video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1744
|
videos/HRA_part1/1744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 contrasting scene, a lone hyena stands in the foreground, its silhouette framed against a golden sunset, while in the distance, meticulously aligned rows of lush green vines stretch across the landscape, indicating a vast vineyard. As the camera pans, a luxurious swimming pool comes into view, nestled amidst the vineyard, shimmering under the fading sunlight, offering a surreal juxtaposition of wild and cultivated beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2147
|
videos/HRA_part2/2147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse in a sky-blue uniform, complete with a matching cap, stands at the edge of a bustling harbor. The sun illuminates her figure as she prepares to leap into the air, her silhouette framed by the vibrant scene of ships and docks in the background. Her joyful expression contrasts with the busy maritime activities, capturing a spontaneous moment of playfulness amidst a working waterfront.]"
},
{
"from": "gpt",
"value": "Bad. The nurse in the video has missing limbs, facial deformities, and a twisted body."
}
] |
seed42_1888
|
videos/HRA_part0/1888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, empty warehouse with high ceilings and large, open spaces, four young children, two boys and two girls, are gleefully jumping and laughing as they play a game of tag. The boys wear matching blue striped shirts and khaki pants, while the girls are dressed in pink floral dresses and white leggings. The warehouse's concrete floors and metal beams provide an industrial yet spacious setting for their energetic play. The children's joyous expressions and animated movements capture the essence of carefree childhood fun in an unconventional environment.]"
},
{
"from": "gpt",
"value": "Bad. The facial expressions and arm generation of the children in the video are abnormal."
}
] |
seed46_1818
|
videos/HRA_part2/1818.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant botanical garden, a middle-aged janitor, wearing a green vest over a blue collared shirt and tan pants, gently caresses a camel. The scene opens with the janitor standing near a wooden fence, holding a leaf blower, before focusing on him tenderly touching the camel's nose. The setting shifts to the janitor embracing the camel's head, conveying a sense of affection and care. Lastly, he is seen feeding the camel from his hand, surrounded by the vibrant greenery of the botanical garden, creating a harmonious and unexpected connection between man and animal in a serene environment.]"
},
{
"from": "gpt",
"value": "Bad. The leaf blower in the worker's hand suddenly disappears, and the hand and arm become deformed, with the hand showing signs of malformation."
}
] |
seed46_191
|
videos/HRA_part2/191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cosmic setting, a cashier, clad in a unique space suit adorned with symbols of diplomacy, traverses the mammoth hall of an intergalactic embassy. She walks with purpose, passing through a grand archway, her eyes set on a distant goal. Behind her, a massive window reveals the breathtaking expanse of stars and galaxies, highlighting the enormity of her mission among the celestial bodies. Her every step echoes in the spacious corridor, resonating with the gravity of her role in maintaining galactic peace.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2995
|
videos/HRA_part1/2995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, with its bushy tail swaying, dances gracefully in a clearing surrounded by lush green foliage. Its movements are fluid and lively, as if performing a choreographed routine under the dappled sunlight filtering through the leaves. The fox leaps and twirls, its fur shimmering with golden highlights, embodying the spirit of the wild in a joyful, uninhibited dance. Against the backdrop of the vibrant forest, the fox's agile form and animated expressions convey a sense of freedom and playfulness in nature.]"
},
{
"from": "gpt",
"value": "Bad. The fox's limbs and head are missing in the video, and the body is slightly distorted."
}
] |
seed44_1085
|
videos/HRA_part1/1085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, neatly trimmed facial hair, and wearing a gray jacket over a blue shirt, tends to lush green plants in a spacious atrium. He waters the plants with a green watering can, moving methodically from one plant to another. The atrium features large windows letting in ample natural light, and the plants are arranged on multiple levels, creating a vibrant indoor garden atmosphere. The man focuses intently on his task, his actions conveying a sense of care and routine, as he nurtures the plants in this verdant environment.]"
},
{
"from": "gpt",
"value": "Bad. The fingers of the character and the teapot in the video have generation issues."
}
] |
seed46_1602
|
videos/HRA_part2/1602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 stylish woman in a red dress walks purposefully through the grand lobby of a luxurious hotel, her high heels clicking on the marble floor. The opulent space features tall windows, plush velvet sofas, and an elegant chandelier, all bathed in warm, inviting light. As she strides confidently, she passes by the reception desk, where a concierge is busy assisting guests. In the background, a group of tourists consults a map, adding a touch of bustling activity to the otherwise refined atmosphere. The woman's poise and the hotel's grandeur create a captivating scene of urban sophistication.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1194
|
videos/HRA_part0/1194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his uniform consisting of a navy blue shirt with badges, dark pants, and black shoes, vacuums the carpet in a modest living room. The room features a small brown couch, a glass coffee table, and a beige recliner, with sunlight streaming through the window, highlighting dust particles in the air. The officer, displaying a serious demeanor, methodically maneuvers the vacuum cleaner across the carpeted floor, revealing his commitment to household chores despite his profession. The domestic scene contrasts sharply with his authoritative attire, emphasizing the duality of his role as both protector and provider.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2424
|
videos/HRA_part1/2424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 waiter, dressed in a black vest and tie, crouches low, engaging in a playful crawl across a textured wooden floor. Unexpectedly, a squirrel appears, its bushy tail bouncing, as it curiously crawls alongside the waiter. The two crawl in unison, the squirrel mirroring the waiter's movements, against a backdrop that subtly hints at a 'Quantum Leap' style time warp, indicated by a faint, swirling visual effect. This surreal moment captures the unusual pairing of the crawling waiter and squirrel, blending elements of fantasy and reality.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1324
|
videos/HRA_part1/1324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man with glasses and a gray beanie, wearing a dark jacket, leans into the soil with a green-handled shovel, his wedding band glinting in the light. He pauses to wipe sweat from his brow, revealing a determined look. Moments later, he is joined by another man, both digging in unison, the second man dressed in a brown jacket, jeans, and a white t-shirt. The scene transitions to the first man, now shirtless and covered in dirt, continuing to dig with intense focus, highlighting the hard labor involved. Finally, the two men stand back, shovels resting on their shoulders, surveying their deep, freshly-dug hole, a sense of accomplishment evident in their satisfied expressions. Throughout the scene, the man with the beanie remains the central figure, his actions and expressions conveying the physical and emotional demands of the task.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is deformed."
