video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1381
|
videos/HRA_part2/1381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with short brown hair, styled in a pixie cut, sits serenely on a yoga mat placed atop a wooden floor, set within a minimalistic room illuminated by soft, natural light. She wears a black tank top and gray yoga pants, her eyes gently closed as she focuses on her breathing. Her hands rest gracefully on her knees, adorned with a silver ring and bracelet, while a single earring dangles from her left ear. The atmosphere is calm and peaceful, with a potted plant and a water bottle visible in the background, hinting at her wellness routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2217
|
videos/HRA_part2/2217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed writer, wearing a gray t-shirt, sits at a desk in a modern, minimally decorated room with large windows and a wooden floor, yawning widely as he leans back in his chair. The room is sparsely furnished, featuring a desk lamp and a painting on the wall. As the scene progresses, the yawning writer, now seen from the side, wears a black cap and glasses, revealing more of his appearance. He continues to yawn, appearing tired yet relaxed, as he rests his head on his hand, gazing out the window. Throughout, the setting remains a contemporary space with ample natural light and simple decor.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2812
|
videos/HRA_part0/2812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green prehistoric landscape under a soft, cloudy sky, a large woolly mammoth tenderly caresses a smaller mammoth with its trunk. The smaller mammoth, likely a calf, stands close by, its body gently leaning into the larger mammoth, both enveloped in a moment of affection. The setting, with its rich vegetation and distant hills, provides a vivid backdrop for this intimate scene between two members of this ancient species.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1937
|
videos/HRA_part0/1937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, known for his role in a space-themed reality TV series, gently caresses the smooth, metallic surface of a spacecraft console, his face illuminated by the soft glow of the control panel lights. Dressed in a futuristic silver jumpsuit with black accents, he leans over the controls, his eyes locked onto a screen displaying complex data, conveying a sense of focused intimacy with the technology. The scene is set inside a sleek, modern spaceship cabin, with large windows showing the vastness of space beyond, stars twinkling against the dark cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1547
|
videos/HRA_part0/1547.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 Asian nurse wearing a white uniform and a name tag takes a break from her hospital duties to clean the large, rectangular window in the patient's room. Holding a squeegee in her right hand and a spray bottle in her left, she sprays the glass with a cleaning solution, creating a fine mist. She then wipes it down with the squeegee, leaving a clear, streak-free surface. The natural light from outside illuminates the room, casting a warm glow on the nurse as she works diligently, ensuring the window is spotless.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's body is not generated in the video, there is a missing finger, and the tool in her hand is deformed."
}
] |
seed42_1953
|
videos/HRA_part0/1953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2496
|
videos/HRA_part2/2496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, green-brown jungle cobra crawls across a lush, moss-covered log in the dense rainforest undergrowth. The snake's hood is slightly raised, revealing its distinctive markings as it navigates the textured surface. Sunlight filters through the canopy, casting dappled light on the cobra, emphasizing its muscular body and smooth scales as it moves with purpose and grace in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2165
|
videos/HRA_part0/2165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, ancient-looking turtle with a mossy, textured shell slowly moves across a lush, green forest floor, surrounded by vibrant ferns and fallen leaves. Its wise, gentle eyes and wrinkled skin reflect its age and resilience. Nearby, a small stream glistens in the dappled sunlight, while tall trees tower overhead, creating a serene, natural habitat for this majestic creature. The turtle continues its unhurried journey, embodying the peaceful, enduring spirit of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space 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": "Normal. The person's fingers appear deformed."
}
] |
seed44_1110
|
videos/HRA_part1/1110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black vest, sprints across a vast, barren lunar landscape, the iconic first steps of Neil Armstrong visible in the distance. Dust from the moon's surface billows behind him as he races, his movements fluid and effortless in the low gravity environment. A lunar module sits in the background, a stark contrast to the elegant attire of the sprinting waiter, who carries a silver serving tray in one hand, merging the worlds of fine dining and space exploration in a surreal scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2856
|
videos/HRA_part1/2856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a yellow blouse and khaki pants, is seen joyfully dancing in a classroom decorated with educational posters. On a nearby desk sits a small, curious gerbil, nibbling on a piece of wood inside its cage. The teacher's energetic movements and warm smile create a vibrant atmosphere, while the gerbil's playful antics add a touch of whimsy to the scene. The camera captures the dynamic interaction between the dancing teacher and the fascinated gerbil, highlighting the unique bond they share within the educational environment.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's movements in the video are not smooth."
}
] |
seed42_1341
|
videos/HRA_part0/1341.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, exhibiting a powerful build with thick, dark fur and a muscular physique, runs across a lush, green savanna landscape under a bright, sunlit sky. The chimp's expressive face, featuring a wide mouth and intense eyes, conveys determination as it moves with agility and strength. Running in a hunched posture typical of its species, the chimpanzee demonstrates its natural locomotion, bounding over the terrain with a sense of purpose. The scene captures the essence of wild chimpanzees in motion, highlighting their dynamic physicality and the vibrant environment they inhabit.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2542
|
videos/HRA_part0/2542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sprawling landfill under a hazy sky, three children, two boys and a girl, wearing ragged clothes and protective masks, stand together. One boy, in a red shirt, holds a large rag and wipes the grimy face of another boy, who wears a yellow shirt, while the girl, in a blue dress, watches intently. The action conveys a sense of care and support among the children in this challenging environment. Nearby, piles of discarded electronics, tires, and debris form a bleak landscape, contrasting with the children's resilience and connection.]"
},
{
"from": "gpt",
"value": "Bad. The girl's hand and the red-shirted boy's hand, as well as the cloth, have generation issues in the video."
}
] |
seed44_1915
|
videos/HRA_part1/1915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space-suited worker, complete with helmet and backpack, sits inside a lunar buggy, which is a small rover designed for moon exploration. The vehicle is adorned with various equipment and tools necessary for extraterrestrial missions. The worker is engaged in wiping down the interior surfaces of the buggy, ensuring cleanliness in the zero-gravity environment. The action takes place against the stark, desolate backdrop of the lunar landscape, with the Earth visible as a brilliant blue orb in the distance, providing a dramatic contrast to the monochrome moon surface.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, and the sudden changes make it hard to see the wiping motion."
