video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1689
|
videos/HRA_part1/1689.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a crisp, white linen suit and dark sunglasses, sits beside a gorilla wearing a tiny, matching outfit, on a vibrant, sandy beach bustling with activity. The lawyer and gorilla share a lighthearted moment, enjoying the coastal scenery. Nearby, a group of people splash and swim in the crystal-clear water, their laughter blending with the rhythmic sound of the waves. The camera captures this whimsical scene, focusing on the lawyer and gorilla's playful interaction against the backdrop of a stunning beach and swimmers enjoying the refreshing waters.]"
},
{
"from": "gpt",
"value": "Bad. The swimmers' movements in the background of the video are very unsmooth and uncoordinated."
}
] |
seed46_1725
|
videos/HRA_part2/1725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt and black pants, serves a dingo seated at a table set amidst dense green thickets. The dingo, wearing a red bandana, looks expectantly at the waiter, who holds a platter of food. Nearby, a swimming pool glistens under the sun, its clear blue water contrasting with the lush vegetation surrounding it. The waiter, with a friendly smile, places the dish before the dingo, who eagerly leans forward, creating a surreal yet charming tableau.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's fingers were not fully generated, the face appeared distorted, and the dog had two extra legs."
}
] |
seed46_2541
|
videos/HRA_part2/2541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, seemingly a teacher, sits at a sewing machine in a homey, cluttered room filled with natural light. She wears a simple white shirt and has short, neatly styled brown hair. The room is decorated with a large painting and a calendar on the wall, adding a personal touch. The teacher deftly operates the sewing machine, carefully hemming a pair of pants, demonstrating her skill and focus on the task at hand.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2497
|
videos/HRA_part1/2497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sandy desert under a wide, cloudless blue sky, a single brown camel moves slowly across the dunes, its large, padded feet carefully placing one in front of the other in a crawling motion. The desert stretches out behind and ahead of the camel, unbroken except for the undulating lines of sand. The sun, high and bright, casts the camel's long, distinct shadow on the dune it has just crossed, emphasizing the creature's solitary journey through this immense, arid landscape.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the camel in the video are missing, the humps and face have generation issues, and the tail is generated unreasonably."
}
] |
seed42_2849
|
videos/HRA_part0/2849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant desert landscape under a warm, golden sun, two people clad in traditional white robes stand beside a camel, which is kneeling obligingly in the sand. Moments later, these individuals mount the camel, which rises to its feet, ready to embark on a journey. Subsequently, the camel starts moving, walking steadily across the sandy dunes with the riders holding on. Finally, gaining momentum, the camel begins to run, carrying the passengers across the undulating desert terrain at an exhilarating pace, their white garments billowing in the wind.]"
},
{
"from": "gpt",
"value": "Bad. The camel's walking movements in the video are uncoordinated."
}
] |
seed46_2009
|
videos/HRA_part2/2009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an astrophysics laboratory filled with high-tech equipment and screens displaying cosmic data, a worker, wearing a white lab coat over a gray shirt and dark pants, dances energetically. Accompanying him is a live rabbit, hopping playfully nearby, seemingly unfazed by the unusual environment. The scientist's joyful movements contrast with the serious scientific surroundings, creating a whimsical and unexpected scene. Throughout, the lab remains brightly lit and organized, with the scientist and the rabbit sharing a moment of lightheartedness amidst the serious pursuit of knowledge.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1575
|
videos/HRA_part1/1575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker in a lab coat walks purposefully across a large, open laboratory space filled with complex machinery and high-tech equipment, the setting for a quantum entanglement experiment. The room is illuminated by bright overhead lights, casting a sterile glow over everything. In the background, scientists can be seen observing data on computer screens and discussing theories, their faces serious and focused. The worker carries a clipboard, pausing occasionally to check notes or adjust settings on various machines, all while surrounded by the hum of active scientific inquiry into the mysteries of quantum mechanics.]"
},
{
"from": "gpt",
"value": "Normal. The character's legs are twisted, hands are twisted, and face is distorted."
}
] |
seed42_141
|
videos/HRA_part0/141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 room filled with natural light, two young children sit cross-legged on a wooden floor, engrossed in crocheting a vibrant blanket. One child, wearing a yellow T-shirt and denim shorts, focuses intently on their work, their tongue slightly protruding in concentration. The other, dressed in a pink sweater and khaki pants, looks up momentarily, a smile playing on their lips, before returning to the colorful yarn in their hands. The atmosphere is warm and inviting, with the half-finished blanket spreading across their laps, a testament to their patience and creativity. Beside them, a basket of yarn in various shades adds a touch of whimsy to the scene, as the children continue to crochet, their movements steady and practiced.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2383
|
videos/HRA_part0/2383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful writer, clad in a brown jacket and blue jeans, traverses the sunlit chaparral landscape, his attire complemented by brown shoes and a backpack. He pauses to gaze into the distance, the vast expanse of shrubland stretching before him. Continuing his journey, he walks among the low-lying vegetation, the golden grasses swaying gently in the breeze. Occasionally, he stops to jot down notes, his focus intense, capturing the essence of his surroundings in his leather-bound journal. Throughout his walk, the chaparral scenery provides a serene backdrop, punctuated by the rustling of leaves and the distant call of birds.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2376
|
videos/HRA_part1/2376.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, vibrant green lizard with intricate patterns on its back traverses slowly across a dry, cracked earth surface, its movements deliberate and methodical. The terrain is peppered with small rocks and tufts of sparse vegetation, providing contrast against the lizard's vivid coloring. Sunlight filters down, casting dappled shadows and highlighting the texture of the lizard's skin as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1807
|
videos/HRA_part1/1807.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional-looking woman, dressed in a dark blazer, white blouse, and black trousers, sits at a cluttered desk in her office, surrounded by bookshelves filled with law books. Despite the serious environment, she is knitting a vibrant red scarf with a look of concentration on her face, her hands moving deftly as she works on her craft. The room is illuminated by a desk lamp, casting a warm glow over the scene, and a window can be seen behind her, offering a glimpse of a city skyline at twilight.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand is deformed, and the red yarn is moving on its own."
