video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2841
|
videos/HRA_part1/2841.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a red flannel shirt and denim overalls, dances joyously in a lush green field, while a curious deer watches from a distance, its ears perked up, intrigued by the unusual sight. The farmer's movements are lively and free, embodying a sense of unbridled happiness, as the deer remains frozen in place, observing the dance with wide, expressive eyes. The scene is set against a backdrop of rolling hills and a clear blue sky, creating a picturesque rural landscape that complements the harmonious interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face and hands are distorted in the video, and the deer's head is abnormally generated."
}
] |
seed44_2752
|
videos/HRA_part1/2752.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two small children wearing vibrant yellow raincoats and boots venture into a lush, green forest on a misty day. They walk side by side on a narrow dirt path, surrounded by towering trees and a dense undergrowth of ferns and moss. Suddenly, a curious red fox emerges from the foliage, its bright orange fur contrasting against the verdant backdrop. The fox pauses, looking directly at the children with intelligent eyes, as if sharing a silent moment of connection. The children, undeterred and full of wonder, continue their journey, leaving the fox to watch them from the safety of the woods, creating a heartwarming and enchanting moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the child's hand is missing, the feet are deformed, and the red fox's facial features are blurry."
}
] |
seed42_172
|
videos/HRA_part0/172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, multicolored kite soars majestically against a clear blue sky, its intricate geometric patterns catching the sunlight. Attached to it is a long string held tightly by a child wearing a yellow t-shirt, blue jeans, and a wide-brimmed hat, standing on a lush green hill dotted with wildflowers. The child's face is lifted towards the sky, eyes full of wonder and joy, while the wind gently tousles their hair. Around them, a panoramic view of rolling hills and distant mountains provides a stunning backdrop to this scene of youthful delight and freedom.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1244
|
videos/HRA_part2/1244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense, misty rainforest, a sleek black panther emerges from the undergrowth, its coat glistening with moisture. It pauses by a moss-covered tree trunk, the camera capturing every detail in high-definition clarity. The panther begins to groom itself, using its rough tongue to meticulously clean its fur, wiping away water droplets and debris, all against the lush, verdant backdrop of the rainforest environment. The focus is on the panther's self-cleaning behavior, highlighting the textures of its fur and the intricate patterns of the surrounding foliage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2114
|
videos/HRA_part0/2114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its distinctive black-and-white plumage gleaming under the sunlight filtering through the leaves of a large tree. The bird's eyes are sharp and alert, its beak curved and ready to snatch any unsuspecting prey. Behind it, the lush green foliage of the forest provides a stark contrast to its striking feathers, while the soft chirping of other birds creates a peaceful atmosphere. Suddenly, the magpie takes flight, its wings beating gracefully as it soars through the air, leaving a trail of black and white behind it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2975
|
videos/HRA_part0/2975.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a NASA jumpsuit walks alongside a curious, friendly bear in a space helmet, both exploring a futuristic space station designed for tourism. The station, filled with advanced technology and panoramic views of the cosmos, offers a unique blend of engineering marvels and extraterrestrial wildlife encounters. The engineer, equipped with tools and a tablet, ensures the safety and functionality of the space station's systems, while the bear, adorned with a custom spacesuit and helmet, roams freely, interacting with visitors and adding an unexpected touch of whimsy to the space tourism experience. Together, they navigate the corridors and observation decks, creating an unforgettable scene of human and animal adaptation to life beyond Earth's atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1096
|
videos/HRA_part0/1096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 reality TV set, an antelope, wearing a small golden bell around its neck, stands calmly against a backdrop of stars and galaxies. The animal is gently caressed by a human figure dressed in a spacesuit, conveying a sense of comfort and companionship in the vastness of space. The astronaut's gloved hand softly touches the antelope's face, while the creature looks on serenely, the golden bell shining under the starlight, creating a surreal and touching moment in an extraterrestrial environment.]"
},
{
"from": "gpt",
"value": "Bad. The stroking action is uncoordinated."
}
] |
seed42_1269
|
videos/HRA_part0/1269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara slowly crawls through a lush, green meadow dotted with small shrubs and trees, its round ears and alert eyes scanning the environment. It moves deliberately, showcasing its unique gait, as it navigates the vibrant grassland under a bright, sunny sky. The rodent's textured fur glistens in the sunlight, highlighting its wet, semi-aquatic nature, as it continues its unhurried crawl across the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1827
|
videos/HRA_part1/1827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, adorned in a stylish yellow dress, gracefully caresses the powdery sand of an idyllic beach resort as the turquoise sea gently laps at the shore. Her eyes closed, she savors the serene moment, feeling the warmth of the sand between her toes. The peaceful atmosphere is punctuated by the rhythmic sounds of the ocean, the soft rustle of palm fronds, and the distant calls of seagulls, all contributing to a scene of blissful tranquility. The vibrant colors of her attire contrast beautifully with the natural hues of the beach, creating a captivating visual harmony.]"
},
{
"from": "gpt",
"value": "Normal. The woman's limbs in the video are generated abnormally."
}
] |
seed44_2523
|
videos/HRA_part1/2523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, complete with a tailored gray suit, white shirt, and red tie, takes an unconventional break from his legal duties to clean windows on a busy city street. Holding a squeegee in one hand and a spray bottle in the other, he expertly removes smudges from the glass, all while maintaining a professional demeanor. Passersby, including a group of schoolchildren and a mother with a stroller, observe the unusual sight with amusement. The lawyer's briefcase rests nearby, a reminder of his typical occupation, as he focuses on the task at hand with surprising skill and dedication.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1257
|
videos/HRA_part0/1257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a red jacket, gray beanie, and blue jeans, hikes through a dense forest with sunlight filtering through the trees, casting dappled shadows on the trail. They pause to observe a small stream, the water gently flowing over rocks, before continuing on the path, notebook in hand, ready to capture inspiration from nature's beauty. The scene focuses on the writer's contemplative gaze, the vibrant colors of autumn leaves surrounding them, and the peaceful atmosphere of the woodland setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1080
|
videos/HRA_part0/1080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna dotted with small shrubs and trees, a large herd of buffalo gathers. Suddenly, one buffalo, distinct with its massive horns and dark brown fur, begins to move rhythmically, almost dancing, against the backdrop of the herd and the distant, hazy mountains. Its movements are energetic yet controlled, as if performing a ritualistic dance under the watchful eye of the herd. The camera focuses on this unique spectacle, capturing the buffalo's dance in the midst of its natural habitat, surrounded by the rest of the herd and the serene beauty of the African landscape.]"
},
{
"from": "gpt",
"value": "Normal. The buffalo's head and legs appear deformed."
