video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1188
|
videos/HRA_part1/1188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform with a badge and a hat, sits in a well-lit room with white walls. He nods slowly and deliberately in response to something off-screen, his serious demeanor and attentive body language conveying a sense of authority and engagement. The clean, organized setting and the officer's focused gaze suggest a formal environment, possibly an office or an interrogation room, where he listens intently to another person, nodding to show understanding and agreement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2444
|
videos/HRA_part0/2444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with a round face, brown hair styled in a bun, and wearing a gray top is seen sitting alone, her eyes welling up with tears that stream down her cheeks. She looks lost in thought, her gaze distant, as she holds a tissue in her right hand. Moments later, she wipes away her tears with the tissue, her emotions visible in her expressive face. Then, she is captured in a close-up, her eyes closed, a tear rolling down her cheek, her lips slightly parted, as she seems to be taking a deep breath. Lastly, she looks directly at the camera, her eyes filled with unshed tears, her cheeks flushed, conveying a sense of vulnerability and strength in her emotional state.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1579
|
videos/HRA_part1/1579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courtroom with an intricate, geometric design, a distinguished actor, portraying a space captain, strides purposefully down the aisle. He wears a tailored uniform, complete with silver insignias, and carries himself with the air of someone accustomed to command. The room is filled with alien spectators of various species, seated on elevated benches, observing the unfolding drama. The lighting is dramatic, casting stark shadows and highlighting the tension in the scene. As the actor walks, the camera follows him, capturing every confident step and the intensity in his eyes, setting the stage for a pivotal moment in the space court trial.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks very awkwardly, with uncoordinated movements."
}
] |
seed46_2720
|
videos/HRA_part2/2720.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished male doctor, wearing a white lab coat over casual attire, skillfully prepares dinner in a modern kitchen with stainless steel appliances and granite countertops. He expertly chops vegetables on a wooden cutting board, using a sharp chef's knife, while a pot simmers on the stove, releasing aromatic steam. The kitchen is illuminated by soft overhead lights, casting a warm glow over the scene. Behind him, a large window displays an urban skyline at twilight, adding a touch of sophistication to the domestic setting.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's fingers are deformed in the video, the ears are generated with issues, and the vegetables and knife on the cutting board are distorted."
}
] |
seed46_2150
|
videos/HRA_part2/2150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Grouper fish, known for its speckled brown and white skin, swims serenely in clear, blue-green waters, surrounded by vibrant coral reefs teeming with life. Its powerful body, complete with a wide mouth and large eyes, glides effortlessly through the underwater environment. The Grouper pauses, hovering near a cluster of colorful corals and exotic marine life, showcasing its size and strength against the intricate patterns of the reef. The scene captures the fish's natural habitat, highlighting the contrast between its imposing presence and the delicate beauty of the coral ecosystem.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_26
|
videos/HRA_part0/26.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a bustling metropolis, a sleek, black cat is gently caressed by a young woman wearing a blue shirt and glasses. The cat, adorned with a red ribbon, sits atop a wooden crate, surrounded by urban elements like a fire hydrant, a green trash can, and a street sign. The woman, with her hair tied back in a bun, interacts affectionately with the cat, which responds with a content gaze. Behind them, the vibrant cityscape is visible, featuring tall buildings, a busy sidewalk, and a red traffic light, capturing the unique connection between human, animal, and urban environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_3167
|
videos/HRA_part1/3167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a simple black one-piece swimsuit, swims calmly in a vast, prehistoric lake, with a woolly mammoth standing watchfully nearby on the shore, its massive frame and shaggy coat a stark contrast against the serene water. The setting sun casts a warm glow over the scene, highlighting the woman's strokes and the mammoth's still form, creating a captivating juxtaposition of ancient and modern elements in a natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_267
|
videos/HRA_part0/267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 orchard, a hardworking farmer pauses from his labor, wiping sweat from his brow, while in the foreground, a mongoose is seen playfully exploring its surroundings. The farmer, dressed in a straw hat, denim overalls, and a plaid shirt, leans against a wooden fence, offering a warm smile. Nearby, the mongoose, with its slender body and bushy tail, darts between tree trunks, seemingly unbothered by the human presence. In the distance, a shimmering swimming pool, surrounded by a wooden deck and sun loungers, provides a refreshing contrast to the vibrant orchard setting.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's movements in the video are not smooth."
}
] |
seed46_3178
|
videos/HRA_part2/3178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a red beret and carrying a large canvas, walks purposefully down a bustling city street lined with vintage cinemas. Each theater features marquee signs advertising classic films from the golden age of cinema. The artist's attire includes a striped shirt, dark trousers, and a pair of worn-out sneakers, giving a sense of his creative and casual lifestyle. As he strides, passersby glance curiously at his oversized artwork, which is draped in a protective cloth, hinting at the mystery and anticipation of his latest creation. The vibrant atmosphere of the old movie houses and the artist's journey through the urban landscape evoke a sense of nostalgia and artistic inspiration.]"
},
{
"from": "gpt",
"value": "Normal. The artist's hands and feet are deformed, and the passersby are generated blurry."
}
] |
seed46_1109
|
videos/HRA_part2/1109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense, lush canopy of a subtropical wet forest, a small brown bat clings upside-down from a branch, its wings folded tightly. The bat begins to groom itself, carefully wiping its wing membranes with its mouth, a behavior essential for maintaining health and flight efficiency. The bat continues its meticulous grooming, wiping its body and wings with its mouth, highlighting the importance of self-care in these nocturnal creatures. Throughout the scene, the bat remains in the same position, hanging upside-down from a branch in the rich greenery of the subtropical wet forest, as it focuses on cleaning its wings.]"
},
{
"from": "gpt",
"value": "Bad. The bat's head is deformed, wings are twisted, and claws are deformed."
}
] |
seed46_2475
|
videos/HRA_part2/2475.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a farmer wearing a straw hat and overalls stands in a lush green field, holding a golden retriever puppy in his arms. Around him, a swarm of nanobots, resembling tiny silver spheres, diligently repairs a broken-down tractor, each one equipped with miniature tools. The farmer's eyes twinkle with delight as he watches the efficient repair crew. Nearby, a sparkling blue swimming pool is nestled among the crops, where a group of people in colorful swimwear splash and play, enjoying a refreshing break from the summer heat. The juxtaposition of rural life, advanced technology, and leisure creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face and hands, the puppy, and the people in the pool in the video were generated abnormally, and a dog suddenly appeared in the farmer's hand in the middle frame."
