video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_3028
|
videos/HRA_part0/3028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1699
|
videos/HRA_part1/1699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a blue button-down shirt and khaki pants, rearranges furniture in a cozy room with wooden floors and a fireplace, aiming to find inspiration. He thoughtfully adjusts a brown leather sofa, placing it at an angle near the hearth, with a glass coffee table in front. Next, he moves a wooden chair with a green cushion to the right side of the sofa, creating a conversational space. Then, he positions a tall bookshelf behind the chair, filled with books and trinkets, adding character to the room. Lastly, he places a small wooden desk with a typewriter next to the window, basking in natural light, perfect for writing, all while maintaining the warm, inviting atmosphere of the space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3109
|
videos/HRA_part0/3109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned in a cozy red sweater and glasses, sits at a wooden table in a rustic cabin, illuminated by the warm glow of a lamp. She holds knitting needles and a half-completed green scarf, with a laptop displaying a novel manuscript nearby. The atmosphere is serene, with the occasional sound of knitting needles clicking and the soft clacking of keys as she types. A cup of tea sits beside her, adding to the peaceful scene. Behind her, a large window frames a view of lush greenery, providing a natural backdrop to her creative space.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1044
|
videos/HRA_part1/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers appear deformed."
}
] |
seed46_1298
|
videos/HRA_part2/1298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a crisp white shirt, black vest, and black trousers, is seen playfully dancing with an otter. The otter, wearing a tiny bow tie, mirrors the waiter's movements, adding to the surreal atmosphere. The two are surrounded by a softly lit, elegant dining room, with tables set for dinner and fine art adorning the walls. The waiter, with his professional attire, and the otter, with its playful nature, create a harmonious and unexpected dance partnership, captivating the audience with their synchronized steps.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not smooth, and the otter's movements are not smooth."
}
] |
seed44_1012
|
videos/HRA_part1/1012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 waiter dressed in a crisp white shirt and black trousers finds himself in an unexpected dance-off with a mischievous monkey. The two are surrounded by an array of exotic plants and flowers, giving the impression of a lush garden or jungle setting. The waiter, maintaining a professional demeanor despite the oddity of the situation, gracefully moves to an unseen rhythm, while the monkey, dressed in a miniature tuxedo, gleefully mimics his every step. The playful exchange is captured in high definition, with vibrant colors and dynamic movements, creating a surreal yet captivating spectacle.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_244
|
videos/HRA_part2/244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and holding a fire axe, leaps over a low obstacle in a training course, with a large, taxidermied leopard positioned on the ground nearby, creating an unusual juxtaposition of elements. The firefighter's helmet gleams under the bright lights, and the scene is set against a backdrop of firefighting equipment and vehicles, emphasizing the intensity and unpredictability of their training exercises.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's hands and feet, and the specimen leopard generation have issues; the fire axe in the firefighter's hand suddenly disappears in the middle frame."
}
] |
seed42_1178
|
videos/HRA_part0/1178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene reminiscent of a futuristic sci-fi film, a CGI-generated cobra, adorned with bioluminescent patterns, slithers across a metallic, interstellar platform set against the backdrop of a cosmic wormhole. The snake's scales shimmer with neon colors, creating a mesmerizing contrast against the cold, metallic surface. As it moves, the cobra passes by a series of glowing control panels, hinting at advanced technology integrated into the environment. In the distance, the swirling vortex of the wormhole pulses with vibrant hues, adding an element of mystery and wonder to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The cobra in the video is not fully generated."
}
] |
seed46_1143
|
videos/HRA_part2/1143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret walks across a wooden floor in a cozy home, its soft, brown fur glistening under the warm indoor lighting. It moves with curiosity, exploring its surroundings with a playful spirit. The ferret wears a tiny red bow tie around its neck, adding a touch of whimsy to its adventurous journey. Its bright eyes and twitching nose showcase its alertness and interest in the environment, making for an endearing scene of a domesticated pet enjoying its day.]"
},
{
"from": "gpt",
"value": "Normal. The video shows an unreasonable generation where the ferret's legs are cut off."
}
] |
seed44_1027
|
videos/HRA_part1/1027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, clad in a red jacket, blue jeans, and black running shoes, races through the bustling city streets at night, passing by a diverse array of shops and restaurants. The urban landscape is illuminated by the glow of neon signs and streetlights, casting dynamic shadows as the runner weaves through the crowd. The scene captures the energy and vibrancy of city life, with the writer's determination and focus highlighted by the motion blur of the passing scenery. The narrative unfolds as the runner passes landmarks like a movie theater, a busy crosswalk, and a street food vendor, all contributing to the vivid tapestry of the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The legs twist and suddenly disappear or reappear in between frames, passing through obstacles."
}
] |
seed46_1492
|
videos/HRA_part2/1492.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire of a gray shirt and black shorts, playfully swings a bat at a small pinata hanging from a tree branch in a backyard setting, surrounded by lush greenery. Moments later, the same student is seen enjoying a refreshing swim in a backyard pool, splashing about in a yellow swimsuit, with a diving board visible in the background. The scene captures the essence of youthful fun and leisure activities, transitioning seamlessly from a game of bat-and-ball to a spontaneous dip in the pool.]"
},
{
"from": "gpt",
"value": "Normal. The student's movements are not smooth."
}
] |
seed44_2955
|
videos/HRA_part1/2955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, is kneeling by a blocked drain on a rainy day, amidst urban surroundings. He wields a long, coiled hose and a specialized tool, methodically working to unclog the drain. His focused expression and the rain-soaked environment underscore the challenging task at hand. Moments later, he pulls the clog from the drain, revealing a mix of debris, while water begins to flow freely again, thanks to his diligent efforts. Throughout, the firefighter's protective gear and the wet cityscape provide context to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed44_2997
|
videos/HRA_part1/2997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tropical dry forest, two smiling children, a boy and a girl, are seen caressing a friendly wild animal, possibly a capybara, against the backdrop of a dense forest with tall trees and patches of sunlight filtering through the leaves. The children wear simple clothing suitable for outdoor adventures, and their joyful expressions convey a sense of connection with nature. They sit on the forest floor covered with dry leaves and twigs, surrounded by various plants and vegetation typical of a tropical dry forest environment. The scene captures a tender moment of human-animal interaction in a natural setting, highlighting the innocence and curiosity of childhood amidst the wonders of the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of children in the video is uncoordinated, fingers are deformed, feet are missing, and the heads and paws of wild animals are generated inconsistently."
}
] |
seed46_214
|
videos/HRA_part2/214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young 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 video does not generate a ladder."