}
] |
seed46_2346
|
videos/HRA_part2/2346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a plush koala toy, complete with realistic details and a charming face, comes to life against a green, leafy background reminiscent of eucalyptus. This adorable koala, clad in miniature jeans and a checkered shirt, begins to dance gracefully, its movements synchronized with an upbeat melody. Its paws sway side to side, and it gently bounces in place, capturing the essence of joy and playfulness. The dancing koala, set against the lush foliage, creates a delightful and enchanting moment, perfect for evoking smiles and happiness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1006
|
videos/HRA_part1/1006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a police officer, clad in a navy uniform with a badge, cap, and sunglasses, interacts with a large brown teddy bear outside a row of shops, which include a bakery, a bookstore, and a clothing store, each with colorful awnings and signs. The officer gently lifts the stuffed animal, which is nearly as big as him, into the air. Nearby, a group of children watch in awe, sitting cross-legged on the sidewalk, their faces alight with wonder and joy. The officer then crawls on his hands and knees next to the bear, playfully engaging with the delighted kids, creating a heartwarming moment of connection between law enforcement and the community, all against the backdrop of a bustling street lined with charming stores.]"
},
{
"from": "gpt",
"value": "Good. Basically no obvious problems."
}
] |
seed42_2699
|
videos/HRA_part0/2699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 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 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 video generated an extra brown bear."
}
] |
seed44_2424
|
videos/HRA_part1/2424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest and tie, crouches low, engaging in a playful crawl across a textured wooden floor. Unexpectedly, a squirrel appears, its bushy tail bouncing, as it curiously crawls alongside the waiter. The two crawl in unison, the squirrel mirroring the waiter's movements, against a backdrop that subtly hints at a 'Quantum Leap' style time warp, indicated by a faint, swirling visual effect. This surreal moment captures the unusual pairing of the crawling waiter and squirrel, blending elements of fantasy and reality.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change, the waiter lacks crawling movements, almost remaining stationary."
}
] |
seed44_1465
|
videos/HRA_part1/1465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, bundled in a green winter coat, brown boots, and a colorful scarf, energetically shovels snow from the school's front steps. Snowflakes gently fall from a cloudy gray sky, creating a peaceful atmosphere. The teacher, wearing a warm hat and gloves, clears a path on the steps, revealing the red brick beneath. They pause for a moment, holding the shovel in mid-air, their breath visible in the cold air. The teacher continues shoveling, making progress against the accumulating snow, as the school building stands tall in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2277
|
videos/HRA_part1/2277.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow safety vest, blue jeans, and a gray shirt, sits on a wooden beam high above the city skyline, nodding thoughtfully as he listens to his supervisor's instructions. His hard hat is resting beside him, and he holds a water bottle in one hand, pausing from his labor under the clear blue sky. The bustling cityscape, complete with skyscrapers and moving cars, provides a dynamic backdrop to his momentary break. His facial expression conveys attentiveness and understanding, emphasizing the importance of communication in his line of work.]"
},
{
"from": "gpt",
"value": "Normal. The worker's hand shows a deformed mutation."
}
] |
seed46_2668
|
videos/HRA_part2/2668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a white shirt and black vest, crawls across a vibrant boardwalk, his face a mask of determination. Wooden planks stretch out beneath him, dotted with colorful umbrellas and lively beachgoers. The scene is bathed in warm sunlight, casting dramatic shadows from the boardwalk's railings and nearby beachside cafes. The waiter's unusual mode of transport draws curious glances from passersby, creating a surreal and engaging moment against the backdrop of a bustling seaside promenade.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_2843
|
videos/HRA_part0/2843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A uniformed police officer, clad in a navy-blue jacket adorned with badges and a matching hat, diligently shovels snow from the sidewalk in front of a modest, red-brick building. The scene is set in the early morning hours, as indicated by the dimly lit street and the absence of pedestrians. Snowflakes continue to fall gently from the gray sky, accumulating on the officer's shoulders and the brim of his hat. Despite the cold, he works with determination, clearing a path for safe passage, embodying the spirit of service and community. The shovel he uses is standard issue, with a sturdy wooden handle and a metal blade, further emphasizing the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2478
|
videos/HRA_part0/2478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, wearing a black t-shirt, showcases a ferret jumping from his right shoulder onto his left arm. Set against a dark grey background, the scene highlights the ferret's agility and the actor's engagement with the small animal. The actor's facial expression conveys amusement and surprise, emphasizing the playful interaction between man and pet. Throughout the sequence, the ferret performs several jumps, each time landing gracefully on different parts of the actor's body, while he remains fully engaged and attentive, his black t-shirt providing a stark contrast against the neutral backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The actor's hands, the ferret's head, and limbs are generated abnormally, and the ferret's tail and paws suddenly disappear or appear in the middle frames."
}
] |
seed42_1975
|
videos/HRA_part0/1975.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 handsome waiter, dressed in a white shirt, black vest, and striped tie, walks through a bustling market, surrounded by vibrant stalls selling fruits, vegetables, and spices. The scene captures him navigating the lively crowd, his confident stride and focused gaze highlighting his purposeful movement. Market vendors and customers are visible in the background, adding to the dynamic atmosphere of the location. The waiter's attire contrasts with the colorful market environment, emphasizing his role as he moves through this energetic space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1394
|
videos/HRA_part1/1394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, donning a classic black vest, crisp white shirt, and black tie, diligently cleans the expansive windows of a charming bistro. The scene is set against a vibrant city backdrop, with the golden hour casting a warm glow. He meticulously wipes the glass, revealing the bustling café interior, filled with patrons enjoying their meals. The waiter's attention to detail is evident as he ensures every corner of the window is spotless, enhancing the inviting atmosphere of the establishment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1857
|
videos/HRA_part1/1857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, named Bingo, energetically jumps onto a wooden platform in a spacious outdoor enclosure, surrounded by lush greenery and trees. Dressed in a tiny red jacket, Bingo displays his strength and agility, with the sunlight filtering through the leaves highlighting his movement. He then leaps from the platform onto a thick branch, showcasing his natural climbing skills. Next, he swings from a hanging tire, his joyful expressions and animated body language capturing the essence of playfulness. Finally, he bounds across the enclosure, his powerful legs propelling him forward, as he explores his environment with boundless energy and curiosity.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_28
|
videos/HRA_part0/28.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush forest setting filled with tall, verdant trees and patches of sunlight filtering through the leaves, a mongoose is gently caressing a smaller mongoose, possibly its offspring, with its nose. The larger mongoose, with its sleek brown fur and attentive eyes, exhibits tenderness and care, creating a heartwarming scene of familial affection in the midst of the natural environment.]"
