video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2123
|
videos/HRA_part0/2123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid orange kite with intricate black patterns soars majestically against a clear blue sky, its long white tail streaming gracefully behind it. The kite, resembling a dynamic bird in flight, is seen from various angles, showcasing its detailed design and the fluidity of its movements. Against the serene backdrop of fluffy white clouds and the vast horizon, the kite seems to dance with the wind, captivating viewers with its aerial ballet. The interplay of sunlight and shadow enhances the kite's vibrant colors, making it a striking focal point against the peaceful sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1780
|
videos/HRA_part2/1780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 friendly female cashier with brown hair pulled into a bun, wearing a green apron over a striped shirt, leans over to gently caress a koala standing on its hind legs on the counter. The koala, with its soft gray fur and curious expression, reaches up with its paw toward the cashier's face, creating a heartwarming interaction between the two. Behind the counter, a cash register and various retail items can be seen, adding to the unique setting of this tender moment.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's face and hands, as well as the koala's face and hands, are poorly generated, with the cashier's hand suddenly distorting in the middle frames."
}
] |
seed42_1981
|
videos/HRA_part0/1981.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast warehouse environment filled with neatly stacked crates and industrial kitchen equipment, a chef clad in a white uniform and black trousers sprints down the aisles with determination. His arms swing energetically, and his gaze is set forward, indicating urgency and purpose. Behind him, the bustling activity of the kitchen continues, with chefs in white coats busily preparing meals. The chef races past stainless steel shelves stocked with food supplies, his black shoes pounding against the concrete floor, highlighting the dynamic energy of the scene. Throughout, the warehouse's high ceilings and industrial aesthetic provide a distinctive backdrop to the chef's energetic run.]"
},
{
"from": "gpt",
"value": "Bad. The chef's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed46_2622
|
videos/HRA_part2/2622.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male chef with a neatly trimmed beard, wearing a brown jacket over his white kitchen uniform, expertly flips a crepe in a large pan over a high flame, demonstrating his culinary skills in a professional kitchen. The kitchen is modern and well-lit, with stainless steel appliances and countertops. The chef's focused expression and the sizzling sound of the cooking crepe fill the space, capturing the essence of his craft. Moments later, he carefully folds the perfectly cooked crepe, showcasing his precision and expertise in the art of cooking.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1514
|
videos/HRA_part1/1514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, windswept grassland under a partly cloudy sky, a janitor wearing a yellow vest, blue jeans, and a white shirt is seen wiping a transparent, rectangular window that floats in front of him. The serene landscape stretches to the horizon, dotted with distant trees, while the janitor diligently cleans the window with a cloth, revealing the pristine clarity of the glass. The peaceful scene is punctuated by the gentle sway of the tall grass and the solitude of the janitor's task, emphasizing the unexpected context of maintenance in the midst of nature.]"
},
{
"from": "gpt",
"value": "Bad. The man's arm in the video is generated too long, his facial features are not generated, there are issues with the fingers, and the cloth is deformed."
}
] |
seed42_1477
|
videos/HRA_part0/1477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a distinguished film director, clad in a black jacket, blue jeans, and brown boots, stands on a rocky outcropping, passionately directing the action. Nearby, an agile ibex leaps over a boulder with remarkable grace, its brown fur and curved horns vivid against the craggy landscape. The camera focuses on the ibex mid-jump, capturing the animal's strength and agility, while the director observes intently, his silhouette framed against the dramatic mountain scenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3166
|
videos/HRA_part0/3166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a compassionate female doctor, wearing a white lab coat and blue surgical mask, gently caresses an injured elephant's trunk. They stand under a colossal, weathered stone bridge, its arches towering above them, providing a dramatic backdrop. The elephant, adorned with vibrant red and yellow decorations, hints at cultural significance, while the bridge's ancient stonework contrasts with the modern attire of the doctor, highlighting the juxtaposition of old and new. The tender interaction between the two, set against the imposing structure of the bridge, conveys a message of care and connection across species and time.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_168
|
videos/HRA_part0/168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1318
|
videos/HRA_part2/1318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting illuminated by neon lights, a police officer, clad in a silver metallic uniform with a red sash, stands solemnly. Beside him, a robotic dog with glowing blue eyes sits attentively. The officer holds a ceremonial staff, participating in a galactic religious ceremony on a vast, holographic dance floor. Alien beings of various species gather around, some in traditional garb, others in futuristic attire, all engaged in a synchronized dance that combines elements of ancient rituals with modern electronic beats. The dance is a ritual to honor the cosmic connection between law enforcement, technology, and spirituality in this interstellar society.]"
},
{
"from": "gpt",
"value": "Normal. No ceremony was generated."
}
] |
seed44_1187
|
videos/HRA_part1/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1548
|
videos/HRA_part2/1548.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station 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": "Normal. The man in the video moves awkwardly."
}
] |
seed44_2540
|
videos/HRA_part1/2540.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a bustling metropolis, a police officer, clad in a navy uniform and cap, stands beside a large, friendly dog. The officer gently caresses the animal's head with a smile, forming a contrast against the urban backdrop of towering skyscrapers and busy streets. This tender moment between the law enforcer and the canine companion is captured against the steel and glass skyline, offering a glimpse of compassion amidst the city's concrete jungle.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2282
|
videos/HRA_part2/2282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer clad in a grey jumpsuit and safety helmet walks through a lush, green landscape, holding a clipboard. In the background, a koala casually climbs down from a eucalyptus tree, its furry body contrasting against the vibrant vegetation. The engineer stops to observe the koala, crouching down to examine it closely, while still maintaining a professional demeanor. The scene is set under a clear blue sky, with sunlight filtering through the leaves, highlighting the interaction between the human and the wildlife in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's action of stopping and squatting down to carefully examine the koala in the video is not very smooth and continuous, showing some inconsistency; the koala's movement of climbing down from the tree in the video is also not continuous, showing some inconsistency."
}
] |
seed42_2391
|
videos/HRA_part0/2391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a dark suit, white shirt, and red tie, is shown in slow motion kicking a ball on a grassy field under a clear blue sky, embodying a moment of leisure. The lawyer, with short brown hair and a serious demeanor, kicks the soccer ball with his right foot, his left leg slightly bent, and his arms outstretched for balance. In another angle, he is captured mid-kick, the ball frozen in the air, highlighting his form and the vibrant green field. The final shot shows the ball soaring through the air, the lawyer watching intently, encapsulating the essence of unexpected playfulness in a professional setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's arms and legs appear deformed and mutated, after kicking the football, another football suddenly appears behind him. The football also undergoes deformation."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a 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": "Good. No obvious issues."
