video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1838
|
videos/HRA_part2/1838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 somber space funeral setting, a lone janitor, dressed in a black suit and tie, leaps gracefully over a floating row of mops and brooms that are held aloft by unseen forces, against the backdrop of a distant, glowing nebula. His face is marked with determination, and his movements are fluid and controlled, as if dancing among the stars. The funeral attendees, dressed in various mourning attire, watch him in awe, their expressions a mix of grief and admiration. The scene is both surreal and poignant, capturing the unique juxtaposition of everyday duties and extraordinary circumstances in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, legs, and hands."
}
] |
seed42_2092
|
videos/HRA_part0/2092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video dances very unsmoothly, with uncoordinated movements."
}
] |
seed44_2773
|
videos/HRA_part1/2773.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate female teacher, clad in a gray blazer, white blouse, and dark pants, walks purposefully across a bustling university campus, animatedly discussing the recent discovery of a habitable exoplanet. She gestures enthusiastically, engaging with her students who walk alongside her, their faces alight with curiosity and excitement. The backdrop shifts subtly from the interior of a modern lecture hall, filled with attentive students, to the outdoor campus, where the teacher continues her captivating lesson under the open sky, emphasizing the significance of the exoplanet find. Throughout the scene, the teacher's energy and dedication to teaching are evident, inspiring her students to explore the wonders of the universe.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_1803
|
videos/HRA_part0/1803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set in a subtropical desert landscape, a police officer, clad in a tan uniform and wide-brimmed hat, is gently wiping the face of a curious capybara. The officer, showing unexpected tenderness, kneels beside the large rodent, which is sitting calmly on the sandy terrain, surrounded by sparse vegetation typical of arid environments. The interaction between the law enforcement figure and the capybara underlines an unusual yet touching moment in the vast, sun-baked wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The video has missing features on the capybara's face, incomplete generation of the police officer's fingers, and issues with the eyes."
}
] |
seed44_2403
|
videos/HRA_part1/2403.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate teacher, wearing a cozy, cream-colored sweater and dark jeans, sits cross-legged on a lush green meadow under a clear blue sky, gently caressing a small, timid hare. The teacher's serene expression and soft touch convey a sense of safety and comfort to the animal. The hare, with its soft brown fur and curious eyes, leans into the teacher's hand, seemingly enjoying the affection. Surrounding them are wildflowers and tall grass swaying gently in the breeze, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_116
|
videos/HRA_part2/116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green valley, a hardworking man in a blue shirt and beige pants is crawling on his hands and knees, inspecting the rich soil for cultivation. Nearby, an otter playfully frolics in a clear, bubbling stream, its antics providing a charming contrast to the industrious human activity. The setting is idyllic, with rolling hills framing the scene, and the worker's dedication to his craft is evident in his meticulous attention to the land. The otter, seemingly unperturbed by the presence of the human, continues its joyful exploration, highlighting the harmonious coexistence between nature and humanity in this tranquil valley.]"
},
{
"from": "gpt",
"value": "Bad. The human's hands and face appear deformed, and the otter undergoes mutations and deformities when moving."
}
] |
seed44_1907
|
videos/HRA_part1/1907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary vulture, with its distinctive bald head and dark, rugged feathers, perches on a branch in a barren tree set against a cloudy sky. The bird's sharp eyes scan the surroundings, while its large wings remain folded, ready for flight. In the next scene, the vulture takes off, its powerful wings propelling it into the air as it begins to circle above the landscape, searching for carrion. The video then focuses on the vulture in mid-flight, its wings spread wide, gliding effortlessly through the air with a backdrop of rolling hills and distant mountains. Finally, the bird lands gracefully on a rocky outcropping, where it stands alert, surveying its territory with a commanding presence.]"
},
{
"from": "gpt",
"value": "Normal. The vulture's movements in the video are not smooth."
}
] |
seed46_165
|
videos/HRA_part2/165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lush greenery, a distinguished doctor, wearing a classic white lab coat over a crisp blue shirt, performs a solemn wedding ceremony. The couple, dressed in elegant spacesuits with transparent helmets, exchange loving glances as they gently caress each other's hands, symbolizing their deep connection. Behind them, a panoramic view of the Earth and stars provides a breathtaking backdrop, while the doctor's compassionate demeanor adds a touch of humanity to this extraordinary union in zero gravity.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the bride and groom wearing space suits with transparent helmets, touching hands, and loving eyes."
}
] |
seed46_1154
|
videos/HRA_part2/1154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, dressed in a black vest and white shirt, walks purposefully through a series of art galleries, each filled with unique paintings and sculptures. He carries a small, white tray with two wine glasses, moving from one gallery to another, passing by various artworks. In the first gallery, he walks past a large, abstract painting in red and yellow tones. In the second, he strolls by a modern sculpture, and in the third, he passes under a chandelier, all while maintaining a focused demeanor, showcasing the dynamic interplay between service and art.]"
},
{
"from": "gpt",
"value": "Normal. The server's legs appear deformed, and the face is distorted."
}
] |
seed42_3058
|
videos/HRA_part0/3058.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious monkey, dressed in a red life jacket, sits on a wooden pier extending over a serene body of water, surrounded by lush greenery and tall trees. The monkey then playfully jumps into the clear blue water, creating ripples that spread outward. It swims energetically, its small arms paddling through the water, while a pair of sunglasses float nearby, adding a touch of whimsy to the scene. The monkey eventually climbs back onto the pier, shaking off droplets of water, with the sun casting a warm glow over the entire setting.]"
},
{
"from": "gpt",
"value": "Bad. The monkey's movements in the video are not smooth."