},
{
"from": "gpt",
"value": "Bad. The mongoose's head is twisted, and its body is contorted."
}
] |
seed44_1169
|
videos/HRA_part1/1169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron, with its signature blue-gray feathers and long, slender legs, stands majestically in the shallow waters of a serene lake. Its sharp, yellow eyes scan the water's surface as it patiently awaits its next meal. Suddenly, the heron strikes with lightning speed, its sharp beak piercing the water to catch a small fish. As it emerges victorious, the heron proudly displays its catch before swallowing it whole. All the while, the calm surroundings of the lake provide a peaceful backdrop, with gentle ripples on the water and the distant silhouette of trees completing the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3118
|
videos/HRA_part0/3118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red-tailed hawk soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rugged terrain below. It circles effortlessly, riding the thermals with grace, its sharp eyes scanning the ground for prey. The hawk's brown and white striped feathers shimmer in the sunlight, and its piercing yellow eyes and sharp curved beak are sharply defined. In the background, rolling hills and distant mountains provide a stunning natural landscape, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3066
|
videos/HRA_part0/3066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vibrant scene, a group of people wearing colorful swimsuits swim in a large, clear pool, with a majestic giraffe standing nearby, observing the swimmers with curiosity. Overhead, a futuristic Photon sail floats gracefully in the sky, reflecting sunlight and casting dynamic shadows onto the water below. The people interact with the giraffe gently, feeding it leaves, while the sail continues its serene journey across the sky, creating a harmonious blend of nature and advanced technology.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2907
|
videos/HRA_part2/2907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male baker with short brown hair and glasses, wearing a brown apron over a white shirt, expertly folds ingredients together in a large stainless steel bowl using a wooden spoon. The kitchen is modern and minimalist, featuring sleek silver appliances and countertops. He then spreads batter evenly into a round cake pan, which he places into a preheated oven. As he waits, he wipes his hands on his apron and checks the temperature with a digital thermometer, ensuring the perfect bake. Finally, he removes the golden-brown cake from the oven, its surface smooth and evenly risen, ready for decoration.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video is basically normal, but there is slight uncoordination in his movements."
}
] |
seed46_1894
|
videos/HRA_part2/1894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a navy suit, white shirt, and striped tie, races through a lush green forest, holding a koala in one arm. The koala, clinging tightly, wears a tiny barrister's wig and round spectacles, adding a whimsical touch to the scene. They run past tall trees, ferns, and flowers, with the lawyer's facial expressions alternating between determination and a smile, highlighting the unusual yet playful nature of the chase. The vibrant forest setting, complete with sunlight filtering through the leaves, enhances the dynamic and surreal atmosphere of the scenario.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's running motion in the video is not smooth and continuous, with abrupt changes in movement."
}
] |
seed44_1728
|
videos/HRA_part1/1728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female barista, wearing a gray apron over a black shirt, completes a transaction with a customer at a contemporary coffee shop. The cafe features wooden floors, a glass cooler, and a large digital menu display. After the sale, she turns to prepare a coffee beverage, carefully measuring ingredients into a French press. With practiced movements, she adds hot water from a stainless steel kettle and stirs the mixture. The barista then pours the freshly brewed coffee into a white ceramic cup, adding a touch of foam art on top before presenting it to the customer with a warm smile. Throughout the process, the cafe's modern decor, including high-top tables and minimalist chairs, provides a backdrop to the barista's efficient and skilled routine.]"
},
{
"from": "gpt",
"value": "Normal. The fingers and the ceramic cup in the video have generation issues."
}
] |
seed46_2518
|
videos/HRA_part2/2518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil woodlands setting, characterized by lush vegetation and a serene atmosphere, a herd of majestic buffalo graze peacefully. The scene focuses on a single buffalo, its massive frame gently caressed by the soft branches of a weeping willow tree. The willow's slender leaves delicately brush against the buffalo's sturdy body, creating a tender and unexpected interaction between nature and wildlife. The buffalo's calm demeanor and the gentle sway of the willow branches in the breeze convey a sense of harmony and tranquility in the midst of the dense woodland.]"
},
{
"from": "gpt",
"value": "Good. The bison's grass-eating actions in the video are basically normal."
}
] |
seed42_2290
|
videos/HRA_part0/2290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and gray sweatpants, diligently wipes down a large, brown bison statue with a white cloth, showing care and attention to detail. The scene takes place on a grassy campus, with trees in the background, highlighting the unique connection between the student and the symbolic animal figure. The student's focused expression and the careful motion of wiping the bison's surface convey a sense of respect and tradition associated with university life.]"
},
{
"from": "gpt",
"value": "Bad. The student's face and hands in the video have generation issues."
}
] |
seed44_3067
|
videos/HRA_part1/3067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit with black markings sits upright on a checkered cloth, using its right paw to wipe its face, as if cleaning or grooming itself, against a simple gray backdrop. The bunny pauses mid-wipe, its paw still touching its face, offering a candid glimpse of its self-care routine. This intimate moment is captured in high detail, highlighting the rabbit's endearing behavior and the textural contrast between its fur and the patterned fabric beneath it.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the rabbit using its paws to wipe its face, the movements are basically normal but there is some lack of coordination."
}
] |
seed44_2232
|
videos/HRA_part1/2232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a green apron over a gray shirt and dark pants, runs down a dimly lit corridor in a large cinema complex. The hall is lined with red carpeting and features a series of doors leading into various screening rooms. The man's facial hair and glasses are distinctive, and he carries a cleaning tool in his right hand. As he sprints, his eyes are set forward, and he passes by a sign with movie titles and showtimes, creating a sense of urgency in the vast, quiet space. The scene captures the hurried pace and isolated environment of the janitor's duties within the cinema.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2907
|
videos/HRA_part1/2907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male baker with short brown hair and glasses, wearing a brown apron over a white shirt, expertly folds ingredients together in a large stainless steel bowl using a wooden spoon. The kitchen is modern and minimalist, featuring sleek silver appliances and countertops. He then spreads batter evenly into a round cake pan, which he places into a preheated oven. As he waits, he wipes his hands on his apron and checks the temperature with a digital thermometer, ensuring the perfect bake. Finally, he removes the golden-brown cake from the oven, its surface smooth and evenly risen, ready for decoration.]"
},
{
"from": "gpt",
"value": "Bad. The action of the male baker placing the round cake mold into a preheated oven in the video is not very smooth and coordinated."
}
] |
seed44_1309
|
videos/HRA_part1/1309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_220
|
videos/HRA_part0/220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched subtropical shrubland, a striking red fox gently caresses the foliage with its bushy tail as it moves gracefully through the sparse landscape. The fox, with its vibrant fur and alert demeanor, interacts tenderly with the arid environment, highlighting the delicate balance between predator and habitat. Against the backdrop of scrub vegetation and scattered trees, the fox's movements convey a sense of care and connection to the natural world.]"