}
] |
seed46_1195
|
videos/HRA_part2/1195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, standing on its hind legs, dons a yellow tutu and green ballet slippers, dancing energetically in a grassy field under a bright blue sky. It leaps and twirls gracefully, its movements fluid and expressive, showcasing its unexpected talent for dance. The dingo's joyful expression and animated body language convey a sense of freedom and delight in its unusual activity, captivating the viewer with its unique performance.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2793
|
videos/HRA_part1/2793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a crisp, white lab coat over a blue shirt and khaki pants, leaps playfully along a weathered boardwalk by the ocean, his stethoscope swinging freely. The setting sun casts a golden hue over the scene, highlighting the contrast between his professional attire and the casual, joyful activity. The boardwalk, lined with aged wooden planks, extends into the distance, offering a picturesque view of the shoreline and the sea beyond. The doctor's action, captured mid-jump, conveys a sense of freedom and happiness, juxtaposed against the typically serious context associated with medical professionals.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's jumping in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_1453
|
videos/HRA_part0/1453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning common pheasant, characterized by its vibrant plumage, is captured in a natural habitat, surrounded by lush green foliage. The male bird, with its distinctive red face, prominent white neck collar, and golden crest, struts confidently on the forest floor. Its iridescent green head and long, brownish-green tail feathers are highlighted as it moves through the underbrush. The setting showcases the pheasant's environment, featuring tall grasses and leafy plants, providing a rich, textured backdrop for this captivating display of avian beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2150
|
videos/HRA_part0/2150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Grouper fish, known for its speckled brown and white skin, swims serenely in clear, blue-green waters, surrounded by vibrant coral reefs teeming with life. Its powerful body, complete with a wide mouth and large eyes, glides effortlessly through the underwater environment. The Grouper pauses, hovering near a cluster of colorful corals and exotic marine life, showcasing its size and strength against the intricate patterns of the reef. The scene captures the fish's natural habitat, highlighting the contrast between its imposing presence and the delicate beauty of the coral ecosystem.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2748
|
videos/HRA_part1/2748.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic vineyard setting, a young female cashier, dressed in a red apron over a white blouse, diligently wipes down the wooden counter of the quaint tasting room. Sunlight streams in through large windows, highlighting the rich textures of the wood and the lush greenery outside. The atmosphere is peaceful and inviting, with the sound of gentle music playing in the background and the distant hum of vineyard activities. The cashier's focused demeanor and meticulous cleaning convey a sense of pride in her work and the establishment, creating a welcoming environment for visitors.]"
},
{
"from": "gpt",
"value": "Normal. The female cashier's movements in the video are slightly unsmooth."
}
] |
seed46_214
|
videos/HRA_part2/214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young college student, casually dressed in a white T-shirt and blue jeans, diligently paints a room with bright yellow walls, focusing on a corner where two walls meet. The room is filled with natural light from a nearby window, illuminating the student's task. They wear protective goggles and a face mask, ensuring safety while working. The student is surrounded by painting supplies, including a ladder, paint cans, and brushes, indicating a thorough preparation for the project. As the camera pans out, we see the student's friends in similar attire, contributing to the painting effort, fostering a sense of camaraderie and teamwork in transforming the space.]"
},
{
"from": "gpt",
"value": "Bad. The student's hand and brush, as well as the head and hand of the student's friend, have generation issues, with the friend's head and hand suddenly appearing in the middle frames."
}
] |
seed44_1666
|
videos/HRA_part1/1666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning round glasses and a yellow sweater, sits at a wooden table cluttered with writing tools and a laptop, knitting a vibrant red scarf with large needles. The scene is set in a cozy room with a rustic wooden floor and a large window, through which daylight softly illuminates the space. On the wall hangs a large, colorful painting, adding a touch of artistic flair. The writer's hands, adorned with rings and bracelets, skillfully manipulate the knitting needles as they work on the scarf, all while surrounded by the warm, inviting atmosphere of the room.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are not smooth and coordinated."
}
] |
seed46_2985
|
videos/HRA_part2/2985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist with a shaved head and wearing a gray shirt is seen organizing items on metal shelves against a gray backdrop. Initially, he is placing objects with care, showcasing his meticulous nature. Moments later, he is shown adjusting the arrangement of items, revealing his attention to detail. Then, he is seen moving an object to another shelf, indicating his methodical approach to organization. Finally, he looks satisfied with his efforts, his posture and facial expression reflecting a sense of accomplishment, all within the minimalist setting of a gray room with metal shelving units.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2910
|
videos/HRA_part0/2910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a yellow reflective vest, ascends a rocky terrain during the day, exhibiting determination and resilience. His tactical gear, including a backpack and a helmet, is visible as he scales the rugged landscape. The camera captures his focused face, set on completing the climb, and the lush greenery surrounding the rocky area, providing a stark contrast to his mission-driven ascent. Despite the challenging environment, the officer's resolve is evident, making for a compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2683
|
videos/HRA_part1/2683.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sits in a dimly lit room, her face softly illuminated by a single light source. She is wearing a simple white shirt, her brown hair falling gently over her shoulders. The camera focuses on her chest, rising and falling slowly as she takes deep, deliberate breaths. Each inhale is visible, drawing attention to the tranquility of the moment. Her eyes are closed, her lips slightly parted, as she finds peace in the rhythm of her breathing. The quiet atmosphere is punctuated only by the sound of her breath, creating a serene and intimate portrait of mindfulness.]"
},
{
"from": "gpt",
"value": "Bad. The woman mentioned in the caption is not shown closing her eyes in the video."
}
] |
seed44_2721
|
videos/HRA_part1/2721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a yellow firefighting jacket, gently wipes soot off a small, brown hedgehog that's been rescued from a fire. The hedgehog, nestled in the firefighter's protective glove, looks up with curious eyes as it's being cleaned. The scene takes place against the backdrop of a fire-damaged building, with smoke still lingering in the air, emphasizing the tender moment between the rescuer and the rescued animal.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's wiping motion in the video is basically normal, with slight awkwardness."
}
] |
seed46_2197
|
videos/HRA_part2/2197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 arid scrublands under a vast, cloud-dappled sky, a golden jackal pauses mid-stride, its russet fur gleaming in the sunlight. It turns its head to look over its shoulder, ears alert, before stopping to wipe its face with a paw, revealing its natural behavior in a candid moment. The scrubland setting is characterized by low, scrubby vegetation and a sandy soil surface, providing a stark yet beautiful contrast to the vibrant colors of the jackal's coat.]"
},
{
"from": "gpt",
"value": "Bad. The golden jackal's legs show deformities, and its face and body also appear distorted at times, with its tail falling off at one point."
}
] |
seed42_1066
|
videos/HRA_part0/1066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, is perched on a concrete ledge. It has a full, round body and is situated in an urban environment, as indicated by the presence of a streetlight and a partial view of a building's facade with windows. The bird faces right, its head turned slightly toward the viewer, revealing one bright, alert eye. Its beak is open, perhaps mid-call, and its feet grasp the edge of the ledge firmly. The scene is set against a backdrop of a clear, blue sky, offering a simple yet effective contrast to the textured details of the pigeon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1903
|
videos/HRA_part1/1903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous woman wearing a thick, brown jacket and dark pants stands on a rocky ledge overlooking a vast, misty valley, preparing to leap from the cliffside. Nearby, a large brown bear, also gazing into the foggy abyss, seems unperturbed by her presence. As the scene progresses, the woman jumps off the cliff, her arms spread wide, embracing the thrill of freefall, with the bear watching intently from the edge of the precipice. Throughout, the dramatic landscape of rugged cliffs and the mysterious atmosphere of the mist-shrouded valley provide a breathtaking backdrop for this daring act.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hands and legs, as well as the brown bear's head, are generated incorrectly in the video, with the woman's hands and legs suddenly distorting in the middle frames."
