video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_189
|
videos/HRA_part2/189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a gray hoodie and blue jeans, sits cross-legged on a hardwood floor in a room with large windows, a desk with a laptop, and a bookshelf in the background. A curious cat crawls onto the student's lap, interrupting their study session. The student gently strokes the cat, which is adorned with a red collar, as it snuggles into their lap. The room is filled with natural light from the windows, creating a warm and cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2735
|
videos/HRA_part1/2735.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished by his gray hair and wearing a black turtleneck, is seen playfully dancing in a studio. Beside him, a giraffe, animatedly rendered with large, expressive eyes and long eyelashes, also dances, adding a whimsical touch to the scene. Both the director and the giraffe exhibit exaggerated, comical dance moves, creating a lighthearted and surreal atmosphere. The studio space is filled with vibrant colors and patterns, further enhancing the playful mood. Throughout the scene, the focus remains on the amusing interaction between the dancing director and the animated giraffe.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand in the video is generated blurry, and the giraffe's head is generated abnormally."
}
] |
seed42_2856
|
videos/HRA_part0/2856.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful teacher, wearing a yellow blouse and khaki pants, is seen joyfully dancing in a classroom decorated with educational posters. On a nearby desk sits a small, curious gerbil, nibbling on a piece of wood inside its cage. The teacher's energetic movements and warm smile create a vibrant atmosphere, while the gerbil's playful antics add a touch of whimsy to the scene. The camera captures the dynamic interaction between the dancing teacher and the fascinated gerbil, highlighting the unique bond they share within the educational environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's dance moves in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed44_2331
|
videos/HRA_part1/2331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a sky-blue scrubs top and pants, takes a break from her duties to enjoy the outdoors. She is raking a large pile of autumn leaves in a residential backyard, her actions revealing a playful side to her personality. She pauses to look up, smiling at the camera, her brown hair tied back in a practical ponytail. Despite her work clothes, which include a stethoscope hanging around her neck, she tackles the task with enthusiasm, her movements energetic and joyful. The sunny weather and colorful leaves provide a vibrant backdrop for this unexpected scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2512
|
videos/HRA_part1/2512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter wearing a black suit and white shirt, complete with a bow tie and name tag, holds a silver serving tray with a glass of red wine as he runs swiftly through a vast, meticulously maintained cemetery. The grass is neatly trimmed, and the tombstones are lined up in perfect rows, extending into the horizon under a clear blue sky. Suddenly, a cheetah appears, running alongside the waiter, matching his pace effortlessly. Both the waiter and the cheetah continue their run through the peaceful graveyard, the cheetah's spots contrasting against the greenery, while the waiter remains composed, maintaining a professional demeanor despite the unusual circumstances.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, and legs are distorted in the video, as well as the cheetah's body, head, legs, and claws."
}
] |
seed44_2890
|
videos/HRA_part1/2890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, meticulously irons his clothes in a modern, minimalist bedroom. The room features wooden floors, a large window with white blinds, and a white bed. The doctor stands at an ironing board placed next to a wooden dresser, focusing intently on smoothing out the wrinkles in a garment. The scene conveys a sense of professionalism and attention to detail, as the well-groomed doctor prepares his attire with care.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1002
|
videos/HRA_part0/1002.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A patient teacher, dressed in a khaki shirt and denim jeans, sits on a wooden pier with fishing gear, teaching a young student the art of fishing. The teacher demonstrates casting a line into a serene lake at sunset, the water reflecting the warm hues of twilight. The student, wearing a red cap and a green vest, attentively watches, holding a fishing rod, as the teacher guides them on the pier. The teacher then hands the student a small fish, caught during the lesson, fostering a connection between nature and learning. Throughout, the teacher wears a wide-brimmed hat and a yellow life jacket, while the student is dressed in a red baseball cap, a green fishing vest, and holds a child-sized fishing rod, both immersed in the peaceful act of fishing by the water's edge.]"
},
{
"from": "gpt",
"value": "Bad. The child's fingers are not fully formed, and the fishing rod is detached from the hand."
}
] |
seed44_152
|
videos/HRA_part1/152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a museum dedicated to firefighting history, a lone firefighter, dressed in full gear except for his helmet, meticulously wipes an antique fire engine, showing respect and care for the vintage piece. The museum is filled with various firefighting artifacts, creating a rich historical context. The firefighter, wearing a yellow shirt underneath his uniform, is deeply engaged in cleaning the old fire truck, highlighting the connection between present-day firefighters and their heritage. Surrounded by firefighting memorabilia, he continues to polish the vehicle, emphasizing the importance of preserving the past within the firefighting community.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2563
|
videos/HRA_part2/2563.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a crisp blue uniform and black shoes, stands in a spotless hallway illuminated by overhead lights, holding a large, black trash bag. Moments later, he walks down the hall, passing neatly arranged lockers, as he heads towards a propped-open exit door. Upon reaching the door, he pauses under the EXIT sign, preparing to step outside. Finally, he exits into the well-lit outdoors, walking towards a dumpster, his figure silhouetted against the bright sky, embodying the essence of hard work and cleanliness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_250
|
videos/HRA_part0/250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room filled with bookshelves, two young boys, one wearing a gray shirt and the other in a navy blue sweater, are diligently organizing books on a lower shelf. The atmosphere is calm and focused, with the boys working attentively side by side. One child carefully selects a book from a pile, examining it before placing it on the shelf, while the other arranges the books alphabetically, ensuring each title is correctly positioned. The room is warm and welcoming, with sunlight streaming in through a nearby window, casting a soft glow over the children as they engage in this educational activity together.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1906
|
videos/HRA_part2/1906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, garbed in a vibrant red jacket, plays a traditional wooden flute, his eyes closed in concentration, set against a backdrop of rolling hills and lush greenery. In the foreground, an ibex, distinguished by its curved horns, leaps gracefully over a small obstacle, embodying freedom and agility. The harmonious blend of the musician's melodic tunes and the ibex's acrobatic leap creates a captivating scene, where nature and artistry coalesce beautifully under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the argali jumping over obstacles in the video are very unsmooth and uncoordinated."