},
{
"from": "gpt",
"value": "Normal. The red fox in the video is basically normal, but there are slightly uncoordinated movements."
}
] |
seed44_2416
|
videos/HRA_part1/2416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully cooked piece of salmon is presented on a plate, its skin crispy and charred to perfection, the flesh a rich pink hue that contrasts strikingly with the green of the accompanying asparagus spears. The dish is garnished with lemon wedges and fresh dill, enhancing the vibrant colors and textures. The salmon is shown from multiple angles, revealing its succulent interior and the delicate grill marks that add depth and character to the presentation. Set against a rustic wooden table, the scene is completed by a glass of white wine and a simple white bowl containing a side of creamy mashed potatoes, offering a perfect balance of flavors and visual appeal.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_3036
|
videos/HRA_part1/3036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage boy wearing a red jacket and khaki pants is sprinting across a grassy field, his gaze fixed ahead with determination. As he runs, a small rabbit enters the frame from the bottom right corner, bounding alongside him. The student acknowledges the rabbit with a brief glance, but both continue their run, the student maintaining his focus and the rabbit keeping pace, against the backdrop of a clear blue sky and distant green hills.]"
},
{
"from": "gpt",
"value": "Bad. The boy's limbs are missing in the video, and his face is generated blurily."
}
] |
seed46_2828
|
videos/HRA_part2/2828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, donning a navy blue cap and sunglasses, runs along the sandy shore of a bustling beach resort, where vibrant umbrellas and lively beachgoers fill the background. His attire includes a navy blue shirt with badge, navy blue trousers, and black shoes. The setting is a crowded beach during daytime, with the officer's movement capturing the essence of duty amidst leisure. He sprints past colorful umbrellas and animated vacationers, highlighting the contrast between his purposeful stride and the relaxed atmosphere of the resort.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands, arms, feet, legs, and face are distorted in the video."
}
] |
seed42_2775
|
videos/HRA_part0/2775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful-looking young man, possibly a librarian or a bookstore employee, organizes books on a shelf in a cozy library corner. He wears a mustard yellow sweater over a button-down shirt, khaki pants, and a stylish watch. The library is filled with bookshelves and has a warm, inviting atmosphere, enhanced by the wooden furniture and green plants. He carefully arranges the books, occasionally stopping to read titles or adjust their placement. The shelves are filled with various genres of literature, from classics to contemporary works, reflecting the diverse interests of the library's patrons. Throughout the scene, the man's dedication to his task is evident, as he meticulously organizes the books with a sense of purpose and care.]"
},
{
"from": "gpt",
"value": "Bad. The young man's hands and the book in his hands are deformed in the video."
}
] |
seed42_2633
|
videos/HRA_part0/2633.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": "Normal. The bird mentioned in the caption as perching on a branch to preen its feathers is not shown in the video."
}
] |
seed44_1655
|
videos/HRA_part1/1655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit with pink ears sprints across a grassy field adjacent to a busy highway, its powerful hind legs propelling it forward urgently. The highway, bustling with vehicles, forms a stark contrast to the natural landscape where the rabbit runs. Sunlight filters through cumulus clouds, casting dynamic shadows on the scene as the rabbit continues its hurried journey, highlighting the unexpected encounter between nature and urban infrastructure.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's head and limbs in the video have generation issues."
}
] |
seed46_1507
|
videos/HRA_part2/1507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a warm, sandy landscape under a clear blue sky, two young children, a boy and a girl, are gently caressing a calm camel. The boy, wearing a yellow shirt and brown shorts, strokes the camel's nose tenderly, while the girl, dressed in a pink dress and sandals, pets its lower leg with a smile. Both children are barefoot, standing on the soft sand, and the camel, adorned with traditional red and white saddle cloths, accepts their affection with a patient demeanor, creating a heartwarming scene of human-animal interaction in a desert environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1224
|
videos/HRA_part2/1224.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a blue uniform and a stethoscope around her neck, is delightedly interacting with a small gerbil in a cozy living room. The gerbil, perched on a tiny platform, suddenly leaps into the air, its action frozen in mid-jump, capturing a moment of playful exuberance. The nurse, with a warm smile, watches the gerbil's antics, her caring demeanor evident in her facial expression and body language. The scene is set against a backdrop of a homely living space, with a couch, coffee table, and various household items visible in the background, creating a sense of domestic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's jumping action in the video is very discontinuous and not smooth."
}
] |
seed44_2660
|
videos/HRA_part1/2660.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee dressed in a miniature waiter's outfit, complete with a crisp white shirt, black vest, and bow tie, walks on its hind legs through a lush, green forest. It carries a small silver tray balanced on its right hand, adding to the whimsical scene. The chimp's expressive face, with furrowed brows and a slight smile, conveys a sense of playfulness and determination as it navigates the natural environment, surrounded by tall trees and dappled sunlight filtering through the leaves.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1061
|
videos/HRA_part0/1061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a yellow shirt and black pants, is seen carefully cleaning a large aquarium filled with vibrant fish. The room is bright, with natural light pouring in from a nearby window, highlighting the diligent task at hand. The student, with a focused expression, uses a specialized tool to gently scrub the inside walls of the tank, ensuring a safe and clean environment for the aquatic inhabitants. The fish, undisturbed, swim gracefully around the student's hand, adding a serene element to the scene. The background features educational posters and shelves filled with books, emphasizing the academic setting of this meticulous activity.]"
},
{
"from": "gpt",
"value": "Bad. The fingers on the hand appear deformed, and they are reaching into the fish tank through the glass."
}
] |
seed42_1687
|
videos/HRA_part0/1687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view captures a mole crab, also known as a sand flea, burrowing in the wet sand of a tropical beach. Its sandy brown color perfectly camouflages it against the shoreline, and its shovel-like front legs dig rapidly into the granular substrate. The creature's round body and small size, about an inch long, make it appear as if it's almost melting into the sand, while its eyes, positioned on stalks, scan the environment for predators or prey. The video highlights the mole crab's unique adaptation for life in the intertidal zone, showcasing its survival tactics in the dynamic coastal ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The cave crabs generated in the video are abnormal and do not conform to reality."
}
] |
seed42_2744
|
videos/HRA_part0/2744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene unfolds as a sleek, black king cobra emerges from tall, dense grass, its hood partially spread. It races forward, muscles rippling under its shiny scales, demonstrating the surprising speed of these normally slow-moving serpents. The snake's eyes are intently focused ahead, suggesting a purposeful journey or a response to a nearby threat, all captured against a backdrop of lush, green foliage.]"