}
] |
seed44_2617
|
videos/HRA_part1/2617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, clad in a dark gray jacket, white shirt, and black tie, is shown in a bathroom, intently focused on unclogging a drain. The bathroom features a white sink with chrome fixtures, a mirror above it, and a window in the background. The musician, with his graying hair and serious demeanor, uses a metal wire hanger as a makeshift tool to clear the clogged drain, demonstrating his problem-solving skills in an unexpected domestic task. The scene captures the juxtaposition of his refined appearance and the mundane chore, highlighting his versatility beyond his musical talents.]"
},
{
"from": "gpt",
"value": "Bad. The faucet and mirror were not shown in the video."
}
] |
seed42_2930
|
videos/HRA_part0/2930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray T-shirt and black cargo pants, methodically mops the floor of a modern industrial space, surrounded by sleek machinery and equipment. His attire includes a name badge and a pair of safety glasses hanging around his neck, signifying his professional role. The scene is lit by bright overhead lights, casting shadows that emphasize the rhythmic motion of the mop. The engineer's focused gaze and steady hand convey a sense of duty and precision as he tackles the mundane task of cleaning, set against the backdrop of a high-tech environment.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand appears deformed, and the mop in his hand is also distorted."
}
] |
seed42_2697
|
videos/HRA_part0/2697.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique and whimsical scene, a cheerful nurse, clad in a traditional white uniform and cap, finds herself frolicking in a shallow, clear water body situated amidst vast temperate grasslands. The lush, green landscape stretches far into the horizon, dotted with swaying grasses and a few scattered trees. The nurse, enjoying a spontaneous moment of leisure, splashes water joyfully, her white attire contrasting beautifully against the natural setting. The sunlight filters through partly cloudy skies, casting a warm glow over the entire scene, highlighting the serenity of the temperate grasslands and the nurse's playful spirit.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's face and hands in the video are generated abnormally, and the nurse's hand suddenly deforms in the middle frame."
}
] |
seed42_2427
|
videos/HRA_part0/2427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist 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": "Bad. The artist's limbs in the video are not clearly generated."
}
] |
seed42_1782
|
videos/HRA_part0/1782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, majestic and graceful, glides through crystal-clear waters, its body a stunning contrast of black and white. It somersaults effortlessly, performing acrobatic feats just beneath the ocean's surface, with sunlight filtering through and illuminating the scene. Schools of small fish scatter as the ray passes, highlighting the vastness of its wingspan. The ray then swims upward towards the sunlit water, creating mesmerizing patterns with its movements, before disappearing into the depths, leaving a trail of bubbles in its wake.]"
},
{
"from": "gpt",
"value": "Normal. The manta ray's body is deformed, and the eyes have not been generated."
}
] |
seed44_2120
|
videos/HRA_part1/2120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a white painter's smock and denim jeans, meticulously hangs a series of vibrant oil paintings on a gallery wall, the warm glow of spotlights illuminating each frame. The gallery space is vast, with high ceilings and pristine white walls, providing a stark contrast to the rich colors of the artwork. In another shot, the artist, now wearing a beret and glasses, carefully levels a large abstract piece, its bold strokes and dynamic composition capturing the essence of modern art. Finally, standing back, the artist admires the completed arrangement, a harmonious blend of creativity and craftsmanship, the gallery now transformed into a visual narrative of artistic expression.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1304
|
videos/HRA_part0/1304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A muscular man with short brown hair, wearing a black wetsuit, swims underwater in a clear, blue pool, interacting closely with a live cobra that moves alongside him. The snake, its hood slightly spread, appears calm in the water, its body parallel to the man's outstretched arm. Sunlight filters through the water, casting dappled light on the man's face as he maintains eye contact with the snake, both creatures moving gracefully through the aquatic environment. The scene is set in an outdoor pool, surrounded by lush greenery, emphasizing the natural setting and the unique interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Normal. No lush vegetation was generated."
}
] |
seed42_318
|
videos/HRA_part0/318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged female teacher waves energetically with both hands, standing against a classroom backdrop filled with educational posters and a whiteboard. Dressed in a vibrant red blouse and dark pants, she wears a welcoming smile, her wavy brown hair framing her face. Her enthusiastic gesture conveys warmth and inclusivity, inviting students into the learning environment. The classroom setting includes rows of desks, a bookshelf, and a large window allowing ample natural light, enhancing the sense of openness and engagement.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2980
|
videos/HRA_part0/2980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a brown jacket, beige pants, and brown boots, stands on a dirt floor, meticulously wiping a wooden table with a cloth. The scene takes place in a large, open arena, filled with wooden tables and chairs, reminiscent of a medieval feast setting. Sunlight filters through the high windows, casting a warm glow over the space. The man's focused gaze and the repetitive motion of his hand convey a sense of purpose and care in his task, set against the vastness of the arena.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1636
|
videos/HRA_part2/1636.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 devoted teacher wearing a VR headset and haptic gloves guides students through an immersive virtual reality space training simulation. The teacher demonstrates a caressing gesture, using the VR equipment to teach sensitive and precise movements in zero-gravity conditions. The environment is depicted with advanced graphics, showing the teacher floating among stars and planets, while the students observe from their own VR stations, mimicking the instructor's actions to learn essential space exploration skills.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the student in the video are not smooth and uncoordinated."
}
] |
seed42_2884
|
videos/HRA_part0/2884.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a red flannel shirt, blue jeans, brown work boots, and a wide-brimmed straw hat, rakes a large pile of autumn leaves in the midst of a vast, open farmland. The scene is set during the golden hour, with the sun casting a warm glow across the landscape. The farmer pauses to wipe sweat from his brow, revealing a face lined with the wisdom of years spent working the land. He continues his task with a sense of purpose and pride, the leaves forming a vibrant mosaic of reds, oranges, and yellows around him. The video captures the essence of hard work and the beauty of seasonal change in the rural countryside.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's movements in the video are not smooth."
}
] |
seed42_1314
|
videos/HRA_part0/1314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, snow-dusted wilderness, two majestic bison stand side by side, their large, sturdy bodies nearly touching. One bison gently nudges the other with its snout in a tender caress, their breath visible in the crisp air. Their shaggy coats ripple slightly in the wind, and their eyes meet, conveying a deep bond. The scene is peaceful and intimate, set against a backdrop of distant mountains and a clear blue sky, highlighting the gentle nature of these powerful creatures.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1574
|
videos/HRA_part2/1574.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 detailed close-up, a badger with piercing eyes and sharp teeth runs through a grassy landscape, its fur textured and realistic. Behind it, the silhouette of a large power plant with cooling towers can be seen, emitting steam into the dusky sky. The badger continues its sprint across the terrain, its body language conveying determination and strength, all set against the backdrop of the industrial power plant under the twilight sky.]"