}
] |
seed46_3055
|
videos/HRA_part2/3055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green meadow, two majestic moose gently caress each other with their large, velvety noses, expressing tenderness and affection. They stand side by side, their dark coats contrasting beautifully against the vibrant flora surrounding them. One moose looks intently at its companion, while the other closes its eyes, savoring the intimate moment. Their antlers, impressive and intricate, frame their faces as they share this loving gesture, all captured in stunning high definition. The background is a harmonious blend of nature, with tall grass swaying gently in the breeze, creating a peaceful and idyllic setting for this touching wildlife interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2831
|
videos/HRA_part0/2831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a costumed musician, dressed in a vibrant green hippopotamus outfit, gracefully crawls across a dimly lit stage. The stage is adorned with a red velvet curtain, adding a touch of drama. The musician's movements are slow and deliberate, almost balletic, as they crawl with an air of performance art. The costume is complete with oversized hippo ears and a large, friendly smile, creating a surreal and captivating visual display.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_293
|
videos/HRA_part1/293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, defying expectations, swims powerfully through a tranquil body of water, its golden coat glistening as it propels itself forward with muscular strokes. Its piercing gaze is fixed ahead, conveying determination and grace in this unusual aquatic setting. The lion's head remains above the waterline, mane billowing softly, while its body undulates beneath the surface, showcasing an unexpected display of strength and agility in the liquid environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3197
|
videos/HRA_part0/3197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its wings spread wide against a backdrop of rolling clouds and a cerulean sky. The bird's white plumage is highlighted by the golden rays of the sun, casting a serene glow over the scene. As it glides effortlessly, its keen eyes scan the waters below for signs of prey, demonstrating the harmony between creature and environment. The albatross then swoops down, its silhouette framed by the sun, before rising back into the heavens, embodying the spirit of freedom and the majesty of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3136
|
videos/HRA_part1/3136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a red astronaut suit with gold accents, crawls across a rocky Martian landscape as a vibrant orange and red sunset illuminates the horizon. The chef's outfit includes a matching helmet, which reflects the dramatic sunset, and a tool belt filled with cooking utensils. The rocks beneath him are various shades of brown and red, typical of Mars' surface, while the distant mountains and sandy dunes complete the alien yet stunning scenery. Despite the harsh environment, the chef's determination to explore and perhaps cook under the unique conditions of Mars is evident.]"
},
{
"from": "gpt",
"value": "Normal. The chef in the video moves basically normally, with slightly uncoordinated movements."
}
] |
seed46_1524
|
videos/HRA_part2/1524.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, clad in a gray sweatshirt and jeans, stands on a ladder, diligently cleaning out the rain gutters of a suburban home on a cloudy day. His weathered hands grip a trowel, removing debris from the clogged gutter, while his sweatshirt and jeans are stained with dirt and leaves. The house's siding, painted a neutral beige, serves as a backdrop, with a well-manicured lawn and garden visible below. The man's focused expression and the tools of his task, including the ladder and trowel, emphasize the effort required for this routine home maintenance activity.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1250
|
videos/HRA_part1/1250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit tailor shop, a friendly cashier, dressed in a maroon collared shirt and khaki pants, assists a customer. The cashier, with neatly trimmed facial hair, sits at a sewing machine, carefully hemming a pair of gray pants, demonstrating expertise and precision. The scene highlights the skilled craftsmanship and personal service provided in the store, with the cashier's focused expression and the sewing machine's rhythmic sound adding to the atmosphere. The customer, standing nearby, watches attentively, expressing satisfaction and trust in the cashier's abilities.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1259
|
videos/HRA_part2/1259.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum hall with marble floors, an antelope taxidermy mount is displayed under a spotlight, its majestic form captured mid-leap. A diligent custodian wearing a green apron wipes the glass display case, ensuring the exhibit is pristine. The antelope, with its striking coat and alert posture, seems to leap over a miniature landscape within the display. The custodian, in a green uniform, carefully cleans the case, her reflection visible alongside the antelope's image. Throughout, the museum's grandeur is evident, with high ceilings, ornate moldings, and other exhibits surrounding the featured antelope.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2901
|
videos/HRA_part0/2901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, agile mongoose, with its distinctive reddish-brown fur and sharp eyes, is seen crawling slowly through a dense grassland environment. It moves stealthily, its body hugging the ground, as it searches for prey or navigates its territory. The scene is set under the warm glow of the afternoon sun, casting long shadows and highlighting the mongoose's fur texture against the green backdrop. Its cautious movements and keen senses are evident as it crawls, making it appear both vulnerable and predator in the wild landscape.]"
},
{
"from": "gpt",
"value": "Normal. The mongoose's body and legs show deformities while crawling."
}
] |
seed42_1884
|
videos/HRA_part0/1884.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starship bridge, illuminated by soft blue and green lights, a small, fluffy white hare is crawling across the command deck. The hare moves slowly, its ears perked up, exploring the high-tech environment filled with control panels and large viewing screens displaying cosmic visuals. The bridge is otherwise empty, save for the advanced technology and the occasional blinking lights, creating a surreal contrast between the sci-fi setting and the unexpected presence of the crawling hare.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2487
|
videos/HRA_part1/2487.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, intimate dining room, a sophisticated waiter, dressed in a crisp white shirt, black vest, and tie, tenderly caresses the smooth surface of a wine bottle, as if appreciating its craftsmanship. The scene is set with elegant table settings, fine china, and crystal glasses, creating an atmosphere of luxury. The waiter's hands, adorned with a simple silver ring, move gracefully over the bottle, highlighting his connection to the art of serving. Behind him, the glow of candlelight casts warm shadows on the walls, adding to the romantic ambiance of the restaurant.]"
},
{
"from": "gpt",
"value": "Normal. The server's gesture of touching the wine bottle in the video is not smooth and coordinated."
}
] |
seed46_2552
|
videos/HRA_part2/2552.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate female teacher, wearing a blue blouse and glasses, sits at her desk in a classroom after school hours. She quietly cries, her face in her hands, revealing her vulnerability. Behind her, a world map hangs on the wall, adding depth to the scene. As she weeps, her shoulders gently shaking, the peaceful classroom with its neatly arranged desks and chairs provides a stark contrast to her emotional state. The dim afternoon light filtering through the window highlights her silhouette, emphasizing the solitude and intensity of her private moment.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher's face and hands in the video have generation issues."
}
] |
seed46_2651
|
videos/HRA_part2/2651.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-down shirt, sits in a modern office filled with medical equipment. He is holding a pen and papers, looking concerned as he coughs into his right hand. The scene is set indoors, with the doctor seated at a desk cluttered with medical files and supplies. Soft, ambient lighting highlights the professional yet somber atmosphere. The doctor's cough is noticeable, drawing attention to his discomfort amidst the sterile environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_1783
|
videos/HRA_part2/1783.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, costumed in a vibrant green shirt and brown pants, strolls alongside a life-sized, realistic hippopotamus puppet, which is operated by two puppeteers dressed in all-black attire. The trio walks across a grassy field under a clear blue sky, creating a whimsical and unexpected scene. The actor, with a bemused smile, interacts with the puppet, which responds with lifelike movements and expressions, adding to the surreal atmosphere of the outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the hippo puppet's actions are also not fluid."
}
] |
seed46_1391
|
videos/HRA_part2/1391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a young Tom Hardy, wearing a futuristic space suit with a gorilla mascot emblem, embarks on an exhilarating lunar buggy ride across a desolate moon landscape, capturing the essence of adventure in outer space. Later, he is seen walking purposefully, leading the lunar buggy with ease, as if navigating through a challenging mission. The actor then pauses to admire the vast, starry expanse, evoking a sense of awe and wonder, before continuing his journey, showcasing determination and resilience. Throughout the scenes, the lunar buggy, with its distinctive design and rugged tires, remains a prominent feature, highlighting the vehicle's role in the astronaut's lunar exploration.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the gorilla icon mentioned in the caption."