},
{
"from": "gpt",
"value": "Bad. The cobra's movement in the video is uncoordinated."
}
] |
seed46_3188
|
videos/HRA_part2/3188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a white chef's uniform with black stripes and a matching hat, is seen in a small, empty room with white walls and a gray floor. He stands on a brown wooden ladder, holding a paintbrush in his right hand and a white roller brush in his left. The room is illuminated by a large window to his right, casting a soft glow over the space. The chef, with a full beard and a concentrated look on his face, is in the process of painting the wall a vibrant shade of green. The scene captures his transformation of the room, as he applies the paint with precision and care, highlighting his skills beyond the kitchen.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hands and feet are deformed in the video, the roller brush in his hand is abnormally generated, and the chef's hand disappears in the middle frame."
}
] |
seed44_1012
|
videos/HRA_part1/1012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter dressed in a crisp white shirt and black trousers finds himself in an unexpected dance-off with a mischievous monkey. The two are surrounded by an array of exotic plants and flowers, giving the impression of a lush garden or jungle setting. The waiter, maintaining a professional demeanor despite the oddity of the situation, gracefully moves to an unseen rhythm, while the monkey, dressed in a miniature tuxedo, gleefully mimics his every step. The playful exchange is captured in high definition, with vibrant colors and dynamic movements, creating a surreal yet captivating spectacle.]"
},
{
"from": "gpt",
"value": "Bad. The head and limbs of the person and the head and limbs of the monkey were not generated in the video."
}
] |
seed42_2414
|
videos/HRA_part0/2414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant orchard filled with apple trees heavy with ripe fruit, a large brown bear stands on its hind legs, its shaggy fur glistening in the dappled sunlight. It reaches up with a massive paw, gently swiping at the low-hanging branches laden with apples. The bear then lowers itself to all fours, picking up an apple it has dislodged, and wipes it carefully on its thick fur before taking a hearty bite, savoring the sweet, juicy flavor amidst the peaceful surroundings of the orchard.]"
},
{
"from": "gpt",
"value": "Normal. The bear's hands appear deformed and malformed."
}
] |
seed46_1443
|
videos/HRA_part2/1443.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising and surreal scene, a large, gray rhinoceros leaps into the air, defying expectations, with its powerful legs extended and body arched. This incredible moment is captured against a backdrop of a vast savanna landscape, dotted with trees and stretching to a distant horizon under a bright blue sky. The rhino, known for its heavy, armored skin and imposing horn, is shown mid-jump, creating a unique and unforgettable image that highlights the animal's unexpected agility and strength.]"
},
{
"from": "gpt",
"value": "Bad. The rhino's movements in the video are very unsmooth and its behavior is uncoordinated."
}
] |
seed42_213
|
videos/HRA_part0/213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a green shirt and brown overalls, tends to his crops at a resort-like farm, set against a backdrop of rolling hills and clear skies. A friendly hedgehog, nestled in the farmer's pocket, occasionally pops its head out to observe the surroundings. The farmer pauses to wipe his brow with a red bandana, revealing a content smile, as the hedgehog curls up comfortably in its makeshift home. The scene exudes tranquility and harmony between nature and human life, with the resort's luxurious amenities visible in the distance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1291
|
videos/HRA_part2/1291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge, is seen swimming in a large, outdoor pool with a rhinoceros nearby. The setting is a spacious enclosure with lush greenery, reminiscent of a wildlife sanctuary. The officer, wearing sunglasses and a cap, is shown diving into the water, while the rhinoceros, sporting a police-themed saddle, looks on from the edge of the pool. In another scene, the officer is playfully splashing water with the rhinoceros, both enjoying a moment of leisure under the clear blue sky. The final shot captures the officer and the rhinoceros exiting the pool together, the officer patting the rhino affectionately, highlighting an unusual yet heartwarming bond between law enforcement and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the rhinoceros's claws are deformed, the face is distorted, and the legs are twisted."
}
] |
seed44_1060
|
videos/HRA_part1/1060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 patient, smiling teacher, dressed casually in a blue T-shirt and khaki shorts, tenderly bathes a small, brown dog in a white plastic tub placed atop a green picnic table, set against the backdrop of a lush, grassy park. The teacher, wearing a simple blue shirt and beige shorts, gently washes the dog, who looks content and relaxed. In another angle, the teacher, now seen from the back, continues to bathe the dog, demonstrating care and attention. Lastly, the teacher, still wearing the blue top and khaki bottoms, rinses the dog with a handheld showerhead, capturing the essence of a nurturing educator spending quality time with a beloved pet.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand generation in the video is abnormal, with a third hand suddenly appearing in the middle frame."
}
] |
seed44_2354
|
videos/HRA_part1/2354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic juxtaposition, a rugged firefighter, clad in full gear and holding a fire hose, stands tall against a backdrop of scientific equipment and dark matter research posters. The scene shifts to focus on the firefighter gently caressing the side of a large, complex machine, symbolizing a tender connection between humanity and the pursuit of knowledge. The firefighter's protective clothing contrasts with the sterile environment of the research facility, creating a compelling visual narrative. Behind him, screens display data related to dark matter studies, emphasizing the unusual fusion of two vastly different worlds.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1931
|
videos/HRA_part1/1931.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a sandy beach under clear blue skies, three young children, two boys and a girl, wearing colorful swimsuits and sunglasses, jump gleefully into the air in slow motion. Their silhouettes are highlighted by the sun, casting playful shadows on the sand. They leap again, this time with the vast ocean as their backdrop, their laughter echoing in the warm coastal breeze. Their final jump is captured mid-air, faces full of joy and wonder, the sea gently lapping at the shore behind them, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The video generated an extra child."
}
] |
seed42_2946
|
videos/HRA_part0/2946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning close-up of a halibut fish, flat and wide, with a mottled brown and white skin pattern, is showcased against a dark background. The fish has a large, open mouth with small teeth visible, and its eyes are set on the left side of its head, gazing intently. The texture of the halibut's skin is detailed, showing rough spots and a rugged surface, while the background remains uniformly dark, highlighting the unique features of this deep-sea dweller.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2865
|
videos/HRA_part1/2865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled teacher in a yellow polo shirt and khaki shorts kneels beside a small pool, assisting a ferret in its first swimming lesson. The ferret, wearing a tiny life jacket, paddles energetically with its feet, its nose just above the waterline. The teacher gently supports the ferret from behind, offering encouragement and ensuring safety. The scene is set in a brightly lit room with large windows, casting a warm glow over the educational and nurturing moment shared between the teacher and the adventurous ferret.]"