}
] |
seed44_2427
|
videos/HRA_part1/2427.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist 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": "Normal. The artist can be clearly seen crawling in the video, the movements are basically normal but slightly uncoordinated."
}
] |
seed42_2315
|
videos/HRA_part0/2315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lion, king of the beasts, is seen in the early morning, wiping its face with its paw in the grasslands of Africa. The lion, with a full, tawny mane, is lying down, using its right paw to wipe its face, perhaps after a recent meal or simply as a grooming habit. The grassy savanna stretches out behind it, dotted with acacia trees, providing a natural habitat for this powerful creature. The sun, still low in the sky, casts a warm glow over the scene, highlighting the lion's golden fur and the textures of the grass.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2098
|
videos/HRA_part0/2098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin, distinguished by its long, pointed bill and sleek, torpedo-shaped body, gracefully glides through the clear, vibrant blue waters of the open ocean. Its striking silver scales glisten as sunlight filters through the water, illuminating its form. The marlin's powerful tail propels it forward with effortless ease, while schools of smaller fish scatter in its wake, highlighting the apex predator's presence in the underwater ecosystem. Against the vast, deep-blue backdrop, the marlin's silhouette is both awe-inspiring and a testament to the beauty and power of marine life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1649
|
videos/HRA_part0/1649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bright, modern kitchen with white cabinets and countertops, two young children, a boy and a girl, both wearing red aprons over their clothes and chef hats, are attentively stirring ingredients in separate pans on a large, stainless steel gas stove. The boy, with short brown hair, focuses on his task with a serious expression, while the girl, with long blonde hair tied in pigtails, smiles as she stirs. The camera captures the sizzling sound of the food cooking, emphasizing the lively atmosphere. The room is filled with natural light from a window above the sink, illuminating the children as they cook, with a row of hanging pots and pans visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_2893
|
videos/HRA_part1/2893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, donning a white chef's uniform and black apron, kneels beside a granite countertop in a modern kitchen. He focuses intently on fixing a leaky faucet, his hands working diligently with a wrench and screwdriver. The kitchen features high-end stainless steel appliances, a double sink, and sleek cabinetry. Light spills in from a nearby window, illuminating the space as the chef, adorned with a white hat and displaying a serious expression, demonstrates his skills beyond the culinary arts.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_1082
|
videos/HRA_part1/1082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal setting, a student, identifiable by their backpack and casual attire, is crawling through a crowded mall. This unusual behavior attracts the curious gaze of shoppers, who pause to watch. Unexpectedly, a hyena, also crawling and wearing a backpack, joins the student. Both crawl side by side, blending into the urban environment, creating a bizarre yet harmonious scene amidst the mall's vibrant storefronts and bustling pedestrian traffic.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2886
|
videos/HRA_part2/2886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a brown jacket and khaki pants, is seen working on a fence under the clear blue sky of a rural area, far from any city. Despite his occupation as a cashier, he tackles the fence repair with determination, using a hammer to secure wooden planks. The fence, which borders a grassy field, is the focus of his attention as he skillfully hammers in nails. With each strike, his commitment to completing the task is evident, even though it falls outside his usual role. The peaceful countryside setting contrasts with the urban environment typically associated with his profession.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the item in hand is distorted."
}
] |
seed44_2170
|
videos/HRA_part1/2170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man in his thirties, wearing a gray cap, green jacket, and brown hiking pants, strides powerfully uphill on a rocky trail. Surrounded by lush vegetation and towering trees, he carries a large backpack and hiking poles, showcasing his adventurous spirit. The scene captures his determined face as he looks ahead, highlighting his focus and resolve. Moments later, he pauses to gaze at the stunning landscape, his green jacket and brown trousers blending harmoniously with the natural environment, embodying the essence of a dedicated hiker immersed in the beauty of the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video, as well as the hiking stick they are holding."
}
] |
seed44_1049
|
videos/HRA_part1/1049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, distinguished by his stethoscope around his neck and wearing a white lab coat over a button-down shirt and khaki pants, is standing on a chair in a modern office space. He attentively checks a smoke detector mounted on the ceiling, demonstrating unexpected handyman skills. The room is well-lit and features a large window, a desk with a computer, and various medical posters on the walls, creating a professional yet casual atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The hand proportions of the character in the middle frame of the video are not coordinated."
}
] |
seed46_2929
|
videos/HRA_part2/2929.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown jacket over a striped shirt and khaki pants, performs a surprising leap over a row of yellow school lockers, demonstrating unexpected athleticism. In the next scene, he jumps again, this time over a green garbage can, showcasing his lively spirit. Then, he leaps over a red fire extinguisher mounted on a wall, his movements fluid and agile. Finally, the janitor, still clad in his brown jacket and khakis, clears a hurdle formed by a mop and bucket, his face expressing pure delight in these spontaneous acts of physicality, all within the confines of a school corridor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1092
|
videos/HRA_part0/1092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic classroom, a teacher with short brown hair, wearing a gray top, instructs students about space travel, using a large screen displaying a galactic police chase between a red spaceship and several blue police cruisers. The chase unfolds against a backdrop of stars, planets, and asteroids. The scene then transitions to show the teacher leading her class on a field trip to an indoor swimming pool, where they swim and play water games under her watchful eye, all while wearing swimsuits and caps in various colors. The pool area features large windows offering views of the city skyline, creating a vibrant and engaging learning environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and the fingers appear deformed."
}
] |
seed42_1398
|
videos/HRA_part0/1398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with curly brown hair tied back in a ponytail and wearing a red apron over a casual outfit stands in a modern kitchen, illuminated by bright overhead lights. She focuses intently on slicing a red bell pepper on a white cutting board, her silver ring catching the light. Next, she stirs a sizzling pan of vegetables on a stainless steel stove, steam rising from the pan. Then, she adds a pinch of salt and a sprinkle of fresh herbs to the dish, enhancing its aroma. Finally, she smiles as she plates the finished meal, garnishing it with a sprig of parsley, ready to serve a delicious dinner.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_137
|
videos/HRA_part2/137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda wearing a spacesuit floats in zero gravity, gently wiping a tear from its eye with a small cloth. Beside it, two astronauts, also in full space gear, share a tender kiss, signifying a unique 'space wedding'. The panda, adorned with a bow tie and holding a bouquet, serves as a heartwarming witness to this celestial union, all taking place against the backdrop of a starlit universe, with Earth visible through the window of the spacecraft.]"