}
] |
seed44_2192
|
videos/HRA_part1/2192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray T-shirt, blue jeans, and brown shoes, organizes his garage with determination. He begins by sorting through boxes, revealing a cluttered space filled with various items, including bicycles, tools, and old books. As he works, he meticulously arranges the contents, creating order from chaos. The garage walls, adorned with shelves and pegboards, display an array of neatly organized objects, showcasing the writer's commitment to tidiness. Throughout the process, the natural light filtering through the garage windows highlights his efforts, emphasizing the transformation of the space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1210
|
videos/HRA_part2/1210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing a yellow rubber glove on their left hand and a look of determination, scrubs the white tiles of a bathroom shower stall with a green scrub brush. The bathroom has a modern design with stainless steel fixtures. The student, dressed in blue jeans, a gray t-shirt, and sneakers, leans into their task with focused energy. In another angle, the student continues scrubbing the tiles, now revealed to be in a dorm room bathroom, with a shower curtain featuring a geometric pattern in the background. The student's dedication to cleaning is evident in their posture and the intensity of their scrubbing motion.]"
},
{
"from": "gpt",
"value": "Bad. The arms of the college student in the video are deformed, and the face is not fully generated."
}
] |
seed42_1378
|
videos/HRA_part0/1378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with curly brown hair tied in a ponytail engages in gardening activities on a bright, sunny day. She wears a straw hat, a yellow sleeveless top, and green gardening gloves. Her face is turned towards the sun, revealing a joyful smile as she tends to the plants. The garden is lush and colorful, filled with various flowers and greenery. In one scene, she carefully waters the plants using a green watering can, her actions gentle and nurturing. Throughout the video, her expressions convey a sense of peace and satisfaction, encapsulating the therapeutic nature of gardening.]"
},
{
"from": "gpt",
"value": "Bad. No generation of women's faces with smiles."
}
] |
seed46_3040
|
videos/HRA_part2/3040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene set within the lush, sun-dappled understory of a subtropical dry forest, a small, agile ferret emerges from a dense thicket of ferns and moss-covered logs. Its sleek body, wrapped in rich, earthy tones, contrasts beautifully with the vibrant green foliage. The curious creature pauses, engaging in a comical self-cleaning ritual, using its paws to wipe its face and fur meticulously, revealing its playful nature amid the serene woodland setting. The ambient sounds of rustling leaves and distant bird calls add to the immersive atmosphere, capturing the essence of life in this unique ecosystem.]"
},
{
"from": "gpt",
"value": "Bad. The ferret's cleaning movements in the video are not smooth."
}
] |
seed44_1285
|
videos/HRA_part1/1285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imaginative scene, a group of koalas dressed in miniature black suits and top hats gather under a starlit sky, paying respects at a unique space-themed funeral. One koala, standing out from the crowd, begins to dance sorrowfully yet gracefully, its movements illuminated by the glow of distant galaxies and shimmering stars. As it twirls, a cosmic dust trail follows its path, symbolizing the connection between life, death, and the vastness of the universe, creating a surreal and poignant moment in the vast expanse of space.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed44_326
|
videos/HRA_part1/326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and black tactical gear, leaps over a row of lush green vineyards under a bright blue sky, suggesting an urgent pursuit. The officer, equipped with a utility belt and a radio, lands on the other side of the vines, continuing the chase with determination. The scene captures the contrast between the peaceful landscape of the vineyard and the high-stakes action of the law enforcement pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The officer's jumping action over the vineyard in the video is very unsmooth and uncoordinated."
}
] |
seed44_1378
|
videos/HRA_part1/1378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with curly brown hair tied in a ponytail engages in gardening activities on a bright, sunny day. She wears a straw hat, a yellow sleeveless top, and green gardening gloves. Her face is turned towards the sun, revealing a joyful smile as she tends to the plants. The garden is lush and colorful, filled with various flowers and greenery. In one scene, she carefully waters the plants using a green watering can, her actions gentle and nurturing. Throughout the video, her expressions convey a sense of peace and satisfaction, encapsulating the therapeutic nature of gardening.]"
},
{
"from": "gpt",
"value": "Bad. No ponytail or green watering can generated; no woman's face turned towards the sun."
}
] |
seed46_3057
|
videos/HRA_part2/3057.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling Matthew McConaughey, is seen polishing silverware in a well-lit room with high-end furniture. Dressed in a white button-down shirt, brown vest, and black pants, he focuses intently on his task. The room features a wooden table, chairs, and a bookshelf filled with books and knick-knacks. A chandelier hangs overhead, casting a warm glow on the scene. The actor's serious expression and the luxurious surroundings create an atmosphere of professionalism and attention to detail.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1215
|
videos/HRA_part2/1215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a stethoscope around her neck and a name badge on her scrubs, speaks earnestly with a concerned patient in a hospital room. The nurse, with her brown hair pulled back into a bun, leans forward attentively, making direct eye contact, while holding a clipboard with medical records. Moments later, she smiles warmly, offering reassurance and hope, as she continues the conversation. Throughout, the setting remains within the sterile, yet comforting environment of the hospital room, with machines beeping softly in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2247
|
videos/HRA_part0/2247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a janitor in a space museum is seen cleaning near a large, detailed model of the International Space Station, which is submerged in a serene indoor pool. Wearing a yellow vest, gray pants, and a white shirt, he carefully maneuvers around the underwater exhibit, highlighting his unique cleaning duties. The water around him is crystal clear, allowing viewers to appreciate the intricate details of the space station replica. As he works, the ambient lighting from above gently illuminates the water, creating a mesmerizing visual effect that blends the worlds of space exploration and aquatic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The character's head, arms, hands, and legs are distorted in the video."
}
] |
seed44_2779
|
videos/HRA_part1/2779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 seagull, standing solitary on a wooden pier post, looks out across the ocean with its yellow-rimmed eyes, reflecting determination and resilience. It wears a feathered coat of gray and white, with black wingtips, embodying the spirit of the seaside. Against a backdrop of a cloudy sky and the vast sea, it spreads its wings, preparing for flight, as the water gently laps against the pier. This iconic seashore bird, perched majestically, captures the essence of coastal life with its keen gaze and weathered feathers.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1141
|
videos/HRA_part2/1141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged teacher, wearing a blue shirt and khaki pants, stands in the center of a large, old theater, animatedly teaching a lesson about running. The stage is set with props from various plays, adding a touch of theatricality. Suddenly, a dingo, a wild dog native to Australia, runs onto the stage, interrupting the class. The teacher, unperturbed, incorporates the unexpected guest into the lesson, demonstrating running techniques while the dingo playfully bounds around, all under the grand chandelier of the theater.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2495
|
videos/HRA_part1/2495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear including a yellow reflective jacket, black pants, and boots, meticulously irons his uniform in a room with a white wall and a table covered with a white cloth. The room is sparsely decorated, featuring a calendar and a portrait on the wall. The firefighter, sporting a well-groomed beard and a focused expression, demonstrates his attention to detail by carefully smoothing out the wrinkles in his uniform. The camera captures the steam from the iron as it glides over the fabric, highlighting the contrast between the firefighter's rugged appearance and the domestic task at hand.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted in the video."