},
{
"from": "gpt",
"value": "Normal. The badger's body suddenly changes in the middle of the video."
}
] |
seed46_1406
|
videos/HRA_part2/1406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a dark green blazer over a white shirt, is depicted against a backdrop of space exploration imagery, including astronauts and planets. Initially, she stands pensively, holding a book with both hands, her gaze directed downward. Then, she looks up, her expression shifting to one of determination, as if contemplating the vastness of space. Next, she is shown dancing energetically, her right arm raised, embodying the joy and freedom of movement. Finally, she strikes a confident pose, her left hand resting on her hip, her eyes gazing into the distance, encapsulating the spirit of adventure and creativity in the realm of space exploration.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, with sudden changes occurring."
}
] |
seed46_2447
|
videos/HRA_part2/2447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a gorilla wearing an astronaut suit stands before a massive spaceship, its textured surface reflecting the alien landscape. The gorilla looks up at the ship with curiosity and determination, ready to embark on a journey through interstellar space. Suddenly, the scene changes to show the gorilla swimming underwater, its powerful arms propelling it forward through crystal clear water, surrounded by colorful fish and vibrant coral reefs. The contrast between the futuristic space travel and the natural beauty of the underwater world highlights the versatility and adaptability of this extraordinary creature.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's swimming movements in the pool are basically normal, with slight disharmony."
}
] |
seed42_127
|
videos/HRA_part0/127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a blue shirt and gray pants, walks through a park with a calm demeanor, holding a coffee cup in his right hand. Suddenly, a squirrel approaches him, curious and bold, seeking attention or perhaps food. The squirrel is animated and lively, closely interacting with the engineer, who responds with amusement and gentle engagement. The engineer stops to interact with the squirrel, which playfully leaps onto his shoulder, creating a heartwarming moment in the midst of the engineer's daily routine. Throughout the interaction, the engineer's coffee cup remains visible, adding a touch of realism to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the engineer stopping."
}
] |
seed46_2222
|
videos/HRA_part2/2222.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant scene unfolds as a confident female nurse, clad in a leopard-print uniform, strides purposefully down a bustling hospital corridor. The unique pattern of her attire stands out against the sterile environment, drawing attention to her authoritative presence. With a stethoscope around her neck and a chart in hand, she embodies professionalism, while the leopard print adds a touch of unexpected flair to her otherwise conventional nursing uniform. The juxtaposition of her wild print against the clinical setting creates a memorable and intriguing visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2929
|
videos/HRA_part1/2929.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."
}
] |
seed44_3097
|
videos/HRA_part1/3097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 unique setting, a male worker in a red uniform tends to an art gallery space that doubles as a swimming pool, with water visible through a glass wall. He walks along the edge of the pool, which is surrounded by artworks, including a sculpture and framed pieces on the walls. The man, wearing red swim trunks, a red polo shirt, and a black cap, interacts with the space, showcasing the blend of aquatic and artistic elements. He is seen both working and swimming, highlighting the versatility of the environment, with the water's surface shimmering under the gallery lights.]"
},
{
"from": "gpt",
"value": "Bad. The male staff member walking in the pool does not match the text description; an additional person is generated in the video."
}
] |
seed42_2879
|
videos/HRA_part0/2879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a majestic stag with a full, impressive rack of antlers finds itself in an industrial setting, surrounded by large, gray warehouses under a cloudy sky. The deer begins to move gracefully, almost as if it's dancing, its hooves delicately stepping on the concrete ground. The scene is surreal, with the wild animal seemingly unfazed by the urban environment, embodying a unique blend of nature and industry as it prances amidst the towering structures.]"
},
{
"from": "gpt",
"value": "Normal. The deer's hooves generation in the video has problems, there are too many antlers generated, and the face generation is unnatural."
}
] |
seed44_2698
|
videos/HRA_part1/2698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmhand, clad in a khaki shirt, beige trousers, and brown shoes, walks purposefully across a well-kept yard. In the foreground, a vibrant red barn provides contrast against the clear blue sky. The worker pauses, bending down to pick up a lively chicken, its feathers a mix of brown and white, before continuing on his path, the bird calmly tucked under his arm. They stroll together, the worker's gait steady and the chicken seemingly unperturbed, encapsulating the peaceful rhythm of life on the farm.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1966
|
videos/HRA_part1/1966.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit, futuristic classroom filled with advanced technology, two young children, a boy and a girl, both wearing school uniforms, gently caress a small, friendly robot astronaut. The robot, designed with smooth, rounded edges for safety, features a smiling face on its metallic body, which is painted in shades of silver and blue. The room is decorated with educational posters and interactive screens, creating an engaging learning environment. The children, showing curiosity and affection, interact with the robot, which responds with gentle movements and playful sounds, fostering a connection between humans and artificial intelligence in a nurturing setting.]"
},
{
"from": "gpt",
"value": "Normal. The little girl's face is distorted, the little boy's arm is twisted, and the robot's arm is twisted."
}
] |
seed44_1833
|
videos/HRA_part1/1833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white dove with intricate feather patterns perches on a branch, nestled among lush green leaves that contrast beautifully with its pure white plumage. The bird looks towards the camera, revealing its detailed eye and beak. It then spreads its wings, displaying the impressive span and the delicate feather layers that catch the light, before taking flight against a clear blue sky, symbolizing peace and freedom. The final shot captures the dove soaring gracefully, its silhouette framed against the vastness of the sky, leaving behind a trail of tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2453
|
videos/HRA_part0/2453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2294
|
videos/HRA_part2/2294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by vibrant neon lights, a magnificent Bengal tiger, detailed with its distinctive orange fur and black stripes, appears to run gracefully through the aisles, its movement captured in stunning detail. The gallery walls are adorned with abstract art pieces, creating a surreal contrast to the powerful, lifelike depiction of the tiger in motion. The tiger's dynamic pose, mid-stride, conveys a sense of freedom and strength within the confined yet imaginative space of the art gallery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1815
|
videos/HRA_part1/1815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene opens with a koala, typically terrestrial, surprisingly adept in water, swimming in a serene, clear blue pool. Its brown fur glistens as it paddles with determination, showcasing an unexpected talent. The koala, wearing a small yellow swim cap, navigates the water with surprising grace, its limbs moving rhythmically. Moments later, it emerges from the pool, shaking off droplets, revealing a cozy green towel wrapped around its body. The koala then sits on the edge of the pool, seemingly pleased with its aquatic adventure, the sunlight sparkling on the water behind it.]"