},
{
"from": "gpt",
"value": "Bad. One person is missing in the video, the panda is not wearing an astronaut suit and is holding a bouquet of flowers."
}
] |
seed42_1131
|
videos/HRA_part0/1131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate musician, donning a black leather jacket and jeans, pulls vigorously on the strings of an electric violin, his face contorted in intense concentration. The scene is set against a dark, moody backdrop, illuminated only by the warm glow emanating from the instrument. Close-ups capture the intricate movements of his fingers, adorned with silver rings, as they dance across the fretboard. The energy is palpable, as if the very essence of the music is being channeled through him, creating an electrifying performance that captivates the viewer.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth and lack coordination."
}
] |
seed42_1349
|
videos/HRA_part0/1349.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed figure, dressed in a full-body brown bear suit, performs a lively jig atop a lush, green heathland blanketed with purple heather flowers. The dancer's movements are energetic and joyful, their bear-clad form spinning and leaping against the vibrant landscape. The heathland stretches out behind them, dotted with patches of colorful blooms and tall grasses swaying in the breeze. The sky above is a brilliant blue, with wispy clouds adding texture to the horizon. Throughout the scene, the dancing bear remains the central focus, their animated presence captivating against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the brown bear in the video are not fully generated, and there are defects in the facial features."
}
] |
seed46_1601
|
videos/HRA_part2/1601.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sand dollar lies on a bed of pristine white sand, its intricate pattern clearly visible against the stark background. Sunlight filters through crystal-clear water, casting a warm glow on the delicate creature. The sand dollar, positioned at a slight angle, reveals its stunning symmetry and fine details. Surrounding it, the sandy bottom is undisturbed, save for a few tiny grains caught in the gentle current, highlighting the serenity of the underwater scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1001
|
videos/HRA_part2/1001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling firefighter, clad in full gear and a helmet, stands against the backdrop of a fire station. His turnout coat is unzipped, revealing a yellow safety vest, and he holds his helmet in one hand. The fire engine bay is visible behind him, with a red fire truck and a large American flag hanging on the wall. His cheerful demeanor is accentuated by the bright sunlight shining through the open garage door, casting a warm glow over the scene. Despite the serious nature of his profession, his smile conveys a sense of pride, resilience, and community spirit.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_301
|
videos/HRA_part0/301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 marlin breaches the sparkling turquoise ocean, its sleek indigo body glistening in the sunlight. The fish soars through the air, its elongated rostrum pointed skyward, before plunging back into the sea with a splash. Surrounded by the vastness of the ocean, the marlin's powerful leap is captured against a backdrop of rolling waves and a cloud-dappled sky, showcasing the beauty and grace of this magnificent marine creature.]"
},
{
"from": "gpt",
"value": "Normal. The pectoral fins of the barracuda in the video have issues with their generation."
}
] |
seed44_211
|
videos/HRA_part1/211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dramatic scene set within the confines of an art gallery, a firefighter clad in full gear and a helmet, carrying an axe, sprints down a wide hallway lined with large paintings and modern art sculptures. The overhead lights cast shadows, adding to the intensity of the moment. Behind him, the glow of an encroaching fire illuminates the space, its orange and red hues contrasting starkly with the artworks. Amidst the chaos, the firefighter's purposeful stride conveys determination and urgency, his mission to save lives and preserve priceless art pieces from the raging inferno.]"
},
{
"from": "gpt",
"value": "Bad. The axe in the firefighter's hand is flying around everywhere; the firefighter's swift movements are not very smooth and there is a lack of coordination."
}
] |
seed46_3133
|
videos/HRA_part2/3133.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature man with graying hair, dressed in a white T-shirt and black exercise pants, stretches his body against a gray studio wall. He leans forward with his right leg extended, foot against the wall, and his left leg bent, demonstrating flexibility. His hands rest on his right thigh and shin, while his head tilts down, showcasing a focused expression. Behind him, a large window reveals a blurred outdoor view, adding depth to the scene. The room is illuminated by soft, natural light, highlighting the man's dedication to maintaining his physical health.]"
},
{
"from": "gpt",
"value": "Bad. The man's face in the video is distorted, his fingers are deformed, and his feet are abnormally generated."
}
] |
seed44_156
|
videos/HRA_part1/156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 friendly-looking female cashier, wearing a green apron over a pink blouse and denim jeans, stands at a cash register in a grocery store that has been transformed into an aquatic environment. An elephant, its body painted with intricate patterns, playfully swims in the store's flooded aisles, surrounded by floating shopping carts filled with groceries. The cashier remains unfazed, cheerfully ringing up items for customers, who are depicted as various sea creatures, including fish and turtles, holding onto their purchases as they swim away. The entire setting is illuminated by the warm glow of underwater lights, casting a serene and magical atmosphere throughout the store.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3142
|
videos/HRA_part0/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Normal. The animals in the video walk basically normally, with slightly uncoordinated movements."
}
] |
seed46_2902
|
videos/HRA_part2/2902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 distinct black markings, is perched on a concrete ledge. It has a full, rounded body and is situated in an urban environment, as indicated by the presence of a streetlight nearby. The bird's head is turned to the side, revealing its detailed eye and beak. Its wings are folded neatly against its body, and its legs, with their characteristic pinkish hue, grip the ledge firmly. The setting is an everyday city scene, with the pigeon appearing comfortable and unperturbed in its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The pigeon's claws in the video are deformed."
}
] |
seed42_2638
|
videos/HRA_part0/2638.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 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 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": "Good. No obvious issues."