}
] |
seed42_1750
|
videos/HRA_part0/1750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, energetic ferret clad in a miniature red cape sprints across the frame, set against the backdrop of an otherworldly landscape featuring two active volcanoes, one spewing a spectacular eruption of lava and ash into the twilight sky. The ferret, displaying a sense of urgency and adventure, runs through this dramatic scene, its path illuminated by the orange glow from the volcanic activity, creating a surreal and captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2849
|
videos/HRA_part1/2849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant desert landscape under a warm, golden sun, two people clad in traditional white robes stand beside a camel, which is kneeling obligingly in the sand. Moments later, these individuals mount the camel, which rises to its feet, ready to embark on a journey. Subsequently, the camel starts moving, walking steadily across the sandy dunes with the riders holding on. Finally, gaining momentum, the camel begins to run, carrying the passengers across the undulating desert terrain at an exhilarating pace, their white garments billowing in the wind.]"
},
{
"from": "gpt",
"value": "Bad. The camel's walking movements in the video are uncoordinated."
}
] |
seed42_1327
|
videos/HRA_part0/1327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown gerbil with white patches stands on its hind legs, curiously observing a miniature robot astronaut figure. The robot, designed with intricate details including bolts and a clear helmet, takes a step forward on the wooden surface, seemingly on a mission. The gerbil, positioned next to a moss-covered stone, watches intently as the robot continues its journey across the textured table, creating an imaginative and whimsical scene.]"
},
{
"from": "gpt",
"value": "Normal. The hamster did not stand on its hind legs."
}
] |
seed42_1174
|
videos/HRA_part0/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Bad. The sweeping motion can be seen, but the movements are stiff and uncoordinated. "
}
] |
seed42_2310
|
videos/HRA_part0/2310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1545
|
videos/HRA_part1/1545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and khaki pants is seen in a whimsical scene, holding a small mouse on a wheel that matches the color of his shirt. The wheel rotates rapidly as the man watches, his gaze fixed on the active rodent. The scene is set against a plain, white backdrop, with the man's casual attire and focused expression contrasting with the unusual sight of the mouse energetically running on the miniature wheel.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2814
|
videos/HRA_part2/2814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a royal blue scrubs top and light blue pants, stands against a white wall with a large, welcoming smile. She waves energetically with her right hand, her dark brown hair styled in a bun. Behind her, a row of lockers can be seen, adding context to the hospital setting. Her left arm rests by her side, and she wears a silver watch on her wrist. The nurse's eyes are closed as she waves, conveying genuine warmth and friendliness to the viewer.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2803
|
videos/HRA_part2/2803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, walks alongside a capybara on a leash in a lush, green park. The doctor, sporting a neatly trimmed beard and a friendly smile, interacts with the large rodent, which is calmly trotting beside him on the grass. They pass by a wooden bench under the shade of leafy trees, creating a unique and peaceful scene in an urban oasis. The capybara, known for its docile nature, seems comfortable in the presence of the doctor, who gently guides it with the leash, both enjoying a leisurely stroll in the verdant surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The characters and capybara's walking movements in the video are slightly unsmooth."
}
] |
seed42_1947
|
videos/HRA_part0/1947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two graceful antelopes gently touch noses in a tender caress, surrounded by lush grasses and distant acacia silhouettes. The golden light bathes the scene, highlighting the intricate details of their fur, the tenderness in their eyes, and the delicate interaction, creating a moment of serene connection amid the wild beauty of their habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1798
|
videos/HRA_part0/1798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a green shirt and khaki shorts, tends to a lush garden filled with vibrant flowers and greenery. He strums his acoustic guitar, creating a melodic soundtrack for his gardening endeavors. The garden is brimming with life, featuring an array of colorful flowers such as daisies, roses, and tulips. The musician, wearing a wide-brimmed straw hat and sunglasses, works diligently, watering plants and trimming bushes. As he gardens, he occasionally pauses to play his guitar, seamlessly blending his passions for music and nature in a harmonious outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_1068
|
videos/HRA_part2/1068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut engineer, clad in a white spacesuit with a NASA logo, embarks on a critical space rescue mission, crawling through narrow, illuminated corridors inside a damaged spacecraft. The engineer's gloved hands and boots equipped with magnetic soles are prominent as they navigate the confined space. The scene is set against the backdrop of the Earth and stars, visible through a small porthole, emphasizing the perilous nature of the mission. Throughout, the engineer's determination and focus are evident as they work diligently to repair the vital systems of the stranded spaceship.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed44_2850
|
videos/HRA_part1/2850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate nurse, wearing a blue scrubs top and black pants, stands in a verdant garden filled with lush greenery and colorful flowers. She is engaged in digging a hole with a small spade, her face expressing determination and focus. The sunlight filters through the leaves above, casting dappled shadows on the rich soil beneath her feet. Despite her work, her demeanor conveys a sense of peace and purpose, as if tending to the earth is just another form of care she provides.]"
},
{
"from": "gpt",
"value": "Bad. The black pants mentioned in the caption were generated incorrectly in the video."
}
] |
seed44_1636
|
videos/HRA_part1/1636.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": "Normal. The character's movements are not smooth."
}
] |
seed46_2176
|
videos/HRA_part2/2176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating display, a slender cheetah with golden fur and black spots leaps into the air against a vivid, sunlit savanna landscape. Its body curves gracefully mid-leap, capturing the essence of its feline agility. The cheetah's intense, focused gaze is directed forward, suggesting a sense of purpose in its dance-like movements. Its tail extends elegantly, balancing its airborne form as it seemingly dances across the plains, embodying the spirit of the wild. The scene is framed by distant acacia silhouettes, enhancing the dramatic effect of the cheetah's dynamic leap.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's claws in the video were generated abnormally, with severe distortion and deformation in the middle frames."