}
] |
seed46_1822
|
videos/HRA_part2/1822.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": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_3213
|
videos/HRA_part1/3213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet captivating scene, a suave waiter, dressed in a crisp white shirt and black pants, serves refreshments poolside in the middle of a vast temperate shrubland. The swimming pool, an oasis of crystal-clear water, contrasts beautifully with the surrounding landscape of lush green shrubs and scattered trees. The waiter, with a tray balanced expertly in one hand, leans over to offer a glass to a guest, who is seated on a comfortable lounge chair, basking in the warm sunlight filtering through the leaves above. The serene atmosphere is enhanced by the gentle sounds of nature and the occasional splash from the pool, creating a perfect blend of luxury and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The guest's hands and face are distorted in the video."
}
] |
seed42_1331
|
videos/HRA_part0/1331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 writer, wearing a black jacket, leans forward in his chair to gently caress a hyena lying at his feet, the animal seemingly at ease in his presence. The scene takes place in a well-lit room, with a bookshelf filled with various books visible in the background, hinting at the writer's profession. The hyena, displaying a level of comfort unusual for its species, looks up at the writer with a calm demeanor, creating an unexpected yet captivating connection between the two.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_3150
|
videos/HRA_part0/3150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, possibly his cub, against the backdrop of a lush, green savanna during golden hour. The adult lion, with its voluminous tawny mane, displays affection, while the cub, sporting a lighter coat and smaller stature, responds with innocent playfulness. The heartwarming interaction unfolds under a vast, cloud-dappled sky, with scattered acacia trees and distant mountains completing the serene African landscape. This intimate moment captures the rare display of tenderness and bonding within the lion family, far from the typical fierce and powerful image associated with these animals.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1954
|
videos/HRA_part1/1954.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lifelike jaguar mascot, wearing a brown uniform and a name tag, leaps over a green cash register in slow motion, set against a vibrant yellow backdrop. The mascot, with its mouth playfully open, is captured mid-air, just above the register, which is adorned with colorful bills and coins. The cash register itself is old-fashioned, with a large price display and mechanical keys, adding a nostalgic touch to the dynamic scene.]"
},
{
"from": "gpt",
"value": "Normal. The movements are unsmooth."
}
] |
seed44_2466
|
videos/HRA_part1/2466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with badges and a walkie-talkie attached to his belt, points assertively with his right hand while looking intently at something off-screen. He stands in a busy urban street scene, with pedestrians and vehicles in the background, conveying a sense of duty and command. His left hand rests on his hip, near his service weapon, and his authoritative stance is emphasized by the presence of a large, bustling city behind him, complete with tall buildings, traffic lights, and street signs.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_2
|
videos/HRA_part2/2.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic shop filled with natural light, a cheerful cashier, wearing a red apron over a cream sweater and dark jeans, sits behind a wooden counter adorned with a vintage cash register and various knitting supplies. She expertly knits a vibrant, multi-colored scarf, her hands moving swiftly as she focuses intently on her craft. The atmosphere is warm and inviting, with the soft clacking of knitting needles adding a soothing soundtrack to the scene. Shelves stocked with yarn in various textures and hues line the walls, creating a backdrop that complements the cashier's skillful knitting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the item in hand is distorted."
}
] |
seed44_1438
|
videos/HRA_part1/1438.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man, donning a gray beanie, a dark jacket, and a checkered apron, stands against a vibrant blue wall, holding a large ladle as he stirs a bubbling pot. Moments later, he is seen attentively pouring oil into a pan, demonstrating culinary expertise. Then, he skillfully flips a food item in the pan, showcasing his cooking prowess, all while the blue wall and his attire remain consistent. Lastly, he is shown carefully seasoning the dish, his focus unwavering, against the same backdrop of the vivid blue wall and clad in the same attire, exemplifying his dedication to culinary artistry.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1902
|
videos/HRA_part1/1902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic child, donning a vibrant yellow shirt and dark blue jeans, is captured in high definition as they dance with uninhibited joy on a wooden stage. The stage is adorned with a colorful backdrop of balloons in various shades of red, green, and blue, creating a festive atmosphere. The child's face is illuminated by stage lights, highlighting their expressions of pure delight. Their energetic movements fill the frame, conveying the infectious spirit of youthful exuberance against the backdrop of the elaborately decorated stage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1888
|
videos/HRA_part2/1888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, empty warehouse with high ceilings and large, open spaces, four young children, two boys and two girls, are gleefully jumping and laughing as they play a game of tag. The boys wear matching blue striped shirts and khaki pants, while the girls are dressed in pink floral dresses and white leggings. The warehouse's concrete floors and metal beams provide an industrial yet spacious setting for their energetic play. The children's joyous expressions and animated movements capture the essence of carefree childhood fun in an unconventional environment.]"
},
{
"from": "gpt",
"value": "Bad. The facial expressions, arms, and legs of the children in the video are generated abnormally, with one girl having three legs at the same time."
}
] |
seed42_2554
|
videos/HRA_part0/2554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a gray sweater and brown pants, is seen painting en plein air in a lush green forest. Suddenly, a squirrel scurries into the frame, running along the forest floor, its bushy tail bouncing behind it. The artist pauses, observing the squirrel's movements with fascination, capturing the essence of the woodland creature in motion on the canvas. The squirrel, now aware of the artist's presence, stops briefly to look back before continuing its hurried journey, providing a perfect subject for the artist's brushstrokes.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's movements in the video are not smooth."
}
] |
seed46_2378
|
videos/HRA_part2/2378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, dappled sunlight filters through sparse leaves onto a woman wearing a khaki tank top and brown capri pants, standing near a tree trunk. She wipes her face with a white cloth, revealing beads of sweat. Nearby, a backpack rests against a tree, and the landscape is dotted with cacti and shrubs, indicating the arid environment. The woman's action conveys the physical exertion and determination associated with exploring such a unique ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The tree trunk is not displayed."