}
] |
seed44_1415
|
videos/HRA_part1/1415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a Rainbow Trout, showcasing its shimmering silver scales speckled with vibrant pink stripes, fills the frame. The fish's large, expressive eyes and intricate patterns on its fins are clearly visible, set against a dark, blurred aquatic environment. The water around it gently swirls, revealing bubbles and fine particles, while the trout remains remarkably still, allowing for a detailed examination of its stunning features.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2062
|
videos/HRA_part2/2062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars majestically across a clear blue sky, its sharp eyes scanning the terrain below for any signs of movement. Its streamlined body, covered in a mottled brown and gray plumage, cuts through the air with effortless grace. The bird's hooked beak and powerful talons are on full display as it dives suddenly, plummeting towards the earth in pursuit of prey. In a burst of speed, it snatches a small rodent from the tall grass, its sharp claws closing around the struggling creature. The sparrowhawk then rises again into the heavens, carrying its prize back to its nest, a picture of strength and agility against the vastness of the sky.]"
},
{
"from": "gpt",
"value": "Bod. The rodents did not appear in the video."
}
] |
seed46_1240
|
videos/HRA_part2/1240.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds as a musician, donning a brown leather jacket, dark pants, and a red bandana, explores a subtropical wet forest. He crawls on his hands and knees through the dense undergrowth, his face expressing determination and curiosity. The lush vegetation surrounds him, with tall trees towering overhead and a rich tapestry of ferns and mosses covering the forest floor. The air is thick with the sounds of nature, from the chirping of birds to the rustling of leaves, creating a vivid and immersive environment. As the musician continues his crawl, his passion for discovery and connection with the natural world is palpable, encapsulating the spirit of adventure and the beauty of the subtropical wet forest.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1952
|
videos/HRA_part1/1952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young female cashier with a name tag, wearing a yellow shirt and black pants, is playfully jumping over a small, live hamster on the floor of a convenience store, capturing a lighthearted moment during her shift. The hamster, seen from above, scurries across the checkered floor, adding to the unexpected and amusing interaction. The cashier, still mid-jump, is framed by shelves of beverages and snacks, creating a surreal yet charming atmosphere in the store aisle. The scene is set under the bright lights of the shop, highlighting the unusual encounter between the employee and the tiny rodent.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the hamster's movements are also not smooth."
}
] |
seed46_2945
|
videos/HRA_part2/2945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great horned owl perches regally on a rugged tree branch, its piercing yellow eyes gazing intently into the distance under the cover of night. The owl's feathers are a stunning mix of brown, gray, and black, intricately patterned to provide perfect camouflage against the bark of the tree. Its large, feathered body appears robust, and its sharp talons grip the branch firmly. The owl's face is framed by a distinctive set of ear tufts, giving it a fierce and formidable appearance. In the background, the moonlight filters softly through the canopy of the forest, casting an ethereal glow on the owl and its surroundings. The atmosphere is tranquil, with only the sounds of nature breaking the silence, as the owl remains vigilant, ready to swoop down at any moment to catch its prey.]"
},
{
"from": "gpt",
"value": "Normal. The great horned owl's movements in the video are not smooth."
}
] |
seed46_1295
|
videos/HRA_part2/1295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a blue plaid shirt and black pants, sits cross-legged on a wooden floor, surrounded by a variety of eager pets. The room is dimly lit, with a single lamp providing a warm glow. The musician, with a friendly smile, gently strums an acoustic guitar, creating a soothing melody that fills the cozy space. Pets of different sizes and species gather around, their attentive faces showing enjoyment of the music and anticipation of being fed. A fluffy cat perches on the musician's lap, while a small dog sits patiently by a bowl of food, and a parrot watches from its cage. The scene conveys a sense of harmony and love between the musician and the pets, all sharing a special moment together.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand appears deformed."
}
] |
seed44_1709
|
videos/HRA_part1/1709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of a dense boreal forest, dappled sunlight filters through the canopy, illuminating the mossy ground. A curious capuchin monkey, clad in a red vest for visibility, explores this unfamiliar habitat. It cautiously descends from the treetops, venturing onto the forest floor, where it encounters an array of flora and fauna. The monkey walks among tall conifers, its eyes scanning the underbrush for interesting insects and plants, offering a unique perspective on life beneath the towering trees. Throughout the journey, the capuchin's red vest contrasts vividly with the lush greenery, making it a standout figure in the woodland scene.]"
},
{
"from": "gpt",
"value": "Normal. The monkey's red vest in the video is not fully generated."
}
] |
seed46_1727
|
videos/HRA_part2/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements in the video are not smooth."
}
] |
seed46_2085
|
videos/HRA_part2/2085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, donning a brown coat, scurries across a lush, green meadow under a partly cloudy sky. It dashes over the grass with its front paws lifted, revealing a clear view of its full body. Moments later, it continues its run, tail held high, near a wooden fence. The scene shifts to the beaver running alongside a tranquil stream, with trees in the background, showcasing its natural habitat. Lastly, it sprints with determination, its distinctive flat tail visible as it moves through its verdant environment.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's movements in the video are not smooth."
}
] |
seed46_1470
|
videos/HRA_part2/1470.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a navy suit, walks through a dimly lit urban park with tall trees and a brick path, carrying a briefcase in his right hand. Suddenly, a hyena appears, walking alongside him, also on two legs, dressed in a brown jacket and holding a small bag. The lawyer looks surprised but composed, maintaining his stride beside the anthropomorphic hyena, who mirrors his movements, creating a surreal and unexpected duo strolling together.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2774
|
videos/HRA_part2/2774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man with a bushy beard and wearing a brown jacket, blue jeans, and a black cap walks side by side with a coyote on a dirt path. They are set against a background of dense green forest and a sky filled with fluffy white clouds. The man, holding a wooden staff, and the coyote, with its distinctive bushy tail, navigate the wilderness together, their unlikely companionship highlighted by the peaceful, natural setting. Their journey unfolds on a trail marked by fallen leaves and tree roots, with the occasional glimpse of other wildlife in the surrounding woods.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3184
|
videos/HRA_part1/3184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green savanna setting, a gentle giraffe is being affectionately caressed by a human, both standing under a vast, open sky. The giraffe, with its distinctive spotted coat and long neck, leans into the touch, expressing comfort and trust. The human, wearing a khaki safari outfit, reaches up to stroke the giraffe's face, creating a tender moment of interspecies connection. The scene is framed by the natural beauty of the savanna, with distant trees and a clear blue sky, emphasizing the harmony between the human and the majestic animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1184
|
videos/HRA_part1/1184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human-sized hare, dressed in a worker's outfit complete with a yellow helmet, blue overalls, and a red shirt, dances gleefully in a lush green meadow. The hare performs an energetic jig, its oversized feet stomping playfully on the grass, while its long ears sway in time with the music. The background features a vibrant blue sky with fluffy white clouds, adding to the surreal yet delightful atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2766
|
videos/HRA_part1/2766.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a futuristic silver spacesuit and helmet, walks purposefully across a desolate, rocky lunar landscape under a blood-red sky, carrying a large canvas and palette. In the background, the Earth hangs like a blue marble, while space debris floats ominously above. The artist stops, sets up an easel, and begins painting a vivid depiction of the Earth amidst the cluttered cosmos, highlighting the urgent need for space garbage cleanup. The scene is bathed in the eerie glow of distant stars, creating a stark contrast between the barren moon and the vibrant artwork.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1940
|
videos/HRA_part2/1940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a well-dressed lawyer, wearing a dark suit, finds himself in a courtroom that resembles a jungle environment. Seated at a desk adorned with law books and vines, he attentively wipes a chimpanzee's face, which is sitting calmly beside him. The chimp, looking somewhat bewildered, is wearing a miniature suit and tie, adding to the surreal atmosphere of the scene. The lawyer's serious demeanor contrasts with the absurdity of the situation, creating a unique visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the chimpanzee's movements are also not smooth."