}
] |
seed46_1270
|
videos/HRA_part2/1270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome firefighter, wearing a red and yellow vest, blue jeans, and brown shoes, gently caresses a curious gazelle on a vast, sandy beach. The gazelle, with its striking, wide eyes and alert posture, stands on the shore, the waves lapping at its feet. The scene shifts to show the firefighter's strong, comforting hands petting the animal's face, as they both stand against a backdrop of clear blue skies and the endless ocean horizon. The firefighter's caring demeanor and the gazelle's trusting stance on the picturesque beach create a poignant, contrasting image.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1877
|
videos/HRA_part0/1877.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 soft purple and blue lights, a woman with curly brown hair, styled in a bun, wears a silver sleeveless dress and silver earrings. She gently caresses a large, textured, abstract artwork, the colors of which resemble cosmic nebulas, while standing on a transparent floor that reveals city lights below. The walls are lined with similar cosmic-themed art pieces, creating an immersive environment. She leans toward the artwork, her expression showing deep appreciation, as she stands on the glowing, see-through floor, with the dazzling cityscape visible beneath her feet.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1285
|
videos/HRA_part2/1285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imaginative scene, a group of koalas dressed in miniature black suits and top hats gather under a starlit sky, paying respects at a unique space-themed funeral. One koala, standing out from the crowd, begins to dance sorrowfully yet gracefully, its movements illuminated by the glow of distant galaxies and shimmering stars. As it twirls, a cosmic dust trail follows its path, symbolizing the connection between life, death, and the vastness of the universe, creating a surreal and poignant moment in the vast expanse of space.]"
},
{
"from": "gpt",
"value": "Bad. The koala in the video has a twisted body, twisted arms, twisted paws, and a twisted face."
}
] |
seed44_3039
|
videos/HRA_part1/3039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful cashier, wearing a red apron over a casual outfit, is seen vacuuming a spotless living room with a modern upright vacuum cleaner, showcasing an unusual sight of a retail employee handling household chores. The room is impeccably clean, with hardwood floors and minimal furniture, highlighting the thorough cleaning process. The cashier, with her nametag visible, exhibits a sense of pride in her task, as if applying the same diligence to vacuuming as she would to serving customers. The contrast between her job as a cashier and the domestic activity adds a layer of humor and unexpectedness to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1130
|
videos/HRA_part0/1130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, wearing a gray suit and a white shirt, stands in a futuristic, high-tech room filled with screens displaying charts and graphs related to interplanetary trade routes. He gently caresses a large, interactive holographic map, which shows the intricate web of trade connections between various celestial bodies, highlighting the complex network of commerce spanning the solar system. The room is bathed in soft, ambient lighting, emphasizing the director's pensive and focused demeanor as he contemplates the vast opportunities and challenges presented by this expansive trade network.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1369
|
videos/HRA_part0/1369.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A great blue heron stands statuesque on a single leg, its piercing yellow eyes scanning the still waters of a pond fringed with lush green reeds and grasses, set against a serene blue sky. Moments later, it takes flight, wings outstretched against the clear blue sky, revealing their dark trailing edges. It then lands gracefully, standing tall on both legs, alert and watchful, its striking yellow eyes fixed ahead, the water calm and inviting. Lastly, it stretches its neck forward, beak pointed down, ready to strike, the serene surroundings of greenery and clear blue sky providing a tranquil backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_20
|
videos/HRA_part0/20.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1969
|
videos/HRA_part1/1969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow Labrador dog, wearing a red collar and tags, happily swims in a natural hot spring pool, surrounded by lush green vegetation and a wooden dock. The water, clear and inviting, gently laps at the dog's fur as it paddles with ease. The dog's joyful expression and the serene environment of the hot springs create a peaceful and picturesque scene, enhanced by the vibrant greenery and the warm, bubbling water.]"
},
{
"from": "gpt",
"value": "Normal. The dog's tongue is missing in the video, and the collar is not fully generated."
}
] |
seed42_2538
|
videos/HRA_part0/2538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, identifiable by his wedding ring, enjoys a leisurely hike in a rural mountainous area, wearing a white button-down shirt and khaki pants, a departure from his usual doctor's attire. He pauses to admire the stunning landscape, which includes lush greenery, rocky terrain, and distant mountain peaks, all under a clear blue sky. Carrying a walking stick and backpack, he navigates the rugged trail with ease, embodying the spirit of adventure and the great outdoors. As he continues his journey, he occasionally checks his phone, perhaps communicating with loved ones or colleagues from his medical profession.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3207
|
videos/HRA_part2/3207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mongoose, recognized by its sandy brown fur, black-tipped tail, and alert demeanor, runs swiftly across a dry, grassy terrain under a clear blue sky. It bounds gracefully over small tufts of grass, its body elongating and contracting with each leap, showcasing its agility and speed. Its eyes are focused ahead, ears perked, and nose twitching, indicating high alertness as it navigates the open space. The mongoose's movement is fluid and purposeful, its feet barely touching the ground as it darts forward, leaving a slight cloud of dust in its wake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1765
|
videos/HRA_part2/1765.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and sporting sunglasses, stands with his arms crossed, observing the scene at a busy dock. Suddenly, a majestic deer emerges from the background, filled with lush greenery, and leaps gracefully over a small obstacle, drawing the attention of the officer and dock workers alike. The officer watches intently as the deer bounds across the wooden planks, its movements fluid and effortless, before disappearing into the foliage beyond the docks. Throughout the scene, the officer remains poised and watchful, his presence a testament to the unexpected encounters that can occur even in the midst of urban landscapes.]"
},
{
"from": "gpt",
"value": "Normal. The deer's running motion in the video is not smooth and coordinated."
}
] |
seed46_2957
|
videos/HRA_part2/2957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small, energetic ferret, with a brown and white coat, swims through clear, bubbling water, showing its unique swimming style with its head held high and nose just above the waterline. It uses its webbed feet to propel itself forward, highlighting its natural aquatic abilities. The water droplets glisten around it, and its determined face conveys a sense of joy and playfulness in its unusual swimming endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's body and limbs show deformities."