}
] |
seed44_1699
|
videos/HRA_part1/1699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a blue button-down shirt and khaki pants, rearranges furniture in a cozy room with wooden floors and a fireplace, aiming to find inspiration. He thoughtfully adjusts a brown leather sofa, placing it at an angle near the hearth, with a glass coffee table in front. Next, he moves a wooden chair with a green cushion to the right side of the sofa, creating a conversational space. Then, he positions a tall bookshelf behind the chair, filled with books and trinkets, adding character to the room. Lastly, he places a small wooden desk with a typewriter next to the window, basking in natural light, perfect for writing, all while maintaining the warm, inviting atmosphere of the space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2012
|
videos/HRA_part0/2012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman, presumably a writer, sits at a grand dining table, meticulously polishing silverware with a white cloth. He wears a dark blue blazer, a button-down shirt, and glasses, presenting a scholarly appearance. The room is dimly lit, with the only bright spot being the gleam from the silver as he works. The setting suggests a large, elegant dining hall, possibly in an old mansion, where the writer has taken on the unexpected task of preparing the cutlery. His focus and precision convey a sense of dedication to the task, contrasting with his intellectual pursuits.]"
},
{
"from": "gpt",
"value": "Bad. The wiping action is discontinuous, there is a sudden change."
}
] |
seed44_2370
|
videos/HRA_part1/2370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male worker, wearing a brown jacket and gray pants, stands in front of a large industrial machine in a dimly lit factory. He blinks rapidly, perhaps due to fatigue or the strain of focusing on his task. The machine, which features a large gear and various mechanical components, dominates the background, emphasizing the environment's industrial nature. The worker's expression conveys a sense of determination mixed with the physical demands of his job, highlighted by his blinking eyes.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2544
|
videos/HRA_part1/2544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space courtroom under the glow of neon lights, two children, a boy in a gray t-shirt and a girl in a pink dress, engage in a mock trial, surrounded by an audience of plush toys and action figures. The boy, acting as the judge, holds a gavel, while the girl, serving as the defendant, wipes away pretend tears with a small tissue, both participants fully immersed in their roles amidst the imaginative setting. Behind them, a large window reveals the vastness of outer space, complete with stars and planets, adding to the fantastical atmosphere of this unique children's play scenario.]"
},
{
"from": "gpt",
"value": "Bad. Although his movements are basically smooth, there is a lack of coordination."
}
] |
seed44_1792
|
videos/HRA_part1/1792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, donning a straw hat and denim overalls, stands on wooden docks by the water's edge, engaging in an impromptu dance with a mongoose. The mongoose, with its alert eyes and bushy tail, seems equally engaged in the dance, mirroring the farmer's playful steps. The docks, weathered and worn, creak under their movements, providing a rustic stage for this unlikely duo. The sun begins to set, casting a golden glow over the scene, adding a magical touch to the dance between the farmer and the mongoose.]"
},
{
"from": "gpt",
"value": "Normal. The movements of the farmer and the mongoose in the video are not smooth."
}
] |
seed44_1777
|
videos/HRA_part1/1777.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling city square, under the soft glow of streetlights and the clear night sky, a diverse group of individuals, including a man with a beard, a woman with glasses, and another woman with a ponytail, are all looking intently at something above them. Their postures and facial expressions convey a sense of awe and wonder, suggesting they are captivated by an extraordinary sight in the urban landscape. Among them, a man with a beard and a woman with glasses stand side by side, both gazing upwards with intense focus. Beside them, a woman with her hair in a ponytail also looks up, her face reflecting a mix of surprise and fascination. All around, the city continues its nightly activities, but these people remain transfixed, united in their shared attention to an unseen marvel overhead.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1612
|
videos/HRA_part2/1612.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a stethoscope around his neck and a colorful tie, is laughing heartily with his head thrown back, his eyes closed, and his mouth wide open, showing his amusement in a candid moment. The laughter is contagious, spreading joy and positivity in a medical setting, with the doctor's facial features animated and expressive, capturing the essence of happiness and camaraderie in a professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's mouth in the video is overly large, and the face is slightly blurry."
}
] |
seed42_3049
|
videos/HRA_part0/3049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a blue checkered shirt and black pants, meticulously assembles a complex piece of furniture in a modern workshop, illuminated by bright overhead lights. His tools, including a screwdriver and measuring tape, are laid out on a clean, organized workbench. Close-up shots reveal his focused expression and skilled hands as he aligns and tightens screws, demonstrating precision and expertise. The space is filled with the ambient sounds of machinery and the occasional beep of electronic devices, creating a backdrop of industrious activity. Throughout the process, the engineer maintains a calm demeanor, pausing occasionally to consult a blueprint or adjust his glasses, embodying the essence of craftsmanship and dedication.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's assembly actions in the video are not smooth."
}
] |
seed46_2368
|
videos/HRA_part2/2368.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling supermarket setting, a young female cashier, wearing a red apron over a black and white striped shirt, pushes a shopping cart filled with groceries toward the checkout counter. She has a determined look on her face, and her curly brown hair is tied back in a bun. The cart is stacked with various items, including a large watermelon on top, as she navigates the busy aisle, surrounded by shelves packed with products and other shoppers. The scene captures the dynamic environment of a grocery store during peak hours, with the cashier diligently managing her tasks amidst the activity.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1425
|
videos/HRA_part2/1425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint town with brick-paved streets and Victorian-style buildings, a uniformed police officer stands watch over a community swimming pool filled with clear, blue water. The officer, clad in a crisp blue uniform, cap, and sunglasses, leans against a wooden fence, observing the swimmers. Children play joyfully in the shallow end, splashing each other, while adults lounge on deck chairs under colorful umbrellas. The scene is framed by lush greenery and the charming town in the background, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, and the legs are contorted."
}
] |
seed46_1187
|
videos/HRA_part2/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's action of splashing water with its trunk is not smooth and continuous; there are sudden changes in the middle frames."
}
] |
seed46_3003
|
videos/HRA_part2/3003.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, softly lit room, two young children sit on a patterned carpet, engrossed in play, wearing casual clothing suitable for a relaxed day indoors. One child, dressed in a yellow shirt and blue shorts, leans forward with curiosity. Beside them, a ferret, identifiable by its distinct brown and white fur, explores the space, crawling across the floor with agile movements. The scene captures a moment of innocent delight, as the children and the ferret interact in a safe and supervised environment, the warm colors and textures adding to the sense of comfort and security.]"
},
{
"from": "gpt",
"value": "Normal. The ferret's movements in the video are slightly unsmooth."