},
{
"from": "gpt",
"value": "Normal. The koala's paws in the video have generation issues."
}
] |
seed42_2434
|
videos/HRA_part0/2434.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a red-and-white striped shirt, black pants, and a green apron, works as a cashier in a grocery store decorated with Chinese lanterns and bamboo plants. The panda, complete with a name tag and a lanyard, interacts with customers at the register. Suddenly, the panda starts dancing joyfully, swaying to an unseen beat, captivating the shoppers with its playful antics. The panda continues to dance, moving around the store, engaging with various customers, who look on in amusement, while still managing to scan items and handle transactions with dexterity. Throughout the scene, the panda's infectious energy fills the store, creating a memorable and delightful shopping experience.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1727
|
videos/HRA_part2/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2780
|
videos/HRA_part1/2780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, portraying a member of a nanobot repair crew, leaps dramatically across a futuristic, metallic platform. Dressed in a silver jumpsuit, complete with utility belts and pouches, he soars through the air with intense focus. His movements are agile and purposeful, suggesting urgency in his mission. As he lands, ready to tackle the next task, the background features complex machinery and glowing panels, immersing the viewer in a high-tech, sci-fi environment.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed46_1441
|
videos/HRA_part2/1441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, nestled in the fork of a lush eucalyptus tree, gently caresses its companion with a fuzzy paw, both enveloped in the verdant embrace of their arboreal home. The koala, with its round face and endearing expression, tenderly touches another koala, showcasing a heartwarming display of affection. Their interaction is set against the vibrant green foliage, highlighting the tenderness of their connection. As they engage in this intimate gesture, their soft fur and the intricate details of the eucalyptus leaves create a visually captivating scene. Throughout, the two koalas remain in this loving embrace, emphasizing the emotional bond between them.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1402
|
videos/HRA_part0/1402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with glasses, wearing a dark green sweater over a button-down shirt, stands on a chair to change a light bulb in a room with wooden floors and a desk filled with books and writing materials. He holds the new light bulb in his right hand while his left hand grasps the existing bulb, which is attached to a simple ceiling fixture. Behind him, a large window reveals a gray, rainy day outside. The room is dimly lit by a small lamp on the desk, illuminating the clutter of papers, notebooks, and a vintage typewriter. The writer's casual attire, including khaki pants and brown shoes, contrasts with the focused determination on his face as he completes this mundane task amidst his literary surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the hands are deformed, and the legs are contorted."
}
] |
seed42_1944
|
videos/HRA_part0/1944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 silverback gorilla is depicted in a dense, lush forest, illuminated by patches of sunlight filtering through the canopy. Initially, it stands powerfully on all fours, its muscles rippling under its dark fur. It then charges forward, running with a burst of energy, showcasing its strength and agility. The gorilla's movement is captured in a series of dynamic poses, highlighting its powerful build and the determination in its eyes, set against the vibrant greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The running movements of the silverback gorilla in the video are very unsmooth and uncoordinated, with sudden changes."
}
] |
seed42_2515
|
videos/HRA_part0/2515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic male lion, identifiable by his large size and dark mane, crawls stealthily across a dry, grassy savanna landscape. His body is positioned low to the ground, his ears are forward, and his eyes are intensely focused on something beyond the frame, indicating a hunting scenario. The lion's powerful muscles ripple beneath his tawny fur as he moves quietly, demonstrating the predatory nature and hunting prowess of these apex predators. The scene is set against a backdrop of distant acacia trees and an endless sky, capturing the essence of the African wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3029
|
videos/HRA_part1/3029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue floral-patterned scrub top and matching pants, waters indoor plants in a sunlit room. She is seen from behind, her dark hair in a bun, as she carefully tends to a large plant. Next, she faces the camera, smiling warmly, holding a watering can. She then waters another plant, her actions gentle and attentive. Lastly, she pauses, appearing thoughtful, the greenery and natural light creating a serene atmosphere around her.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's hand and the watering pot in her hand are deformed in the video."
}
] |
seed46_1166
|
videos/HRA_part2/1166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning avant-garde space fashion, sprints across a futuristic stage illuminated by neon lights. Dressed in a metallic silver bodysuit, complete with high-tech accessories and a helmet visor, they leap with dynamic energy. The scene is set in a grand, space-themed venue, filled with an audience captivated by the performance. Spotlights follow the actor as they navigate the runway, showcasing the innovative designs against a backdrop of cosmic visuals and ambient electronic music. The fusion of performance art, cutting-edge fashion, and sci-fi aesthetics creates a mesmerizing spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not fluid, and the movements are uncoordinated."
}
] |
seed44_1627
|
videos/HRA_part1/1627.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 parallel universe, a robust farmer leaps high into the air, his body mid-jump, showcasing an extraordinary ability. Dressed in a brown shirt, green vest, beige trousers, and black boots, he appears surprised by his own supernatural power. Behind him, an array of vibrant vegetables and fruits grow in perfect rows, defying the laws of physics in this fantastical realm. The farmer's leap is captured in stunning detail, highlighting his muscular physique and the otherworldly setting that surrounds him.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's brown shirt and green vest in the video are inconsistent."
}
] |
seed42_2947
|
videos/HRA_part0/2947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a gray sweatshirt with the sleeves rolled up, dark pants, and black gloves, stands on a ladder propped against a white house, cleaning the rain gutters. The scene is set in the backyard, with lush green grass and shrubs in the foreground. The artist's tools, including a trowel and a bucket, are visible as they scoop out debris from the gutters. The ladder leans against the house, providing support as the artist works diligently, the greenery and peaceful suburban setting creating a serene backdrop for this everyday task.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and the ladder behind them is also distorted."
}
] |
seed42_2018
|
videos/HRA_part0/2018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a leopard print scarf, sits in a dimly lit room, engaged in caressing a small, furry creature. Behind her, a screen displays complex diagrams related to quantum entanglement experiments, adding a layer of intrigue. Her attire, which includes the eye-catching leopard print accessory, contrasts with the scientific theme of the scene. The focus is on her gentle interaction with the creature, while the backdrop hints at her intellectual pursuits, creating a compelling juxtaposition between the personal and professional aspects of her life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2995
|
videos/HRA_part2/2995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, with its bushy tail swaying, dances gracefully in a clearing surrounded by lush green foliage. Its movements are fluid and lively, as if performing a choreographed routine under the dappled sunlight filtering through the leaves. The fox leaps and twirls, its fur shimmering with golden highlights, embodying the spirit of the wild in a joyful, uninhibited dance. Against the backdrop of the vibrant forest, the fox's agile form and animated expressions convey a sense of freedom and playfulness in nature.]"