}
] |
seed42_2701
|
videos/HRA_part0/2701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly surreal scene, a mongoose, typically a small terrestrial carnivore, is depicted engaging in an extraordinary activity. It is shown riding a horse, specifically a Mars horse, which could imply a horse adapted to the conditions of Mars or having Martian features, across a barren, rocky landscape reminiscent of the Martian surface. The mongoose, now a rider, steers the horse with determination as they race through the rugged terrain. The action intensifies as they begin to run at full speed, the horse's hooves kicking up red dust, while the mongoose holds on tightly, its small size contrasting with the grandeur of the Martian environment. This fantastical scenario combines elements of adventure, science fiction, and nature in a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1260
|
videos/HRA_part2/1260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds where a woman, clad in a vibrant red swimsuit, is swimming alongside a chimpanzee in a serene, tropical pool enclosed by lush greenery. The chimpanzee, also adept in the water, playfully interacts with the woman, showcasing a unique bond between human and primate. Both share moments of laughter and joy, with the chimpanzee occasionally climbing onto a floating device designed for aquatic adventures. The woman's expressive face and engaging demeanor, coupled with the chimpanzee's animated expressions, create a heartwarming narrative of interspecies friendship in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
seed46_1110
|
videos/HRA_part2/1110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black vest, sprints across a vast, barren lunar landscape, the iconic first steps of Neil Armstrong visible in the distance. Dust from the moon's surface billows behind him as he races, his movements fluid and effortless in the low gravity environment. A lunar module sits in the background, a stark contrast to the elegant attire of the sprinting waiter, who carries a silver serving tray in one hand, merging the worlds of fine dining and space exploration in a surreal scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2903
|
videos/HRA_part1/2903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, wearing a red apron over a white collared shirt, black pants, and brown shoes, pulls a heavy, overflowing shopping cart across a busy supermarket floor. She moves with determination, navigating the aisles filled with various products and customers. The cart, brimming with goods, contrasts with her clean and tidy appearance, highlighting the physical demands of her job. Behind her, the supermarket's brightly lit shelves and bustling atmosphere provide a dynamic backdrop to her task.]"
},
{
"from": "gpt",
"value": "Bad. The female cashier's fingers are severely deformed, her feet are twisted, and intermediate frames suddenly disappear or appear."
}
] |
seed46_2858
|
videos/HRA_part2/2858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 glistening under bright lights. The fish has a distinct silver hue, with large, clear eyes and tightly closed gills, indicating its freshness. Its scales reflect the light, and the texture of the skin is smooth yet firm. In the background, other seafood items can be seen, hinting at a bustling market setting where various fish are displayed on ice. The focus remains on the cod, which takes center stage, showcasing its size and quality in vivid detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1451
|
videos/HRA_part1/1451.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a khaki outfit and wide-brimmed hat, leaps energetically over a fallen log in a lush, vibrant rainforest. Surrounded by towering trees and dense foliage, they revel in the beauty of nature, their movement capturing the spirit of adventure. The scene is filled with the sights and sounds of the rainforest, from the dappled sunlight filtering through the canopy to the calls of exotic birds and the chatter of unseen wildlife, all contributing to an immersive experience that inspires the writer's imagination.]"
},
{
"from": "gpt",
"value": "Bad. The writer in the video twists and deforms their limbs while jumping, and a backpack suddenly appears on their back."
}
] |
seed44_2100
|
videos/HRA_part1/2100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, donning swimming trunks and a baseball cap, playfully interacts with a bobcat cub at a serene, secluded lake. The student, showing a friendly smile, gently splashes water as the curious cub watches from the sandy shore. Both the young man and the bobcat cub seem at ease in each other's company, sharing a moment of innocent fun amidst the peaceful natural surroundings, with the clear blue sky and lush greenery framing the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2261
|
videos/HRA_part2/2261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, curious grouper swims gracefully in its underwater habitat, surrounded by vibrant coral reefs and an array of colorful fish. The grouper, with its distinctive spotted pattern and wide, flat head, explores its surroundings with a slow, methodical motion. Its eyes, fixed on the camera, seem to convey intelligence and awareness. The water is crystal clear, allowing every detail of the grouper's body and the intricate ecosystem it inhabits to be visible. The scene is illuminated by natural sunlight filtering through the surface, casting dappled light on the sandy seabed and the marine life above.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1373
|
videos/HRA_part1/1373.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing a red plaid shirt and khaki pants, stands tall with his hands resting on a wooden fence, his gaze directed at a stunning sunset. Behind him, a lush green forest stretches into the distance, while the golden rays of the setting sun illuminate the landscape, casting a warm glow over everything. The man's posture suggests a sense of peace and tranquility as he takes in the breathtaking view before him.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3149
|
videos/HRA_part0/3149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical animated scene, a small, adventurous mouse dons a director's cap and carries a clapperboard, energetically guiding the action within a vibrant space casino. The setting is filled with neon lights, futuristic slot machines, and alien creatures gambling. Our rodent director, wearing a tiny suit and tie, races through the bustling casino floor, dodging patrons and games of chance, all while maintaining control over the film production taking place in this extraordinary intergalactic entertainment hub.]"
},
{
"from": "gpt",
"value": "Bad. The running action of the little mouse is not smooth."
}
] |
seed44_1746
|
videos/HRA_part1/1746.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, covered in shaggy brown fur, is seen swimming in a vast, ancient lake, its large body creating ripples on the water's surface. The mammoth, with distinctive tusks and small ears, moves through the water with surprising grace, its trunk held high above the waterline like a snorkel. The scene is set against a backdrop of lush, green vegetation and towering, majestic mountains in the distance, capturing the essence of a bygone era when these magnificent creatures roamed the earth.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1434
|
videos/HRA_part0/1434.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a casual outfit consisting of a brown jacket, blue jeans, and a gray backpack, is seen walking down a suburban street in a small town. Suddenly, the scene changes to reveal a kangaroo, hopping along the same path, dressed in a miniature replica of the student's outfit, complete with a tiny backpack. The kangaroo continues its journey, passing by a row of neat houses, each with a well-manicured lawn, under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The student's legs appear deformed, and the kangaroo's legs also appear deformed."
}
] |
seed46_1922
|
videos/HRA_part2/1922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scenario, an astronaut clad in a specialized space suit, reminiscent of firefighting gear but adapted for zero gravity, performs a critical spacewalk to repair a damaged satellite. The astronaut's movements are methodical yet fluid, akin to a dance in the vastness of space, as they work against the backdrop of Earth's horizon. Their space suit, complete with a helmet visor that reflects the distant stars, is equipped with tools necessary for the repair, symbolizing a unique blend of firefighting bravery and the elegance of a dancer's precision in the cosmic ballet of space operations.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the Earth's horizon, distant stars, or satellite."