}
] |
seed42_1422
|
videos/HRA_part0/1422.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clean-shaven male chef with short brown hair waves energetically with his right hand, standing in front of a vibrant green wall adorned with a pattern of white dots. He wears a traditional white chef's uniform with a black necktie, and his left hand rests comfortably in his pocket. The chef's warm smile and engaging demeanor convey a sense of welcome and enthusiasm, perfect for a cooking show introduction or a restaurant greeting.]"
},
{
"from": "gpt",
"value": "Normal. The chef swings his right hand basically normally, with slight coordination issues."
}
] |
seed46_1883
|
videos/HRA_part2/1883.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a dark jacket and distressed jeans, stealthily walks through the dimly lit corridors of a futuristic space prison. His intense gaze is directed ahead, revealing his determination. The harsh, cold lighting accentuates the high-tech, metallic surfaces of the prison environment. As he moves, the camera captures the tension in his body language, hinting at the imminent danger. Despite the oppressive surroundings, the musician's confident stride and unwavering focus suggest a plan in motion, ready to execute his daring escape.]"
},
{
"from": "gpt",
"value": "Normal. The fingers of the hand are somewhat deformed."
}
] |
seed44_3177
|
videos/HRA_part1/3177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet, overcast day, a small gerbil sits atop a tombstone in an old cemetery, surrounded by rows of weathered headstones and tall, swaying grass. The gerbil, with its tiny hands clasped together, appears to be contemplating the serene surroundings. Suddenly, it starts wiping its face with both paws, an endearing gesture that adds a touch of whimsy to the somber setting. The scene is captured in high definition, allowing every detail of the gerbil's fur and the intricate carvings on the tombstones to be clearly visible.]"
},
{
"from": "gpt",
"value": "Normal. The hamster in the video uses its paws to wipe its face, and the movements are basically normal, with slight awkwardness."
}
] |
seed46_2243
|
videos/HRA_part2/2243.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic musician, clad in a vibrant yellow raincoat and matching hat, stands under a powerful waterfall in a lush, green forest, playing a harmonica with intense focus. The water cascades over mossy rocks, creating a natural stage for the performer. Suddenly, the musician leaps into the air, harmonica still in mouth, capturing a moment of pure joy and freedom amidst the thundering water and verdant surroundings. The scene is framed by towering trees and ferns, emphasizing the connection between music, nature, and human spirit.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1129
|
videos/HRA_part1/1129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting, a waiter dressed in a crisp white shirt and black pants is seen sprinting energetically between charming houses with red-tiled roofs. The houses are adorned with lush green vines and windows framed by vibrant flowers. The waiter carries a silver tray aloft, maintaining perfect balance as he navigates the cobblestone streets. Each house has its own unique character, from wooden shutters to ornate door knockers, providing a picturesque backdrop for the waiter's urgent dash. The scene is imbued with a sense of community and lively activity, as the waiter's route weaves through the heart of the village, connecting the homes with his swift, professional service.]"
},
{
"from": "gpt",
"value": "Bad. The person's movements are uncoordinated and discontinuous."
}
] |
seed42_2019
|
videos/HRA_part0/2019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, dressed in a straw hat, blue shirt, and khaki shorts, playfully swims in a clear, freshwater pond, holding a rabbit securely above the waterline. The farmer, now wearing a wide-brimmed hat, blue button-down shirt, and khaki shorts, gently cradles the rabbit, which sits comfortably in his hands, as they both float on the surface of the water. The idyllic scene is set against a backdrop of lush greenery and clear blue skies, capturing the essence of a peaceful rural life.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the arms are twisted, the hands are deformed, the rabbit's body is twisted, and the head is distorted."
}
] |
seed46_1689
|
videos/HRA_part2/1689.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 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 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": "Normal. The gorilla's costume did not generate."
}
] |
seed44_1680
|
videos/HRA_part1/1680.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated, sword-like upper jaw, glides gracefully through the clear, turquoise waters of the open ocean. Its sleek, metallic blue body shimmers as it swims, propelled by a powerful tail fin. The fish is seen from various angles, showcasing its impressive size and streamlined shape designed for speed. At one point, it leaps out of the water, displaying its agility and strength, before plunging back into the depths, leaving a trail of shimmering ripples on the ocean surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1617
|
videos/HRA_part2/1617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning a white lab coat over a gray t-shirt and khaki pants, stands in a futuristic, metallic laboratory. Holding a high-tech device, he demonstrates the concept of time dilation, with visual effects distorting the background and a digital clock appearing to slow down. The scene progresses as he uses a cloth to wipe the perspiration from his forehead, emphasizing the intensity and complexity of his scientific endeavor. Throughout, the lab's modern aesthetic and advanced technology underscore the theme of cutting-edge research and experimentation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2453
|
videos/HRA_part1/2453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]"
},
{
"from": "gpt",
"value": "Normal. The vole in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_1032
|
videos/HRA_part1/1032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge, cap, and sunglasses, stands at the edge of a zoo's flamingo enclosure, where vibrant pink birds congregate. The scene shifts slightly to reveal a clear blue pool within the zoological park, where the officer now interacts with the public, demonstrating water safety techniques. Nearby, children and families watch, some seated on benches under the shade of lush trees, while others lean on the railing, observing the swimming demonstration with interest. Throughout, the police officer remains engaged and attentive, fostering a sense of community and safety among the zoo visitors.]"
},
{
"from": "gpt",
"value": "Normal. The person's hands and arms are twisted in the video, as well as the flamingo's neck."
}
] |
seed44_1084
|
videos/HRA_part1/1084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and a brown belt, is on his knees next to a brown horse, which lies on its side on a grassy surface, possibly injured or receiving care. The officer's hands are gently placed on the horse's neck, showing concern and compassion, while the animal's eyes are closed, indicating it might be resting or in a state of distress. The scene is set against a backdrop of green fields and trees, with no other people or horses visible, emphasizing the intimate connection between the officer and the horse.]"
},
{
"from": "gpt",
"value": "Bad. The horse's head generation in the video has issues, and the character's hand proportions are not well balanced."