},
{
"from": "gpt",
"value": "Bad. The fox's limbs and head generation in the video have problems, with the body appearing distorted."
}
] |
seed46_2699
|
videos/HRA_part2/2699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The egret's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_301
|
videos/HRA_part2/301.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic 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": "Good. No obvious issues."
}
] |
seed44_1151
|
videos/HRA_part1/1151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a black beret and glasses, sits at a cluttered desk in a dimly lit room, affectionately caressing a small bat perched on her finger. The bat, appearing relaxed and comfortable, is nestled against her hand, which is adorned with silver rings. The scene is set against a backdrop of bookshelves filled with various books, adding to the intellectual and mysterious atmosphere. The writer's other hand rests on a vintage typewriter, hinting at her profession, while the bat's presence introduces an element of the unusual into the intimate scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2412
|
videos/HRA_part0/2412.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray hoodie, black pants, and black shoes, jumps dynamically in front of a large-scale painting that depicts a swirling, cosmic-like antimatter containment facility. The artwork showcases vibrant colors and intricate details, capturing the essence of a high-energy, science fiction-inspired scene. The artist's pose, mid-air with arms extended, adds a sense of movement and creativity to the composition. The room is illuminated by a soft, ambient light, highlighting the artist's silhouette and the captivating artwork behind them.]"
},
{
"from": "gpt",
"value": "Bad. The artist's jumping in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_1003
|
videos/HRA_part1/1003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, form-fitting spacesuit, adorned with intricate details and a VR helmet, is seen in a futuristic, high-tech room filled with advanced equipment. He leaps into the air, seemingly weightless, as the virtual environment around him simulates the zero-gravity conditions of space. The room is illuminated by soft, ambient lighting, highlighting the man's movements as he trains for space missions, surrounded by screens displaying complex data and simulations. The focus remains on the astronaut in the center of the room, his body language conveying determination and excitement as he experiences the thrill of jumping in a virtual space environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are unsmooth."
}
] |
seed44_1490
|
videos/HRA_part1/1490.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, leaps over debris inside a burning apartment complex, the intense flames and smoke creating a dramatic backdrop. The scene highlights the heroism and physical demands faced by firefighters in rescue operations. The exterior of the complex shows multiple stories engulfed in fire, emphasizing the scale of the emergency. The firefighter's decisive action, jumping over obstacles, symbolizes the urgent and dangerous nature of their mission to save lives and contain the blaze.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, with distorted arms and legs."
}
] |
seed46_3117
|
videos/HRA_part2/3117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in a tan vest and brown pants walks purposefully through a dense forest, his muscular build and focused gaze conveying strength and determination. Beside him, a large, colorful lizard with vibrant green and orange scales scurries along, keeping pace effortlessly. The lush vegetation of the jungle surrounds them, with tall trees overhead filtering the sunlight into dappled patches on the forest floor. The man and the lizard continue their journey together, navigating the complex terrain as they move deeper into the wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1267
|
videos/HRA_part0/1267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, clad in a brown fedora and matching suspenders over a striped shirt, tap dances on a wooden stage under a spotlight. Behind him, a red velvet curtain provides a dramatic backdrop. He executes a series of lively dance moves, including a tap routine, a spin, and a leap, all with a joyful expression on his face. Throughout the performance, he maintains his polished appearance, complete with a vest, watch chain, and spats, as he channels the spirit of a vaudeville entertainer.]"
},
{
"from": "gpt",
"value": "Normal. The beaver is not wearing a striped shirt."
}
] |
seed46_1962
|
videos/HRA_part2/1962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young children, a boy and a girl, both wearing red jackets, are seen walking together with a realistic, animated beaver on a wooden path in a park during daytime. The beaver, positioned between the children, is slightly ahead, leading the way as if guiding them, while the girl looks down at it with a smile. The trio continues walking on the wooden trail, surrounded by lush greenery, with the beaver still in the lead, its bushy tail swaying side-to-side, and the children following closely behind, engaged in a joyful outdoor adventure.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's movements in the video are not smooth."
}
] |
seed42_1188
|
videos/HRA_part0/1188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform with a badge and a hat, sits in a well-lit room with white walls. He nods slowly and deliberately in response to something off-screen, his serious demeanor and attentive body language conveying a sense of authority and engagement. The clean, organized setting and the officer's focused gaze suggest a formal environment, possibly an office or an interrogation room, where he listens intently to another person, nodding to show understanding and agreement.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's head in the video is generated incorrectly, and the eyes are not fully generated."
}
] |
seed42_1773
|
videos/HRA_part0/1773.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a yellow hazmat suit typically worn in industrial areas, paints a vivid mural featuring a graceful gazelle sprinting across a barren urban landscape. The scene is set against the backdrop of industrial zones, with the artist's focused expression and steady hand capturing the gazelle's dynamic movement on a large concrete wall. The artwork comes to life as the painter adds final touches, highlighting the gazelle's speed and agility, juxtaposed against the gritty industrial setting, while the artist, still in the yellow protective gear, steps back to admire the finished piece.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2100
|
videos/HRA_part2/2100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, 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": "Normal. The hands of the college student, and the head and limbs of the lynx in the video have generation issues."
}
] |
seed44_1742
|
videos/HRA_part1/1742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 aquarium filled with clear, blue water, a translucent ghost shrimp, barely visible, floats motionless near the bottom, its delicate legs folded. It then swims upward slowly, revealing its transparent body and the tiny creature inside, before coming to a stop near the surface. The shrimp hovers there, seemingly weightless, before descending again to the sandy bottom, dotted with small stones and pieces of aquatic plants, offering a glimpse into the elusive life of this ethereal crustacean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1168
|
videos/HRA_part0/1168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant park, a majestic leopard, its golden eyes alert, crouches near the edge of a pristine swimming pool, surrounded by vibrant greenery and towering palm trees. The big cat, with its distinctive rosette patterns on a tawny coat, gazes intently at the clear water, contemplating a playful leap. Moments later, it leaps gracefully into the pool, its powerful body slicing through the water in a fluid motion. Emerging from the pool, the leopard shakes off droplets, revealing its muscular physique, as it strides confidently across the park, leaving behind a trail of shimmering water on the sun-drenched pavement.]"