}
] |
seed44_2289
|
videos/HRA_part1/2289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, donning a straw hat, a plaid shirt, and denim overalls, is shown exerting effort as he pulls on a rope tied to a stubborn old tractor stuck in a muddy farm field. The farmer's weathered hands grip the rope tightly, his face contorted with determination, while the lush greenery and distant rolling hills provide a picturesque rural setting. The scene highlights the farmer's resilience and hard work against the backdrop of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3022
|
videos/HRA_part1/3022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing swimming trunks and a cap, playfully interacts with a live rabbit at a backyard pool party. Surrounded by friends, he gently holds the rabbit, which remains calm, near the water's edge. The scene transitions to show the student swimming in the pool, while the rabbit sits safely on a towel nearby, being petted by another person. Throughout, the atmosphere is one of carefree enjoyment, with the student and his friends laughing and splashing in the water, and the rabbit seeming content in its temporary role as a poolside companion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1437
|
videos/HRA_part0/1437.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning rainbow trout, exhibiting vibrant hues of pink, silver, and green, gracefully swims in a clear, freshwater stream, surrounded by smooth stones and lush vegetation. The water gently cascades over rocks, creating a serene environment for the fish. Sunlight filters through the surface, highlighting the trout's shimmering scales and fins as it navigates the current with effortless ease. The trout occasionally opens its mouth, filtering oxygen from the water, demonstrating its natural survival skills in the pristine aquatic habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1705
|
videos/HRA_part2/1705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 casino, a distinguished chef, donning a traditional white chef's uniform with black stripes and a black necktie, walks with purpose. He carries a large, covered silver platter, its lid adorned with a golden handle. Behind him, a bustling kitchen reveals chefs in action, preparing exquisite dishes. The casino's opulent decor is visible through a glass partition, featuring patrons enjoying themselves at various gaming tables. The chef's confident stride and the casino's lively atmosphere create a captivating contrast between culinary expertise and the thrill of gambling in outer space.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is slightly distorted, and the hands are twisted."
}
] |
seed44_1460
|
videos/HRA_part1/1460.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful red fox, its fur thick and lustrous, stands at the edge of a steaming hot spring nestled in a lush, green forest. The water bubbles gently, releasing tendrils of mist that swirl around the fox, creating a mystical atmosphere. The fox dips its paw into the warm water, seeming to caress the surface, its eyes closed in apparent bliss. The steam rises from the hot spring, enveloping the fox in a soft, glowing haze, while the dense foliage and tall trees surrounding the clearing provide a serene and secluded setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2316
|
videos/HRA_part2/2316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, donning a gray turtleneck sweater and brown corduroy jacket, meticulously polishes silver cutlery using a white cloth, revealing a surprising domestic side. He sits at a large, cluttered wooden table, surrounded by an array of musical instruments, sheet music, and recording equipment, indicating his passion for music. The scene is set in a dimly lit room with vintage furniture, giving it a cozy, intimate atmosphere. The musician's focus is intense as he carefully cleans each piece of silverware, a task typically associated with waiters preparing for service, juxtaposed with his artistic profession.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1201
|
videos/HRA_part0/1201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a silver spacesuit, floats weightlessly in orbit around Earth, cradling a vibrant red electric guitar. His helmet visor reflects the stunning view of our planet, encapsulating the vastness of space. He gently caresses the guitar, playing it in zero gravity, as the blue and green hues of Earth contrast beautifully with the darkness of space behind him. The visual conveys a sense of tranquility and isolation, with the musician appearing lost in music amid the cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The musician in the video plays the guitar basically normally, with only slightly uncoordinated movements."
}
] |
seed46_2602
|
videos/HRA_part2/2602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European starling perches on a branch, its iridescent feathers shimmering in the sunlight, showcasing shades of green and purple against a blurred background of lush green foliage. The bird's beady eye and curved beak are sharply detailed, while its body language suggests alertness. Moments later, it takes flight, wings spread wide, revealing the full spectrum of its plumage's colors against the clear blue sky. The video concludes with a close-up of the starling's head, its distinctive features and vibrant feathers displayed prominently against a softly blurred green backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The video shows abnormal generation of the crow's wings."
}
] |
seed42_2848
|
videos/HRA_part0/2848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young boys, one in a red shirt and the other in a blue shirt, dance gleefully on a wooden floor inside a rustic building with log walls and wooden beams. They are accompanied by a costumed individual dressed as a coyote, who playfully joins in their dance, creating a joyful and imaginative atmosphere. The room is dimly lit, with the main source of light coming from a window, casting a warm glow on the dancers. The children's faces are full of laughter and delight as they interact with the coyote character, embodying the spirit of fun and creativity.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a boy in a red shirt and a person dressed as a hyena dancing, with movements that are not continuous and smooth, and there are abrupt changes."
}
] |
seed42_3181
|
videos/HRA_part0/3181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an underwater scene illuminated by natural light filtering through the water's surface, a school of vibrant, multicolored fish swim together in unison. The fish display a range of hues, including orange, yellow, and blue, with intricate patterns adorning their scales. They gracefully navigate the aquatic environment, surrounded by lush green seaweed gently swaying in the current. The detailed textures of the fish's bodies and the vivid colors of their surroundings create a captivating and serene underwater world.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show blue fish."
}
] |
seed42_3148
|
videos/HRA_part0/3148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer, donning a gray beanie, blue flannel shirt, and glasses, sits on a wooden chair in a sunlit barn. He cradles a large crochet hook and works on a vibrant, multicolored blanket, surrounded by rustic details like hay bales and farm tools. The scene highlights his unexpected hobby, showcasing the rich textures of the yarn against the rough wood of the barn. The warm, golden light illuminates his focused face and the intricate pattern emerging from his skilled hands, creating a serene and surprising contrast between traditional farming life and the art of crochet.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1143
|
videos/HRA_part1/1143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor in a cozy home, its soft, brown fur glistening under the warm indoor lighting. It moves with curiosity, exploring its surroundings with a playful spirit. The ferret wears a tiny red bow tie around its neck, adding a touch of whimsy to its adventurous journey. Its bright eyes and twitching nose showcase its alertness and interest in the environment, making for an endearing scene of a domesticated pet enjoying its day.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the snow leopard with extra claws, which is unrealistic."
}
] |
seed42_1174
|
videos/HRA_part0/1174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dark green shirt and khaki pants, is seen wiping a wet floor with a mop, leaving behind a clean, glistening surface. Beside him, a small, fluffy white dog, possibly a Bichon Frise, looks up with curious brown eyes. The janitor pauses, resting the mop against a wall covered with inspirational posters and a fire extinguisher, before bending down to interact with the dog, who eagerly responds with a wagging tail and playful energy, creating a heartwarming moment in an otherwise mundane setting.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm elongates, and the hand becomes deformed. It drags on, disappearing and reappearing. The hand finally disappears."