}
] |
seed46_1115
|
videos/HRA_part2/1115.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fantastical scene, a man wearing a brown fur coat and matching furry boots is seen dancing joyfully next to a massive, ancient mammoth with long, curved tusks. The mammoth stands placidly, observing the man's lively movements. Behind them, a quaint village is visible, featuring a row of charming, colorful houses with thatched roofs. The houses are nestled among lush greenery, creating a picturesque and harmonious setting. The man's animated dancing contrasts with the mammoth's calm presence, while the village in the background adds a touch of warmth and community to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character experiences sudden changes and deformities during the actions."
}
] |
seed44_1695
|
videos/HRA_part1/1695.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, middle-aged musician, wearing a black leather jacket, black jeans, and black boots, checks a smoke detector in a modern, sparsely decorated living room. He stands on a white chair, his guitar hanging from a strap around his neck, as he inspects the device with a focused expression. The room features a large window allowing ample natural light, a white couch, and a white coffee table, creating a contrast against the musician's dark attire. The scene captures a moment of domestic responsibility in the life of an artist.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1285
|
videos/HRA_part0/1285.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": "Normal. The koala is slightly deformed when it dances."
}
] |
seed46_1572
|
videos/HRA_part2/1572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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: [Two young children, a boy and a girl, are diligently cleaning a large fish tank positioned against a wall covered with a floral-patterned curtain. The boy, wearing a gray shirt and dark pants, uses a net to scoop debris from the water, while the girl, dressed in a yellow shirt and blue jeans, scrubs the glass with a small brush. Both children work attentively, surrounded by an array of aquarium supplies, including bags of gravel, fish food containers, and various cleaning tools. The tank is home to several colorful fish that swim tranquilly in the background, undisturbed by the children's careful efforts to maintain their environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, 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 video shows the police officer with missing limbs and facial features not generated, and the walkie-talkie is blurry."
}
] |
seed44_2294
|
videos/HRA_part1/2294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by vibrant neon lights, a magnificent Bengal tiger, detailed with its distinctive orange fur and black stripes, appears to run gracefully through the aisles, its movement captured in stunning detail. The gallery walls are adorned with abstract art pieces, creating a surreal contrast to the powerful, lifelike depiction of the tiger in motion. The tiger's dynamic pose, mid-stride, conveys a sense of freedom and strength within the confined yet imaginative space of the art gallery.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2957
|
videos/HRA_part1/2957.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 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, 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": "Good. Basically no problem."
}
] |
seed46_3188
|
videos/HRA_part2/3188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a white chef's uniform with black stripes and a matching hat, is seen in a small, empty room with white walls and a gray floor. He stands on a brown wooden ladder, holding a paintbrush in his right hand and a white roller brush in his left. The room is illuminated by a large window to his right, casting a soft glow over the space. The chef, with a full beard and a concentrated look on his face, is in the process of painting the wall a vibrant shade of green. The scene captures his transformation of the room, as he applies the paint with precision and care, highlighting his skills beyond the kitchen.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2250
|
videos/HRA_part2/2250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male farmhand, clad in a white shirt and brown apron, gently caresses a small, fluffy yellow chick with a tender smile on his face, showcasing a moment of care and connection in a rural setting. The scene is set against a backdrop of wooden crates and greenery, highlighting the peaceful atmosphere of the farm. His hands, rough from labor yet gentle in touch, cradle the delicate creature, emphasizing the bond between man and nature.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's fingers and the chicks' faces were poorly generated in the video."
}
] |
seed46_1832
|
videos/HRA_part2/1832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's limbs in the video have generation issues; fingers are not fully generated, the deer has extra legs, and the face features and antlers are not properly generated."
}
] |
seed44_2855
|
videos/HRA_part1/2855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer clad in a blue shirt and khaki pants is seen walking alongside a chimpanzee wearing a tiny red cap, both navigating through a lush, verdant forest. The engineer, carrying a backpack and holding a machete, looks thoughtful as they traverse the underbrush. The chimp, balancing on two legs with a banana in its hand, occasionally glances up at the engineer with curiosity. They continue their journey together, the engineer leading the way with purpose, while the chimpanzee follows closely, the dense greenery of the forest enveloping them.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the engineer and the gorilla crossing through the bushes, their movements are basically normal but there is some lack of coordination."
}
] |
seed42_1893
|
videos/HRA_part0/1893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, spacious room filled with smoke and vibrant lights, two individuals, a man in a dark green shirt and a woman in a black top, are dancing enthusiastically. Suddenly, they stop, looking startled as a beam of green light illuminates them. An alien creature, with large, expressive eyes and a smooth, gray skin tone, descends from above, capturing their attention. The extraterrestrial being, adorned with a metallic, futuristic outfit, lands gracefully beside them, prompting the humans to react with a mix of fear and curiosity. Despite the initial shock, the trio begins to move in unison, engaging in an otherworldly dance, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3211
|
videos/HRA_part1/3211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, embodying the essence of a 'quantum leap,' sprints across a futuristic cityscape under a vibrant aurora borealis sky, wearing a neon green tracksuit that illuminates against the dark urban background. The artist's forward motion is captured in a series of dynamic poses, showcasing the fluidity and power of their stride. The cityscape, featuring sleek skyscrapers and holographic billboards, reflects the energy of the run. The aurora's ethereal glow adds a mystical touch to the scene, highlighting the artist's journey as a metaphorical leap into the unknown. Throughout the sequence, the artist's determination and the pulsating city life create a visual narrative of innovation and progress.]"
},
{
"from": "gpt",
"value": "Bad. The artist's body is twisted, head is twisted, legs are twisted, feet are twisted, arms are twisted, and hands are twisted."