}
] |
seed42_214
|
videos/HRA_part0/214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young college student, casually dressed in a white T-shirt and blue jeans, diligently paints a room with bright yellow walls, focusing on a corner where two walls meet. The room is filled with natural light from a nearby window, illuminating the student's task. They wear protective goggles and a face mask, ensuring safety while working. The student is surrounded by painting supplies, including a ladder, paint cans, and brushes, indicating a thorough preparation for the project. As the camera pans out, we see the student's friends in similar attire, contributing to the painting effort, fostering a sense of camaraderie and teamwork in transforming the space.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, and the hand is distorted."
}
] |
seed42_1079
|
videos/HRA_part0/1079.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird's eyes are sharp and alert, observing its surroundings with an almost human-like curiosity. The bark of the tree it rests on is textured and dark, contrasting against the lighter shades of green leaves that surround it. In the background, the forest is alive with the sounds of nature; other birds calling, leaves rustling in the breeze, and the distant murmur of a stream. The crow, a symbol of intelligence and adaptability, stands proud and solitary, a master of its domain.]"
},
{
"from": "gpt",
"value": "Good. The crow's movements in the video are basically normal and smooth."
}
] |
seed42_1089
|
videos/HRA_part0/1089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dimly lit museum hall, a life-sized jaguar statue leaps across the space, seemingly frozen in mid-air as it jumps from one side to the other. The museum is filled with exhibits of historical artifacts, including ancient pottery and weaponry displayed in glass cases along the walls. The jaguar, crafted with intricate details and positioned mid-jump, captures the animal's agility and power, making it the focal point of the room. Its leap is so vividly portrayed that it appears ready to pounce at any moment, adding a dynamic element to the otherwise static environment.]"
},
{
"from": "gpt",
"value": "Bad. The head generation of the jaguar statue in the video is problematic."
}
] |
seed44_3085
|
videos/HRA_part1/3085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful swan floats on a serene lake, its elegant white feathers glistening under the golden afternoon sun. The water reflects the bird and the lush green trees that surround the peaceful scene, creating a harmonious blend of nature's beauty. The swan's long, curved neck forms a gentle S-shape as it gently propels itself through the crystal-clear water, leaving a series of delicate ripples in its wake. The tranquility of the moment is punctuated by the occasional sound of the swan's wings softly brushing against the surface of the lake.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2035
|
videos/HRA_part1/2035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape, a large, hairy mammoth tenderly caresses a smaller mammoth with its trunk, creating a touching scene of familial affection. The larger mammoth, covered in thick, shaggy fur, gently touches the younger one, who stands beside it, also covered in a coat of dark, coarse hair. Both creatures possess impressive tusks, with the adult displaying a more formidable set. They are surrounded by green vegetation and tall trees, with a waterfall visible in the distance, contributing to the serene atmosphere of this ancient bonding moment.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the action of the large mammoth touching the small mammoth with its trunk."
}
] |
seed44_1732
|
videos/HRA_part1/1732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, wide flounder fish is seen lying motionless on a clean, white surface, its right eye gazing upwards, while the left side of its body, which lacks an eye, is pressed against the surface. The fish has a natural sandy-brown color with darker mottled spots, giving it a realistic appearance. Its texture is depicted with fine, realistic details, emphasizing the flatness and unique form of the flounder species. The setting is minimalistic, focusing solely on the fish against the pristine white background, allowing for a clear and unobstructed view of the subject.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
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 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 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 hermit crab's digging actions in the video are basically normal, with slight inconsistency."
}
] |
seed44_3182
|
videos/HRA_part1/3182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male chef, wearing a clean white chef's jacket with short sleeves, meticulously polishes silverware in a well-lit kitchen. The utensils, which include forks, knives, and spoons, gleam under the bright lights as he works. Behind him, a large window reveals a bustling city skyline during daytime, adding a touch of urban sophistication to the scene. The chef's focused expression and the contrast between the shiny silverware and the white chef's jacket create a visually appealing composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1326
|
videos/HRA_part2/1326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a dark, rugged outfit, crawls across a desolate landscape marked by the aftermath of a white hole explosion, which illuminates the scene with an eerie glow. The actor's face is partially obscured by shadows, adding to the suspense. As he moves, the ruins of a futuristic city can be seen in the background, hinting at a catastrophic event. The actor's intense gaze and strained posture convey a sense of urgency and survival in this post-apocalyptic setting. The scene is framed by the remnants of advanced technology and the haunting beauty of the white hole's light, creating a dramatic contrast between destruction and awe.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1110
|
videos/HRA_part1/1110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black vest, sprints across a vast, barren lunar landscape, the iconic first steps of Neil Armstrong visible in the distance. Dust from the moon's surface billows behind him as he races, his movements fluid and effortless in the low gravity environment. A lunar module sits in the background, a stark contrast to the elegant attire of the sprinting waiter, who carries a silver serving tray in one hand, merging the worlds of fine dining and space exploration in a surreal scene.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated and discontinuous."
