses a soft cloth to clean its fur. The scene conveys a sense of care and attention to detail, with the musician's focused gaze and gentle movements highlighting the bond between the two beings. Despite the unusual pairing, there is a palpable sense of trust and mutual respect between the musician and the hyena, making for a captivating and intriguing visual.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm and hand appear deformed. The towel in the hand also appears distorted. The towel is barely visible."
}
] |
seed46_1954
|
videos/HRA_part2/1954.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a lifelike jaguar mascot, wearing a brown uniform and a name tag, leaps over a green cash register in slow motion, set against a vibrant yellow backdrop. The mascot, with its mouth playfully open, is captured mid-air, just above the register, which is adorned with colorful bills and coins. The cash register itself is old-fashioned, with a large price display and mechanical keys, adding a nostalgic touch to the dynamic scene.]"
},
{
"from": "gpt",
"value": "Normal. The name tag did not appear in the video."
}
] |
seed42_1712
|
videos/HRA_part0/1712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, perches on a stone statue in the middle of a bustling city square. It has a full, rounded body, and its wings are slightly spread, revealing a flash of green and purple iridescence near the base. Its head, adorned with a small red beak, turns to face the camera, displaying its alertness and curiosity. The bird's legs, pink and sturdy, grip the statue firmly, while its red eyes, surrounded by yellow orbital rings, watch the surroundings keenly. The pigeon is set against a backdrop of urban life, with pedestrians, buildings, and traffic providing a sense of scale and context.]"
},
{
"from": "gpt",
"value": "Normal. The pigeon's claws are over-generated, and there are issues with the eyes."
}
] |
seed44_1399
|
videos/HRA_part1/1399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating fusion of elements, a majestic black panther, its body outlined in vibrant neon green, is depicted leaping across a cosmic landscape. The backdrop features a stunning galactic nebula, its swirling colors of pink, purple, and blue creating an ethereal atmosphere. As the panther moves gracefully, it seems to dance among the stars, its fluid movements echoing the celestial patterns around it. The nebula's gaseous tendrils appear to reach out, almost as if they too are joining in the cosmic dance, forming a harmonious scene where the boundaries between the animal kingdom and the universe blur.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the black panther in the video were not fully generated."
}
] |
seed44_2189
|
videos/HRA_part1/2189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a sleek black panther, adorned with a red bow tie, calmly walks down a brightly lit supermarket aisle filled with neatly arranged products. The panther gently wipes its paw across the shelves, leaving a trail of sparkling cleanliness. The shelves are stocked with various goods, from canned foods to household items, all bathed in a warm, inviting glow. The panther continues its meticulous cleaning, moving gracefully through the aisles, as if it were a routine task in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's claws, limbs, and eyes in the video have generation issues, the tail is semi-transparent, and it walks backward."
}
] |
seed42_1547
|
videos/HRA_part0/1547.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young Asian nurse wearing a white uniform and a name tag takes a break from her hospital duties to clean the large, rectangular window in the patient's room. Holding a squeegee in her right hand and a spray bottle in her left, she sprays the glass with a cleaning solution, creating a fine mist. She then wipes it down with the squeegee, leaving a clear, streak-free surface. The natural light from outside illuminates the room, casting a warm glow on the nurse as she works diligently, ensuring the window is spotless.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2382
|
videos/HRA_part0/2382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 name tag, is fixing a mountain bike in a community center. The space is filled with various tools hanging from the walls, and the officer is seen working intently on the bike's rear wheel. He wears a utility belt with a radio and other equipment, emphasizing his official role. The bicycle, with its vibrant red frame, is partially disassembled, showing the officer's commitment to helping the community beyond his law enforcement duties. The scene takes place indoors, with fluorescent lights casting a warm glow on the officer and the bike, highlighting the act of service in a public space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2479
|
videos/HRA_part2/2479.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent cheetah leaps gracefully over a low branch in a sun-dappled savanna, its body stretched in mid-air, showcasing its remarkable agility and strength. The big cat's spotted coat glistens under the warm sunlight, every muscle taut and defined as it propels itself upward. The surrounding landscape is filled with lush grasses and scattered acacia trees, providing a vivid contrast to the cheetah's dynamic movement. In the background, the horizon stretches far into the distance, marked by a hazy skyline and the promise of endless space, highlighting the cheetah's natural habitat and freedom.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's jump in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_2374
|
videos/HRA_part0/2374.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 waiter, distinctively attired in a crisp white shirt, black vest, and black trousers, diligently cleans the expansive windows of an upscale restaurant. Surrounded by lush greenery, he expertly maneuvers a squeegee across the glass, ensuring crystal-clear transparency. With focused determination, he tackles the task at hand, his movements methodical and efficient. The vibrant outdoor foliage contrasts sharply with the clean, modern lines of the building, highlighting the meticulous attention to detail in maintaining the restaurant's pristine appearance.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2577
|
videos/HRA_part1/2577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a dark blue shirt and gray pants, walks purposefully through a modern art gallery, surrounded by large, abstract paintings and sculptures. He pauses to examine a piece closely, his posture attentive and engaged. Continuing his stroll, he passes by minimalist artworks, each occupying its own space within the spacious, well-lit gallery. Finally, he stops before a particularly striking sculpture, tilting his head to study it from different angles, his attire and demeanor contrasting with the avant-garde surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The hands and legs are slightly deformed."