}
] |
seed42_2331
|
videos/HRA_part0/2331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a sky-blue scrubs top and pants, takes a break from her duties to enjoy the outdoors. She is raking a large pile of autumn leaves in a residential backyard, her actions revealing a playful side to her personality. She pauses to look up, smiling at the camera, her brown hair tied back in a practical ponytail. Despite her work clothes, which include a stethoscope hanging around her neck, she tackles the task with enthusiasm, her movements energetic and joyful. The sunny weather and colorful leaves provide a vibrant backdrop for this unexpected scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1593
|
videos/HRA_part0/1593.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray shirt and blue jeans stands on a green ladder, cleaning out debris from the clogged gutters of a two-story house with a red roof, set against a clear blue sky. His focus is intense as he uses a small garden trowel to scoop out leaves and dirt. The house facade, painted in a warm beige hue, contrasts with the lush greenery surrounding it. A pile of removed debris sits on the ground beneath him, indicating progress in his task. His gray shirt and blue jeans are slightly soiled from the work, highlighting the effort and dedication put into maintaining the home's exterior.]"
},
{
"from": "gpt",
"value": "Bad. The shovel in hand suddenly disappears and reappears. The human hand appears deformed."
}
] |
seed44_2057
|
videos/HRA_part1/2057.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, with its fur darkened by water, swims gracefully in a lush, green outdoor enclosure, moving purposefully towards the camera. It shares the water with another chimpanzee, both navigating their environment with ease. In the next scene, the chimpanzee, now soaking wet, interacts playfully with another chimp in the water, highlighting their social bond. Finally, a lone chimpanzee, drenched from swimming, sits pensively at the edge of the water, offering a captivating close-up of its expressive face, all set against a backdrop of dense foliage and trees.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
seed44_2193
|
videos/HRA_part1/2193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with brown hair tied back in a ponytail, wearing a gray cardigan over a white blouse and jeans, meticulously dusts furniture in a classroom. She moves with precision, her facial expression one of concentration. The room is filled with sunlight, illuminating the specks of dust floating in the air. She pauses for a moment, her hands on her hips, surveying her work before continuing. The classroom is mostly empty, save for a few desks and chairs, giving the impression of a quiet, orderly space. Throughout the scene, she remains focused on her task, her movements deliberate and efficient.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand generation in the video has problems, with her hand flying around randomly in the middle frames."
}
] |
seed46_1849
|
videos/HRA_part2/1849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary vulture, with its distinctive bald head and dark plumage, perches majestically on a rocky outcropping, overlooking a vast, arid landscape under an overcast sky. Its powerful, hooked beak is slightly open, revealing its pinkish-red interior, while its piercing eyes survey the terrain for potential prey. The bird's textured skin and feather details are highlighted by the natural lighting, emphasizing its rugged survival instincts in the harsh environment. As it prepares to take flight, the vulture's wings spread wide, displaying their impressive span against the muted tones of the rocky surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1327
|
videos/HRA_part2/1327.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": "Good. Basically correct."
}
] |
seed42_2661
|
videos/HRA_part0/2661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space hotel with large windows revealing the vast cosmos beyond, a lone gray wolf, wearing an orange collar with a glowing green tag, stands on its hind legs, using its front paws to wipe down a stainless steel countertop. The wolf's movements are deliberate and efficient, as if it has performed this task many times before. The space hotel interior is sleek and modern, with curved walls and soft, ambient lighting that casts a warm glow on the surfaces. Through the windows, stars twinkle in the distance, providing a stunning backdrop to the unusual scene of a wolf performing cleaning duties in zero gravity.]"
},
{
"from": "gpt",
"value": "Normal. The wolf's movements in the video are slightly unsmooth."
}
] |
seed44_260
|
videos/HRA_part1/260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a yellow t-shirt and khaki shorts, sits at a wooden desk in a rural backyard, typing on a laptop while referencing notes about wormhole travel. Nearby, a brown chicken pecks at the ground, seemingly curious about the writer's work. The scene then shifts to show the writer swimming in a clear blue pool, contemplating the mysteries of the universe and wormhole navigation. The camera captures the water droplets on the writer's face, hinting at the fluidity of time and space, while the chicken watches from the poolside, adding a touch of whimsy to the intellectual exploration.]"
},
{
"from": "gpt",
"value": "Normal. The writer's swimming movements in the video are not smooth and coordinated."
}
] |
seed42_2764
|
videos/HRA_part0/2764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone penguin stands majestically on a frosty, ice-covered shore, its sleek black and white feathers glistening under the soft, diffused light of an overcast sky. The penguin, with its round body, small flippers, and distinctive tuxedo-like appearance, looks out to the vast, icy sea, creating a sense of solitude and resilience in the harsh Antarctic environment. The scene is framed by rugged, snow-capped mountains in the distance, emphasizing the penguin's natural habitat and the stark beauty of its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's eyes were not generated in the video, there were issues with the generation of the claws, and the mouth was missing when the head turned."
}
] |
seed42_1769
|
videos/HRA_part0/1769.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow safety vest and dark pants, sprints with urgency across a wooden bridge overlooking a geyser's steamy plume in the background. The scene shifts to show the janitor running from right to left, with the geyser's eruption seen erupting behind him, emphasizing his hurried pace. Next, he is depicted dashing down a stone pathway, with the geyser's intermittent eruptions providing a dramatic backdrop. Finally, the janitor is shown sprinting on a dirt path, with the geyser's majestic plumes in the distance, highlighting his perseverance against the geothermal landscape.]"
},
{
"from": "gpt",
"value": "Bad. The limbs are missing, fingers are not fully generated, and the body is distorted."