},
{
"from": "gpt",
"value": "Bad. The hands and legs appear deformed."
}
] |
seed44_1886
|
videos/HRA_part1/1886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, clad in rich brown fur, dashes across a lush, verdant forest floor, its bushy tail swaying energetically. The scene is captured in vibrant detail, with the beaver's small ears and alert eyes clearly visible as it navigates the underbrush. Its front paws, equipped with dexterous digits, grip the mossy ground, propelling it forward with a sense of urgency. The background features a dense thicket of trees and foliage, providing a natural habitat for the beaver's lively sprint.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's paws in the video have issues."
}
] |
seed44_1832
|
videos/HRA_part1/1832.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic scenario, an astronaut wearing a gray spacesuit walks on an asteroid's surface, which is rich in minerals, while in the background, an unexpected sight unfolds: a full-grown moose, also wearing a spacesuit, roams freely, seemingly adapted to zero gravity. The astronaut, equipped with a helmet and backpack, explores the rocky terrain, while the moose, with its large antlers and hefty frame, adds an element of surrealism to the scene. Both figures are set against the backdrop of space, with distant stars and galaxies visible in the vast emptiness.]"
},
{
"from": "gpt",
"value": "Bad. The moose's body is twisted, the head is twisted, and the legs are twisted; the astronaut's body is twisted, the arms are twisted, the legs are twisted, and the hands are twisted."
}
] |
seed44_2029
|
videos/HRA_part1/2029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a tailored gray suit, stands confidently in a lush green backyard, holding a golden chicken with care. The vibrant green grass complements his attire, while the chicken adds a touch of whimsy. Nearby, a swimming pool glistens under the sunlight, its clear blue water contrasting beautifully with the greenery. The lawyer gently places the chicken on the grass, its feathers gleaming in the sun, before walking towards the pool. He pauses at the edge, contemplating the serene water, creating a juxtaposition between his professional demeanor and the unexpected presence of the chicken in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2245
|
videos/HRA_part1/2245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning close-up of a Brook Trout fills the frame, its vibrant colors and intricate patterns mesmerizing. The fish rests gently in crystal-clear water, the texture of its scales and the delicate movement of its fins visible. Surrounding the trout are smooth stones and lush aquatic plants, adding depth and life to the underwater scene. Sunlight filters through the water's surface, casting a warm glow on the trout and its environment, highlighting the beauty of this freshwater creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the trout's mouth and fins in the video has issues."
}
] |
seed46_2299
|
videos/HRA_part2/2299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A great egret, standing tall with folded wings, perches gracefully on one leg atop a weathered wooden post in the midst of a serene marsh landscape, surrounded by lush green vegetation and calm waters. Its pristine white feathers contrast beautifully against the natural backdrop, while its sharp yellow eyes scan the environment keenly. The scene is set during the golden hour, with the warm sunlight casting a soft glow over the bird and its habitat, highlighting the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1712
|
videos/HRA_part2/1712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, perches on a stone statue in the middle of a bustling city square. It has a full, rounded body, and its wings are slightly spread, revealing a flash of green and purple iridescence near the base. Its head, adorned with a small red beak, turns to face the camera, displaying its alertness and curiosity. The bird's legs, pink and sturdy, grip the statue firmly, while its red eyes, surrounded by yellow orbital rings, watch the surroundings keenly. The pigeon is set against a backdrop of urban life, with pedestrians, buildings, and traffic providing a sense of scale and context.]"
},
{
"from": "gpt",
"value": "Normal. The pigeon's feet in the video are not fully generated and there is an extra foot."
}
] |
seed44_2760
|
videos/HRA_part1/2760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a neatly trimmed beard and a muscular build rearranges furniture in a modern living room. He lifts a heavy wooden coffee table with ease, his biceps flexing under a tight-fitting gray T-shirt. Wearing dark blue jeans and white sneakers, he positions the table in the center of the room, then pauses to consider the layout. Satisfied, he proceeds to adjust the placement of two large, plush armchairs, ensuring they are perfectly aligned with the table. The room features minimalist decor, with white walls, a large window letting in ample natural light, and a sleek flat-screen TV mounted above a low-profile entertainment unit. Throughout the scene, the man's confident demeanor and attention to detail are evident as he meticulously arranges the furniture to achieve a balanced and inviting space.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, feet, and legs are distorted in the video."
}
] |
seed44_2671
|
videos/HRA_part1/2671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grey suit, white shirt, and patterned tie, walks purposefully across a grassy field under a twilight sky, carrying a large, transparent bag. In the distance, a comet streaks across the night sky, its tail glowing brightly. The lawyer pauses, turning his head to gaze up at the celestial phenomenon, his expression a mix of awe and determination. Despite the extraordinary sight, he continues his steady walk, the comet's light illuminating his path forward.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's walking movements in the video are not continuous and smooth, there is a lack of coordination."
}
] |
seed46_2400
|
videos/HRA_part2/2400.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear including a yellow reflective jacket, black helmet, and breathing apparatus, rests his head on his hands atop a wooden table in a dimly lit room. The scene conveys a sense of quiet repose after a night shift, with the firefighter appearing tired yet ready to respond at a moment's notice. His equipment is scattered around him, including a flashlight, gloves, and boots, adding to the realism of the setting. The firefighter's body language suggests exhaustion, as he leans forward with his elbows on the table, seeking solace in a brief moment of rest.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's hand generation in the video has issues."
}
] |
seed42_2229
|
videos/HRA_part0/2229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a majestic brown horse gallops gracefully across the foreground, its muscular form silhouetted against a backdrop of sprawling factories with billowing smokestacks. Amidst this industrial landscape, a group of diverse individuals dressed in vibrant, eclectic clothing forms a stark contrast as they engage in expressive dance moves, their joyous expressions and dynamic movements standing out against the grey, mechanical setting. This unlikely fusion of nature, industry, and human spirit creates a compelling narrative of resilience and vitality.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is distorted, the head is twisted, the feet are distorted, the legs are twisted, the arms are distorted, the horse's head is twisted, the body is distorted, the legs are twisted."
}
] |
seed46_1117
|
videos/HRA_part2/1117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor, its curious nature evident as it explores its surroundings. It wears a tiny red harness, adding a pop of color against its natural brown and white fur. The room is spacious, with a large window letting in ample sunlight, casting warm light on the ferret as it moves about. In the background, a potted plant and a comfortable couch can be seen, providing context to the indoor environment where the ferret is freely walking.]"
},
{
"from": "gpt",
"value": "Normal. The ferret in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2163
|
videos/HRA_part2/2163.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 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 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": "Bad. The actions of the twin toddlers in the video are not smooth."