}
] |
seed44_1485
|
videos/HRA_part1/1485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguishable by his classic black vest and white button-down shirt, is shown shoveling snow with determination. His attire is uniquely juxtaposed with the wintry task at hand, as he clears a path in front of a charming, snow-covered cottage. Snowflakes gently fall from a cloudy sky, accumulating on the roof and surrounding trees, while the waiter, wearing black gloves and sensible shoes for traction, focuses on his unexpected duty. Despite the cold, he works diligently, the snow creating a picturesque setting that contrasts with his formal waiter's uniform.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video clears snow very unsmoothly, with uncoordinated movements."
}
] |
seed42_2324
|
videos/HRA_part0/2324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, embodying the essence of carefree summer days, walks along a pristine beach with white sand, wearing a vibrant floral shirt, khaki shorts, and brown leather sandals. He gently caresses the smooth, sun-warmed surface of a driftwood log, as the crystal-clear turquoise waters of the sea softly lap at the shore behind him. The serene beach landscape, with lush greenery and palm trees framing the horizon, complements the peaceful atmosphere. The man's relaxed posture and the idyllic beach setting evoke a sense of tranquility and connection with nature.]"
},
{
"from": "gpt",
"value": "Bad. The man's walking movements in the video are not continuous and smooth, showing disharmony."
}
] |
seed42_2485
|
videos/HRA_part0/2485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a black cap and a blue flannel shirt, is seen painting an antelope on a large canvas set against a background of lush greenery. The canvas is placed on an easel, and the artist, with a concentrated look, applies vibrant orange paint to depict the animal. The antelope, depicted as running with its head turned back, is captured mid-stride, its movement and grace highlighted by the artist's brushstrokes. The setting sun casts a warm glow over the scene, illuminating the artist's silhouette and the vivid depiction of the antelope in motion.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_111
|
videos/HRA_part1/111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with gold accents and a peaked cap, runs purposefully across a grand hall within a futuristic space station. The hall is lined with flags from various nations and interspersed with abstract art pieces, all illuminated by the soft glow of recessed lighting. In the distance, a large, circular window reveals the vastness of space and the distant twinkle of stars. The officer's run suggests urgency, possibly related to security matters at the ongoing political summit, where delegates from Earth and various space colonies gather to discuss interstellar policy. The polished floor reflects the officer's movement, emphasizing the gravity of the situation in this otherwise serene and majestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1272
|
videos/HRA_part2/1272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush subtropical wet forest, a striking red fox curiously approaches a musician seated on a moss-covered log. The artist, dressed in a green shirt and brown vest, gently wipes away sweat from their brow, momentarily pausing their harmonious tune played on a wooden flute. Sunbeams filter through the dense foliage overhead, casting a warm glow on the scene, as ferns and tall trees surround them, creating a serene and enchanting atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2905
|
videos/HRA_part1/2905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, recognizable by its black ears and eye patches, crawls on all fours across a lush, green forest floor, its fur a striking contrast against the vibrant vegetation. It moves slowly, carefully placing each paw, showcasing its strength and agility. The panda's attention is drawn to something in the distance, its ears perked, adding a layer of curiosity to its demeanor. Surrounded by bamboo plants, a staple in its diet, the panda continues its crawl, encapsulating the essence of its natural habitat in every deliberate motion.]"
},
{
"from": "gpt",
"value": "Normal. The panda's legs show deformities."
}
] |
seed46_130
|
videos/HRA_part2/130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a blue plaid shirt, khaki pants, and glasses, sits in a wooden chair in a cozy living room filled with natural light. They hold a crochet hook and yarn, working on a colorful blanket with a complex geometric pattern. The space around them is cluttered with engineering books, blueprints, and tools, blending the worlds of precision and creativity. The camera captures the intricate process, focusing on their hands as they expertly loop the yarn, creating a vivid contrast between the technical skills of engineering and the artistic craft of crocheting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and there is a sudden change."
}
] |
seed42_2712
|
videos/HRA_part0/2712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo, under the neon lights that bathe the bustling streets, a lone coyote wanders. Its golden eyes reflect the urban glow as it moves through the crowded alleyways. It pauses, the camera capturing a close-up of its face, showing the wild creature in an unexpected environment. The coyote then proceeds to wipe its face with a paw, a moment of natural behavior in stark contrast to the man-made surroundings. Behind it, the signs in Japanese and English, the busy storefronts, and the occasional passerby underscore the unlikely scene of a wild animal navigating the concrete jungle.]"
},
{
"from": "gpt",
"value": "Bad. The color of the coyote's eyes in the video does not match the text description, and the action of the coyote wiping its face with its paw was not generated."
}
] |
seed42_1964
|
videos/HRA_part0/1964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers is perched on a branch, set against a blurred background of lush vegetation. The parrot, with its bright plumage and attentive expression, looks directly at the camera. It then opens its beak slightly, as if about to call out, showcasing its sharp, curved beak. The bird's stance on the branch, combined with its detailed feathering and colorful features, creates a captivating scene in the midst of a dense, verdant forest.]"
},
{
"from": "gpt",
"value": "Normal. The bird in the video is basically normal, with slight disharmony."
}
] |
seed46_1266
|
videos/HRA_part2/1266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, donning a gray beanie, black jacket, and blue jeans, stands on the weathered wooden planks of a dock by the water's edge, with a vibrant cityscape visible across the bay. The artist leaps into the air, capturing the essence of freedom, while holding a sketchbook, which hints at their creative pursuits. The scene is bathed in golden hour sunlight, casting a warm glow over the figure and the urban landscape, creating a sense of serenity and inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, and the legs are severely deformed."
}
] |
seed42_2490
|
videos/HRA_part0/2490.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 chimpanzee, covered in dark fur with lighter features around its eyes and mouth, runs across a grassy terrain under a vibrant blue sky. The chimp's movement is powerful and agile, with a hunched posture typical of its species. Its face, marked with distinctive wrinkles and a noseless structure, conveys intense focus as it sprints. In another moment, the chimpanzee is shown from a side view, highlighting its muscular build and the gracefulness of its stride, set against the backdrop of a lush, green environment.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the black gorilla in the video are missing, the face is slightly blurry, the fingers are missing, and the body proportions are unreasonable."