}
] |
seed44_2498
|
videos/HRA_part1/2498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Michael B. Jordan, sits at a desk in a modern office space. Dressed in a casual white shirt, sleeves rolled up, and stylish glasses perched on his nose, he focuses intently on typing on a sleek, black keyboard. The desk is clutter-free, save for a single, elegant desk lamp casting a warm glow over the scene. Behind him, a large window frames a view of a bustling city skyline, hinting at the high-stakes narrative unfolding as his fingers dance across the keys.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2273
|
videos/HRA_part1/2273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting illuminated by vibrant neon lights, a diligent worker clad in a gray jumpsuit and helmet stands on a sleek, anti-gravity vehicle. The vehicle, featuring a metallic finish and aerodynamic design, hovers above a clean, white platform. The worker is engaged in wiping the vehicle's surface with a cloth, ensuring its spotless condition. Behind the scene, a vast hangar filled with advanced technology and equipment can be seen, emphasizing the high-tech environment in which the worker operates. The worker's focused expression and meticulous attention to detail highlight their commitment to maintaining the anti-gravity vehicle's pristine state.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2596
|
videos/HRA_part2/2596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, dressed in a black jacket, blue jeans, and a gray shirt, is seen in close-up, pulling a metal lever on a movie set. The action takes place against a backdrop of a busy production environment, with crew members and equipment visible. The director's intense focus and the gritty details of the lever convey the essence of hands-on filmmaking. Moments later, the director is shown from the side, still engaged in the task, highlighting the physicality and precision required in the role. The scene is captured in high-definition, ensuring every detail of the director's action and the set is vividly portrayed.]"
},
{
"from": "gpt",
"value": "Bad. The director's operation of the metal lever in the video is not very continuous."
}
] |
seed44_2411
|
videos/HRA_part1/2411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]"
},
{
"from": "gpt",
"value": "Bad. The legs are deformed and hands not fully generated. The buffalo's legs are malformed, with several extra legs."
}
] |
seed42_1657
|
videos/HRA_part0/1657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious living room filled with natural light, a diligent woman wearing a yellow apron over a floral dress meticulously dusts an ornate wooden dresser, her movements methodical and thorough. Beside her, a man in a white shirt and brown trousers assists, carefully wiping down a matching side table. The room is elegantly decorated with antique furniture and Persian rugs, creating a warm and inviting atmosphere. On the walls, framed paintings and family photographs add personal touches to the space. The couple works in harmony, their actions demonstrating a shared commitment to maintaining their cherished home environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2211
|
videos/HRA_part2/2211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape filled with vibrant greenery and ancient flora, a colossal woolly mammoth tenderly caresses another smaller mammoth with its trunk, showcasing a rare, intimate moment between these majestic creatures. The larger mammoth, adorned with thick, shaggy fur and imposing tusks, gently touches the younger one, whose eyes reflect curiosity and trust. The backdrop features a dense forest, with sunlight filtering through the canopy, casting dappled shadows on the ground, highlighting the tenderness and connection shared between the two mammoths.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_120
|
videos/HRA_part0/120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a brown jacket and khaki pants, stands in a savanna environment, engaged in gently wiping the face of a seated cheetah. The big cat is calm, displaying trust, as it sits on a sandy ground strewn with rocks and twigs. The director's caring action is evident as they tenderly clean the cheetah's face using a soft cloth, all while surrounded by the natural habitat of tall grass and distant trees.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1696
|
videos/HRA_part2/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Bad. The character's body movements in the video are not coordinated, and the cheetah's movements are not smooth."
}
] |
seed44_2212
|
videos/HRA_part1/2212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 silver spacesuit, reminiscent of a high-tech astronaut, walks across a vast, barren landscape under a twilight sky, reminiscent of a distant planet. A cobra, its scales shimmering with iridescent colors, slithers along the ground beside him, seemingly unphased by the alien environment. In the background, a massive deep space communication array rises into the sky, its dishes facing the cosmos, ready to transmit messages across the universe. The man stops, looking up at the stars, while the cobra rears up, mirroring his stance, both figures framed by the imposing silhouette of the communication array.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1454
|
videos/HRA_part2/1454.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, dressed in a khaki safari outfit, complete with a wide-brimmed hat, kneels in a lush, green environment, closely observing a large hippopotamus. The director's intense focus and proximity to the wild animal emphasize the unique and potentially dangerous nature of the scene. The hippopotamus, with its massive body and distinctive features, slowly crawls through the tall grass, creating a sense of movement and life in the otherwise still landscape. The director's presence adds a narrative element, suggesting a story unfolding between human curiosity and the untamed wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The hippo's head is twisted."
}
] |
seed46_1626
|
videos/HRA_part2/1626.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic golden-brown lion leaps through the air against a vivid blue sky, its powerful muscles straining against the force of gravity. The lion, with piercing amber eyes and a thick mane, is suspended mid-jump, showcasing its agility and strength. Its leap is captured against a backdrop of lush green grass and scattered trees, highlighting the animal's natural habitat. The lion's claws are extended, ready to grip its prey, emphasizing the raw power and predatory nature of this iconic creature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1246
|
videos/HRA_part2/1246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a full uniform complete with a hat, rests peacefully on a bench in a quiet, empty city park during the daytime. The serene atmosphere is highlighted by the soft play of sunlight filtering through the trees, casting dappled shadows on the ground. The officer's hat is tilted down, partially obscuring their face, while they lean back against the wooden slats of the bench, their body language conveying a sense of well-deserved rest. Beside them, a water bottle sits on the bench, and in the distance, the peaceful urban landscape is visible, punctuated by the occasional passerby and the gentle sway of tree branches.]"
},
{
"from": "gpt",
"value": "Bad. People are deformed, and the chair's backrest is unrealistic."
}
] |
seed46_2360
|
videos/HRA_part2/2360.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in outdoor gear, including a brown jacket, beige pants, and brown shoes, crawls on hands and knees across a grassy landscape under a cloudy sky. Beside him, a massive bison, its shaggy coat and large horns distinct, grazes on the lush vegetation, seemingly unperturbed by the man's presence. The scene conveys a sense of harmony between the man and the wild animal in their shared natural environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1331
|
videos/HRA_part0/1331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 writer, wearing a black jacket, leans forward in his chair to gently caress a hyena lying at his feet, the animal seemingly at ease in his presence. The scene takes place in a well-lit room, with a bookshelf filled with various books visible in the background, hinting at the writer's profession. The hyena, displaying a level of comfort unusual for its species, looks up at the writer with a calm demeanor, creating an unexpected yet captivating connection between the two.]"
},
{
"from": "gpt",
"value": "Normal. The writer in the video is not shown leaning forward."