}
] |
seed46_2686
|
videos/HRA_part2/2686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged female teacher, wearing a dark blue blazer over a white blouse and carrying a black handbag, walks purposefully down a wide hallway with high ceilings, resembling the interior of a university building. The walls are adorned with educational posters, and the floors are covered with brown carpeting. As she strides forward, the scene subtly transitions to reveal a large window behind her, displaying a breathtaking view of Neptune's turbulent atmosphere, filled with vivid blue and green clouds swirling majestically. This unique setting, combining the familiar environment of a school with the awe-inspiring backdrop of a distant planet, creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2136
|
videos/HRA_part2/2136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed character, resembling a panda with black-rimmed eyes and a friendly smile, walks down a bustling city street. Dressed in a full-body panda suit, they navigate the urban landscape, passing by pedestrians and city structures. The panda mascot's outfit includes large, padded paws and a fuzzy, rounded silhouette, adding to the whimsical nature of the scene. As they stroll, the surrounding environment, filled with buildings and people going about their day, contrasts with the playful presence of the panda.]"
},
{
"from": "gpt",
"value": "Normal. The panda's walking motion in the video is basically normal, but there is slight disharmony."
}
] |
seed42_2825
|
videos/HRA_part0/2825.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a red swimming cap and goggles is seen underwater, swimming in a clear, blue pool. Above the water, a majestic lion stands on the edge of the pool, observing the swimmer. The scene is set against the backdrop of quaint towns in the distance, their rooftops visible above the trees, creating a surreal and unexpected juxtaposition of elements. The engineer's swimming motion is smooth and deliberate, contrasting with the stillness of the lion, which adds to the dreamlike quality of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1763
|
videos/HRA_part2/1763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious living room, a cashier, wearing a red shirt and khaki pants, is seen assembling a wooden table. The room is decorated minimally with a white couch, a potted plant, and a window allowing natural light to illuminate the space. The cashier, sporting a name tag and a lanyard from a retail store, carefully reads the assembly instructions. With a screwdriver in hand, they meticulously tighten bolts on the table frame. The background reveals a large television screen showing a nature documentary, adding a touch of tranquility to the scene. Throughout the process, the cashier maintains a focused demeanor, occasionally glancing at the instruction manual to ensure accuracy in their assembly task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_116
|
videos/HRA_part1/116.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green 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": "Normal. The otter's movements in the video are not smooth."
}
] |
seed46_1661
|
videos/HRA_part2/1661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh Atlantic cod fish, with clear eyes and shiny skin, rests on a bed of ice. Its mouth is slightly open, and it has a small silver ring through its lip. The fish is surrounded by green herbs and lemon slices, adding a pop of color against the icy background. The camera captures the cod from various angles, highlighting its texture and freshness, perfect for culinary preparations. Throughout the video, the fish remains stationary on the ice, the camera's movement providing dynamic visuals.]"
},
{
"from": "gpt",
"value": "Normal. The small silver ring mentioned in the caption on the cod's mouth does not appear in the video."
}
] |
seed46_1882
|
videos/HRA_part2/1882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated female nurse, clad in a white uniform and wearing her hair in a bun, attentively checks a smoke detector mounted on the ceiling in a modern hospital hallway. The space is pristine and well-lit, with pale green walls and white trim, exuding a sense of cleanliness and professionalism. The nurse, displaying her commitment to safety, uses a long, red-handled tool to test the device, ensuring it functions properly in the healthcare environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_271
|
videos/HRA_part1/271.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow safety vest, blue jeans, and a brown shirt, interacts with a moose in a serene lake, both swimming together in the cool, clear water. The scene opens with the worker paddling gently, the moose swimming nearby, and lush greenery framing the tranquil waterscape. Next, the worker and the moose are seen swimming side by side, the man's safety vest and the moose's large antlers clearly visible above water. Then, the worker, still in his yellow safety vest, blue jeans, and brown shirt, floats on his back, the moose swimming peacefully beside him. Finally, the two unlikely companions, the worker in his distinctive attire and the majestic moose, continue to swim together in harmony, the peaceful lake and verdant surroundings creating a picturesque setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth."
}
] |
seed42_3150
|
videos/HRA_part0/3150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, possibly his cub, against the backdrop of a lush, green savanna during golden hour. The adult lion, with its voluminous tawny mane, displays affection, while the cub, sporting a lighter coat and smaller stature, responds with innocent playfulness. The heartwarming interaction unfolds under a vast, cloud-dappled sky, with scattered acacia trees and distant mountains completing the serene African landscape. This intimate moment captures the rare display of tenderness and bonding within the lion family, far from the typical fierce and powerful image associated with these animals.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2920
|
videos/HRA_part1/2920.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a crisp white shirt, black trousers, and a waistcoat, unexpectedly finds himself fixing a leaky faucet in a vintage-styled restroom. With a wrench in hand, he leans over the basin, his face concentrated as he works under the sink. The scene captures the unusual sight of the waiter, his attire contrasting with the task at hand, as he tightens the faucet, the water now streaming smoothly. The room is adorned with antique fixtures and a classic mirror above the basin, adding to the unique scenario of a waiter turned handyman.]"
},
{
"from": "gpt",
"value": "Bad. The server's hands appear deformed. The faucet appears out of nowhere, which does not match real life."
}
] |
seed42_1651
|
videos/HRA_part0/1651.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a costume reminiscent of the 1920s, complete with a flapper dress and feather headband, dances gracefully amidst the lush greenery of a temperate rainforest. Sunlight filters through the dense canopy, casting dappled shadows on the forest floor. The actor performs a series of fluid movements, twirling and leaping with the elegance of a seasoned performer, while the vibrant flora and fauna of the rainforest provide a stunning natural backdrop. The atmosphere is one of enchantment and vitality, as the dancer's artistry harmonizes with the beauty of the ancient woodland.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, legs, and hands."
}
] |
seed46_2108
|
videos/HRA_part2/2108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an imaginative scene, a waiter, dressed in a classic black suit and tie, carefully balances a tray of cocktails above his head as he swims underwater. Surrounding him are porcupines, wearing tiny swim caps and goggles, swimming alongside in a synchronized pattern, all submerged in a vast, clear pool under soft, ambient lighting. The waiter's face, visible beneath the water, shows a mix of concentration and amusement at the unusual company he keeps during his aquatic beverage service.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand is deformed, with a third hand appearing, and the hedgehog's body is deformed while swimming."