},
{
"from": "gpt",
"value": "Bad. The leopard has extra tails, and its legs are twisted."
}
] |
seed42_1013
|
videos/HRA_part0/1013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a futuristic silver jumpsuit and helmet, dances joyously on a meticulously designed space movie set, surrounded by intricate control panels and glowing buttons. The set is filled with high-tech equipment and large, detailed screens displaying cosmic visuals. The writer's movements are expressive and free, conveying a sense of liberation and creativity amidst the futuristic environment. As they dance, the lights from the set illuminate their figure, highlighting their passion for storytelling in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_128
|
videos/HRA_part1/128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its greenish-blue body with orange highlights and yellow fins, swims gracefully among the coral reefs. Its intricate scales resemble armor, providing a unique texture. It explores its underwater world, surrounded by various corals of purple, red, and orange, creating a stunning contrast against the blue water. The fish's beak-like mouth, a characteristic feature, is clearly visible as it feeds on algae-covered rocks, demonstrating its natural behavior in its marine habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3005
|
videos/HRA_part0/3005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's facial features are missing, fingers are deformed, and feet are problematic; the video does not realistically represent reality."
}
] |
seed42_2724
|
videos/HRA_part0/2724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red flannel shirt, beige pants, and brown suspenders, stands at a white sink in a rustic kitchen. He is washing dishes by hand using a sponge, with a wooden cutting board and a bowl of fruit visible nearby. The farmer, who has short brown hair and a neatly trimmed beard, demonstrates his commitment to household chores with a focused expression. The kitchen is warm and inviting, with wood-paneled walls, a white refrigerator, and a window above the sink offering a view of green fields. The farmer's strong hands, calloused from years of working the land, now deftly clean plates and utensils, showcasing the versatility of his daily tasks.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2337
|
videos/HRA_part2/2337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer in a crisp, white lab coat stands within a futuristic, neon-lit control room, his face reflecting determination as he gazes intently at a holographic interface displaying complex schematics. Suddenly, the scene changes to reveal the same engineer navigating through a parallel universe, where technology and nature intertwine in unexpected ways. He wipes away a layer of mist from a transparent panel, revealing an intricate circuit design beneath, symbolizing the merging of worlds and the power of innovation. The engineer's focused expression and the vivid, otherworldly landscapes around him emphasize the limitless possibilities of exploration and discovery.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2845
|
videos/HRA_part1/2845.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [Amid the lush greenery of a tropical rainforest, twin toddlers, a boy and a girl, crawl on a mossy rock near a cascading waterfall, their clothing soaked from the water. The boy wears a red shirt and gray shorts, while the girl is dressed in a pink top and yellow shorts, both sporting wide smiles as they explore their watery surroundings. Their crawling movements contrast with the powerful rush of the waterfall, creating a dynamic scene of innocence and nature's grandeur. The camera captures this intimate moment, focusing on the children's expressions of wonder and joy as they interact with the natural world around them.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1875
|
videos/HRA_part2/1875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a white shirt and denim overalls, stands on the edge of a serene pond, watching attentively as a rabbit swims gracefully through the clear water. The rabbit, defying expectations, moves with surprising agility, its brown fur glistening beneath the golden afternoon sunlight. The farmer, hat in hand, looks on with a mix of surprise and delight, the rolling green fields and distant barn providing a quintessential rural backdrop to this unexpected scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2165
|
videos/HRA_part1/2165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, ancient-looking turtle with a mossy, textured shell slowly moves across a lush, green forest floor, surrounded by vibrant ferns and fallen leaves. Its wise, gentle eyes and wrinkled skin reflect its age and resilience. Nearby, a small stream glistens in the dappled sunlight, while tall trees tower overhead, creating a serene, natural habitat for this majestic creature. The turtle continues its unhurried journey, embodying the peaceful, enduring spirit of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3179
|
videos/HRA_part1/3179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 salaryman strides purposefully down a bustling Tokyo street, his black business attire contrasting sharply with the neon signs and billboards towering overhead. The urban landscape is alive with the energy of the city, as the pedestrian moves through crowds of similarly dressed workers. The architecture reflects a blend of traditional and modern styles, with historic buildings standing alongside sleek skyscrapers. Throughout the scene, the salaryman maintains his steady pace, his journey punctuated by the vibrant colors and dynamic movements of the city around him.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_191
|
videos/HRA_part0/191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cosmic setting, a cashier, clad in a unique space suit adorned with symbols of diplomacy, traverses the mammoth hall of an intergalactic embassy. She walks with purpose, passing through a grand archway, her eyes set on a distant goal. Behind her, a massive window reveals the breathtaking expanse of stars and galaxies, highlighting the enormity of her mission among the celestial bodies. Her every step echoes in the spacious corridor, resonating with the gravity of her role in maintaining galactic peace.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1736
|
videos/HRA_part0/1736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 strong woman dressed in black pants, a black sports bra, and protective gear, including shin guards and arm pads, is seen in a well-lit gym. She delivers a powerful roundhouse kick, her body exhibiting grace and power, with boxing gloves on her hands and her hair tied back in a ponytail. Moments later, she throws a fierce punch, her face a mask of determination, showcasing her martial arts skills in a space adorned with punching bags and boxing posters. Finally, she executes a high kick, her form impeccable, against a backdrop of gym equipment and motivational wall art, encapsulating her strength and discipline.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs in the video are missing, and her facial features are blurry."
}
] |
seed46_2170
|
videos/HRA_part2/2170.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": "Normal. The man's hands and feet, and the hiking stick in the video have generation issues; the hiking stick in the man's hand suddenly twists and separates in the middle frames."
}
] |
seed46_3204
|
videos/HRA_part2/3204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded male musician, wearing a brown hat and a blue shirt with suspenders, sits against a plain gray backdrop. He is knitting a long, cream-colored scarf with large needles, showcasing his dexterity. In another scene, he holds the growing scarf in his hands, his facial expression one of concentration. Next, he looks directly at the camera, his eyes conveying a sense of peace and contentment. Finally, he continues knitting, his fingers moving skillfully, set against the simple gray background that emphasizes his artistic endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The musician can be seen knitting a scarf in the video, with basically normal movements, but there is some lack of coordination."