}
] |
seed42_1034
|
videos/HRA_part0/1034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic buzzard soars through the sky, its broad wings spread wide as it glides over a rugged, rocky landscape. The bird's sharp eyes scan the ground below, searching for prey among the boulders and sparse vegetation. Its feathers catch the sunlight, revealing shades of brown and white, while its powerful talons remain ready to strike at a moment's notice. The scene is set against a vast, open sky, emphasizing the buzzard's freedom and dominance over its territory.]"
},
{
"from": "gpt",
"value": "Bad. An extra wing, deformed head, missing claws, and twisted body."
}
] |
seed44_1794
|
videos/HRA_part1/1794.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a brown beret, red scarf, and green jacket, walks through a quaint, snow-covered village. The scene focuses on shops with wooden signs and red brick facades, reminiscent of a European winter market. Among the crowd, the artist carries a large painting wrapped in brown paper, attracting curious looks from passersby. In the background, a life-sized beaver statue stands outside a shop, adding a whimsical touch to the picturesque setting. The artist continues walking, blending into the festive atmosphere, with the beaver statue remaining a quirky focal point among the bustling shoppers.]"
},
{
"from": "gpt",
"value": "Bad. The face generation of pedestrians in the video is abnormal."
}
] |
seed46_1698
|
videos/HRA_part2/1698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nimble squirrel, brimming with energy, leaps from a moss-covered branch in a lush, vibrant forest. The scene is bathed in a soft, golden light filtering through the dense canopy above. The squirrel's movement is captured mid-jump, its body arched gracefully in the air, showcasing its agility and speed. Its bushy tail trails behind, adding to the dynamic feel of the action. The background is a tapestry of green foliage, dotted with various tree trunks, providing a rich, textured setting for the squirrel's acrobatics.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel in the video has incomplete facial features and limbs, a deformed body, is missing an ear, and has incomplete paws."
}
] |
seed44_1859
|
videos/HRA_part1/1859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer kneels on a grassy park area, attentively watching a squirrel. The squirrel, emboldened, leaps from the ground onto the officer's outstretched arm, seeking a nut held in the officer's other hand. The cop wears a standard police uniform, including a navy blue shirt, black tactical pants, and a badge, while the greenery and trees in the background set a peaceful outdoor scene. The squirrel's acrobatic leap and the officer's gentle interaction create a heartwarming moment in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel's jumping movements in the video are not smooth and continuous, showing some inconsistencies."
}
] |
seed46_1959
|
videos/HRA_part2/1959.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, wearing a gray t-shirt and black tactical pants, stands in a modern, open-plan kitchen with white cabinets and stainless steel appliances. He confidently flips a crepe on a large, round griddle, showcasing his culinary skills. The kitchen is part of a fire station, with a red fire truck visible through an arched doorway behind him. The firefighter, now donning an apron over his attire, carefully adds ingredients to the crepe, demonstrating his ability to balance the demands of firefighting with the precision required in cooking. The scene captures the unexpected yet harmonious blend of a firefighter's life-saving duties and his passion for creating delicious meals.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed46_2633
|
videos/HRA_part2/2633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and purple, hovers in a sunny garden, its wings a blur as it feeds from a red salvia flower. The bird moves to another scarlet blossom, its long beak piercing the flower to drink nectar, all set against a lush, green foliage backdrop. It then perches on a branch, preening its feathers with a bright pink beak, before resuming flight, hovering near a spray of orange and yellow flowers. Finally, the hummingbird returns to the red blooms, feeding once more with the sun illuminating its iridescent plumage, showcasing its agility and grace against a garden filled with various colorful flowers.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird mentioned in the caption hovering by the red flower and then returning to the red flower beside the black video does not appear."
}
] |
seed42_3053
|
videos/HRA_part0/3053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, kneels on a wooden floor next to a small mouse. The mouse scurries across the floor, its movements quick and agile, as the doctor watches with a mix of curiosity and concern. The scene is set in a brightly lit room with white walls, and the doctor's facial expression conveys a sense of focused attention on the tiny creature's actions.]"
},
{
"from": "gpt",
"value": "Normal. The rat's legs deform abnormally when it moves."
}
] |
seed46_1110
|
videos/HRA_part2/1110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, 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": "Bad. The man in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed42_1430
|
videos/HRA_part0/1430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic laboratory filled with advanced scientific equipment, an artist clad in a protective suit and goggles paints a life-sized depiction of a woolly mammoth on a large canvas. The mammoth is portrayed in its natural icy habitat, with the aurora borealis illuminating the sky, symbolizing the mysteries of dark matter. Meanwhile, in the background, a group of dedicated researchers in lab coats analyze data from sophisticated machines designed to explore the enigmatic properties of dark matter. The scene is completed by a large aquarium tank filled with clear water, where a swimmer performs synchronized swimming movements, creating mesmerizing patterns that echo the cosmic dance of dark matter in the universe.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_3203
|
videos/HRA_part0/3203.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weasel, with its slender body and brown fur, crawls through a dense forest underbrush. It moves stealthily, weaving between moss-covered logs and beneath a canopy of ferns and fallen branches. The weasel's sharp eyes scan the ground for prey as it navigates the intricate network of foliage, demonstrating its agility and adaptability in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The overall generation of the weasel in the video is deformed."
}
] |
seed46_144
|
videos/HRA_part2/144.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a casual striped shirt and beige shorts, walks leisurely on a sandy beach, with the ocean's edge just beyond his feet. He pauses for a moment, looking down thoughtfully, before continuing his stroll. The chef, now wearing a straw hat, is seen from behind, walking with purpose along the shoreline, with the vast sea stretching out behind him. In the final scene, he stands still, gazing out at the horizon, his posture conveying a sense of peace and reflection, all set against the serene backdrop of the beach and sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2548
|
videos/HRA_part0/2548.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, with its vast wingspan, glides effortlessly through crystal-clear waters, illuminated by rays of sunlight filtering down from the surface above. Its body, a stunning contrast of dark above and pale below, is adorned with unique spot patterns that serve as nature's fingerprint. Surrounding it, schools of shimmering fish scatter and regroup, reacting to the gentle giant's presence. In the distance, the silhouette of a coral reef provides a textured backdrop, highlighting the biodiversity of the underwater world. The manta ray's serene flight, captured in high definition, showcases the grace and power of these magnificent creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The mantas in the video move unsmoothly."
}
] |
seed44_1677
|
videos/HRA_part1/1677.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a yellow shirt and denim jeans is organizing a cluttered garage, illuminated by overhead lights. She sorts through items on a wooden table, her hands moving purposefully. Nearby, a brown dog sits attentively, watching her actions. Behind her, shelves filled with various objects and tools line the walls, indicating a space dedicated to storage and projects. The atmosphere is one of industriousness, as she focuses on tidying the space, creating order from chaos.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video is organizing and categorizing items on a wooden table, but the movements are not smooth and continuous, with abrupt changes."