}
] |
seed46_2313
|
videos/HRA_part2/2313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden jackal leaps gracefully over a log in the middle of a grassy savanna, its body stretched mid-air, showing agility and strength. The jackal, with its keen eyes and alert posture, exhibits a powerful jump, clearing the obstacle effortlessly. The scene captures the animal's dynamic movement against a backdrop of tall grasses swaying in the breeze, highlighting the beauty and resilience of this wild canine in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2024
|
videos/HRA_part0/2024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, bespectacled female student sits cross-legged on a clean, white surface, diligently hemming a pair of black pants with a focused expression. She wears a grey cardigan over a white collared shirt and blue jeans, her attire casual yet neat. The environment is bright and minimalistic, with ample natural light illuminating her task. Tools of her activity, such as scissors, thread, and a needle, are neatly arranged within reach, highlighting her attention to detail and organization. The scene captures her absorbed in the sewing process, her hands skillfully manipulating the fabric, demonstrating a blend of practical skill and academic studiousness.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed46_3208
|
videos/HRA_part2/3208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful male chef, wearing a traditional white chef's uniform with a red neckerchief and a brown apron, stands in a modern kitchen. He holds a large, open recipe book in his hands and writes with a silver pen, his face expressing deep concentration. The kitchen is filled with stainless steel appliances and shelves stocked with various cooking ingredients, creating a professional culinary atmosphere. The chef's sleeves are rolled up, revealing a watch on his wrist, and he occasionally glances up from the book, likely checking the progress of dishes being prepared in the bustling kitchen environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3148
|
videos/HRA_part2/3148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 weathered farmer, donning a gray beanie, blue flannel shirt, and glasses, sits on a wooden chair in a sunlit barn. He cradles a large crochet hook and works on a vibrant, multicolored blanket, surrounded by rustic details like hay bales and farm tools. The scene highlights his unexpected hobby, showcasing the rich textures of the yarn against the rough wood of the barn. The warm, golden light illuminates his focused face and the intricate pattern emerging from his skilled hands, creating a serene and surprising contrast between traditional farming life and the art of crochet.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's action of weaving a blanket is not smooth."
}
] |
seed42_288
|
videos/HRA_part0/288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short, brown hair and glasses, wearing a patterned, blue medical scrub top and black pants, hangs framed pictures on the walls of a brightly lit hospital room. She stands on a small, yellow stool to reach the wall above a patient's bed, where a colorful, abstract artwork is already hung. The nurse carefully aligns a new frame next to it, creating a comforting environment for patients. She uses a level to ensure each piece is straight, revealing her attention to detail in the cozy, well-decorated space. Throughout, she maintains a warm smile, demonstrating her caring nature as she enhances the room's aesthetic with more framed prints.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1514
|
videos/HRA_part0/1514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, windswept grassland under a partly cloudy sky, a janitor wearing a yellow vest, blue jeans, and a white shirt is seen wiping a transparent, rectangular window that floats in front of him. The serene landscape stretches to the horizon, dotted with distant trees, while the janitor diligently cleans the window with a cloth, revealing the pristine clarity of the glass. The peaceful scene is punctuated by the gentle sway of the tall grass and the solitude of the janitor's task, emphasizing the unexpected context of maintenance in the midst of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1871
|
videos/HRA_part1/1871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled features and casual attire of a blue shirt and jeans, gently caresses an antelope at a zoological park. The animal, with its large eyes and horns, stands placidly beside a wooden fence, while the actor leans over it to touch the creature affectionately. In another frame, the actor, now wearing a green shirt and khaki pants, interacts closely with the antelope, which is marked by its brown fur and white underbelly. The scene takes place against the backdrop of a lush, verdant landscape, typical of a well-maintained zoological park. Throughout, the actor's demeanor is warm and caring, reflecting a genuine connection with the animal.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears to have undergone a deformity mutation."
}
] |
seed46_1290
|
videos/HRA_part2/1290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man wearing a brown leather jacket and a tan hat sits on a large rock in the middle of a vast, grassy plain, writing intently in a small notebook. In the background, a majestic bison is seen grazing peacefully on the lush vegetation. Suddenly, the man lowers his book, revealing a look of awe and inspiration as he watches the bison. He then resumes writing, his posture reflecting deep concentration. The scene shifts to show the bison lying down, seemingly resting, as the man continues to write, now with a sense of urgency, capturing the essence of his experience in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2519
|
videos/HRA_part0/2519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man, dressed in a green jacket, beige slacks, and brown shoes, performs a joyful dance on a vast, verdant heath, with rolling hills and lush greenery stretching into the horizon. Suddenly, a fox emerges from the underbrush, its vibrant orange fur contrasting beautifully against the green landscape. The man continues his dance, now accompanied by the curious fox, which playfully circles him, adding a whimsical touch to the scene set against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs are missing, his face is blurry, his body is deformed, and the fox is generally deformed."
}
] |
seed42_2726
|
videos/HRA_part0/2726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 whole, fresh cod fish is presented on a bed of ice, its body a pristine silver with a distinctive dark spot pattern. The fish's eyes are bright and clear, indicating freshness, while the gills are a vivid red. The scene is set in a bustling fish market, with other varieties of seafood visible in the background, adding to the atmosphere of a vibrant marketplace. The focus remains on the cod, emphasizing its quality and size, perfect for a gourmet meal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2416
|
videos/HRA_part2/2416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A beautifully cooked piece of salmon is presented on a plate, its skin crispy and charred to perfection, the flesh a rich pink hue that contrasts strikingly with the green of the accompanying asparagus spears. The dish is garnished with lemon wedges and fresh dill, enhancing the vibrant colors and textures. The salmon is shown from multiple angles, revealing its succulent interior and the delicate grill marks that add depth and character to the presentation. Set against a rustic wooden table, the scene is completed by a glass of white wine and a simple white bowl containing a side of creamy mashed potatoes, offering a perfect balance of flavors and visual appeal.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_303
|
videos/HRA_part2/303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, open ocean scene where sunlight filters through the water's surface, illuminating a majestic manta ray as it glides effortlessly through the clear blue depths. The manta ray, with its impressive wingspan, showcases its graceful movements, framed against the vibrant coral reef below. Its dark dorsal side contrasts sharply with the lighter underbelly, creating a stunning visual as it maneuvers with fluidity. Nearby, smaller fish swim alongside the manta ray, highlighting the peaceful coexistence in the underwater ecosystem. The scene is serene and captivating, offering a rare glimpse into the beauty of marine life.]"