}
] |
seed42_1976
|
videos/HRA_part0/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_3120
|
videos/HRA_part2/3120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, donning a brown bear costume, complete with furry details and a snout, finds himself on a vast, cosmic stage set against the majestic backdrop of Saturn and its intricate ring system, clearly visible in the distance. Under the celestial lights, he begins to dance gracefully, his movements animated and lively, creating a surreal and whimsical scene that juxtaposes the grandeur of space with the playful nature of his attire. The detailed rings of Saturn, comprised of countless ice particles, shimmer in the background, providing a stunning contrast to the earthy tones of the bear suit. Throughout the dance, the man's expressive body language conveys a sense of joy and freedom, inviting the viewer to join in this otherworldly celebration.]"
},
{
"from": "gpt",
"value": "Normal. The man dressed in a brown bear costume in the video has incomplete finger generation and blurry facial features."
}
] |
seed42_2267
|
videos/HRA_part0/2267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a white shirt, black vest, and black trousers, diligently mops the floor of an empty restaurant during the daytime. The space is notably devoid of customers, with only a single table set with plates and cutlery visible in the background. The waiter's focus is intense as he works, pushing the mop back and forth across the smooth, light-colored tile flooring. His movements are methodical and purposeful, emphasizing his commitment to maintaining a clean dining environment. The natural light filtering through the windows highlights the cleanliness of the space, further emphasizing the waiter's efforts.]"
},
{
"from": "gpt",
"value": "Normal. The arms, hands, feet, and the mop in the hand are distorted in the video."
}
] |
seed46_1356
|
videos/HRA_part2/1356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A hummingbird, vibrant green and iridescent, hovers in a close-up shot against a blurred background of lush vegetation. Its wings, a blur of motion, propel it as it feeds from a red salvia flower, the curved beak piercing the bloom. The bird's small size, quick movements, and the detailed feathers are highlighted, set against the rich greenery and soft, natural lighting. The scene captures the hummingbird's agility and the delicate interaction between the bird and the flower, encapsulating the beauty of nature in high definition.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's eyes were not generated in the video."
}
] |
seed46_1824
|
videos/HRA_part2/1824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, adventurous ferret, wearing a red life jacket, gleefully swims in a clear blue pool, its paws energetically paddling as it looks around with curious eyes. The pool is surrounded by a lush garden filled with vibrant greenery and colorful flowers, creating a serene and idyllic setting. Sunlight filters through the leaves above, casting dappled shadows on the water's surface, highlighting the ferret's playful movements as it enjoys its aquatic adventure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_148
|
videos/HRA_part0/148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bison, framed against a vivid orange sunset, leaps gracefully over a wooden fence in slow motion, showcasing its muscular physique and determination. Its shaggy, dark brown fur billows in the wind as it clears the barrier with ease, highlighting the animal's surprising agility and strength. The contrast between the bison's robust form and the delicate beauty of the twilight sky creates a dramatic and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2149
|
videos/HRA_part2/2149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant display under the aurora-lit sky, several figures clad in traditional fur coats and hats, reminiscent of indigenous Siberian attire, gather around a blazing bonfire set amidst the dense taiga forest. They begin to sway in unison, their movements a harmonious blend of ancient and modern dance styles. The firelight flickers across their faces, casting dramatic shadows as they leap and twirl, their feet barely touching the snow-covered ground. The camera captures the dancers from various angles, emphasizing the connection between their lively steps and the serene, starlit wilderness that surrounds them.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_143
|
videos/HRA_part0/143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, dressed in a white lab coat over khaki cargo pants and brown leather shoes, runs through a lush, green jungle environment. In his right hand, he holds a clear, plastic container housing a live lizard, which scurries about inside. The doctor navigates through the dense foliage, dodging vines and leaping over fallen logs, his face set with determination as he focuses on his mission. The vibrant greenery of the jungle provides a stark contrast to the doctor's attire, highlighting the unusual nature of this scenario.]"
},
{
"from": "gpt",
"value": "Normal. The character's running motion is not smooth."
}
] |
seed44_1849
|
videos/HRA_part1/1849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary vulture, with its distinctive bald head and dark plumage, perches majestically on a rocky outcropping, overlooking a vast, arid landscape under an overcast sky. Its powerful, hooked beak is slightly open, revealing its pinkish-red interior, while its piercing eyes survey the terrain for potential prey. The bird's textured skin and feather details are highlighted by the natural lighting, emphasizing its rugged survival instincts in the harsh environment. As it prepares to take flight, the vulture's wings spread wide, displaying their impressive span against the muted tones of the rocky surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2871
|
videos/HRA_part0/2871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 upscale restaurant, a waiter, dressed in a black suit with a white shirt, black tie, and a pocket square, gently caresses a small, live vole on a pristine white tablecloth. The scene is set against a backdrop of expensive cutlery, crystal glasses, and fine china. The waiter's facial expression conveys a sense of care and tenderness, while the vole appears calm and unafraid. The room is softly lit, casting warm shadows on the walls adorned with elegant paintings and tapestries. This unusual interaction unfolds in slow motion, capturing every detail of the waiter's delicate touch and the vole's relaxed demeanor.]"
},
{
"from": "gpt",
"value": "Normal. The server's action of petting the mouse in the video is basically normal, with slight disharmony."
}
] |
seed42_2293
|
videos/HRA_part0/2293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An albatross soars through a vivid orange sunset, its expansive wings nearly touching the rippling water below. The bird's white plumage is highlighted by golden light, casting a serene shadow on the sea's surface. Against a dramatic sky, the majestic bird flies gracefully, occasionally gliding over gentle waves. Its wings, outstretched against the horizon, seem to embrace the vastness of the ocean, creating a captivating contrast between the bird's silhouette and the fiery sky.]"
},
{
"from": "gpt",
"value": "Normal. The albatross's claws were not generated."
}
] |
seed46_2649
|
videos/HRA_part2/2649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, clad in a navy blue NASA spacesuit with patches and a white name tag, walks purposefully down a pristine, metallic corridor aboard a futuristic space station. The station's interior is illuminated by soft, ambient lighting, and features advanced technology, including touch-screen panels and monitoring equipment, highlighting the cutting-edge nature of the facility. The doctor's movements are unhurried yet deliberate, conveying a sense of routine and familiarity within the microgravity environment. The backdrop showcases the intricate design of the space station, with various modules visible through windows, offering glimpses into different areas where scientific research and daily activities take place.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's fingers in the video are deformed, and there are issues with the mouth generation."