}
] |
seed44_1013
|
videos/HRA_part1/1013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a futuristic silver jumpsuit and helmet, dances joyously on a meticulously designed space movie set, surrounded by intricate control panels and glowing buttons. The set is filled with high-tech equipment and large, detailed screens displaying cosmic visuals. The writer's movements are expressive and free, conveying a sense of liberation and creativity amidst the futuristic environment. As they dance, the lights from the set illuminate their figure, highlighting their passion for storytelling in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1833
|
videos/HRA_part2/1833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dove with intricate feather patterns perches on a branch, nestled among lush green leaves that contrast beautifully with its pure white plumage. The bird looks towards the camera, revealing its detailed eye and beak. It then spreads its wings, displaying the impressive span and the delicate feather layers that catch the light, before taking flight against a clear blue sky, symbolizing peace and freedom. The final shot captures the dove soaring gracefully, its silhouette framed against the vastness of the sky, leaving behind a trail of tranquility.]"
},
{
"from": "gpt",
"value": "Bad. In the scene where the dove perches on a branch, the dove's beak is not generated, and there are issues with the generation of the dove's claws; in the scene where the dove soars in the clear blue sky, the dove's body structure is abnormally generated."
}
] |
seed42_1811
|
videos/HRA_part0/1811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black leggings, walks briskly across a campus path, holding textbooks and a coffee cup. Suddenly, a coyote appears in the frame, walking parallel to the path, about ten feet away from the student. The coyote, seemingly unbothered by the human presence, has a gray and brown coat, alert ears, and a bushy tail. It continues to walk alongside the path, offering a unique encounter between urban wildlife and a busy student on the go.]"
},
{
"from": "gpt",
"value": "Normal. The student's fingers in the video are not fully generated, there is a lack of facial generation, the hyena's limbs are partially missing, the walking is unrealistic, and there are issues with the eye generation."
}
] |
seed46_2453
|
videos/HRA_part2/2453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]"
},
{
"from": "gpt",
"value": "Bad. While crawling, the movements are not continuous."
}
] |
seed46_2247
|
videos/HRA_part2/2247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 captivating scene, a janitor in a space museum is seen cleaning near a large, detailed model of the International Space Station, which is submerged in a serene indoor pool. Wearing a yellow vest, gray pants, and a white shirt, he carefully maneuvers around the underwater exhibit, highlighting his unique cleaning duties. The water around him is crystal clear, allowing viewers to appreciate the intricate details of the space station replica. As he works, the ambient lighting from above gently illuminates the water, creating a mesmerizing visual effect that blends the worlds of space exploration and aquatic tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3085
|
videos/HRA_part1/3085.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 swan floats on a serene lake, its elegant white feathers glistening under the golden afternoon sun. The water reflects the bird and the lush green trees that surround the peaceful scene, creating a harmonious blend of nature's beauty. The swan's long, curved neck forms a gentle S-shape as it gently propels itself through the crystal-clear water, leaving a series of delicate ripples in its wake. The tranquility of the moment is punctuated by the occasional sound of the swan's wings softly brushing against the surface of the lake.]"
},
{
"from": "gpt",
"value": "Normal. The swan's eyes were not generated in the video."
}
] |
seed44_2377
|
videos/HRA_part1/2377.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic medical bay, a doctor, wearing a silver lab coat over a black jumpsuit, tends to a wounded panther-like alien with iridescent fur, bandaging its muscular foreleg. Suddenly, a space pirate bursts into the room, clad in red armor with a menacing helmet, brandishing a glowing plasma sword. The doctor, displaying remarkable courage, grabs a high-tech medical tool, which transforms into a defensive weapon, and prepares to protect the injured creature from the marauder. As the pirate advances, the doctor wipes sweat from their brow, their determined gaze never leaving the threat, ready to defend the alien panther at any cost.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1244
|
videos/HRA_part1/1244.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."
}
] |
seed46_1353
|
videos/HRA_part2/1353.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kangaroo stands in a vast, sunlit Australian outback, its shadow cast long on the sandy ground. It lifts a paw to its face, wiping it in a human-like gesture, its fur ruffled by a gentle breeze. The kangaroo's expressive face, with large, curious eyes, focuses intently as it performs this action, its body language conveying a sense of self-awareness. Behind it, the outback stretches to the horizon, dotted with scrub and sparse vegetation, creating a stark contrast to the active, sentient creature in the foreground.]"
},
{
"from": "gpt",
"value": "Normal. The kangaroo's movements are not smooth."
}
] |
seed42_3169
|
videos/HRA_part0/3169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray jacket and blue jeans stands outside a historic cinema, its marquee displaying classic film posters, evoking a sense of nostalgia and cinematic history. Moments later, the focus is on the man swimming in an indoor pool, surrounded by large windows that let in natural light, creating a contrast between the urban environment and the tranquility of water. He swims with purpose and strength, his silhouette framed by the water and the reflections of the pool tiles. The scene captures the essence of leisure and physical activity, juxtaposing the cultural experience of cinema with the personal enjoyment of swimming.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video did not appear."
}
] |
seed44_1856
|
videos/HRA_part1/1856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, identifiable by her backpack, dances whimsically across the screen, transitioning from a campus setting to an unexpected otter enclosure at a zoo. She's wearing a yellow top, denim shorts, and sneakers, embodying youthful energy. Suddenly, the scene shifts to a somber cemetery, where she continues to dance among the tombstones, now adorned in a black dress and boots, carrying a red umbrella. The juxtaposition of lively dancing in these varied locations, from educational grounds to wildlife exhibits to a place of remembrance, creates a surreal and captivating narrative.]"
},
{
"from": "gpt",
"value": "Bad. The video does not feature campus scenes, denim shorts, or sneakers as mentioned in the caption."
}
] |
seed44_112
|
videos/HRA_part1/112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 of fresh mackerel fish, glistening under bright lights, showcases their vibrant silver scales, deep blue stripes, and dark spots. The fish lie on a bed of ice, their eyes clear and shiny, indicating peak freshness. The background features a bustling market scene, with vendors selling various seafood and customers browsing the selection. Focused on the mackerel, the camera captures every detail of the fish's texture and color, making them the star of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1259
|
videos/HRA_part2/1259.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum hall with marble floors, an antelope taxidermy mount is displayed under a spotlight, its majestic form captured mid-leap. A diligent custodian wearing a green apron wipes the glass display case, ensuring the exhibit is pristine. The antelope, with its striking coat and alert posture, seems to leap over a miniature landscape within the display. The custodian, in a green uniform, carefully cleans the case, her reflection visible alongside the antelope's image. Throughout, the museum's grandeur is evident, with high ceilings, ornate moldings, and other exhibits surrounding the featured antelope.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1177
|
videos/HRA_part2/1177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and blue jeans, playfully swings a baseball bat near a serene swimming pool, backlit by the golden hour sunlight. He pauses mid-swing, the bat held aloft, with the shimmering water and lush greenery framing the scene. The worker then leans on the bat, gazing pensively at the inviting pool, the warm glow of the setting sun casting long shadows across the tranquil water. Finally, he takes a powerful swing, the motion frozen in time, with the idyllic pool setting and the vibrant colors of nature providing a vivid contrast to his robust action.]"