},
{
"from": "gpt",
"value": "Normal. The manta ray's swimming in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed46_1496
|
videos/HRA_part2/1496.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned farmer, wearing a brown shirt and denim overalls, drives a futuristic lunar buggy across a vast, barren moon landscape, dotted with craters and boulders under a starlit sky. Suddenly, the scene transitions to a serene, earthbound setting where the same farmer is seen leisurely floating on an inflatable raft, fully clothed, in the middle of a tranquil, crystal-clear lake surrounded by lush greenery. The peaceful atmosphere is punctuated by the occasional splash as the farmer gently moves through the water, enjoying a refreshing break from his daily chores.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1784
|
videos/HRA_part1/1784.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a black leather jacket, a graphic tee, and dark jeans, walks his energetic, medium-sized brown dog in an urban park. The artist wears a baseball cap and sports a beard, presenting a relaxed and down-to-earth demeanor. The dog, on a leash, enthusiastically explores the grassy area, its tail wagging. In another scene, the musician, now with his acoustic guitar slung over his back, continues his leisurely stroll, his dog trotting alongside him. The pair strolls past a stone building, adding to the laid-back vibe of the day.]"
},
{
"from": "gpt",
"value": "Bad. No scene of a musician walking with a wooden guitar on his back, with a dog trotting alongside him; no generation of the musician's bearded face under a baseball cap."
}
] |
seed42_1749
|
videos/HRA_part0/1749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white lab coat over a black turtleneck and black pants, runs down a sleek, futuristic corridor of a space medical facility. The hallway is lined with glass panels that offer glimpses into advanced treatment rooms. The artist's stride is purposeful, their gaze determined, as they navigate the sterile environment illuminated by soft, ambient lighting. The facility's design incorporates curved walls and high-tech equipment, creating a blend of artistry and cutting-edge medicine in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1581
|
videos/HRA_part0/1581.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 indoor gymnasium illuminated by natural light from large windows, four children wearing colorful clothes engage in various acts of physical exertion. One child, dressed in a red shirt and black shorts, lifts a heavy barbell above their head with a look of intense concentration, demonstrating impressive strength. Another child, wearing a yellow top and blue leggings, performs a handstand against a mirrored wall, showing remarkable balance and poise. A third child, clad in green, does pull-ups on a bar, highlighting their upper body strength. Lastly, a child in a blue outfit leaps over a series of hurdles, capturing the essence of agility and athleticism. The gym's wooden floors and equipment provide a backdrop for these dynamic scenes of youthful energy and determination.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the legs are deformed."
}
] |
seed44_2267
|
videos/HRA_part1/2267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white shirt, black vest, and black trousers, diligently mops the floor of an empty restaurant during the daytime. The space is notably devoid of customers, with only a single table set with plates and cutlery visible in the background. The waiter's focus is intense as he works, pushing the mop back and forth across the smooth, light-colored tile flooring. His movements are methodical and purposeful, emphasizing his commitment to maintaining a clean dining environment. The natural light filtering through the windows highlights the cleanliness of the space, further emphasizing the waiter's efforts.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_165
|
videos/HRA_part0/165.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": "Good. Basically no problem."
}
] |
seed46_3116
|
videos/HRA_part2/3116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a black cap, black jacket, and khaki pants, pushes a large, vintage amp through a crowded, dimly lit backstage area at a music venue. The scene is filled with the energy of an upcoming performance, as the musician maneuvers the amp with determination, highlighting the physical effort and dedication required behind the scenes. The musician's attire and the bustling environment capture the spirit of live music culture.]"
},
{
"from": "gpt",
"value": "Bad. The man's legs are deformed. His arms and hands are also deformed, and the box in his hand is distorted."
}
] |
seed46_231
|
videos/HRA_part2/231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room illuminated by the soft glow of a Martian sunset, visible through a large window displaying the red planet's horizon, two young children sit cross-legged on a wooden floor. They gently caress a small, furry gerbil sitting on a colorful blanket, their faces reflecting expressions of pure delight and wonder, as they interact with the pet in the unique, alien environment.]"
},
{
"from": "gpt",
"value": "Bad. The hand and arm appear deformed. A child in blue clothing suddenly slides into the frame, and their hand and arm also appear deformed. The child's legs are also deformed."
}
] |
seed42_1714
|
videos/HRA_part0/1714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 midst of arid scrublands, a spotted hyena, characterized by its distinctive spots and robust build, is unexpectedly seen swimming across a shallow, sunlit waterhole. Its head held high above the clear water, the hyena propels itself forward with powerful strokes, showcasing its rarely observed aquatic abilities. The serene environment is punctuated by the distant silhouette of a lone tree, highlighting the surprising scene unfolding in this typically dry habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1559
|
videos/HRA_part2/1559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a crisp uniform consisting of a navy blue shirt, matching trousers, and a peaked cap, is engaged in an unusual task inside a busy restaurant district. He is meticulously wiping down a row of outdoor tables, each set with white tablecloths and surrounded by patrons enjoying their meals. The backdrop features a variety of restaurants, ranging from elegant dining establishments to casual eateries, all bustling with activity. The scene captures the unexpected sight of law enforcement taking on a service role, contributing to the cleanliness and ambiance of the dining area.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1270
|
videos/HRA_part1/1270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A ruggedly handsome firefighter, wearing a red and yellow vest, blue jeans, and brown shoes, gently caresses a curious gazelle on a vast, sandy beach. The gazelle, with its striking, wide eyes and alert posture, stands on the shore, the waves lapping at its feet. The scene shifts to show the firefighter's strong, comforting hands petting the animal's face, as they both stand against a backdrop of clear blue skies and the endless ocean horizon. The firefighter's caring demeanor and the gazelle's trusting stance on the picturesque beach create a poignant, contrasting image.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1946
|
videos/HRA_part1/1946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat is seen grooming itself meticulously, its paws lifting to wipe across its face and whiskers. Positioned against a neutral grey backdrop, the rat's actions are the focal point, as it carefully tends to its cleanliness, showcasing the natural behavior of self-care in rodents. The scene is intimate, with the rat's fur and whiskers detailed in high definition, emphasizing the texture and vibrancy of its coat against the monochromatic setting.]"
},
{
"from": "gpt",
"value": "Normal. The brown rat in the video moves basically normally, with slight coordination issues."
}
] |
seed42_1399
|
videos/HRA_part0/1399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fusion of elements, a majestic black panther, its body outlined in vibrant neon green, is depicted leaping across a cosmic landscape. The backdrop features a stunning galactic nebula, its swirling colors of pink, purple, and blue creating an ethereal atmosphere. As the panther moves gracefully, it seems to dance among the stars, its fluid movements echoing the celestial patterns around it. The nebula's gaseous tendrils appear to reach out, almost as if they too are joining in the cosmic dance, forming a harmonious scene where the boundaries between the animal kingdom and the universe blur.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1793
|
videos/HRA_part0/1793.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a skilled musician, dressed in a black leather jacket, plays a gleaming silver electric guitar. Nearby, an enormous, friendly bear, adorned with a red bow tie, listens intently, its paw gently resting on the musician's shoulder in a gesture of companionship. Suddenly, a shimmering wormhole opens behind them, revealing a kaleidoscope of colors and swirling galaxies. The musician and the bear look into the wormhole, their expressions a mix of awe and curiosity, as they contemplate the mysteries of the universe together.]"