}
] |
seed44_119
|
videos/HRA_part1/119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, two children, a boy and a girl, are seen gently caressing a juvenile antelope in a lush, green meadow. The boy, wearing a blue shirt and shorts, leans over to pet the animal with a tender smile, while the girl, dressed in a yellow dress, watches adoringly, her hands clasped together. Moments later, the girl takes her turn, stroking the antelope's back as it stands calmly, accepting the affection. The boy looks on with a joyful expression, his right hand raised in excitement. The idyllic setting, complete with verdant grass and blue skies, adds to the peaceful and endearing nature of the interaction between the children and the young antelope.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1537
|
videos/HRA_part0/1537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene and lush environment, a graceful gazelle is seen gently caressing the face of another smaller gazelle, possibly its offspring, creating a tender and intimate moment between them. The scene is set in a verdant savanna landscape, with tall grass swaying softly in the breeze and trees scattered in the background, providing a peaceful and natural setting for this heartwarming interaction. The larger gazelle, with its delicate features and caring demeanor, conveys a sense of protection and affection toward the younger one, emphasizing the bond between them.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1566
|
videos/HRA_part0/1566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, with a ferret perched on his shoulder, floats weightlessly in a vast cosmic pool that mirrors Jupiter's Great Red Spot. Dressed in a dark wetsuit and goggles, he somersaults gracefully through the water, the ferret securely nestled and seemingly unfazed. The swirling red and white clouds of Jupiter envelop the scene, creating a surreal and captivating contrast to the serene swimming motion. Throughout, the ferret remains a constant presence, its curious gaze following the actor's every move in this otherworldly aquatic environment.]"
},
{
"from": "gpt",
"value": "Bad. The hand of the person and the head of the ferret in the video have generation issues, and there appears to be two left hands on the person in the middle frames."
}
] |
seed46_1420
|
videos/HRA_part2/1420.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a bright, cloudless sky, a single dromedary camel leaps gracefully over a fallen tree trunk. Its tan fur contrasts starkly with the pale sand, and its large, expressive eyes are fixed ahead. The camel, wearing a simple brown strap across its torso, lands softly on the other side of the obstacle, continuing its journey across the dunes with a sense of purpose and freedom. The scene captures the unexpected agility of this desert dweller against the serene, unbroken landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2697
|
videos/HRA_part0/2697.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique and whimsical scene, a cheerful nurse, clad in a traditional white uniform and cap, finds herself frolicking in a shallow, clear water body situated amidst vast temperate grasslands. The lush, green landscape stretches far into the horizon, dotted with swaying grasses and a few scattered trees. The nurse, enjoying a spontaneous moment of leisure, splashes water joyfully, her white attire contrasting beautifully against the natural setting. The sunlight filters through partly cloudy skies, casting a warm glow over the entire scene, highlighting the serenity of the temperate grasslands and the nurse's playful spirit.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_1122
|
videos/HRA_part1/1122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white button-down shirt, kneels in a lush green meadow. He gently caresses a meerkat standing on its hind legs, which is perched on a small wooden table covered with a white cloth and decorated with a single red rose in a vase. The waiter's face is filled with a warm smile, his eyes softly gazing at the meerkat as he tenderly strokes its back with his right hand. The scene is peaceful and heartwarming, with the sun casting a golden glow over the meadow and the meerkat's curious expression adding to the charm of the moment.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand generation is problematic, and the meerkat's head and forelimbs suddenly change direction in the middle frames."
}
] |
seed46_3098
|
videos/HRA_part2/3098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 forest environment, two individuals wearing khaki safari outfits are seen running alongside a chimpanzee, engaged in playful interaction. The scene is vibrant and full of life, with the humans and the chimpanzee moving together in harmony. They dash across a dirt path, surrounded by dense vegetation, as the chimpanzee exhibits its natural agility and strength. The trio's energetic run is captured in high detail, highlighting the dynamic movement and the unique bond between humans and this primate in their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows a person running alongside a chimpanzee, but the movements are not very smooth and continuous, with noticeable abrupt changes."
}
] |
seed42_2725
|
videos/HRA_part0/2725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 urban alleyway, a middle-aged man wearing a worn-out brown jacket and blue jeans leans against a brick wall. He cradles a small rat in his hands, gently stroking it, while standing next to large, green dumpsters. The rat nestles in his palm, seemingly tamed and cared for, as the man looks down at it with a warm smile. Behind him, the bustling city streets are visible, with passersby and traffic lights, creating a contrast between the tenderness of the moment and the harshness of the urban environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2123
|
videos/HRA_part2/2123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid orange kite with intricate black patterns soars majestically against a clear blue sky, its long white tail streaming gracefully behind it. The kite, resembling a dynamic bird in flight, is seen from various angles, showcasing its detailed design and the fluidity of its movements. Against the serene backdrop of fluffy white clouds and the vast horizon, the kite seems to dance with the wind, captivating viewers with its aerial ballet. The interplay of sunlight and shadow enhances the kite's vibrant colors, making it a striking focal point against the peaceful sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_193
|
videos/HRA_part2/193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a crisp white shirt, black vest, and tie, is seen in an upscale restaurant, standing on a chair to check a smoke detector. The room is modern and stylish, with wooden floors, a white ceiling, and large windows. The waiter, displaying a conscientious attitude towards safety, carefully inspects the device. The scene conveys a sense of professionalism and attention to detail, as the waiter ensures the restaurant is equipped with functional safety equipment. The establishment is empty except for the waiter, emphasizing the routine nature of the task. The waiter's attire and the restaurant's decor suggest a high-end dining environment, where safety measures are taken seriously.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1037
|
videos/HRA_part2/1037.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, complete with a stethoscope around his neck, dons a brown jacket, dark trousers, and black boots as he shovels snow from a walkway. Snowflakes gently fall from a gray sky, settling on the green pine tree in the background. The doctor, wearing glasses and a wedding ring, pauses to wipe his brow, revealing his determination. He continues to clear the snow, demonstrating his commitment to his duties despite the weather. Throughout the scene, the doctor's attire remains unchanged, emphasizing his professional identity even in this domestic task.]"
},
{
"from": "gpt",
"value": "Bad. The glasses worn by the character in the video are distorted, and in the middle frame, the character's arm is suddenly shorter."
}
] |
seed42_2888
|
videos/HRA_part0/2888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 theater, the spotlight reveals two young children, a boy and a girl, both dressed in casual attire, sitting on a red velvet couch. The boy, wearing a blue T-shirt and khaki shorts, looks at the girl with a smile, his hand gently caressing her arm. The girl, dressed in a yellow sundress, returns his affectionate gesture with a warm look and a tender touch to his cheek, all against the backdrop of a classic theater setting with plush red curtains and ornate decorations. The scene captures a moment of innocent connection between the two children, emphasizing the tenderness of their interaction within the grandeur of the theater environment.]"
},
{
"from": "gpt",
"value": "Bad. In the video, you can see the boy stroking the girl's arm, but the action is very discontinuous and choppy, with sudden changes."