}
] |
seed42_2260
|
videos/HRA_part0/2260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, dressed as a waiter in a crisp white shirt, black vest, and striped bow tie, crawls across a wooden floor. The room is dimly lit, with a large, elegant chandelier hanging above. The badger moves toward a grand dining table set with fine china and silverware, passing by a towering bookshelf filled with leather-bound books. The camera captures the badger's earnest expression and the intricate details of its costume, all set against the backdrop of a lavishly decorated room.]"
},
{
"from": "gpt",
"value": "Normal. The badger in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1975
|
videos/HRA_part0/1975.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, dressed in a white shirt, black vest, and striped tie, walks through a bustling market, surrounded by vibrant stalls selling fruits, vegetables, and spices. The scene captures him navigating the lively crowd, his confident stride and focused gaze highlighting his purposeful movement. Market vendors and customers are visible in the background, adding to the dynamic atmosphere of the location. The waiter's attire contrasts with the colorful market environment, emphasizing his role as he moves through this energetic space.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted in the video."
}
] |
seed42_1673
|
videos/HRA_part0/1673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly imagined scene, a majestic African lion, distinguished by its thick mane and muscular build, runs across a futuristic landscape where solar sails, vast and gleaming, catch the sunlight high above like enormous kites adrift in the sky. The lion's powerful strides and focused gaze contrast beautifully with the serene, almost surreal sight of the solar sails, which seem to float effortlessly in the still air, their surfaces shimmering with reflected light. This unlikely juxtaposition of nature and technology creates a striking and memorable visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The lion's running in the video is not smooth and the movements are uncoordinated."
}
] |
seed44_2188
|
videos/HRA_part1/2188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike scene, a firefighter wearing a spacesuit and helmet, equipped with a traditional yellow fire axe, is seen wiping the surface of the moon. The lunar landscape, with its stark contrast of dark shadows and bright highlights, is visible behind him. The firefighter's gloved hand, holding a cloth, carefully cleans a spot on the moon's dusty terrain, creating a stark visual against the desolate background. The American flag, planted nearby, adds a patriotic touch to the unusual juxtaposition of a firefighter performing a mundane task in an extraordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. It can be seen that there is a wiping action, but the action is not continuous and undergoes sudden changes."
}
] |
seed42_140
|
videos/HRA_part0/140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2067
|
videos/HRA_part1/2067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown bat with intricate wing details is seen crawling along a cave floor, illuminated by a soft, ambient light. It slowly makes its way across the rocky terrain, revealing its unique features in close-up. Meanwhile, in the distance, the planet Venus can be seen as a bright spot in the night sky, providing a celestial contrast to the terrestrial scene below. The bat's movements are deliberate and methodical, highlighting its adaptation to navigating dark environments, while Venus' presence adds a cosmic element to the composition.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and wings of the bat in the video are missing, and the facial features are distorted."
}
] |
seed42_2820
|
videos/HRA_part0/2820.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 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 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 problems."
}
] |
seed46_194
|
videos/HRA_part2/194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sparrowhawk soars gracefully in a clear blue sky, its sharp eyes scanning the grassy meadows below for prey. Its body is a sleek silhouette against the brightness, with a prominent head and compact wings. It then swoops down with remarkable agility, talons extended, targeting a small rodent in the tall grass. The bird's plumage is a striking mix of brown and gray, with a white underbelly marked by dark bands, as it lands on a branch, alert and ready to strike again. Finally, it takes flight once more, its powerful beats and aerodynamic form cutting through the air with precision, embodying the essence of a skilled avian predator.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the sparrowhawk's head twisted, claws twisted, and wings twisted."
}
] |
seed44_1224
|
videos/HRA_part1/1224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue uniform and a stethoscope around her neck, is delightedly interacting with a small gerbil in a cozy living room. The gerbil, perched on a tiny platform, suddenly leaps into the air, its action frozen in mid-jump, capturing a moment of playful exuberance. The nurse, with a warm smile, watches the gerbil's antics, her caring demeanor evident in her facial expression and body language. The scene is set against a backdrop of a homely living space, with a couch, coffee table, and various household items visible in the background, creating a sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's movements are not fluid, and its limbs are uncoordinated."
}
] |
seed42_2095
|
videos/HRA_part0/2095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room filled with the scent of old books and memories, two people sit on a vintage, worn-out sofa, their faces reflecting deep sorrow. One, a woman with long, wavy brown hair, wears a simple gray sweater and blue jeans, her eyes red from crying, as she holds a well-loved teddy bear. Beside her, a man in a plaid shirt and khaki pants, his face equally stricken with grief, leans his forehead against hers, both of them finding solace in each other's presence. Tears stream down their cheeks, highlighting the raw emotion of the moment, as they seek comfort in the quiet space they share.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2722
|
videos/HRA_part2/2722.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green park under the bright summer sun, two happy children, a boy and a girl, are energetically chasing each other on the grass. The boy, wearing a red t-shirt and blue shorts, stretches out his hands, playfully trying to catch the girl. She, donned in a yellow dress and sandals, giggles as she skillfully dodges him, both enjoying the thrill of the chase. They run amidst a scattering of colorful wildflowers, their laughter echoing through the serene environment, encapsulating the joy and innocence of childhood.]"
},
{
"from": "gpt",
"value": "Bad. The facial features of the children in the video are generated blurry, and their limbs are generated distorted."
}
] |
seed44_202
|
videos/HRA_part1/202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room with a soft, ambient glow, two young children, a girl and a boy, sit cross-legged on a patterned rug, their eyes wide with wonder and attention. The girl, wearing a yellow dress, leans forward slightly, her hands resting on her thighs, while the boy, dressed in a blue t-shirt and shorts, holds a toy car in one hand, both engrossed in listening to a story being told by an unseen narrator. The camera captures the children from a low angle, highlighting their expressions of rapt attention and the slight tilt of their heads, indicating their deep engagement with the tale unfolding before them.]"
},
{
"from": "gpt",
"value": "Bad. The boy mentioned in the caption is holding a toy car, which does not appear in the video."