},
{
"from": "gpt",
"value": "Normal. The bear's movements in the video are not smooth."
}
] |
seed44_252
|
videos/HRA_part1/252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An extraordinary scene unfolds where a young elephant, covered in dust and dirt, crawls through a lush vineyard at sunset. Its trunk occasionally touches the soil, and it wears a simple rope around its neck. The elephant is surrounded by rows of green grapevines, with a wooden fence and a small, distant house set against a purple sky. The camera captures the animal from various angles, emphasizing its unique behavior in an unexpected environment, all bathed in the warm glow of twilight.]"
},
{
"from": "gpt",
"value": "Bad. The baby elephant's head generation in the video has problems; two noses appeared, and the ivory suddenly disappeared in the middle frame."
}
] |
seed42_3093
|
videos/HRA_part0/3093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, modern space education center, a diligent janitorial worker, clad in a gray uniform, meticulously wipes down an expansive, glass-topped display table. The room is filled with futuristic exhibits, including a large model of the solar system hanging from the ceiling, and interactive screens showing detailed information about planets and galaxies. The worker's attention to detail is evident as they ensure every inch of the table is spotless, allowing visitors to fully appreciate the educational materials displayed beneath the clear surface. The backdrop of the space-themed decor highlights the importance of cleanliness in maintaining a conducive learning environment for students eager to explore the cosmos.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner can be clearly seen wiping the glass display table in the video, the actions are basically normal but there is some lack of coordination."
}
] |
seed44_1313
|
videos/HRA_part1/1313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene unfolds on a bustling Shanghai street, where a creative writer, dressed in a brown jacket and khaki pants, kneels on the pavement, engrossed in scribbling notes. Beside them, an unexpected giraffe, adorned with a red bow tie, also kneels, observing the writer with curiosity. The vibrant urban landscape, filled with pedestrians and vehicles, serves as a lively backdrop, contrasting the unusual duo's focused yet peculiar crawling position on the crowded sidewalk.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe didn't tie a bow tie."
}
] |
seed44_1913
|
videos/HRA_part1/1913.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary writer sits at a contemporary desk, crafting stories about space exploration, surrounded by swimming gear and a large aquarium filled with exotic fish. The room is illuminated by a floor lamp with a large shade, casting a warm glow on the writer's face. They wear a black shirt and a necklace, their focus intense as they type on a laptop. Behind them, a window reveals a starry night sky, evoking a sense of wonder and adventure into the cosmos. Beside the desk, a modern painting in shades of blue and green adds a splash of color, reminiscent of water, perhaps reflecting the writer's love for swimming. The aquarium, visible in the background, features colorful fish swimming among plants and rocks, adding a dynamic element to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1904
|
videos/HRA_part0/1904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed man in a white shirt and dark pants walks through a lush, green meadow dotted with vibrant wildflowers under a bright, clear blue sky. He strides purposefully, his hands clasped behind his back, exuding a sense of peace and connection with nature. The tall grass sways gently in the breeze around him, and in the distance, a range of rolling hills provides a picturesque backdrop, enhancing the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2942
|
videos/HRA_part2/2942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 strong, focused woman wearing a red helmet and climbing gear scales a towering rock face, the texture of the stone rough under her hands and feet. The camera captures her intense concentration, the strain in her muscles, and the determination in her eyes. Sunlight filters through wispy clouds, casting dramatic shadows on the cliffside as she ascends higher, leaving the green valley far below. The scene is framed by rugged terrain, emphasizing her solitary endeavor against the vast, natural landscape.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed44_1072
|
videos/HRA_part1/1072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, donning a casual gray shirt and black cap, is shown engaged in an unexpected task: unclogging a drain. In the first scene, he is kneeling on a hardwood floor, attentively examining a drain with a serious look on his face. Next, he is seen plunging the clogged drain with a red plunger, demonstrating his hands-on approach to problem-solving. Following this, the director is depicted using a drain snake to clear the blockage, his expression one of determination. Lastly, he inspects the drain once more, now clean, with a look of satisfaction, his casual attire contrasting with his professional role.]"
},
{
"from": "gpt",
"value": "Bad. The cue stick flew out of hand."
}
] |
seed46_1799
|
videos/HRA_part2/1799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meadow under a partly cloudy sky, a majestic stag stands tall, its large, expressive eyes gazing into the distance. It shakes its head vigorously, sending droplets of water flying from its fur. The stag, with its impressive antlers and auburn coat, continues to shake itself dry after what seems to have been a refreshing drink from a nearby stream. The rolling hills and scattered trees provide a serene backdrop, emphasizing the beauty and tranquility of nature. As it finishes drying off, the deer looks around, alert and aware, before returning to its peaceful grazing.]"
},
{
"from": "gpt",
"value": "Normal. The corner of the road in the video is generated incorrectly, the facial features are slightly distorted, the tail is generated unreasonably, one ear is missing, there are parts of the legs missing, and the body is generated unreasonably."
}
] |
seed42_2674
|
videos/HRA_part0/2674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young college student, dressed in a green shirt, gray jacket, and khaki pants, walks through the bustling streets of a metropolis, passing by a glass office building with a reflection of the surroundings. Moments later, he continues his journey, navigating the urban landscape near a construction site with yellow barriers. He then crosses a busy street, dodging between pedestrians, cars, and a street sweeper. Finally, he reaches a subway station entrance, marked by a red canopy and illuminated signage, ready to descend into the underground network of the city.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate scenes of the student passing glass office buildings, yellow barriers, and construction sites."
}
] |
seed46_2652
|
videos/HRA_part2/2652.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling nurse with a red stethoscope around her neck is seated on a grassy area, holding a small hedgehog in her hands, which looks curious and alert. Behind her, a vibrant, colorful depiction of a quantum leap phenomenon is visible, symbolized by swirling, dynamic patterns of light and color. In the background, a serene swimming pool with clear blue water and lush greenery can be seen, adding a peaceful contrast to the energetic visuals of the quantum leap. The nurse's attire includes a white uniform and name badge, while the hedgehog is depicted in natural detail, its spines clearly visible.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2401
|
videos/HRA_part1/2401.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, athletic woman with a pixie haircut, wearing a blue t-shirt and khaki cargo pants, kneels on a concrete floor in a garage. She focuses intently on repairing a mountain bike, her tools spread out on a red mat beside her. Her blue scrubs, adorned with colorful medical symbols, hint at her profession as a nurse. In another angle, she lifts the bike, revealing her strength and determination. Throughout, she exhibits a confident smile, demonstrating her dual passions for healthcare and cycling. The garage space is filled with various tools and equipment, emphasizing her hands-on approach to both her work and hobbies.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2842
|
videos/HRA_part0/2842.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space casino illuminated by neon lights, a golden retriever dog dons a stylish astronaut suit and a green swimming cap. The dog stands beside a luxurious, crystal-clear pool, surrounded by floating poker tables and slot machines, all set against the backdrop of a vast, star-studded universe. The dog appears happy and curious, ready to enjoy a refreshing swim among the celestial gambling atmosphere. Nearby, an alien bartender mixes a colorful cocktail, adding to the surreal and playful scene.]"