}
] |
seed42_273
|
videos/HRA_part0/273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Turkey, a vibrant market comes alive with colors and aromas. Rows of stalls adorned with strings of bright red Turkish peppers hang from the ceiling, creating a striking contrast against the blue sky visible through the open roof. Intricately woven rugs in shades of red, green, and yellow cover the walls and floors, while golden lanterns dangle overhead. Amidst the bustling crowd, a vendor passionately promotes his goods, his gestures animated and expressive. Shoppers haggle over prices, their lively exchanges adding to the market's energetic atmosphere. The scene captures the essence of Turkish culture, blending tradition with the dynamic spirit of commerce.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_3026
|
videos/HRA_part0/3026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a navy blue t-shirt and beige cargo pants, meticulously organizes his cluttered garage, transforming it into a space of efficiency and order. The scene opens with him standing amidst a disorganized mess, shelves packed with tools and miscellaneous items. He begins by sorting through the chaos, creating piles of items to keep, donate, or discard. As the process unfolds, the garage gradually becomes a well-ordered workspace, with tools neatly arranged on pegboards, shelves neatly stocked, and the floor cleared of debris. The engineer, now in a clean environment, proudly surveys his accomplishment, the once chaotic garage now a testament to his organizational skills.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2800
|
videos/HRA_part1/2800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bald eagle soars through the crisp, blue sky, its powerful wings outstretched against a backdrop of puffy white clouds. The eagle's piercing yellow eyes and sharp, curved beak are sharply detailed. It effortlessly glides over a vast, serene lake, surrounded by lush, green coniferous trees and a rugged mountain range. The eagle's regal presence is highlighted by the sun's golden rays filtering through the clouds, casting a warm glow on the landscape below. The bird's brown and white feathers ruffle in the wind as it continues its graceful flight, embodying freedom and strength in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The eagle's wings and claws are deformed in the video, the body is generated unreasonably, and there is an issue with the mouth."
}
] |
seed44_1099
|
videos/HRA_part1/1099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 meerkat wearing a green apron and a name tag stands behind a wooden cash register, located on a small island amidst a vast desert. The meerkat, resembling a human cashier, rings up purchases with expertise, surrounded by volcanic landscapes visible in the distance. The sandy terrain is dotted with various items for sale, creating a surreal marketplace. In the next moment, the meerkat walks across the sandy ground, navigating between the cash register and the products, with the volcanoes providing a dramatic backdrop to this unusual shopping experience.]"
},
{
"from": "gpt",
"value": "Bad. The meerkat appears deformed and malformed, and a second meerkat suddenly appears in the scene."
}
] |
seed44_2326
|
videos/HRA_part1/2326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen laboratory, a distinguished chef wearing a pristine white chef's jacket and black trousers walks purposefully toward a high-tech, glass-enclosed antimatter containment unit, which emits a soft, eerie glow. The chef's attire is impeccably clean, contrasting with the advanced technology surrounding him. He carries a small, sleek device in his right hand, possibly a tool for interacting with the antimatter. The room is filled with stainless steel counters and equipment, giving it a modern, industrial feel. The chef approaches the containment unit with determination, ready to harness the unique properties of antimatter for an extraordinary culinary creation.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2171
|
videos/HRA_part0/2171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit African savanna, a herd of majestic Cape buffaloes gathers near a watering hole. The scene opens with a panoramic view of the landscape, emphasizing the natural habitat. A buffalo, its body glistening with water droplets, emerges from the watering hole and begins to rub against a tree, its large horns and muscular frame highlighted. Another buffalo, also wet, vigorously shakes its head, spraying water around. The herd grazes peacefully nearby, showcasing their daily routine in the wild, with the watering hole as a central point, surrounded by tall grasses and scattered acacia trees.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1495
|
videos/HRA_part1/1495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful buffalo, its body robust and muscular, leaps gracefully over a wooden fence in the midst of a lush, green prairie. The fence, made of weathered logs, stretches across the frame, adding texture and depth to the scene. The buffalo, its large horns curving outward, is captured mid-jump, showcasing its agility and strength. The background is filled with the vibrant hues of nature, from the deep greens of the grass to the soft blues of the sky, creating a stunning contrast against the dark brown of the buffalo. This majestic creature, defying expectations with its leap, embodies the spirit of the wild, free and untamed.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3039
|
videos/HRA_part0/3039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a casual outfit, is seen vacuuming a spotless living room with a modern upright vacuum cleaner, showcasing an unusual sight of a retail employee handling household chores. The room is impeccably clean, with hardwood floors and minimal furniture, highlighting the thorough cleaning process. The cashier, with her nametag visible, exhibits a sense of pride in her task, as if applying the same diligence to vacuuming as she would to serving customers. The contrast between her job as a cashier and the domestic activity adds a layer of humor and unexpectedness to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2514
|
videos/HRA_part2/2514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space habitat designed to mimic Earth's savanna, a majestic rhinoceros, fitted with a specialized spacesuit, calmly walks on artificial grass under a simulated sky. Tourists, dressed in sleek, white spacesuits, observe from a safe distance behind transparent barriers, their expressions a mix of awe and curiosity. The rhino moves gracefully, its every step monitored by advanced technology to ensure its well-being in the zero-gravity environment. This unique scene captures the harmony between wildlife conservation and the boundless possibilities of space exploration, offering viewers a glimpse into a world where nature and technology coexist in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros's movements in the video are not smooth."
}
] |
seed42_2268
|
videos/HRA_part0/2268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, cave-like setting, a brown bat clings to the rocky ceiling, its wings folded, and its form illuminated by a faint light source, evoking a sense of mystery and exploration. Nearby, a scientist wearing a white lab coat examines a high-tech device, possibly a particle detector, which emits a soft glow, indicating advanced research into dark matter. On the ground, a small, unidentified creature crawls slowly across the rocky floor, adding an element of intrigue to the scene. The juxtaposition of the bat, the scientist, and the crawling creature creates a captivating narrative about the intersection of nature, science, and the unknown.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1670
|
videos/HRA_part2/1670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, lit by neon lights, a diverse group of reality TV contestants from the show 'Mongoose' gather in the communal area. One contestant, a young woman with a purple mohawk, gently caresses a small, robotic mongoose, designed to mimic Earth wildlife. The robot mongoose, covered in metallic fur, responds with affectionate whirrs and beeps. The background features sleek, metallic surfaces and screens displaying space vistas, creating an atmosphere of high-tech comfort. The other contestants, dressed in colorful, futuristic outfits, watch with curiosity and amusement, their expressions a mix of fascination and relaxation.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, hands are twisted, arms are deformed, the small robot's body is twisted, face is distorted, arms are deformed, and legs are twisted."