}
] |
seed42_1786
|
videos/HRA_part0/1786.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small, vibrant green lizard, adorned with intricate patterns, traverses slowly across a weathered stone surface, basking in the warm sunlight that highlights its textured skin. Its movements are deliberate and methodical, showcasing the strength in its tiny limbs as it explores its ancient, sun-soaked environment. With each step, the lizard reveals the resilience and adaptability of nature, set against a backdrop of natural elements, including stones and plants, that have been shaped by time and the elements.]"
},
{
"from": "gpt",
"value": "Normal. The lizard's legs in the video are incomplete, and the claws are not generated."
}
] |
seed44_1726
|
videos/HRA_part1/1726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, clad in a gray suit, white shirt, and patterned tie, rearranges furniture in an office setting. He lifts a wooden chair with leather seating, moving it across the room with ease. The scene is set in a corner office, featuring a large window with a cityscape view, a desk adorned with legal documents, and a bookshelf filled with law books. The lawyer's actions are deliberate, indicating a need for change or reorganization in his workspace. Despite the professional environment, the act of rearranging furniture adds a personal touch to the narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_3123
|
videos/HRA_part2/3123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dimly lit warehouse complex, a renowned film director, wearing a black leather jacket, gray shirt, and jeans, kneels among stacks of wooden crates. With a handheld camera, he captures footage of a giant panda cub crawling across the dusty floor, its fluffy black and white fur contrasting with the industrial setting. The panda moves slowly, exploring its surroundings with curiosity, while the director films intently, capturing every detail of this unusual encounter in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The panda's legs show deformities."
}
] |
seed44_1025
|
videos/HRA_part1/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1156
|
videos/HRA_part1/1156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, wearing a yellow swim cap and goggles, swims in an infinity pool that mirrors the celestial aesthetics of Jupiter's Great Red Spot. The pool's water color shifts between red and orange hues, mimicking the storm's appearance. Surrounded by lush greenery and under a clear blue sky, the swimmer effortlessly glides through the water, embodying the harmony between human endeavor and cosmic inspiration. The artist's swimming movements contrast beautifully with the serene environment, creating a captivating visual metaphor for exploring the universe's mysteries within the confines of our earthly existence.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2951
|
videos/HRA_part0/2951.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, donning a wide-brimmed hat and a brown leather vest, finds himself amidst a cosmic dust storm, its ethereal particles swirling around him like a celestial sandstorm under the night sky. Suddenly, the scene transforms to reveal the farmer diving into a tranquil oasis, the water shimmering with stardust from the storm, as he swims gracefully beneath the sparkling surface, encapsulating a surreal blend of earthy resilience and otherworldly enchantment.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's face is distorted in the video."
}
] |
seed44_1382
|
videos/HRA_part1/1382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical space-themed casino, a large brown bear, standing on two feet, walks with a casual gait, wearing a red shirt, blue jeans, and a gold watch. The bear is surrounded by various elements of the space casino, including a bar with neon lights, slot machines, and a large window displaying a view of the galaxy. As it strides through the casino, the bear passes by a table where alien creatures play cards, their eyes following the unexpected visitor. The atmosphere is filled with a sense of wonder and fun, as the bear continues its stroll, blending seamlessly into the otherworldly environment.]"
},
{
"from": "gpt",
"value": "Normal. No golden watch was generated."
}
] |
seed46_2017
|
videos/HRA_part2/2017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-drenched savanna, two graceful antelopes engage in a tender moment of affection, their brown coats glistening under the golden light. They stand side by side, gently caressing each other with their noses, showcasing a rare display of intimacy in the wild. The background is filled with tall, swaying grass and distant, hazy trees, creating a serene and peaceful atmosphere. Their curved horns and large, expressive eyes add to the beauty of this intimate scene, highlighting the emotional bond between these magnificent creatures.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2363
|
videos/HRA_part2/2363.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy desert landscape under a bright, cloudless sky, two children, a boy and a girl, both wearing vibrant, culturally-inspired clothing, approach a calm camel. The camel, with two humps and a red and white cloth draped over it, stands patiently in the middle of the sandy dunes. The boy, dressed in a blue outfit, reaches out gently to caress the camel's nose, showing trust and connection. The girl, wearing a pink dress, watches with a smile, her hands on her hips, displaying comfort and familiarity with the animal, emphasizing a tender moment of human-animal interaction in a stunning natural setting.]"
},
{
"from": "gpt",
"value": "Bad. A boy and a girl child appeared, but at the end, the little girl suddenly turned into a boy, which does not match the text description."
}
] |
seed44_1822
|
videos/HRA_part1/1822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, complete with a stethoscope around his neck and wearing a white lab coat over a blue button-down shirt and khaki pants, sits by a serene lake, holding a fishing rod. The peaceful scene is set against a backdrop of lush greenery and a clear blue sky, with the doctor's attire and occupation contrasting with the tranquil activity of fishing. As he casts his line into the water, the camera captures the reflective surface of the lake and the doctor's focused yet relaxed demeanor, highlighting the juxtaposition between his professional life and his leisurely pursuit.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1705
|
videos/HRA_part0/1705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casino, a distinguished chef, donning a traditional white chef's uniform with black stripes and a black necktie, walks with purpose. He carries a large, covered silver platter, its lid adorned with a golden handle. Behind him, a bustling kitchen reveals chefs in action, preparing exquisite dishes. The casino's opulent decor is visible through a glass partition, featuring patrons enjoying themselves at various gaming tables. The chef's confident stride and the casino's lively atmosphere create a captivating contrast between culinary expertise and the thrill of gambling in outer space.]"
},
{
"from": "gpt",
"value": "Normal. The chef is missing a silver tray."
}
] |
seed42_2952
|
videos/HRA_part0/2952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown leather jacket and dark pants, kneels on a wooden floor, engaged in a crawling motion, as he observes a live hare sitting on a white table nearby. The scene is set indoors, with a large window in the background, allowing natural light to illuminate the room. The director's intent gaze and careful movement convey a sense of focus and determination as he studies the animal, which remains calm and still, seemingly unfazed by the presence of the human.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements in the video are not smooth."
}
] |
seed42_2288
|
videos/HRA_part0/2288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a black jacket and khaki pants, is seen in a close-up shot, wiping his brow with a white handkerchief. Behind him, a herd of antelopes can be observed grazing in a vast, grassy savanna, creating a juxtaposition between the director's world and the natural habitat of the antelopes. The director's weathered face and focused gaze suggest a moment of intense concentration during a film shoot, while the antelopes continue their serene existence in the background, unaware of the human drama unfolding nearby.]"