},
{
"from": "gpt",
"value": "Normal. The dog's movements in the video are slightly not smooth."
}
] |
seed42_2444
|
videos/HRA_part0/2444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with a round face, brown hair styled in a bun, and wearing a gray top is seen sitting alone, her eyes welling up with tears that stream down her cheeks. She looks lost in thought, her gaze distant, as she holds a tissue in her right hand. Moments later, she wipes away her tears with the tissue, her emotions visible in her expressive face. Then, she is captured in a close-up, her eyes closed, a tear rolling down her cheek, her lips slightly parted, as she seems to be taking a deep breath. Lastly, she looks directly at the camera, her eyes filled with unshed tears, her cheeks flushed, conveying a sense of vulnerability and strength in her emotional state.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1574
|
videos/HRA_part1/1574.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 detailed close-up, a badger with piercing eyes and sharp teeth runs through a grassy landscape, its fur textured and realistic. Behind it, the silhouette of a large power plant with cooling towers can be seen, emitting steam into the dusky sky. The badger continues its sprint across the terrain, its body language conveying determination and strength, all set against the backdrop of the industrial power plant under the twilight sky.]"
},
{
"from": "gpt",
"value": "Normal. The badger's limbs in the video are not fully generated."
}
] |
seed46_1909
|
videos/HRA_part2/1909.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, complete with a suit, tie, and leather briefcase, walks through lush wetlands filled with tall grasses and cattails, accompanied by a koala casually perched on their shoulder. The lawyer, with a determined look, strides forward on a narrow wooden boardwalk that winds through the wetland habitat. The koala, seemingly unfazed by its unusual companion, clings comfortably to the lawyer's shoulder, occasionally glancing around at the surrounding environment. The pair moves purposefully through the scenic wetlands, with the lawyer's polished shoes and professional attire contrasting sharply with the natural surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1184
|
videos/HRA_part0/1184.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a 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": "Bad. The rabbit's face is severely distorted, and its legs are also severely twisted."
}
] |
seed46_103
|
videos/HRA_part2/103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning a brown jacket and khaki pants, stands at a modern bus stop, gently caressing the sleek metal pole, seemingly finding comfort in its solid presence. His eyes are closed, lost in thought, as the urban landscape hums around him. The bus stop is designed with clean lines and glass panels, offering a glimpse into the daily life of the city. Passersby glance curiously at the engineer, his connection to the inanimate object a stark contrast to the hurried pace of the surroundings. The scene captures a rare moment of intimacy between a person and the urban infrastructure they interact with daily.]"
},
{
"from": "gpt",
"value": "Normal. The faces of the characters in the background appear distorted."
}
] |
seed44_2124
|
videos/HRA_part1/2124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, donning a high-tech suit and goggles, operates a gravity manipulation device in a sleek, futuristic lab. He sprints across the room, defying gravity as he runs upside-down on the ceiling, his movements fluid and purposeful. The device, a compact, intricate mechanism attached to his back, emits a soft glow, highlighting its active state. Around him, the lab is filled with advanced equipment and screens displaying complex data, emphasizing the cutting-edge nature of his work. Throughout the sequence, the engineer's confident expression and dynamic actions showcase the thrilling potential of gravity-altering technology.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1800
|
videos/HRA_part0/1800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's limbs are missing in the video, and its body and face are deformed."
}
] |
seed46_2362
|
videos/HRA_part2/2362.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, dressed in a casual blue jacket and khaki pants, leaps joyfully in slow motion over the sandy shore near a vast ocean, capturing the essence of freedom and inspiration. Against a backdrop of the sea's horizon, the writer's silhouette is outlined dramatically during the jump, with the sun illuminating the scene from behind. The figure is then shown landing softly on the sand, surrounded by the serene beauty of the ocean, embodying a moment of pure bliss and connection with nature. Throughout, the writer's attire remains consistent, with the focus on the expressive leap and the stunning coastal scenery.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs generation in the video has problems, and the face generation is blurry."
}
] |
seed44_310
|
videos/HRA_part1/310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a black jacket and khaki pants, confidently walks alongside a zebra in the middle of a desert landscape, both seemingly unfazed by the arid environment. The director holds a megaphone in one hand and a script in the other, while the zebra, a symbol of the untamed, ambles beside him, the two forming an unlikely duo in this surreal scene. The sun casts long shadows, highlighting the stark beauty of the desert, as the director and the zebra continue their journey together, a testament to the unexpected alliances that can occur in the pursuit of art.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2517
|
videos/HRA_part1/2517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male worker, wearing a white shirt, beige pants, and a traditional headscarf, is seen wiping the face of a brown camel with a white cloth. The action takes place in a sandy environment, with other camels standing in the background, creating a scene that highlights the care and connection between the worker and the animal. The worker's focused expression and gentle touch convey a sense of respect and familiarity, while the setting sun casts a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3102
|
videos/HRA_part1/3102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical prehistoric scene, a massive woolly mammoth leaps over a frozen log in a snow-covered forest during the Ice Age, with tall pine trees framing the action. The mammoth, complete with shaggy brown fur and impressive tusks, is captured mid-air, its large body defying expectations as it clears the obstacle with surprising agility. The icy landscape, dotted with ancient conifers, adds to the dramatic effect of this unlikely jump, highlighting the creature's strength and adaptability in its harsh environment.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's walking in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed42_1538
|
videos/HRA_part0/1538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and unexpected scene, a dedicated teacher, wearing a vibrant yellow swimsuit and cap, instructs a curious jackal pup, who dons a miniature life jacket, in the art of swimming. They are in a serene, clear blue pool surrounded by lush greenery, creating a harmonious blend of nature and learning. The teacher gently supports the jackal pup, both displaying expressions of concentration and determination as they navigate the water together, embodying an unconventional yet touching teaching moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1939
|
videos/HRA_part1/1939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling student, dressed in a green T-shirt and gray pants, joyfully jumps alongside a kangaroo in a lush, green field under a clear blue sky. The student, wearing brown shoes and a wristwatch, mimics the kangaroo's hopping motion, capturing a moment of playful interaction between human and nature. The kangaroo, with its distinctive features and powerful hind legs, bounds gracefully next to the enthusiastic student, both enjoying the freedom of movement against the serene backdrop of the outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The jumping actions of the student and the kangaroo in the video are not continuous and smooth, there are abrupt changes."