},
{
"from": "gpt",
"value": "Bad. The baseball bat flew away at the end, and the person's arm and hand became deformed. The person's head suddenly turned to the back."
}
] |
seed46_1896
|
videos/HRA_part2/1896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike sequence, an astronaut clad in a pristine spacesuit gently caresses a bobcat on the lunar surface, under the Earth's watchful gaze. The astronaut's visor reflects the desolate landscape, while the bobcat, undeterred by its extraterrestrial surroundings, responds with curiosity. The scene is illuminated by the distant Earthshine, casting a soft glow on the moon's dusty terrain, highlighting the tenderness of this interstellar encounter.]"
},
{
"from": "gpt",
"value": "Normal. The cat in the video has uncoordinated movements while walking."
}
] |
seed44_2043
|
videos/HRA_part1/2043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket and dark pants, walks down a clean hallway illuminated by bright overhead lights, holding a small, active gerbil in a transparent plastic ball. The gerbil, running energetically on its wheel inside the ball, seems unfazed by the movement. The janitor navigates around a corner, continuing his journey with the gerbil in tow, the clean environment and well-lit corridor reflecting the diligence of his custodial duties.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's body is twisted, the face is distorted, and the person's hand is twisted."
}
] |
seed44_1535
|
videos/HRA_part1/1535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, wearing a red plaid shirt and blue jeans, tenderly bathes a muddy dog outside on a sunny day, using a white hose with a red nozzle. The farmer, with a warm smile and caring hands, rinses the dog with water from the hose, as the playful animal stands on its hind legs, paws resting on the farmer's knee, enjoying the attention. The scene is set against a backdrop of lush green fields and a clear blue sky, with the farmer's weathered barn in the distance, creating a heartwarming rural atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers appear deformed, and the water is not coming from the pipe."
}
] |
seed44_2712
|
videos/HRA_part1/2712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo, under the neon lights that bathe the bustling streets, a lone coyote wanders. Its golden eyes reflect the urban glow as it moves through the crowded alleyways. It pauses, the camera capturing a close-up of its face, showing the wild creature in an unexpected environment. The coyote then proceeds to wipe its face with a paw, a moment of natural behavior in stark contrast to the man-made surroundings. Behind it, the signs in Japanese and English, the busy storefronts, and the occasional passerby underscore the unlikely scene of a wild animal navigating the concrete jungle.]"
},
{
"from": "gpt",
"value": "Normal. The jackal can be clearly seen turning its head to look around, the movements are basically normal but there is some lack of coordination."
}
] |
seed42_1384
|
videos/HRA_part0/1384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, spiky European hedgehog runs energetically across a lush, green garden, its tiny legs moving swiftly beneath it. The hedgehog, with its distinctive white-tipped spines, navigates through the foliage with determination, its snout pointed forward. In another scene, the hedgehog continues its journey, now scampering across a wooden deck, its movements quick and agile. The video captures the hedgehog's active nature, showcasing its ability to navigate various terrains with ease, all under the cover of night, as indicated by the dimly lit surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's claws in the video are deformed."
}
] |
seed46_2525
|
videos/HRA_part2/2525.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, sci-fi setting, a large moose, adorned with a futuristic, glowing harness, stands calmly beside a colossal space elevator. The moose is being gently caressed by a figure dressed in a spacesuit, creating an unexpected yet tender moment between species. The vastness of space looms overhead, with stars and distant galaxies visible, contrasting with the intimate interaction on the ground. The space-suited individual continues to stroke the moose affectionately, while the majestic animal remains serene, its eyes reflecting curiosity and trust in this otherworldly encounter.]"
},
{
"from": "gpt",
"value": "Bad. The moose and astronaut's movements in the video are not smooth."
}
] |
seed42_2009
|
videos/HRA_part0/2009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an astrophysics laboratory filled with high-tech equipment and screens displaying cosmic data, a worker, wearing a white lab coat over a gray shirt and dark pants, dances energetically. Accompanying him is a live rabbit, hopping playfully nearby, seemingly unfazed by the unusual environment. The scientist's joyful movements contrast with the serious scientific surroundings, creating a whimsical and unexpected scene. Throughout, the lab remains brightly lit and organized, with the scientist and the rabbit sharing a moment of lightheartedness amidst the serious pursuit of knowledge.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1109
|
videos/HRA_part1/1109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense, lush canopy of a subtropical wet forest, a small brown bat clings upside-down from a branch, its wings folded tightly. The bat begins to groom itself, carefully wiping its wing membranes with its mouth, a behavior essential for maintaining health and flight efficiency. The bat continues its meticulous grooming, wiping its body and wings with its mouth, highlighting the importance of self-care in these nocturnal creatures. Throughout the scene, the bat remains in the same position, hanging upside-down from a branch in the rich greenery of the subtropical wet forest, as it focuses on cleaning its wings.]"
},
{
"from": "gpt",
"value": "Bad. The bat's head is deformed, and the wings are twisted."
}
] |
seed46_2202
|
videos/HRA_part2/2202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone giraffe runs across an open savanna, its distinctive patterned coat and long legs propelling it forward in a graceful stride. The scene is captured in vibrant detail, with the grassy plains stretching out behind the majestic creature. The sky is a brilliant blue, dotted with fluffy white clouds, providing a stunning contrast to the earthy tones of the giraffe's coat. As it runs, its spots seem to blur, creating a mesmerizing effect that highlights the beauty and power of this remarkable animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_31
|
videos/HRA_part2/31.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, round and plump, navigates the vibrant coral reef with its intricate patterns and varied marine life, showcasing the wonders of the underwater world. Its body, inflated to twice its normal size, displays a mesmerizing display of geometric shapes in muted tones against the backdrop of the deep blue sea. The fish's small, beady eyes stand out prominently on its distended form, while its fins propel it gracefully through the water, surrounded by an array of colorful corals and other sea creatures. This underwater scene highlights the unique survival mechanism of the pufferfish in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1436
|
videos/HRA_part2/1436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red starfish with five arms and tiny white spots rests on a bed of pristine white sand, surrounded by shallow turquoise waters that gently lap at its sides. Sunlight filters through the water, casting shimmering light patterns on the starfish and sand. In the background, a vast ocean stretches to the horizon, meeting a clear blue sky dotted with fluffy white clouds. The overall scene exudes tranquility and beauty, capturing the essence of life beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2604
|
videos/HRA_part1/2604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate fashionable glasses, the director was not standing by the swimming pool, and the ibex did not swim gracefully underwater."