}
] |
seed42_3059
|
videos/HRA_part0/3059.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, dressed in a yellow high-visibility jacket and blue jeans, stands near a buffalo swimming in a serene, placid lake, surrounded by lush greenery. The buffalo, with its massive frame and shaggy coat, gracefully paddles through the clear water, creating ripples that extend outward. In the background, a wooden pier extends into the lake, and tall trees line the shore, providing shade and a sense of serenity. The janitor looks on, perhaps during a break from his duties, observing the buffalo in its natural habitat, a harmonious blend of nature and human presence.]"
},
{
"from": "gpt",
"value": "Normal. The buffalo's head in the video is generated with slight inconsistency."
}
] |
seed46_2685
|
videos/HRA_part2/2685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown leather jacket and dark jeans, stands in a rugged chaparral landscape, gesturing emphatically. He watches intently as a porcupine, quills fully displayed, jumps over a small log, showcasing its surprising agility in the wild environment. The director's focused stance and the porcupine's unexpected leap are framed by the chaparral vegetation, highlighting the unique interaction between human creativity and natural wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, hedgehog body is deformed, head is twisted, and legs are distorted."
}
] |
seed44_2014
|
videos/HRA_part1/2014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a sea urchin reveals its intricate, symmetrical structure as it clings to a rocky surface underwater. Sunlight filters through the clear, blue water, casting a soft glow on the urchin's spines, which are a striking contrast to the dark rocks. The camera captures the water gently swaying the urchin, emphasizing its resilience in the marine environment. The scene is framed by the rocky crevices of the seabed, highlighting the creature's natural habitat, while the muted colors of the rocks and sand provide a serene backdrop for the brightly colored sea urchin.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2703
|
videos/HRA_part1/2703.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park setting, a young woman with dark hair pulled back into a ponytail works at a ticket booth decorated with colorful animal illustrations. She wears a green polo shirt with a name tag, signifying her role as a cashier. A small, friendly kinkajou rests on her shoulder, its fur blending with her brown hair. The animal playfully explores the area around her head as she smiles warmly, gently caressing it with her right hand, her nametag partially visible. This intimate interaction between the cashier and the kinkajou occurs within the vibrant, wildlife-themed environment of the zoo.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video, the kinkajou's body is twisted, and the head is distorted."
}
] |
seed44_2305
|
videos/HRA_part1/2305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student wearing a gray jacket walks through a vast, sunny temperate shrubland, with a yellow signpost and a lush green landscape stretching into the distance. The young man, carrying a backpack, strolls along a sandy path bordered by dense shrubbery, under a clear blue sky. He pauses to observe his surroundings, revealing a serene environment with distant mountains and a rich array of vegetation, including shrubs and small trees, all set against a backdrop of bright sunlight. Continuing his journey, he moves through the shrubland, which is characterized by its temperate climate and diverse plant life, offering a peaceful scene of nature and exploration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_326
|
videos/HRA_part0/326.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."
}
] |
seed42_1221
|
videos/HRA_part0/1221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its glossy black and white feathers shimmering under the sunlight, showcasing the bird's striking plumage against a lush green forest backdrop. The magpie turns its head, revealing its intelligent eyes and sharp beak, highlighting its curious nature. Moments later, it spreads its wings, displaying the full span of its black and white feathers, before taking flight, leaving behind a flurry of feathers and a sense of awe at its beauty and grace. Throughout the scene, the magpie remains the central focus, captivating the viewer with its natural elegance and charm.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_200
|
videos/HRA_part0/200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single camel, distinguished by its brown fur and a patterned red, yellow, and green saddle, stands against a desert landscape under a clear blue sky. It begins to move rhythmically, swaying to an unseen beat, its large eyes gazing into the distance. Moments later, it raises its head proudly, its mouth open in a gesture that suggests a joyful call or song. Then, the camel continues its dance, gracefully moving its legs in time with the music, its body language conveying a sense of happiness and freedom in the vast, sandy expanse.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 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, 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": "Good. No obvious problems."
}
] |
seed44_2514
|
videos/HRA_part1/2514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 habitat designed to mimic Earth's savanna, a majestic rhinoceros, fitted with a specialized spacesuit, calmly walks on artificial grass under a simulated sky. Tourists, dressed in sleek, white spacesuits, observe from a safe distance behind transparent barriers, their expressions a mix of awe and curiosity. The rhino moves gracefully, its every step monitored by advanced technology to ensure its well-being in the zero-gravity environment. This unique scene captures the harmony between wildlife conservation and the boundless possibilities of space exploration, offering viewers a glimpse into a world where nature and technology coexist in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_122
|
videos/HRA_part0/122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, imaginative scene, a giraffe wearing a silver spacesuit floats weightlessly inside a spaceship, its large, curious eyes gazing around. The ship's interior is illuminated by soft blue lights, creating a futuristic atmosphere. Against the backdrop of space visible through the windows, a graceful alien figure, adorned in a flowing golden robe, dances elegantly. The fluid movements of the alien dancer contrast with the zero-gravity environment, while the giraffe observes, seemingly captivated by the performance. The spaceship docks seamlessly with another vessel, its exterior adorned with intricate patterns, as the dance continues, blending elements of fantasy and science fiction.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the legs are severely deformed, the hands are misshapen, and the giraffe's body is twisted."
}
] |
seed44_1038
|
videos/HRA_part1/1038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic silver uniform with gold accents, is seen piloting a sleek, chrome hover vehicle through a neon-lit cityscape under a starry night sky, suggesting a high-tech urban environment. Moments later, the officer steps out of the vehicle, equipped with a utility belt and helmet, and walks purposefully down a busy, illuminated street filled with pedestrians and flying cars, creating a vivid image of law enforcement in a sci-fi metropolis.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3030
|
videos/HRA_part2/3030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a human-like jackal, dressed in a red apron and name tag, stands behind a checkout counter. The background features a vibrant, turquoise water surface, suggesting a swimming pool or body of water. The jackal, with its distinctive canine features and upright posture, interacts with customers, handling items scanned over a register. The setting is illuminated by bright, warm lighting, casting a glow on the turquoise water, which stretches out behind the cashier area, merging the indoor and outdoor environments in an unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.