}
] |
seed46_328
|
videos/HRA_part2/328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 temperate deciduous forest, a professional lawyer, dressed in a gray suit and carrying a leather briefcase, wipes his brow as he pauses from his hike. The lush green forest, filled with tall trees and sunlight filtering through the leaves, provides a serene backdrop. The lawyer, wearing a gray blazer, button-down shirt, and khaki pants, is shown wiping his face with a handkerchief, revealing a moment of respite during his outdoor excursion. The peaceful atmosphere of the forest is highlighted by the dappled sunlight and the vibrant greenery surrounding the well-dressed man.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer wiping sweat in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_1048
|
videos/HRA_part2/1048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space prison, a rugged man with a shaved head, dressed in a torn orange jumpsuit, stealthily caresses a metallic wall panel, searching for a hidden mechanism. His intense eyes scan the surroundings, alert for any sign of danger. He gently touches the cold surface, feeling for inconsistencies. Suddenly, his fingers find a concealed switch, and he looks relieved yet cautious. With a quick glance over his shoulder, he presses the button, triggering a sequence that promises his daring escape from the confined, sterile prison cell.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are severely distorted."
}
] |
seed42_1206
|
videos/HRA_part0/1206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars gracefully through the crisp, blue sky, its powerful wings spread wide, casting a shadow on the rugged mountain terrain below. The eagle's piercing golden eyes scan the landscape intently, searching for prey. Its striking white head and tail feathers contrast vividly against the dark brown body, creating an awe-inspiring sight against the panoramic backdrop of snow-capped peaks and lush valleys. As it glides effortlessly, the wind ruffles its feathers, highlighting the intricate patterns and textures of its plumage, while the sun illuminates the scene, casting a warm glow on the breathtaking view.]"
},
{
"from": "gpt",
"value": "Normal. The claws were not fully generated."
}
] |
seed46_1446
|
videos/HRA_part2/1446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches regally on a branch, its vibrant plumage a stunning mix of green, blue, and brown feathers, set against a backdrop of lush foliage and clear blue sky. Its long, curved beak points upward, ready to snatch prey from the air. In the next frame, it takes flight, wings outstretched, revealing the striking contrast of its underbelly and the iridescent sheen of its back feathers. It swoops gracefully, capturing an unsuspecting insect in mid-air, before returning to its perch, triumphant, the captured prey visible in its beak, all set against the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_107
|
videos/HRA_part2/107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast temperate grassland, a dedicated doctor, clad in a white lab coat, blue shirt, and khaki shorts, runs along a dirt path, passing by tall, swaying grass and isolated trees under a partly cloudy sky. The doctor, wearing sunglasses, a white medical coat, blue t-shirt, and brown shorts, sprints with focused determination across the open landscape, the scenery punctuated by distant hills and clear blue skies. Throughout the video, the doctor maintains a steady pace, showcasing resilience and strength in the midst of nature's tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are uncoordinated, and the body sways are not in harmony."
}
] |
seed46_291
|
videos/HRA_part2/291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed doctor, wearing a white button-down shirt and khaki shorts, leaps into the air on a pristine, sandy beach, with crystal-clear water visible in the background. The doctor, who has brown hair and glasses, is captured mid-jump, displaying a sense of freedom and joy. The scene is set against a stunning backdrop of palm trees and a clear blue sky, creating a perfect blend of professional and leisure elements. The doctor's relaxed attire and the idyllic beach setting convey a sense of balance between work and personal life.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_3110
|
videos/HRA_part1/3110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy white rabbit sits upright on a clean, wooden surface, using its paw to wipe its face meticulously, akin to a cat grooming itself. The action is repeated several times, showcasing the rabbit's cleanliness and the texture of its fur against the smooth wood. The rabbit then pauses, sitting still with its paws down and ears perked up, before resuming the wiping motion, its pink nose twitching occasionally. Throughout the sequence, the rabbit's focus remains on its grooming, offering a charming display of its self-care routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2739
|
videos/HRA_part2/2739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, clad in a light blue uniform, gently caresses the fur of a calm, gray wolf sitting beside her, both under the shade of a large tree in a grassy field. The wolf looks up at her with a relaxed demeanor, while she tenderly strokes its head, conveying a sense of mutual trust and peace between human and wild animal. Moments later, she holds the wolf's snout softly, her caring gaze meeting its calm eyes, with the serene natural surroundings enhancing the emotional connection depicted.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the gray wolf's mouth in the video has problems, the nurse's fingers are deformed, the face is generated blurry, and the generation is unreasonable when the nurse's and gray wolf's ears overlap."
}
] |
seed46_1607
|
videos/HRA_part2/1607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, open field under a clear blue sky, two young children, a boy and a girl, both wearing vibrant yellow raincoats, wide-brimmed hats, and boots, are seen walking together. They carry a large, reflective solar sail, its metallic surface shimmering in the sunlight. The sail, supported by a wooden frame they hold, catches the wind as they walk, propelling them forward playfully across the grassy landscape. Their joyful expressions and the sail's gentle movements create a whimsical scene, blending elements of childhood wonder with futuristic technology.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2106
|
videos/HRA_part0/2106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a black vest, button-down shirt, and striped tie, meticulously mops the floor of an empty restaurant with white walls and ceiling, wooden tables and chairs, and large windows. The room is illuminated by soft artificial lighting, casting a warm glow on the clean, wet floor. The waiter's movements are deliberate and focused, his mop leaving a trail of cleanliness across the tile surface. In the background, a fully set table with a white cloth, silverware, and glasses awaits the next guests, while a row of wine bottles sits on a shelf above. The scene conveys a sense of preparation and attention to detail, as the waiter ensures the dining area is spotless for the upcoming service.]"
},
{
"from": "gpt",
"value": "Bad. The facial and hand generation of the server in the video has issues."
}
] |
seed42_1596
|
videos/HRA_part0/1596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stag strides purposefully across an ancient stone bridge, its antlers framing the scene like natural architecture against a backdrop of lush greenery and a misty morning sky. The deer's confident gait and the bridge's weathered texture tell a story of time and resilience in nature. As it walks, the stag's hooves make soft sounds on the moss-covered stones, creating a harmonious melody echoing through the serene woodland setting. The bridge, arching gracefully over a tranquil stream, becomes a pathway connecting two verdant forests, with the deer serving as a symbol of grace and wildness moving between these spaces.]"
},
{
"from": "gpt",
"value": "Bad. The deer's movements in the video are unsmooth."