}
] |
seed46_2891
|
videos/HRA_part2/2891.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal scene, a miniature giraffe, no taller than a foot, crawls slowly across the surface of a vast, cosmic solar sail, its fabric shimmering with ethereal light against the backdrop of a star-studded universe. The giraffe, with its distinctive pattern and gentle demeanor, moves deliberately, exploring the alien landscape as if it were a terrestrial savanna. The sail, stretched taut and capturing the rays of a distant sun, provides a mesmerizing contrast to the earthly creature traversing its surface, creating a dreamlike juxtaposition between the terrestrial and the celestial.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1912
|
videos/HRA_part1/1912.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bald musician, donning a black turtleneck, focuses intently on fixing a leaky faucet in an upscale bathroom with marble countertops. Initially, he looks thoughtful, holding a wrench and examining the faucet. Moments later, he is seen tightening the faucet with the tool, his sleeves rolled up, revealing a tattoo on his arm. He then tests the faucet, turning it on and off, ensuring no leaks remain. Finally, he wipes his hands on a towel, looking satisfied with his handiwork, all set against the backdrop of a luxurious bathroom with a marble sink and countertop.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3060
|
videos/HRA_part2/3060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, wearing a white tank top, blue jeans, and black sneakers, meticulously cleans a car using a sponge and bucket filled with soapy water, under a clear blue sky. He begins by pouring water from a green hose nozzle onto the vehicle, the bubbles catching the sunlight. Next, he uses a sponge to scrub the car's hood, his focused gaze and dedicated posture conveying his commitment to the task. Then, he rinses the suds away with the hose, revealing the car's now gleaming surface. Lastly, he wipes down the clean car door with a cloth, the contrast between the dirty rag and the shiny paintwork highlighting the effectiveness of his efforts.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements while cleaning the car in the video are not smooth and coordinated."
}
] |
seed44_1375
|
videos/HRA_part1/1375.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning close-up of a rainbow trout fills the frame, its vibrant colors and intricate patterns captivating the viewer. The fish, partially submerged in crystal-clear water, showcases its beauty against a backdrop of smooth river stones and lush green vegetation. Its silver scales glisten in the sunlight, while its red and blue stripes stand out against the clear water. The trout's large, expressive eyes and delicate fins add to its charm, making it the undeniable star of the scene. The rippling water around it creates a sense of movement and life, immersing the viewer in the tranquil yet dynamic environment of a freshwater stream.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2898
|
videos/HRA_part0/2898.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 bull moose, distinguished by its dark brown fur and impressive rack of antlers, strides purposefully through a shallow, crystal-clear river. The water, teeming with lush vegetation, reflects the vibrant greenery of the surrounding forest, creating a serene and picturesque scene. The moose, with its shaggy coat and large, expressive eyes, moves with a graceful determination, its massive body rippling with each step it takes across the riverbed. The dense forest looms in the background, casting dappled shadows onto the water's surface, adding depth and texture to the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1665
|
videos/HRA_part0/1665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lion, with a full golden mane and regal features, is sprinting across a barren quarry landscape, its powerful muscles rippling under tawny fur. The terrain is rocky and arid, dotted with sparse vegetation, as the lion runs with focused determination, showcasing its strength and agility in the wild. The quarry's rough, uneven ground stretches out behind the lion, while the horizon frames the scene with distant mountains and a clear blue sky, highlighting the vastness of the lion's natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The lion's limbs in the video are incomplete, with the paws not generated, and the body proportions are unreasonable."
}
] |
seed46_1995
|
videos/HRA_part2/1995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged doctor, wearing a gray sweater over a white shirt, dark jeans, and black shoes, stands in his well-lit garage, surrounded by various tools and equipment. He is organizing his belongings, rearranging items on metal shelves, and sweeping the floor. The garage walls are painted a light color, and the space is cluttered yet functional. As he works, the doctor occasionally pauses to examine objects more closely, demonstrating care and attention to detail in his task of tidying up the garage environment.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, the hand is twisted, the face is distorted, the legs are twisted and deformed, and the item in the hand is also twisted."
}
] |
seed46_2779
|
videos/HRA_part2/2779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull, standing solitary on a wooden pier post, looks out across the ocean with its yellow-rimmed eyes, reflecting determination and resilience. It wears a feathered coat of gray and white, with black wingtips, embodying the spirit of the seaside. Against a backdrop of a cloudy sky and the vast sea, it spreads its wings, preparing for flight, as the water gently laps against the pier. This iconic seashore bird, perched majestically, captures the essence of coastal life with its keen gaze and weathered feathers.]"
},
{
"from": "gpt",
"value": "Bad. The seagull's claws in the video have generation issues, and multiple wings are generated that are not spread out."
}
] |
seed44_1571
|
videos/HRA_part1/1571.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara is seen swimming across a tranquil body of water, its ears and nose poking above the surface as it propels itself forward with powerful kicks from its webbed feet. The scene is set against a lush, green forest backdrop, with sunlight filtering through the trees and casting dappled shadows on the water. Peaceful ripples spread out from the capybara's movements, creating a serene and captivating view of this aquatic rodent in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3157
|
videos/HRA_part2/3157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large hippopotamus, identifiable by its gray skin and rotund body, is seen walking through a shallow river, creating ripples in the water with each step. Its small ears, round eyes, and wide mouth are clearly visible as it moves slowly through the riverbed. The scene is set against a backdrop of lush vegetation and a clear blue sky, with the water reflecting the greenery and the hippo's movements. The hippopotamus continues its leisurely walk, leaving a trail of disturbed water behind it, all captured in high definition to showcase the details of this magnificent creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The hippopotamus in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_216
|
videos/HRA_part1/216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male lawyer, wearing a dark suit and a white shirt, attentively listens in a courtroom setting, his face expressing concern and focus. Seated at a wooden desk adorned with legal documents, he leans forward intently, his right hand resting on his chin in a gesture of deep consideration. The background features a traditional court setting with wood-paneled walls and a high ceiling, emphasizing the seriousness and formality of the legal proceedings. The judge and other participants are partially visible, adding context to the scene without detracting from the central figure of the engaged lawyer.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is slightly distorted, and the hands are twisted."
}
] |
seed44_1392
|
videos/HRA_part1/1392.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a doctor dressed in a white lab coat and stethoscope hangs around his neck, kneels on the floor, examining a jaguar cub. The cub, with its distinctive golden fur and black spots, is crawling on the checkered tile floor, exploring its surroundings with curiosity. The room is filled with medical equipment, indicating it's likely an animal clinic. The jaguar cub's small size and playful behavior contrast sharply with the doctor's professional demeanor, creating a unique and touching scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1821
|
videos/HRA_part2/1821.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mongoose, exhibiting resilience and adaptability, is seen walking through a vast, sunlit landfill. The creature, with its sandy brown fur and alert eyes, navigates the discarded human debris, from plastic bottles to broken electronics. It pauses on a pile of waste, scanning its surroundings with curiosity and survival instinct, highlighting the animal's presence in an unlikely habitat. The mongoose then continues its journey across the landfill, its small figure contrasting against the expansive landscape of garbage under the open sky.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and claws of the mongoose in the video are missing, there are issues with the body generation, and the tail position is incorrect."