},
{
"from": "gpt",
"value": "Bad. The director's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_3031
|
videos/HRA_part0/3031.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a full beard, dressed in a green shirt and brown pants, is kneeling in a forest clearing. He gently wipes a small, injured porcupine with a white cloth, his face expressing deep concern and care. The porcupine, quills visible, lies quietly on a bed of moss and leaves, seemingly aware of the man's protective presence. The forest surroundings, with tall trees and dappled sunlight, provide a natural and peaceful setting for this tender interaction between man and wildlife.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 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 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. No yellow swim cap was generated."
}
] |
seed46_1396
|
videos/HRA_part2/1396.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a red tracksuit, emulates a monkey with playful antics, running energetically across a vibrant green field under a clear blue sky. The student's facial expression, complete with wide eyes and an open mouth, mirrors the monkey's characteristic features, enhancing the mimicry. Accompanied by a group of friends, who cheer and laugh in the background, the scene captures a moment of carefree fun and youthful exuberance. The student's attire, which includes a red jacket and matching pants, stands out against the lush greenery, while the clear blue sky provides a perfect backdrop for the lively scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2686
|
videos/HRA_part1/2686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female teacher, wearing a dark blue blazer over a white blouse and carrying a black handbag, walks purposefully down a wide hallway with high ceilings, resembling the interior of a university building. The walls are adorned with educational posters, and the floors are covered with brown carpeting. As she strides forward, the scene subtly transitions to reveal a large window behind her, displaying a breathtaking view of Neptune's turbulent atmosphere, filled with vivid blue and green clouds swirling majestically. This unique setting, combining the familiar environment of a school with the awe-inspiring backdrop of a distant planet, creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1156
|
videos/HRA_part2/1156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic individual, wearing a yellow swim cap and goggles, swims in an infinity pool that mirrors the celestial aesthetics of Jupiter's Great Red Spot. The pool's water color shifts between red and orange hues, mimicking the storm's appearance. Surrounded by lush greenery and under a clear blue sky, the swimmer effortlessly glides through the water, embodying the harmony between human endeavor and cosmic inspiration. The artist's swimming movements contrast beautifully with the serene environment, creating a captivating visual metaphor for exploring the universe's mysteries within the confines of our earthly existence.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1674
|
videos/HRA_part1/1674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, typically found in woodland streams, curiously explores a sandy beach near a vibrant beach resort, walking along the shoreline with its distinctive flat tail and brown fur. It passes by colorful umbrellas and sun loungers, a unique sight among the usual beachgoers enjoying the sunny weather. The beaver's presence adds an element of surprise and charm to the bustling beach scene, as it navigates the sandy terrain with its natural grace and agility.]"
},
{
"from": "gpt",
"value": "Normal. The beaver in the video has a twisted body, a contorted face, and twisted legs."
}
] |
seed42_1135
|
videos/HRA_part0/1135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a utility belt, leaps into the air against a backdrop of cosmic dust swirling in the night sky, creating a surreal and dramatic scene. The officer's silhouette is highlighted by the celestial phenomenon, with the dust storm's ethereal glow illuminating the surroundings. The jump, captured mid-air, adds a dynamic element to the composition, juxtaposing the grounded authority figure with the otherworldly cosmic event.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2820
|
videos/HRA_part1/2820.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a white collared shirt, points with her right hand to something outside the frame, her left hand resting on the counter. Behind her, a row of colorful candy bars lines the shelf, while above her head, a sign displays various services offered, such as check cashing and lottery tickets. The scene takes place inside a busy convenience store, with customers visible in the background, creating a snapshot of daily life in a bustling urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2987
|
videos/HRA_part0/2987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant floral-print dress over her swimsuit, stands before a majestic waterfall cascading into a serene pool. She joyfully leaps into the water, her dress fluttering in the breeze, revealing her red swimwear beneath. Emerging from the pool, she playfully splashes water, her laughter echoing through the lush, green surroundings. As she exits the frame, a panoramic view of the waterfall and its misty spray enveloping the tranquil pool takes center stage, offering a peaceful contrast to the nurse's lively energy.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's body is twisted, head is twisted, feet are twisted, legs are twisted, arms are twisted, and hands are twisted."
}
] |
seed44_2726
|
videos/HRA_part1/2726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whole, fresh cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the cod's mouth in the video has issues."
}
] |
seed44_2524
|
videos/HRA_part1/2524.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a young, cheerful cashier, wearing a green apron over a striped shirt, is seen enjoying a swim in a clear, tranquil body of water surrounded by scrublands. The cashier, with short, wavy hair and a nose ring, alternates between swimming and floating on the water's surface, showcasing a sense of freedom and relaxation. The scrublands, with their sparse vegetation and sandy soil, provide a stark contrast to the refreshing water, creating a unique and captivating scene. Throughout, the cashier's attire remains consistent, featuring the green apron and striped shirt, as they immerse themselves in the peaceful environment.]"
},
{
"from": "gpt",
"value": "Normal. No nose ring was generated."
}
] |
seed46_2676
|
videos/HRA_part2/2676.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dapper musician, clad in a black suit and red tie, strolls down a gravel path in the midst of a lush forest, accompanied by a friendly moose. The pair walk side by side, the musician holding his violin case, while the moose ambles along, its large antlers brushing against the tree branches. Sunlight filters through the dense canopy overhead, casting dappled shadows on the path as the duo continues their peaceful journey together.]"
},
{
"from": "gpt",
"value": "Bad. The person's face is distorted, hands are twisted, the moose's head is distorted, and the legs are twisted."
}
] |
seed46_2879
|
videos/HRA_part2/2879.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 antlers and hooves of the deer in the video were generated abnormally, there were issues with the head generation, and the tail was not generated."