}
] |
seed44_2498
|
videos/HRA_part1/2498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Michael B. Jordan, sits at a desk in a modern office space. Dressed in a casual white shirt, sleeves rolled up, and stylish glasses perched on his nose, he focuses intently on typing on a sleek, black keyboard. The desk is clutter-free, save for a single, elegant desk lamp casting a warm glow over the scene. Behind him, a large window frames a view of a bustling city skyline, hinting at the high-stakes narrative unfolding as his fingers dance across the keys.]"
},
{
"from": "gpt",
"value": "Normal. The man in the video types basically normally, but there is slight uncoordination in his movements."
}
] |
seed42_1333
|
videos/HRA_part0/1333.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lively brown and white dog bounds through the shallow waters of a serene lake at sunset, its fur glistening with droplets. It shakes vigorously, sending water flying in a sparkling mist, while standing on the sandy shore. Against the backdrop of a tranquil lake and a stunning sunset, the energetic canine leaps into the air, capturing the essence of joy and freedom. As it lands, it shakes again, creating a captivating spray against the golden hour light, highlighting every droplet in the air. Throughout, the dog wears a red collar, adding a pop of color against the natural hues of the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1602
|
videos/HRA_part1/1602.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman in a red dress walks purposefully through the grand lobby of a luxurious hotel, her high heels clicking on the marble floor. The opulent space features tall windows, plush velvet sofas, and an elegant chandelier, all bathed in warm, inviting light. As she strides confidently, she passes by the reception desk, where a concierge is busy assisting guests. In the background, a group of tourists consults a map, adding a touch of bustling activity to the otherwise refined atmosphere. The woman's poise and the hotel's grandeur create a captivating scene of urban sophistication.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3089
|
videos/HRA_part0/3089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, colorful scene unfolds where a person dressed in a black cape and white shirt, reminiscent of a bat, engages in an energetic dance. Their movements are fluid and dynamic, capturing the essence of nocturnal flight against a dark, starry sky. As they spin and leap, the cape billows dramatically, creating dramatic silhouettes against the twinkling celestial backdrop. The dancer's face is painted in black and white, accentuating the bat-like features, adding to the theatricality of the performance. Throughout the dance, the focus remains on the captivating interplay between the dancer's bat-inspired costume and the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2922
|
videos/HRA_part0/2922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a sea urchin reveals its intricate, spiny exterior, showcasing a variety of colors including green, purple, and brown. The spherical creature sits atop a rocky reef, surrounded by a vibrant marine environment teeming with life. Sunlight filters through the water, casting a warm glow on the sea urchin's textured surface, highlighting its natural beauty and resilience in the underwater world. Against the backdrop of the reef, the sea urchin appears both delicate and formidable, a testament to the diversity of oceanic fauna.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1988
|
videos/HRA_part0/1988.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprawling mall, a middle-aged janitor, clad in a yellow high-visibility vest and dark pants, runs with purpose through the corridors. The scene begins with him standing alert, mop in hand, amidst the vibrant retail environment. Then, he sprints past various storefronts, the motion blur from his movement emphasizing his haste. As he continues, he deftly maneuvers around a corner, demonstrating agility in his work boots. Lastly, he is shown running with determination across a checkered tile floor, the bustling mall life continuing around him, highlighting his role in maintaining the facility's cleanliness amidst the daily hustle and bustle.]"
},
{
"from": "gpt",
"value": "Bad. The mop mentioned in the caption does not appear in the video."
}
] |
seed44_3131
|
videos/HRA_part1/3131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a navy uniform with badge and name tag, meticulously cleans a large aquarium filled with colorful fish and aquatic plants, set against a backdrop of a modern, minimalist interior. The officer, displaying a gentle side, carefully tends to the tank, ensuring the well-being of the marine life within. The aquarium, illuminated by overhead lights, showcases various species of fish swimming calmly, oblivious to the officer's presence. The room's clean lines and neutral tones contrast with the vibrant colors of the fish, creating a visually striking scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2976
|
videos/HRA_part0/2976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal space setting illuminated by cosmic lights, a brave firefighter in full gear, complete with a helmet and breathing apparatus, stands solemnly beside a wise-looking badger, both participating in a mysterious, otherworldly religious ceremony. The ceremony takes place on a floating platform surrounded by stars, galaxies, and celestial bodies. The scene then shifts underwater, where the firefighter and the badger are swimming gracefully in a clear, tranquil pool, with the firefighter's gear now adapted for aquatic environments. The pool is encircled by ancient, space-themed ruins, giving the impression of an extraterrestrial civilization. Throughout the sequence, the two characters maintain a sense of reverence, as if honoring a sacred tradition in this unique blend of terrestrial heroism, woodland wisdom, and cosmic spirituality.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the firefighter wearing a helmet and breathing apparatus or the badger underwater."
}
] |
seed44_114
|
videos/HRA_part1/114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a red jacket and gray pants, dances joyfully on a mountain trail, surrounded by lush greenery and towering trees. The scene is set in the afternoon, with the sunlight filtering through the leaves, casting dappled shadows on the ground. The student performs a series of energetic dance moves, twirling and leaping across the rocky path, their face beaming with happiness and freedom. The mountain range looms majestically in the background, providing a breathtaking backdrop to this spontaneous dance performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2385
|
videos/HRA_part1/2385.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a yellow shirt, green vest, and brown shorts leaps into the air with his arms extended above his head, against a backdrop of dense subtropical forest. The lush green foliage, including palm fronds and ferns, provides a vibrant setting. In another frame, he jumps again, this time with his arms wide open, wearing a white cap, dark sunglasses, and a smile, against a similar background of rich, verdant trees. Throughout the sequence, the man's joyful expressions and dynamic poses capture the essence of his energetic exploration within the vibrant subtropical woodland environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1709
|
videos/HRA_part2/1709.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 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 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": "Bad. The squirrel monkey in the video has a twisted body, a distorted face, twisted legs, and contorted paws."
}
] |
seed44_2348
|
videos/HRA_part1/2348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in traditional African garb, comprised of a tan shirt, green shorts, and brown sandals, performs an impressive jump over a prone hyena in the middle of a sandy desert. The hyena, positioned on the ground with its head turned toward the man, exhibits a relaxed demeanor. The man's leap is captured mid-air, showcasing his athletic prowess against the stark, arid landscape, with distant mountains providing a scenic backdrop. The scene conveys a sense of adventure and cultural intrigue, highlighting the unique interaction between human and wildlife in a dramatic, yet peaceful, encounter.]"
},
{
"from": "gpt",
"value": "Bad. The man's legs and arms deform and become distorted during the jump. Additionally, the man's feet are always sliding off the ground, which is unrealistic."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.