}
] |
seed46_2786
|
videos/HRA_part2/2786.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a gray t-shirt and apron, stands in a small, dorm-like kitchen filled with natural light. They are preparing a meal, chopping vegetables on a cutting board placed on a countertop cluttered with cooking utensils and ingredients. The student, with a look of concentration, moves with practiced ease, flipping a pan on a stove top where steam rises from a pot. The atmosphere is casual and homely, with posters and notes adorning the walls, giving a glimpse into the student's daily life. Throughout, the student's enthusiasm for cooking is evident in their animated expressions and gestures, creating a vibrant and engaging scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_299
|
videos/HRA_part2/299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, resembling a timber wolf with his scruffy beard and wild eyes, leaps through the air in a dramatic display of strength and agility. Dressed in a blue plaid shirt, black pants, and brown work boots, he soars over a pile of logs in a forest clearing. The scene is reminiscent of a werewolf transformation, with the man's intense gaze and powerful muscles highlighting his primal nature. The action takes place under a full moon, casting an eerie glow over the landscape and emphasizing the supernatural theme.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2088
|
videos/HRA_part2/2088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-covered landscape, a group of people in winter gear are seen interacting with a herd of majestic bison. The individuals are wiping snow off the bison's fur, showing care and connection with the animals. Their faces, wrapped warmly in scarves and hats, express determination and compassion. The bison, with their powerful statures and shaggy coats, stand calmly, accepting the attention. The scene is framed by the serene beauty of nature, with snowflakes gently falling and the distant silhouette of trees providing a peaceful backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The man's action of petting the buffalo suddenly becomes deformed, and his hand and arm also show deformation and malformation. The face of the woman in the background also appears distorted, and the buffalo's head is not fully generated."
}
] |
seed46_2809
|
videos/HRA_part2/2809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, elegant restaurant, a cunning weasel, dressed in a crisp white waiter's outfit with a black bow tie, gracefully crawls across a wooden floor, passing beneath a table draped with a pristine white cloth. The weasel's sleek body and sharp features are accentuated by the warm glow of candlelight, casting dramatic shadows as it moves stealthily, weaving between the legs of ornate chairs. Its eyes gleam with mischief, hinting at some secretive mission unfolding among the unsuspecting diners.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1011
|
videos/HRA_part2/1011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a beige jacket, navy-blue shirt, and brown trousers, kneels on the floor of an art gallery, observing a taxidermied beaver. The setting is an exhibition space filled with various artworks, including paintings and sculptures. The director's intent gaze and body language suggest deep engagement with the beaver specimen, which is placed on a pedestal among other natural history exhibits. The camera captures this curious interaction from multiple angles, highlighting the director's fascination and the eclectic atmosphere of the gallery.]"
},
{
"from": "gpt",
"value": "Bad. The beaver specimen and sculpture were not generated in the video."
}
] |
seed44_1870
|
videos/HRA_part1/1870.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 attractive male actor wearing a black t-shirt and dark jeans is seen running alongside a large, energetic yellow dog in an expansive park. The two are captured mid-stride, with the actor's focused gaze and the dog's joyful expression highlighting their shared activity. They run together in harmony, the actor's casual attire and the dog's bounding energy creating a dynamic and engaging scene against the lush greenery of the park.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the person and the dog in the video are not smooth."
}
] |
seed42_1792
|
videos/HRA_part0/1792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, donning a straw hat and denim overalls, stands on wooden docks by the water's edge, engaging in an impromptu dance with a mongoose. The mongoose, with its alert eyes and bushy tail, seems equally engaged in the dance, mirroring the farmer's playful steps. The docks, weathered and worn, creak under their movements, providing a rustic stage for this unlikely duo. The sun begins to set, casting a golden glow over the scene, adding a magical touch to the dance between the farmer and the mongoose.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1558
|
videos/HRA_part2/1558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, athletic female nurse with short brown hair, wearing a navy scrubs top and gray pants, stretches her body against a white wall. She performs various stretches, including touching her toes and raising her arms overhead, highlighting her flexibility and physical fitness. The room is brightly lit, with a large window and a whiteboard in the background, providing a clinical yet dynamic setting for her routine. Throughout the sequence, she maintains a focused expression, showcasing her dedication to maintaining her physical health in a medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's arm is deformed and missing in the video, her fingers are not generated, her face is generated blurry, and there are issues with the generation of her legs."
}
] |
seed42_2248
|
videos/HRA_part0/2248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an urban park, a worker dressed in a green shirt and beige pants tends to the lush grass, unaware that a vibrant fox is watching from behind a tree. The fox, with its fiery red fur and piercing eyes, crouches low, ready to spring into action. Suddenly, it leaps into the air, jumping over a wooden bench in a graceful arc, capturing the essence of playfulness and freedom in the heart of the city. The worker, noticing the commotion, turns to see the fox mid-jump, a moment of surprise and delight shared between the two, set against a backdrop of tall buildings and green foliage.]"
},
{
"from": "gpt",
"value": "Bad. The fox's movements are discontinuous and undergo sudden changes when jumping and running."