}
] |
seed42_2163
|
videos/HRA_part0/2163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical wet forest, twin toddlers wearing colorful, waterproof overalls and wide-brimmed hats are crawling on a natural wooden log bridge, exploring their surroundings with wide-eyed curiosity. They crawl through a dense thicket of vibrant green foliage, their clothing bright against the earthy tones of the forest floor. The babies continue their adventure, crawling over a carpet of moss and fallen leaves, undeterred by the rugged terrain. Their journey concludes as they crawl towards a shaft of sunlight filtering through the dense canopy above, illuminating their path in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_210
|
videos/HRA_part2/210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, solitary rhinoceros is seen swimming in a natural body of water, surrounded by lush green vegetation. Its body is partially submerged, showing off its powerful swimming capabilities as it moves through the water. The rhino's head remains above the surface, its eyes focused ahead, and its mouth occasionally opening to breathe. The water gently laps at its thick skin, creating ripples that extend outward. In the background, tall trees and dense foliage provide a contrast to the open water where the rhinoceros swims.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2749
|
videos/HRA_part1/2749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown pelican with a large, distinctive orange pouch flies low over the surface of a calm bay, its wings spread wide against the vivid blue sky. It gracefully swoops down, diving into the water to catch fish, its body momentarily submerged before it resurfaces, triumphant. The pelican then floats on the water, preening its feathers with a meticulous beak, showcasing its survival skills in the serene coastal environment. Against the backdrop of a clear sky and calm waters, the pelican's flight and feeding habits are highlighted, emphasizing its unique features and behaviors in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The pelican's wings in the video are twisted."
}
] |
seed46_2119
|
videos/HRA_part2/2119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, a firefighter clad in a specialized silver suit and equipped with an advanced helmet wipes down a high-tech control panel with a cloth, ensuring cleanliness in zero gravity. The background showcases intricate machinery and complex equipment typical of a space exploration module, with the firefighter's actions highlighting the routine maintenance tasks necessary for maintaining operational integrity in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm and hand are twisted in the video."
}
] |
seed46_1194
|
videos/HRA_part2/1194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, distinguished by his uniform consisting of a navy blue shirt with badges, dark pants, and black shoes, vacuums the carpet in a modest living room. The room features a small brown couch, a glass coffee table, and a beige recliner, with sunlight streaming through the window, highlighting dust particles in the air. The officer, displaying a serious demeanor, methodically maneuvers the vacuum cleaner across the carpeted floor, revealing his commitment to household chores despite his profession. The domestic scene contrasts sharply with his authoritative attire, emphasizing the duality of his role as both protector and provider.]"
},
{
"from": "gpt",
"value": "Normal. The character's arm is twisted, the hand is twisted, the face is distorted, and the vacuum cleaner in the hand is also twisted."
}
] |
seed42_2650
|
videos/HRA_part0/2650.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sophisticated office setting, a professional lawyer, dressed in a navy suit, white shirt, and striped tie, sits at a cluttered desk adorned with legal documents and a laptop. He pauses from his work to look up, captivated by a stunning holographic display of an exoplanet orbiting its star, projected from his device. The lawyer then wipes away the hologram with a sweeping hand gesture, returning his attention to the challenging legal briefs spread out before him, highlighting the contrast between his daily duties and the captivating world of astronomical discoveries.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1537
|
videos/HRA_part1/1537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene and lush environment, a graceful gazelle is seen gently caressing the face of another smaller gazelle, possibly its offspring, creating a tender and intimate moment between them. The scene is set in a verdant savanna landscape, with tall grass swaying softly in the breeze and trees scattered in the background, providing a peaceful and natural setting for this heartwarming interaction. The larger gazelle, with its delicate features and caring demeanor, conveys a sense of protection and affection toward the younger one, emphasizing the bond between them.]"
},
{
"from": "gpt",
"value": "Normal. The antelope in the video uses its mouth to touch a smaller antelope, but the movement is very unsmooth and uncoordinated."
}
] |
seed46_2983
|
videos/HRA_part2/2983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a hyena leaps gracefully over pipes and machinery in an industrial oil refinery, backlit by the golden glow of sunset. The animal, wild and untamed, seems momentarily suspended in mid-air above the cold, metallic structures. Its spotted coat contrasts starkly with the urban landscape, highlighting the unusual and unexpected nature of this scene. Despite the hard edges of the refinery, there's a sense of fluid motion as the hyena propels itself forward, embodying a blend of natural agility and industrial might.]"
},
{
"from": "gpt",
"value": "Bad. The hyena's movements in the video are not smooth."
}
] |
seed44_2904
|
videos/HRA_part1/2904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bull moose, antlers wide and impressive, runs through a lush, green meadow under a clear blue sky, with a distant mountain range visible on the horizon. Its powerful legs propel it forward in a graceful gallop, kicking up small clouds of dust from the dry earth beneath its hooves. The moose's coat is a deep brown, nearly black, and its large body ripples with muscles as it bounds across the landscape, the embodiment of wild strength and freedom. In the background, tall trees frame the edges of the clearing, their leaves whispering softly in the breeze, while birds take flight, startled by the majestic creature's sudden movement.]"
},
{
"from": "gpt",
"value": "Normal. The moose's head and limbs are deformed in the video, with three front legs appearing in some middle frames, and the limbs suddenly disappearing or reappearing."
}
] |
seed44_1125
|
videos/HRA_part1/1125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a dark suit, shirt, and tie, walks through a stunning geothermal field, surrounded by steaming geysers and colorful mineral deposits. The scene begins with the lawyer walking towards a large, erupting geyser, the water shooting high into the air against the dramatic landscape. Next, he pauses to observe another geyser, the steam rising from it creating a mystical atmosphere. Then, he continues walking, passing by a series of smaller geysers, their bubbling waters and vibrant colors contrasting sharply with his formal attire. Lastly, the lawyer is seen walking away from the camera, the vast geothermal field stretching out behind him, the geysers and steam adding an otherworldly touch to the professional setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1949
|
videos/HRA_part2/1949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, appearing to be in his thirties, with short brown hair and wearing a grey t-shirt and black pants, is shown in a close-up shot. He exhibits signs of severe trembling, with beads of sweat visible on his forehead, indicating intense physical or emotional distress. The shaky movement is the focal point, capturing the viewer's attention and conveying a sense of urgency and concern. The background is blurred, keeping the emphasis solely on the man's shaking figure, which fills the screen, making his distress the central theme of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_11
|
videos/HRA_part0/11.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rocky terrain below. It circles gracefully, riding the thermals, with a backdrop of lush green mountains and a distant waterfall. Its piercing yellow eyes scan the landscape, searching for prey, while its sharp talons remain ready to strike. The eagle's brown and white plumage glistens in the sunlight, a symbol of freedom and strength against the stunning natural scenery.]"
},
{
"from": "gpt",
"value": "Bad. The head of the bald eagle was not fully formed, and its claws were also deformed."