}
] |
seed44_328
|
videos/HRA_part1/328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 temperate deciduous forest, a professional lawyer, dressed in a gray suit and carrying a leather briefcase, wipes his brow as he pauses from his hike. The lush green forest, filled with tall trees and sunlight filtering through the leaves, provides a serene backdrop. The lawyer, wearing a gray blazer, button-down shirt, and khaki pants, is shown wiping his face with a handkerchief, revealing a moment of respite during his outdoor excursion. The peaceful atmosphere of the forest is highlighted by the dappled sunlight and the vibrant greenery surrounding the well-dressed man.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's fingers and arms are deformed in the video, the handbag is generated in the wrong position, the face is distorted, and the sweat towel is generated unnaturally."
}
] |
seed42_1025
|
videos/HRA_part0/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 lone seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Bad. The wings are moving, but the bird's body is not."
}
] |
seed44_1063
|
videos/HRA_part1/1063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising scene, a bobcat, recognizable by its short tail and tufted ears, dashes across the frame, passing by an automated checkout machine in a minimally designed convenience store. The animal's panicked sprint is juxtaposed against the sterile environment of the store, where the self-checkout machine stands idle. The bobcat's unexpected intrusion adds an element of chaos to the otherwise mundane setting, creating a surreal moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The cat's movements in the video are not smooth."
}
] |
seed44_1575
|
videos/HRA_part1/1575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 worker in a lab coat walks purposefully across a large, open laboratory space filled with complex machinery and high-tech equipment, the setting for a quantum entanglement experiment. The room is illuminated by bright overhead lights, casting a sterile glow over everything. In the background, scientists can be seen observing data on computer screens and discussing theories, their faces serious and focused. The worker carries a clipboard, pausing occasionally to check notes or adjust settings on various machines, all while surrounded by the hum of active scientific inquiry into the mysteries of quantum mechanics.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2284
|
videos/HRA_part2/2284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a brown jacket, blue shirt, and green trousers, promenades leisurely through a vast cornfield, the golden stalks towering over him as he walks. He pauses to observe a crawling caterpillar on a large, lush green leaf, its vibrant colors contrasting beautifully against the foliage. The farmer kneels down, his worn hands gently touching the leaf, as he watches the caterpillar slowly inching forward, exploring its world. The camera captures this intimate moment between man and nature, highlighting the farmer's connection to the land and the simple pleasures it offers.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's fingers are missing in the video, and the caterpillar is deformed."
}
] |
seed46_2905
|
videos/HRA_part2/2905.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 giant panda, recognizable by its black ears and eye patches, crawls on all fours across a lush, green forest floor, its fur a striking contrast against the vibrant vegetation. It moves slowly, carefully placing each paw, showcasing its strength and agility. The panda's attention is drawn to something in the distance, its ears perked, adding a layer of curiosity to its demeanor. Surrounded by bamboo plants, a staple in its diet, the panda continues its crawl, encapsulating the essence of its natural habitat in every deliberate motion.]"
},
{
"from": "gpt",
"value": "Normal. The panda's movements are not smooth."
}
] |
seed44_2830
|
videos/HRA_part1/2830.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cityscape illuminated by neon lights, a waiter dressed in a sleek, silver apron over a black uniform walks purposefully across a crowded outdoor plaza filled with diverse patrons enjoying their meals. Behind him, an AI pilot, recognizable by its advanced humanoid form with a polished metallic exterior and glowing blue eyes, strides confidently, carrying what appears to be a flight helmet under its arm. Both figures navigate through the bustling scene, the waiter balancing a tray laden with exotic dishes, while the AI pilot's movements are precise and efficient, highlighting the seamless integration of technology and service in this high-tech environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2088
|
videos/HRA_part0/2088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-covered landscape, a group of people in winter gear are seen interacting with a herd of majestic bison. The individuals are wiping snow off the bison's fur, showing care and connection with the animals. Their faces, wrapped warmly in scarves and hats, express determination and compassion. The bison, with their powerful statures and shaggy coats, stand calmly, accepting the attention. The scene is framed by the serene beauty of nature, with snowflakes gently falling and the distant silhouette of trees providing a peaceful backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The action of people reaching out to clear the accumulated snow on the bison's fur in the video is not very continuous and there is a lack of coordination."
}
] |
seed46_1359
|
videos/HRA_part2/1359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a gun holster, walks through a vast space library with high ceilings and large windows showing distant stars. The officer, with a serious yet calm demeanor, moves between towering bookshelves filled with ancient books and futuristic data pads. The library is illuminated by soft, ambient lighting, casting a warm glow on the officer's path. As they walk, the officer occasionally glances at the titles, perhaps searching for information or simply appreciating the knowledge stored within this unique cosmic repository.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2628
|
videos/HRA_part2/2628.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unexpected urban scene, a wild bobcat stands alert near a glassy skyscraper, its reflection visible on the building's facade. Beside it, a sleek swimming pool shimmers under the city lights, invitingly clear and calm. The bobcat, with its distinctive tufted ears and sharp gaze, seems unperturbed by the towering structures, its presence creating a striking contrast against the urban landscape. The pool, framed by the towering skyscrapers, offers a serene oasis, its still waters reflecting the night sky and the surrounding architecture.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1043
|
videos/HRA_part1/1043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee dressed in a red vest acts as a cashier, sitting at a checkout counter filled with groceries. The chimp, wearing a name tag and a friendly smile, leans forward to scan items with a handheld barcode scanner. Suddenly, it drops the scanner and begins crawling on all fours, playfully moving across the wooden floor of the store. The camera follows the chimp as it crawls between the aisles, its red vest contrasting against the green apples and yellow bananas displayed on the shelves. Throughout the scene, the chimp's expressive face and curious behavior provide a lighthearted and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Bad. The fingers deform and become misshapen during the crawling process."