}
] |
seed44_2605
|
videos/HRA_part1/2605.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara runs energetically across a grassy plain, its wet nose and alert eyes highlighting its distinctive features. It bounds forward with determination, showcasing its muscular legs and agile movements. Moments later, the capybara leaps gracefully over an obstacle, demonstrating its impressive jumping ability. Then, it sprints with focused intensity, ears perked, and nostrils flared, against a backdrop of lush vegetation and distant hills. Finally, the capybara continues its swift run, its body language conveying strength and vitality as it navigates the open landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1495
|
videos/HRA_part1/1495.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 powerful buffalo, its body robust and muscular, leaps gracefully over a wooden fence in the midst of a lush, green prairie. The fence, made of weathered logs, stretches across the frame, adding texture and depth to the scene. The buffalo, its large horns curving outward, is captured mid-jump, showcasing its agility and strength. The background is filled with the vibrant hues of nature, from the deep greens of the grass to the soft blues of the sky, creating a stunning contrast against the dark brown of the buffalo. This majestic creature, defying expectations with its leap, embodies the spirit of the wild, free and untamed.]"
},
{
"from": "gpt",
"value": "Bad. The water buffalo's movements in the video are uncoordinated."
}
] |
seed46_1390
|
videos/HRA_part2/1390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 cormorant, sleek and black, emerges from the water, its dripping feathers glistening in the sunlight. Perched on a low branch near the water's edge, it spreads its broad wings to dry, revealing a flash of orange throat beneath its hooked beak. The bird's intense eyes, set in a striking face, lock onto the camera, displaying its natural curiosity. Against a backdrop of rippling water and lush green foliage, the cormorant stands tall, a testament to its aquatic lifestyle, before diving back into the depths with a powerful flap of its wings.]"
},
{
"from": "gpt",
"value": "Normal. The flapping motion of the wings appears to have a sudden change."
}
] |
seed42_2171
|
videos/HRA_part0/2171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, sunlit African savanna, a herd of majestic Cape buffaloes gathers near a watering hole. The scene opens with a panoramic view of the landscape, emphasizing the natural habitat. A buffalo, its body glistening with water droplets, emerges from the watering hole and begins to rub against a tree, its large horns and muscular frame highlighted. Another buffalo, also wet, vigorously shakes its head, spraying water around. The herd grazes peacefully nearby, showcasing their daily routine in the wild, with the watering hole as a central point, surrounded by tall grasses and scattered acacia trees.]"
},
{
"from": "gpt",
"value": "Normal. The walking action of the water buffalo in the video is basically normal, but there is some lack of coordination."
}
] |
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 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 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 jumping action of the character in the video is not very smooth, and there are sudden changes in the limbs."
}
] |
seed46_1545
|
videos/HRA_part2/1545.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a gray shirt and khaki pants is seen in a whimsical scene, holding a small mouse on a wheel that matches the color of his shirt. The wheel rotates rapidly as the man watches, his gaze fixed on the active rodent. The scene is set against a plain, white backdrop, with the man's casual attire and focused expression contrasting with the unusual sight of the mouse energetically running on the miniature wheel.]"
},
{
"from": "gpt",
"value": "Bad. The mouse's running in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_1248
|
videos/HRA_part2/1248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, young female barista with brown hair pulled into a bun and wearing a gray shirt smiles warmly as she expertly crafts a coffee beverage. Behind her, a vibrant cafe atmosphere is visible, complete with patrons seated at tables and a counter displaying delectable pastries. The barista's hands are busy pouring steaming milk from a silver frothing pitcher into a cup filled with rich, dark coffee, creating a perfect latte. Her name tag identifies her as 'Sara', and she works at a bustling coffee shop where she deftly prepares a frothy cappuccino, her practiced movements and bright smile enhancing the welcoming vibe of the place.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted in the video."
}
] |
seed44_3112
|
videos/HRA_part1/3112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrious engineer, clad in a blue button-down shirt and khaki pants, kneels beside an indoor track designed for mice. The track, illuminated by overhead lights, features a small mouse energetically running within its confines. The engineer observes intently, notebook in hand, ready to record data from the experiment. Behind him, a lab coat hangs on a hook, and a shelf displays various scientific instruments and books, alluding to the academic setting. Throughout the scene, the mouse continues its steady pace on the track, under the watchful eye of the dedicated engineer.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2885
|
videos/HRA_part1/2885.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged lawyer, dressed in a gray suit, white shirt, and blue tie, walks purposefully across a futuristic asteroid mining facility. The setting is a large, circular room with a high ceiling and industrial equipment, bathed in a warm orange glow. He carries a brown leather briefcase in his right hand, displaying a confident and focused demeanor. Behind him, the dimly lit interior of the asteroid can be seen, with mining machinery and workers in protective gear visible in the distance. The lawyer's strides are firm and decisive, highlighting his determination and professionalism in this unique and challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1289
|
videos/HRA_part2/1289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine, high-quality close-up of a fresh cod fillet takes center stage, its surface glistening under bright lights. The fish boasts a clean, white flesh with a hint of natural oils visible, presenting a perfect texture for culinary delights. Set against a simple, dark background, the cod fillet's purity and freshness are accentuated, making it visually appealing for seafood connoisseurs and chefs alike.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1862
|
videos/HRA_part1/1862.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European brown hare sits upright on a grassy meadow under an overcast sky, performing a grooming behavior. It wipes its face with a paw, showcasing the natural habit of self-cleaning. The hare, with its distinctive long ears and brown fur, is shown in a close-up shot, emphasizing the details of its facial features and the texture of its fur. The background is blurred, focusing attention solely on the hare's grooming actions in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1208
|
videos/HRA_part1/1208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meticulously crafted aquarium filled with vibrant green aquatic plants, a ghost shrimp, nearly transparent with faint blue-gray veins, clings to a piece of driftwood. Its delicate antennae wave gently in the water current, and its legs grip the wood securely. Nearby, a stone arch adds to the scenery, while the shrimp's see-through body allows a glimpse of its internal organs. The shrimp's translucent exoskeleton and the lush underwater environment create a captivating scene, enhanced by the play of light and shadow in the tank.]"
},
{
"from": "gpt",
"value": "Bad. The ghost shrimp's body is twisted."
}
] |
seed42_1410
|
videos/HRA_part0/1410.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student wearing a green jacket and khaki pants explores a lush rainforest, observing a koala as it clings to a eucalyptus branch. Moments later, the student leaps over a small stream, demonstrating agility and enthusiasm for nature. Then, the koala is seen jumping from branch to branch, its plush fur glistening with dew, highlighting the playful nature of these marsupials in their natural habitat. Finally, the student sits on a mossy log, watching the koala munch on eucalyptus leaves, capturing the serene beauty of the rainforest and the peaceful coexistence between humans and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the koala's movements are not smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.