}
] |
seed46_1572
|
videos/HRA_part2/1572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young children, a boy and a girl, are diligently cleaning a large fish tank positioned against a wall covered with a floral-patterned curtain. The boy, wearing a gray shirt and dark pants, uses a net to scoop debris from the water, while the girl, dressed in a yellow shirt and blue jeans, scrubs the glass with a small brush. Both children work attentively, surrounded by an array of aquarium supplies, including bags of gravel, fish food containers, and various cleaning tools. The tank is home to several colorful fish that swim tranquilly in the background, undisturbed by the children's careful efforts to maintain their environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1118
|
videos/HRA_part2/1118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged writer, donning a brown jacket, beige slacks, and brown boots, takes a break from his typewriter to rake a large pile of colorful autumn leaves in his backyard, capturing the essence of seasonal change. He pauses, tool in hand, casting a thoughtful gaze at the vintage typewriter sitting on a wooden desk, which is placed under a large, leafy tree. The scene transitions to show him raking leaves with vigor, his attire unchanged, as the leaves form a vibrant heap, evoking a sense of tranquility and the beauty of fall. Finally, he pauses again, this time with a satisfied smile, surveying his neatly raked yard, the pile of leaves a testament to his labor, while the typewriter remains in the background, hinting at his dual passions for writing and nature.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, the hoe in hand deforms and detaches at some point. The character's limbs also seem a bit uncoordinated."
}
] |
seed42_1858
|
videos/HRA_part0/1858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a traditional ceremonial robe, kneels on a lush, green meadow under a clear night sky filled with stars. Beside them, a squirrel, unusually adorned in miniature ceremonial attire, mirrors the student's position. The student gently wipes away what appears to be ceremonial paint from their face using a soft cloth, alluding to a cleansing ritual. This intimate act is witnessed by the squirrel, which seems to participate in its own way, creating a surreal, touching moment between human and nature, set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The student's face and hands in the video are generated abnormally."
}
] |
seed44_2215
|
videos/HRA_part1/2215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a dark suit, sits in an office with wooden shelves and books in the background, gently caressing a porcupine. The lawyer, with neatly combed gray hair and glasses, looks directly at the camera, holding the porcupine with care. In another shot, the lawyer, still in his professional attire, cradles the porcupine in his hands, showing a softer side amidst the serious atmosphere of the law office, filled with books and legal documents. Throughout, the unlikely pairing of the suited lawyer and the spiky porcupine conveys a message of tenderness and unexpected connections.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted, face is distorted, and the hedgehog's face is distorted."
}
] |
seed44_150
|
videos/HRA_part1/150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, softly lit room, two young children sit cross-legged on a vibrant multi-colored rug, surrounded by an array of plush toys and colorful books. The older child, wearing a yellow shirt, leans over a book, animatedly pointing at the pages as they read aloud with enthusiasm. The younger child, dressed in a blue sweater, listens intently, eyes wide with wonder and hands resting on their knees. The walls of the room are painted a calming light blue, adorned with playful artwork and educational posters, creating a nurturing environment that fosters a love for reading and learning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_178
|
videos/HRA_part1/178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a dark suit, finds himself unexpectedly dancing with a chimpanzee in a whimsical scene. Both appear joyful and engaged, with the lawyer maintaining eye contact, smiling, and gesturing with his hands as if leading the dance. The chimpanzee, equally enthusiastic, mirrors the lawyer's movements, wearing a small hat tilted playfully to one side. They dance against a backdrop of a bustling city street, with pedestrians passing by in the background, adding a surreal touch to the urban setting. The lawyer's polished shoes and the chimpanzee's hat become focal points as they whirl around, creating a delightful contrast between professionalism and playfulness.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the chimpanzee's movements are also not smooth."
}
] |
seed44_3042
|
videos/HRA_part1/3042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with salt-and-pepper hair sits in a dimly lit room, wearing a gray blazer and a white shirt with the top button undone. He leans back in a brown leather armchair, holding a book in his hands. The camera captures him from the side, highlighting his profile as he reads intently. Beside him, a wooden table holds a glass of red wine, a vintage lighter, and a half-smoked cigar resting in an ashtray. The atmosphere is cozy and intimate, with the warm glow of a nearby lamp illuminating the scene. Behind the chair, a large bookshelf filled with books adds to the scholarly ambiance. The man's eyes are fixed on the pages, his lips slightly parted, indicating deep concentration as he delves into the story. The setting conveys a sense of leisurely intellectual pursuit, with the elements of wine, cigar, and reading material suggesting a refined evening routine.]"
},
{
"from": "gpt",
"value": "Normal. The man's nose and ears in the video have generation issues, and the fingers are deformed."
}
] |
seed44_1941
|
videos/HRA_part1/1941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy white dog with a pink collar and a polka-dot harness walks down a suburban sidewalk, its ears perked and tail wagging. It pauses to sniff a green fire hydrant, then continues its leisurely stroll. The dog then trots across a quiet street, passing by a row of neatly trimmed hedges and a red mailbox. Finally, it stops to rest under the shade of a large tree, the sunlight filtering through the leaves and casting dappled shadows on the dog's fur.]"
},
{
"from": "gpt",
"value": "Normal. The white fluffy dog in the video has uncoordinated body movements."
}
] |
seed42_1644
|
videos/HRA_part0/1644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 well-lit, organized retail store, two diligent employees wearing red aprons and name tags restock the shelves with groceries. One employee, a man with short brown hair, focuses on neatly arranging cereal boxes, ensuring they face forward. Meanwhile, his female coworker, wearing glasses and with her hair tied back, meticulously stacks cans of soup, aligning them perfectly. The shelves are filled with various food items, including crackers, canned goods, and pasta, all neatly organized and easily accessible to customers. The store is clean and inviting, with a fresh produce section visible in the background, showcasing an array of colorful fruits and vegetables.]"
},
{
"from": "gpt",
"value": "Bad. The face, arms, legs, and hands of the character in the video are distorted."
}
] |
seed44_3016
|
videos/HRA_part1/3016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a khaki shirt and beige chinos, gently caresses a kangaroo in an Australian outback setting, surrounded by shrubbery and distant hills. The engineer, wearing safety goggles around his neck, interacts affectionately with the kangaroo, which stands on the ground, both under a clear blue sky. The kangaroo, with its distinctive marsupial pouch, is calmly accepting the engineer's touch, while the engineer's attire and demeanor suggest a blend of professionalism and compassion in this unexpected interaction.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2004
|
videos/HRA_part0/2004.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male cashier, wearing a red apron with a name tag and a lanyard around his neck, is seen pulling a metal cart filled with various groceries, including a large water jug, milk, bread, and other items typically found in a supermarket. The cart is so full that it requires effort to pull, emphasizing the weight and volume of the goods. This scene takes place in a busy supermarket aisle, with shelves stocked with products and other customers shopping in the background.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.