}
] |
seed42_1957
|
videos/HRA_part0/1957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly lit classroom, a biology teacher, wearing a green button-down shirt and khaki pants, kneels on the floor with a focused gaze. A live lizard, displaying intricate patterns, crawls across the tabletop in front of him. The teacher's hands are positioned ready to guide the creature gently, ensuring its safety during this educational demonstration. Students observe intently from their desks, their faces a mix of fascination and mild concern, as the small lizard explores its temporary environment under the watchful eye of their knowledgeable instructor.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2081
|
videos/HRA_part0/2081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 uniformed police officer, equipped with sunglasses, a badge, and a radio, stands ready on a sandy beach, the ocean visible behind him. He then leaps into the air, his silhouette framed against the bright horizon, showcasing agility and dynamism. Next, he lands gracefully on the sand, his stance firm and authoritative. Finally, he is seen in mid-stride, walking purposefully along the shoreline, the vast ocean and clear blue sky completing the scene, embodying strength and determination in an idyllic coastal setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2663
|
videos/HRA_part2/2663.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert-dwelling lizard, specifically a Bearded Dragon, is shown swimming underwater in clear, sunlit water. Its body is fully submerged, and it moves gracefully through the water, showcasing its rarely seen aquatic locomotion. The lizard's skin ripples as it propels itself forward, and its claws can be seen extended as it navigates the aquatic environment. The water is crystal clear, allowing for a detailed view of the lizard's texture and movement, contrasting with its typical arid habitat. Sunbeams penetrate the water, illuminating the scene and highlighting the unique sight of a lizard swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2318
|
videos/HRA_part2/2318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman stands tall and poised, her blonde hair in a sleek bun, wearing a fitted black blazer over a white collared shirt, black trousers, and black heels. She is positioned in front of a large window with a city skyline visible in the background, her gaze directed towards the urban landscape. The scene is bathed in the warm glow of the setting sun, casting a golden hue over the woman and the cityscape, highlighting her silhouette and the texture of her attire. The contrast between the structured clothing and the fluidity of her stance conveys a sense of power and elegance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2666
|
videos/HRA_part2/2666.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": "Bad. The beaver's movements in the video are not smooth."
}
] |
seed44_1282
|
videos/HRA_part1/1282.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Two young boys, one wearing a red shirt and the other in a white shirt, walk side by side near an oil refinery complex with large tanks and pipes in the background, under a clear blue sky. They stroll along a dirt path, surrounded by the industrial landscape, their expressions serious as they navigate the terrain together. Despite the imposing structures around them, the children maintain a steady pace, their presence creating a stark contrast against the backdrop of the oil facility.]"
},
{
"from": "gpt",
"value": "Bad. The boy's face and hands in the video have generation issues."
}
] |
seed44_1135
|
videos/HRA_part1/1135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2322
|
videos/HRA_part1/2322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a backdrop of lush greenery and blue skies, two young boys, one wearing a yellow shirt and the other in red, are intently engaged in fixing a wooden fence. They work diligently, using a variety of tools spread out before them, their faces concentrated and serious as they tackle the task at hand. One boy, dressed in a yellow shirt, blue shorts, and brown shoes, leans against the fence, his hands busy with repair work, while the other, in a red shirt, khaki shorts, and blue sneakers, stands with a tool in hand, ready to assist. The scene captures the industrious spirit of childhood play, with the boys' clothes and tools adding vibrant details to the image.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2254
|
videos/HRA_part0/2254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, middle-aged with short, neatly trimmed brown hair and a well-groomed beard, pauses in his cleaning duties. Dressed in a dark green uniform with a name badge, he rests a mop against a pristine white wall. His eyes meet the camera, and he gives a slow, deliberate nod, acknowledging an unseen presence. The setting is a spotless, modern school hallway, with large windows casting soft light onto the polished floor, highlighting the cleanliness maintained by the janitor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1657
|
videos/HRA_part2/1657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious living room filled with natural light, a diligent woman wearing a yellow apron over a floral dress meticulously dusts an ornate wooden dresser, her movements methodical and thorough. Beside her, a man in a white shirt and brown trousers assists, carefully wiping down a matching side table. The room is elegantly decorated with antique furniture and Persian rugs, creating a warm and inviting atmosphere. On the walls, framed paintings and family photographs add personal touches to the space. The couple works in harmony, their actions demonstrating a shared commitment to maintaining their cherished home environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2080
|
videos/HRA_part2/2080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two children, a boy and a girl, both dressed in green, are dancing gleefully in a grassy meadow filled with dandelions. They perform a choreographed routine, spinning and leaping with joyful abandon. Suddenly, a vole emerges from the tall grass, peeking curiously at the dancers. Unfazed, the children continue their dance, now incorporating playful gestures towards the small mammal. The vole watches from a safe distance, its presence adding a touch of natural charm to the lively scene. Throughout the dance, the children's outfits, consisting of green shirts and khaki shorts, stand out against the lush greenery of the meadow, creating a vibrant and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuou."
}
] |
seed46_238
|
videos/HRA_part2/238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a red flannel shirt, blue jeans, and brown work boots, rakes a large pile of autumn leaves in his backyard, surrounded by lush greenery and vibrant fall foliage. He pauses to play a harmonica, his joyful expression and the warm, golden sunlight highlighting his love for music and the outdoors. Continuing his task, he rakes the colorful leaves into a sizable heap, his movements energetic and rhythmic, embodying the spirit of the season. Occasionally, he stops to strum his acoustic guitar, the leaves forming a picturesque backdrop, capturing the essence of a musician enjoying the simple pleasures of life amidst nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2205
|
videos/HRA_part1/2205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a yellow sports bra, black leggings, and white running shoes, runs past a series of modern apartment complexes. She has a focused look on her face, her brown hair tied back in a ponytail, and wears a small backpack. The apartments feature large windows, balconies with plants, and are painted in shades of blue and green. The scene is set in the late afternoon, with the sun casting long shadows and highlighting the architectural details of the buildings. In the distance, lush trees provide a natural contrast to the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs and fingers are missing in the video, and her face is generated blurry."
}
] |
seed42_2709
|
videos/HRA_part0/2709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red bandana, black sleeveless shirt, and black jeans, skillfully stir-fries ingredients in a wok over a high flame. The kitchen features a large stainless steel hood vent and several pots hanging above, giving it a professional look. The artist, known for his energetic stage presence, exhibits precision and focus as he deftly flips vegetables and proteins in the pan. The vibrant colors of the food contrast beautifully with the dark metal utensils and the flames beneath the wok, creating a visually engaging scene. Throughout the process, he maintains his cool demeanor, occasionally checking the seasoning and adjusting the heat, demonstrating his culinary prowess alongside his musical talent.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1552
|
videos/HRA_part2/1552.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen note that due to the rule about scene transitions, the last sentence should be disregarded, so here's an alternative ending without a transition:\nThe camera then pans out to show the sand dollar resting peacefully on the sandy seabed, surrounded by a few small pebbles and seaweed, capturing the serenity of its underwater habitat. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view captures the intricate beauty of a sand dollar, its pale color and fine texture contrasting against a dark, grainy sand background. The camera zooms in to reveal the small, delicate spines covering the surface of the sand dollar, emphasizing its natural design. As the focus shifts, the circular shape of the sand dollar becomes prominent, highlighting its symmetrical pattern. The final shot showcases the sand dollar partially buried in the sand, with a blurred oceanic horizon in the distance, evoking a sense of mystery and wonder about this enigmatic sea creature.]"
},
{
"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.