}
] |
seed46_1082
|
videos/HRA_part2/1082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal setting, a student, identifiable by their backpack and casual attire, is crawling through a crowded mall. This unusual behavior attracts the curious gaze of shoppers, who pause to watch. Unexpectedly, a hyena, also crawling and wearing a backpack, joins the student. Both crawl side by side, blending into the urban environment, creating a bizarre yet harmonious scene amidst the mall's vibrant storefronts and bustling pedestrian traffic.]"
},
{
"from": "gpt",
"value": "Bad. The crawling movements of the student and the hyena in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed46_2413
|
videos/HRA_part2/2413.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing a black jacket and dark jeans, crawls along the wooden planks of a weathered pier, the sun casting a warm glow over the scene. The pier extends into a serene body of water, likely a lake or a calm sea, with the man's low position emphasizing vulnerability or stealth. The setting is peaceful, with no other people visible, and the man's unusual behavior draws attention, creating a sense of mystery or urgency in the otherwise tranquil environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1980
|
videos/HRA_part0/1980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a cloudless blue sky, a lone brown camel slowly crawls across the dunes, its large, expressive eyes looking straight ahead. The animal's body is positioned low to the ground, its right front leg extended forward in a crawling motion, and its left hind leg bent beneath it. The texture of the camel's fur is detailed, showing the natural variations in color and the dryness of the skin. The sand dunes form dramatic curves and ridges, with soft shadows highlighting the contours created by the sun's light. In the distance, more dunes stretch to the horizon, emphasizing the camel's solitary journey through this expansive landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2065
|
videos/HRA_part0/2065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy landscape under a clear blue sky, a woman wearing a flowing, cream-colored robe gently caresses a kneeling camel adorned with ornate saddles and blankets. The scene captures the tender bond between the woman and the camel, with her hand softly stroking its head. The woman's attire complements the desert environment, and her gentle touch conveys a sense of care and connection. Nearby, more camels stand, their presence adding to the serene atmosphere of the desert setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, the hand is twisted, the camel's neck is twisted, and the face is distorted."
}
] |
seed42_1377
|
videos/HRA_part0/1377.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with a striking resemblance to Taylor Swift, known for her blonde hair and red lips, is seen in a series of scenes. First, she stands confidently against a backdrop of a gray wall, wearing a black leather jacket, a gray top, and black pants. Her stance suggests strength and determination. In the next scene, she walks away from the camera, showcasing her outfit and a casual, relaxed demeanor. Then, she is captured in a moment of laughter, leaning back, her smile wide and genuine, conveying a sense of joy and freedom. Lastly, she is seen mid-stride, walking purposefully towards the camera, her expression serious and focused, embodying the essence of the song 'Shake It Off' by Taylor Swift.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers in the video are not fully generated, and her facial features are deformed."
}
] |
seed44_2032
|
videos/HRA_part1/2032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red kangaroo, distinguishable by its ruddy fur, bounds across a vast, arid landscape under a cloud-dappled sky, showcasing its powerful hind legs and long, muscular tail for balance. It leaps gracefully over the terrain, highlighting its natural agility and strength in motion. The kangaroo's focused gaze and determined posture emphasize its purposeful sprint across the open, scrubland environment, with distant hills providing a scenic backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's limbs in the video are severely distorted and deformed."
}
] |
seed42_1802
|
videos/HRA_part0/1802.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, wearing a red and white striped shirt, dark pants, and a vibrant tiger head costume, energetically dances in front of a large crowd at a lively pep rally. The atmosphere is electric, filled with cheering fans and the spirit of school pride. The young man, donning the mascot's full-body suit complete with furry orange and black stripes, performs dynamic dance moves to the beat of an upbeat marching band, captivating the audience with his animated antics. Surrounded by enthusiastic supporters waving banners and flags, the scene pulses with excitement and unity, perfectly capturing the essence of collegiate spirit.]"
},
{
"from": "gpt",
"value": "Bad. The body movements of the character in the video are not coordinated."
}
] |
seed46_2930
|
videos/HRA_part2/2930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, clad in a gray T-shirt and black cargo pants, methodically mops the floor of a modern industrial space, surrounded by sleek machinery and equipment. His attire includes a name badge and a pair of safety glasses hanging around his neck, signifying his professional role. The scene is lit by bright overhead lights, casting shadows that emphasize the rhythmic motion of the mop. The engineer's focused gaze and steady hand convey a sense of duty and precision as he tackles the mundane task of cleaning, set against the backdrop of a high-tech environment.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the engineer using a mop, the movements are basically normal but there is some lack of coordination."
}
] |
seed44_2156
|
videos/HRA_part1/2156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, modern clothing store, a friendly, young female cashier with brown hair tied in a bun assists a male customer. She is shown measuring the hem of a pair of beige slacks, using a measuring tape, while the man stands patiently. The pants are held up by the customer, who wears a casual outfit consisting of a blue shirt and dark pants. The cashier, dressed in a black apron over a white blouse, carefully marks the fabric with a tailor's chalk, indicating where the alteration should be made. The scene is set against the backdrop of the store, with various racks of clothes visible in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2506
|
videos/HRA_part1/2506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a lone camel, adorned with vibrant red and yellow fabrics, stands gracefully at the edge of a bustling highway under a vivid orange sunset. Vehicles whiz by in the background, forming streaks of light against the twilight sky. The camel begins to sway and dance, moving its body to an unheard rhythm, creating a surreal contrast between the wild and the urban landscape. Its movements are fluid and expressive, drawing attention despite the chaos of the surrounding traffic. The highway lights and car headlights illuminate the scene, casting dramatic shadows as the camel continues its dance, a captivating spectacle where nature meets the modern world.]"
},
{
"from": "gpt",
"value": "Bad. The camel's dancing movements can be clearly seen in the video, but the movements are not very continuous and smooth, and there is a lack of coordination in the camel's limbs."
}
] |
seed44_3191
|
videos/HRA_part1/3191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, its woolly coat dark and shaggy, is seen wading through a cold, icy lake during the last Ice Age. Its large body creates ripples in the water, and it moves with a surprising grace for its size. The mammoth uses its tusks to navigate through the submerged branches and logs, demonstrating its adaptability to aquatic environments. Despite the freezing temperature, the mammoth appears comfortable, showcasing its ability to thrive in harsh conditions. The backdrop is a lush, green landscape with distant mountains, highlighting the diversity of habitats these ancient creatures inhabited.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's walking in the video is basically normal, but there is slight movement disharmony."