}
] |
seed44_2702
|
videos/HRA_part1/2702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant kitchen filled with the warm glow of overhead lights, a group of four individuals, two men and two women, are energetically washing dishes. One man, wearing a dark green apron over a white t-shirt, vigorously scrubs a pot under running water from a stainless steel sink. Beside him, a woman in a yellow apron laughs as she dries a plate with a colorful cloth. Across the room, another man in a chef's coat rinses glasses, while a woman in a floral apron sorts cutlery, her hands deftly separating forks and spoons. The atmosphere is lively, with steam rising from the sink and the clinking of dishes adding to the symphony of post-meal cleanup.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1388
|
videos/HRA_part1/1388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sunlit indoor environment, three young children sit on a large, comfortable sofa, each gently caressing a small rabbit. One child, dressed in a blue jacket, has short blond hair and a joyful smile, cradling a white rabbit with care. Another child, wearing a yellow shirt, has brown hair and a peaceful expression, softly petting a brown rabbit. The third child, clad in a red hoodie, has curly dark hair and a serene look, tenderly stroking a gray rabbit. The room is filled with a sense of calm and happiness, as the children enjoy the company of the adorable bunnies.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2028
|
videos/HRA_part0/2028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated teacher, dressed in a green and white striped shirt, khaki shorts, and brown shoes, playfully interacts with a panda cub at a zoo enclosure designed like a natural habitat. The teacher gently guides the panda, which is wearing a tiny red swim vest, as they both splash around in a shallow pool. The panda's curiosity and the teacher's patient instruction create a heartwarming scene, with the water shimmering under the sunlight and the lush greenery of the enclosure providing a serene backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1460
|
videos/HRA_part0/1460.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 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 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": "Bad. The red fox's paws are twisted, and its legs are twisted."
}
] |
seed46_3157
|
videos/HRA_part2/3157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hippopotamus, identifiable by its gray skin and rotund body, is seen walking through a shallow river, creating ripples in the water with each step. Its small ears, round eyes, and wide mouth are clearly visible as it moves slowly through the riverbed. The scene is set against a backdrop of lush vegetation and a clear blue sky, with the water reflecting the greenery and the hippo's movements. The hippopotamus continues its leisurely walk, leaving a trail of disturbed water behind it, all captured in high definition to showcase the details of this magnificent creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The hippopotamus's head is deformed, and its legs are twisted."
}
] |
seed44_2675
|
videos/HRA_part1/2675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, resembling Chris Hemsworth, waters plants in a lush, green backyard garden filled with various potted plants and trees. He wears a simple white tank top, brown cargo shorts, and brown flip-flops, giving off a casual, laid-back vibe. The scene is set during the day, with bright sunlight illuminating the vibrant greenery and highlighting the actor's chiseled physique. As he tends to the plants, he occasionally pauses to smile at the camera, showcasing his charming personality and the peaceful atmosphere of the garden.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2570
|
videos/HRA_part0/2570.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an elegant lawyer, attired in a black suit, white shirt, and red tie, sits pensively with his hands clasped. Beside him, a taxidermied jackal wearing a miniature lawyer outfit sits upright on a chair, adding a surreal touch. The lawyer then wipes his brow with a handkerchief, appearing relieved yet cautious, as if contemplating a significant decision. The scene maintains a consistent setting within the theater, focusing on the lawyer's expressions and the unusual presence of the costumed jackal.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's actions in the video, such as sitting with hands clasped or wiping the forehead with a handkerchief, are basically normal but slightly uncoordinated."
}
] |
seed42_1840
|
videos/HRA_part0/1840.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, dressed in a yellow safety vest over a gray shirt and black pants, experiences time dilation as he leaps into the air in a high school gymnasium. The scene is captured from four different angles: first, he is seen standing still, looking at the camera. Then, he jumps into the air, the motion slowed down to emphasize the effect of time dilation, his posture mid-leap. In the next frame, he is frozen mid-air, with a basketball hoop and a volleyball net visible in the background. Lastly, he is shown in slow motion again, this time with a look of determination on his face, highlighting the unique experience of time distortion during his jump.]"
},
{
"from": "gpt",
"value": "Bad. No basketball hoop and volleyball net were generated."
}
] |
seed44_2230
|
videos/HRA_part1/2230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, lush green forest setting, a pair of beavers are seen intimately caressing each other, their brown fur glistening with moisture from the nearby river. The male beaver gently touches the female's face with his forepaw, a tender gesture of affection. They are surrounded by tall trees and vegetation, providing a natural and peaceful environment for their interaction. The female beaver responds with a soft look, her whiskers moving slightly as she nuzzles closer to him. This heartwarming scene captures the emotional bond between these two creatures, highlighting the beauty of wildlife relationships.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2318
|
videos/HRA_part1/2318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 stands tall and poised, her blonde hair in a sleek bun, wearing a fitted black blazer over a white collared shirt, black trousers, and black heels. She is positioned in front of a large window with a city skyline visible in the background, her gaze directed towards the urban landscape. The scene is bathed in the warm glow of the setting sun, casting a golden hue over the woman and the cityscape, highlighting her silhouette and the texture of her attire. The contrast between the structured clothing and the fluidity of her stance conveys a sense of power and elegance.]"
},
{
"from": "gpt",
"value": "Normal. Lack of action, the character is almost stationary."
}
] |
seed42_2863
|
videos/HRA_part0/2863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing swimming trunks and a snorkel mask, playfully interacts with a gorilla, which is also wearing swimming gear, including swim trunks and goggles, as they splash around in a large outdoor pool. The gorilla, standing upright, reaches its arm out toward the student, who is seen from the waist up, submerged in the water. The scene is set against a backdrop of lush greenery and trees, creating a whimsical and unexpected atmosphere. The student and the gorilla are both engaged in a lighthearted game, enjoying each other's company in the water, with the gorilla's human-like posture adding a touch of surrealism to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The student's head, the gorilla's facial features, and claws in the video have generation issues."
}
] |
seed44_1025
|
videos/HRA_part1/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Bad. The wings show deformities and mutations."
}
] |
seed44_1152
|
videos/HRA_part1/1152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a female cashier, dressed in a brown apron over a black top and gray pants, is fixing a mountain bike in a grocery store. The bike, with its wheels removed, rests on a repair stand, as she focuses intently on her task. Customers can be seen shopping in the background, adding an element of surprise to the setting. She works diligently, surrounded by store shelves stocked with various products, creating a juxtaposition between her usual role and the unusual activity of bike repair in a retail environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2953
|
videos/HRA_part0/2953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a blue t-shirt and khaki shorts, runs across a vast desert landscape under a clear blue sky, with distant mountains providing a dramatic backdrop. The student, wearing a backpack and a cap, navigates the sandy terrain with determination, the camera capturing the texture of the dunes and the play of light and shadow. As the scene progresses, the focus remains on the runner, highlighting their stamina and resilience against the stark beauty of the desert environment.]"
},
{
"from": "gpt",
"value": "Bad. The student's limbs are missing in the video, the face is generated blurry, and the body proportions are incorrect."
}
] |
seed46_1188
|
videos/HRA_part2/1188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a standard uniform with a badge and a hat, sits in a well-lit room with white walls. He nods slowly and deliberately in response to something off-screen, his serious demeanor and attentive body language conveying a sense of authority and engagement. The clean, organized setting and the officer's focused gaze suggest a formal environment, possibly an office or an interrogation room, where he listens intently to another person, nodding to show understanding and agreement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.