}
] |
seed46_3049
|
videos/HRA_part2/3049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a blue checkered shirt and black pants, meticulously assembles a complex piece of furniture in a modern workshop, illuminated by bright overhead lights. His tools, including a screwdriver and measuring tape, are laid out on a clean, organized workbench. Close-up shots reveal his focused expression and skilled hands as he aligns and tightens screws, demonstrating precision and expertise. The space is filled with the ambient sounds of machinery and the occasional beep of electronic devices, creating a backdrop of industrious activity. Throughout the process, the engineer maintains a calm demeanor, pausing occasionally to consult a blueprint or adjust his glasses, embodying the essence of craftsmanship and dedication.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the engineer aiming and tightening the screw, but the movements are not continuous and smooth, and there is a lack of coordination."
}
] |
seed44_1095
|
videos/HRA_part1/1095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 through a clear blue sky, its sleek silhouette framed against the horizon. It dives sharply, wings tight to its body, chasing an unseen prey across the vast expanse. Its sharp eyes, focused and intense, scan the terrain below for any hint of movement. The bird then lands on a branch, its feathers ruffled by the wind, revealing a striking pattern of brown and white. It sits still, perched regally, surveying its domain with a fierce gaze, a true ruler of the skies.]"
},
{
"from": "gpt",
"value": "Bad. The wings suddenly detached from the body during landing."
}
] |
seed46_3209
|
videos/HRA_part2/3209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red t-shirt and black shorts is depicted running alongside a kangaroo on a dusty trail surrounded by lush vegetation, both appearing energetic and engaged in the activity. They run together on a dirt path amidst dense greenery, the kangaroo bounding effortlessly beside the man, who maintains a steady pace. The scene captures the unique companionship between the man, dressed casually in a red top and dark shorts, and the kangaroo, as they traverse the natural environment together. The duo continues their run through the vibrant landscape, the kangaroo's powerful legs propelling it forward in sync with the man's strides, highlighting their shared rhythm and connection amidst the verdant scenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2753
|
videos/HRA_part2/2753.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 stark juxtaposition, a majestic brown horse gallops across a lush green meadow under a vibrant blue sky speckled with white clouds, the rolling hills framing the scene beautifully. Meanwhile, in the distance, smokestacks from sprawling factories loom, emitting plumes of gray smoke into the air. On the ground near the horse, a small creature crawls, its perspective offering a unique view of the vast landscape, highlighting the contrast between nature's grace and industrial might.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1873
|
videos/HRA_part0/1873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by skyscrapers, a young female cashier, dressed in a black apron over a white shirt and black pants, stands behind a checkout counter in a modern, glass-walled convenience store. She gently caresses the edge of the counter with her right hand, her eyes softly closed, as if cherishing a moment of peace amidst the urban rush. The city's towering buildings loom outside the large windows behind her, contrasting with her intimate gesture.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1256
|
videos/HRA_part2/1256.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, a writer, presumably the main character, runs along a sandy path at a luxurious resort, set against a backdrop of lush greenery and palm trees. Dressed in a gray tank top, black shorts, and black running shoes, he wears a determined expression as he focuses ahead. Accompanying him is a black jackal, resembling a wild dog, which runs alongside him, adding a sense of companionship and adventure to the narrative. The resort's opulent buildings and facilities are visible in the background, highlighting the contrast between nature and luxury.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not fluid, and the limbs are uncoordinated."
}
] |
seed44_1959
|
videos/HRA_part1/1959.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, wearing a gray t-shirt and black tactical pants, stands in a modern, open-plan kitchen with white cabinets and stainless steel appliances. He confidently flips a crepe on a large, round griddle, showcasing his culinary skills. The kitchen is part of a fire station, with a red fire truck visible through an arched doorway behind him. The firefighter, now donning an apron over his attire, carefully adds ingredients to the crepe, demonstrating his ability to balance the demands of firefighting with the precision required in cooking. The scene captures the unexpected yet harmonious blend of a firefighter's life-saving duties and his passion for creating delicious meals.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2211
|
videos/HRA_part0/2211.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 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, 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": "Normal. The actions are not continuous, but the caressing motion can be seen."
}
] |
seed42_2655
|
videos/HRA_part0/2655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, wearing a casual button-down shirt and khaki pants, is seen sketching mall blueprints on a large, clear desk, surrounded by architectural models and technical drawings. Moments later, the scene shifts to a vibrant mall interior, where the same engineer is seen interacting with a diverse group of shoppers, pointing out design features and technological advancements. Finally, the video captures the engineer enjoying a well-deserved break by swimming leisurely in a modern, glass-enclosed pool, located on the mall's rooftop, showcasing a harmonious blend of work and relaxation.]"
},
{
"from": "gpt",
"value": "Normal. Missing the scene of the engineer pointing out design features and technological advancements to a diverse group of shoppers in the mall."
}
] |
seed42_175
|
videos/HRA_part0/175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 medical facility, a man wearing a clean, white lab coat and blue surgical mask diligently wipes down advanced, high-tech equipment with precision and care. The room is illuminated by soft, ambient lighting, highlighting the sterile environment. The man's focused gaze and meticulous movements convey a sense of professionalism and dedication to maintaining the cleanliness of the facility. Around him, the walls are lined with monitors and medical devices, emphasizing the cutting-edge technology used in this extraterrestrial healthcare setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2086
|
videos/HRA_part2/2086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric engineer, clad in a green jumpsuit and safety helmet, finds himself in an unexpected scenario amidst the industrial backdrop of a power plant. Surrounded by towering turbines and complex machinery, he encounters a curious lizard, its vibrant scales contrasting starkly with the metallic environment. Inspired by this unusual meeting, the engineer begins to dance, his movements fluid and joyful, as if the rhythms of the machinery have become his own. The lizard watches, almost as if entranced, as the engineer twirls and leaps, creating a surreal scene where the boundaries between human, nature, and industry blur harmoniously.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, twisted hands, and twisted legs, with the lizard's body also twisted."
}
] |
seed46_2329
|
videos/HRA_part2/2329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, dressed in a yellow vest and hard hat, stands in awe, experiencing time dilation as he watches a kangaroo jump in slow motion against a backdrop of a bustling city skyline at sunset. The kangaroo, mid-leap, appears weightless and graceful, its powerful hind legs propelling it forward. The worker's expression reflects a mix of surprise and fascination, as if witnessing a surreal moment where the laws of physics seem to bend. The scene is bathed in golden hour light, adding to the dreamlike quality of the encounter.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1108
|
videos/HRA_part2/1108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic orange Bengal tiger with black stripes swims gracefully in a large, natural pond surrounded by lush green vegetation, showcasing its strength and agility in the water. The tiger, with piercing amber eyes and a powerful body, propels itself through the clear blue water with effortless strokes, its thick tail acting as a rudder. Sunlight filters through the dense foliage above, casting dappled light on the tiger's wet fur, highlighting its muscular physique and the water droplets clinging to its coat. The serene environment, complete with the sounds of nature and the gentle lapping of water against the shore, creates a captivating scene of wild beauty.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.