}
] |
seed44_2163
|
videos/HRA_part1/2163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical wet forest, twin toddlers wearing colorful, waterproof overalls and wide-brimmed hats are crawling on a natural wooden log bridge, exploring their surroundings with wide-eyed curiosity. They crawl through a dense thicket of vibrant green foliage, their clothing bright against the earthy tones of the forest floor. The babies continue their adventure, crawling over a carpet of moss and fallen leaves, undeterred by the rugged terrain. Their journey concludes as they crawl towards a shaft of sunlight filtering through the dense canopy above, illuminating their path in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1478
|
videos/HRA_part1/1478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 her uniform consisting of a white collared shirt, black pants, and a name badge, takes a break from her duties to clean the gutters of the medical facility. She stands on a ladder, her gloved hands scooping out debris, with the sunny day highlighting her dedication beyond her regular responsibilities. The video showcases her multitasking abilities, as she balances her healthcare role with the practical needs of maintaining the clinic's infrastructure, all while dressed in her recognizable nursing attire.]"
},
{
"from": "gpt",
"value": "Normal. The character's actions of clearing trash in the video are basically normal, with slight awkwardness."
}
] |
seed42_2117
|
videos/HRA_part0/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1381
|
videos/HRA_part2/1381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 with short brown hair, styled in a pixie cut, sits serenely on a yoga mat placed atop a wooden floor, set within a minimalistic room illuminated by soft, natural light. She wears a black tank top and gray yoga pants, her eyes gently closed as she focuses on her breathing. Her hands rest gracefully on her knees, adorned with a silver ring and bracelet, while a single earring dangles from her left ear. The atmosphere is calm and peaceful, with a potted plant and a water bottle visible in the background, hinting at her wellness routine.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1163
|
videos/HRA_part0/1163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a vibrant, freshly-caught salmon, its skin shimmering with hues of silver and pink, glistens under bright lights. The fish, set against a dark, textured background, boasts a rich gradient of colors from deep red to pale orange on its flesh, which is artfully presented with a diagonal cut to reveal its succulent texture. Delicate wisps of smoke rise from the salmon, indicating its recent preparation, while a chef's hand, adorned with a simple wedding band, holds a sharp filleting knife nearby, ready to prepare this exquisite piece of seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1484
|
videos/HRA_part0/1484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious, softly lit room with a neutral color palette, two children, a boy and a girl, both wearing pajamas, are seen playing together. The boy, wearing blue pajamas, crawls across the floor, while the girl, dressed in pink pajamas, manipulates a gravity control device, causing everyday objects to float around them. The floating items include a teddy bear, a toy car, and a book, creating a whimsical atmosphere. The children laugh and play among the floating objects, the girl adjusting the gravity device to move the items closer or further away, all within the cozy, safe environment of their playroom.]"
},
{
"from": "gpt",
"value": "Normal. The character's body is twisted, the face is distorted, the arms are twisted, the hands are deformed, and the legs are twisted."
}
] |
seed42_2879
|
videos/HRA_part0/2879.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a majestic stag with a full, impressive rack of antlers finds itself in an industrial setting, surrounded by large, gray warehouses under a cloudy sky. The deer begins to move gracefully, almost as if it's dancing, its hooves delicately stepping on the concrete ground. The scene is surreal, with the wild animal seemingly unfazed by the urban environment, embodying a unique blend of nature and industry as it prances amidst the towering structures.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2649
|
videos/HRA_part0/2649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, clad in a navy blue NASA spacesuit with patches and a white name tag, walks purposefully down a pristine, metallic corridor aboard a futuristic space station. The station's interior is illuminated by soft, ambient lighting, and features advanced technology, including touch-screen panels and monitoring equipment, highlighting the cutting-edge nature of the facility. The doctor's movements are unhurried yet deliberate, conveying a sense of routine and familiarity within the microgravity environment. The backdrop showcases the intricate design of the space station, with various modules visible through windows, offering glimpses into different areas where scientific research and daily activities take place.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2709
|
videos/HRA_part1/2709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red bandana, black sleeveless shirt, and black jeans, skillfully stir-fries ingredients in a wok over a high flame. The kitchen features a large stainless steel hood vent and several pots hanging above, giving it a professional look. The artist, known for his energetic stage presence, exhibits precision and focus as he deftly flips vegetables and proteins in the pan. The vibrant colors of the food contrast beautifully with the dark metal utensils and the flames beneath the wok, creating a visually engaging scene. Throughout the process, he maintains his cool demeanor, occasionally checking the seasoning and adjusting the heat, demonstrating his culinary prowess alongside his musical talent.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_298
|
videos/HRA_part2/298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 enthusiastic engineer in a red shirt, beige vest, and khaki pants is seen in an amusement park, surrounded by roller coasters, with a Ferris wheel visible in the distance. He runs through the park with a map in hand, passing by various rides and attractions. The video captures him stopping briefly to study the map, before continuing his energetic jog through the lively environment, showcasing his passion for both engineering and the thrilling atmosphere of amusement parks.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1148
|
videos/HRA_part0/1148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent male worker, clad in a green jacket, dark pants, and brown gloves, meticulously rakes a large pile of autumn leaves in the foreground, creating a tidy heap. Behind him, a vast expanse of fallen leaves covers the grassy area, extending into the distance. The scene is set in a spacious backyard surrounded by a wooden fence, with a row of mature trees framing the horizon. As the worker continues to rake, the pile of leaves grows larger, highlighting the laborious task at hand. Throughout the process, the worker maintains a focused demeanor, his movements methodical and efficient, embodying the essence of hard work and determination.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2838
|
videos/HRA_part0/2838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate history teacher, dressed in period costume from the Renaissance era, conducts an engaging lesson at a historical site, a grand stone castle surrounded by lush greenery. The teacher, wearing a brown velvet dress and a white lace collar, begins the class by gesturing dramatically towards the ancient stone walls, captivating the students' attention. Suddenly, the teacher breaks into an elegant Renaissance dance, twirling gracefully on the cobblestone courtyard, demonstrating the cultural significance of dance in historical context. The students, inspired by the teacher's enthusiasm, join in, forming a circle around her, as they learn about the rich history and culture of the era through the art of dance.]"
},
{
"from": "gpt",
"value": "Bad. The woman dancing in the video is very unsmooth, with uncoordinated movements."
}
] |
seed44_2312
|
videos/HRA_part1/2312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male chef, donning a white chef's uniform with black stripes and a matching cap, meticulously washes dishes in a commercial kitchen. The room is illuminated by bright overhead lights, casting a glow on the stainless steel sink and countertops. Steam rises from the hot water, creating a misty atmosphere. The chef's sleeves are rolled up to his elbows, revealing tattoos, as he focuses intently on cleaning each plate with precision and care. In the background, the bustling kitchen is visible, with other chefs preparing meals and the sounds of clattering pots and sizzling pans adding to the lively ambiance.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.