}
] |
seed42_2674
|
videos/HRA_part0/2674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a green shirt, gray jacket, and khaki pants, walks through the bustling streets of a metropolis, passing by a glass office building with a reflection of the surroundings. Moments later, he continues his journey, navigating the urban landscape near a construction site with yellow barriers. He then crosses a busy street, dodging between pedestrians, cars, and a street sweeper. Finally, he reaches a subway station entrance, marked by a red canopy and illuminated signage, ready to descend into the underground network of the city.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_2649
|
videos/HRA_part2/2649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, clad in a navy blue NASA spacesuit with patches and a white name tag, walks purposefully down a pristine, metallic corridor aboard a futuristic space station. The station's interior is illuminated by soft, ambient lighting, and features advanced technology, including touch-screen panels and monitoring equipment, highlighting the cutting-edge nature of the facility. The doctor's movements are unhurried yet deliberate, conveying a sense of routine and familiarity within the microgravity environment. The backdrop showcases the intricate design of the space station, with various modules visible through windows, offering glimpses into different areas where scientific research and daily activities take place.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2723
|
videos/HRA_part0/2723.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate nurse, wearing a blue medical uniform, pauses in a hospital room to appreciate a vibrant painting hanging on the wall. The artwork depicts a lush forest landscape, filled with shades of green, brown, and blue, evoking a sense of peace and tranquility. Sunlight filters through the painted trees, casting a warm glow on the nurse's face as she stands beside a patient's bed, momentarily lost in the serene scene before her. The contrast between the sterile hospital environment and the natural beauty of the painting highlights the nurse's ability to find moments of calm amidst the demands of her profession.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3181
|
videos/HRA_part2/3181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an underwater scene illuminated by natural light filtering through the water's surface, a school of vibrant, multicolored fish swim together in unison. The fish display a range of hues, including orange, yellow, and blue, with intricate patterns adorning their scales. They gracefully navigate the aquatic environment, surrounded by lush green seaweed gently swaying in the current. The detailed textures of the fish's bodies and the vivid colors of their surroundings create a captivating and serene underwater world.]"
},
{
"from": "gpt",
"value": "Bad. The fish's eyes in the video have generation issues, with modeling penetration problems."
}
] |
seed42_1340
|
videos/HRA_part0/1340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, known for his captivating performances, sits in a dimly lit room with wooden floors and walls adorned with musical instruments. He is sewing a button onto his burgundy velvet jacket, his fingers adorned with silver rings. His rugged appearance is highlighted by his scruffy beard and long, wavy hair. Behind him, a large window reveals the silhouette of a tree against a gray sky, adding a touch of melancholy to the scene. Despite the somber atmosphere, his focused gaze and the presence of a vintage microphone stand nearby suggest a sense of determination and passion for his craft.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2579
|
videos/HRA_part2/2579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 herd of African buffalo, numbering in the hundreds, thunder across an expansive savanna, kicking up clouds of dust as they run. The buffaloes, with their distinctive large horns and sturdy bodies, move in unison, creating an awe-inspiring display of collective power and movement. The scene is set against a backdrop of distant acacia trees and a clear blue sky, emphasizing the vastness of the African wilderness. The herd's movement is so intense that it sends smaller animals scattering in all directions, highlighting the raw energy and strength of these magnificent creatures in motion.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_201
|
videos/HRA_part2/201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic black panther is filmed in high definition, gently caressing a log with its paw in a lush, green rainforest. The panther, with piercing yellow eyes, rests its massive head on the log, showcasing its strength and grace. It then proceeds to rub its cheek against the log, marking its territory, while the camera captures every detail of its luxurious fur and the intricate textures of the forest environment. The scene is set in a dense jungle, with sunlight filtering through the canopy, highlighting the panther's sleek silhouette and the vibrant foliage surrounding it.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the black panther's claws in the video has issues."
}
] |
seed42_1930
|
videos/HRA_part0/1930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green meadow under a partly cloudy sky, a small brown rabbit crawls through the tall grass, its movements slow and deliberate. The camera captures this scene in high definition, focusing on the rabbit's textured fur and the vibrant vegetation surrounding it. The atmosphere is peaceful and serene, with the gentle swaying of the grass and the soft sounds of nature providing a calming backdrop. The rabbit continues its crawl, seemingly undisturbed by the presence of the camera, offering viewers an intimate glimpse into its natural habitat.]"
},
{
"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.