}
] |
seed44_2272
|
videos/HRA_part1/2272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, rakes leaves in a community garden, his gold nametag gleaming under the sunlight. He pauses to smile warmly at the camera, his friendly demeanor evident. Wearing a dark blue police uniform complete with a name badge and a cap, he continues raking, surrounded by piles of autumn leaves in various shades of orange, red, and brown. The video closes with him raking diligently, highlighting the unexpected sight of a law enforcement officer engaging in a domestic chore, fostering a sense of community and service.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2750
|
videos/HRA_part2/2750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, young musician, clad in a red jacket, dark trousers, and white sneakers, performs energetic jumps against the backdrop of Pluto's icy mountains, which are illuminated by the distant sun. The artist's movements are exaggerated, indicating a sense of weightlessness in this extraterrestrial environment. They leap and dance, arms outstretched, as if embracing the unique landscape. The musician's animated expressions convey a mix of awe and delight, perfectly encapsulating the surreal experience of frolicking on the alien terrain of Pluto.]"
},
{
"from": "gpt",
"value": "Bad. The musician's jumping movements in the video are not smooth."
}
] |
seed46_1072
|
videos/HRA_part2/1072.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished 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": "Good. Basically no problem."
}
] |
seed42_2110
|
videos/HRA_part0/2110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a gray jacket and khaki pants, sits cross-legged on a lush green meadow, gently caressing a docile water buffalo. The buffalo, with its large frame and distinctive horns, stands calmly beside a small body of water, accepting the student's affectionate touch. The student's serene facial expression and the peaceful surroundings, including trees and distant mountains, create a harmonious atmosphere. The scene is bathed in warm sunlight, casting a golden hue over the student and the buffalo, highlighting the tender connection between human and animal in a rural setting.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video, and the buffalo's face is slightly distorted."
}
] |
seed46_1742
|
videos/HRA_part2/1742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an aquarium filled with clear, blue water, a translucent ghost shrimp, barely visible, floats motionless near the bottom, its delicate legs folded. It then swims upward slowly, revealing its transparent body and the tiny creature inside, before coming to a stop near the surface. The shrimp hovers there, seemingly weightless, before descending again to the sandy bottom, dotted with small stones and pieces of aquatic plants, offering a glimpse into the elusive life of this ethereal crustacean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2459
|
videos/HRA_part1/2459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brightly lit classroom filled with educational toys and posters, a caring teacher, dressed in a yellow shirt and khaki pants, gently wipes the face of a young chimpanzee sitting attentively on a small chair. The chimpanzee, wearing a tiny blue cap, looks intently at the teacher, who uses a soft, white cloth to clean its face. The scene conveys a sense of nurturing and education, with the teacher's kind demeanor and the chimpanzee's attentive behavior highlighting the bond between them.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's action of cleaning the chimpanzee's face with white fabric is basically normal, but there is some lack of coordination."
}
] |
seed42_2782
|
videos/HRA_part0/2782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a black shirt and black jeans, is seen in a studio, wiping down a zebra-striped bass guitar with a cloth. The room is filled with musical instruments and equipment, including a drum set, a keyboard, and various guitars. The musician's focus is intense as they meticulously clean the unique instrument, the zebra-striped bass guitar, ensuring it remains in pristine condition. The scene is intimate, capturing the musician's dedication to their craft amidst a backdrop of musical passion and creativity.]"
},
{
"from": "gpt",
"value": "Normal. The musician can be clearly seen wiping the bass guitar with a cloth in the video, the actions are basically normal but there is some lack of coordination."
}
] |
seed44_1666
|
videos/HRA_part1/1666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning round glasses and a yellow sweater, sits at a wooden table cluttered with writing tools and a laptop, knitting a vibrant red scarf with large needles. The scene is set in a cozy room with a rustic wooden floor and a large window, through which daylight softly illuminates the space. On the wall hangs a large, colorful painting, adding a touch of artistic flair. The writer's hands, adorned with rings and bracelets, skillfully manipulate the knitting needles as they work on the scarf, all while surrounded by the warm, inviting atmosphere of the room.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video are incomplete, her eyes are unrealistic, and the knitting needles are broken."
}
] |
seed44_1209
|
videos/HRA_part1/1209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, dressed in a lime green shirt and black shorts, runs through a lush, dense forest filled with tall, vibrant trees and thick foliage, the sunlight filtering through the canopy to illuminate the path. The teacher's face is visible, showing determination and focus, with the camera capturing the motion of their legs and feet as they navigate the terrain. The scenery is rich in detail, with various shades of green from the leaves and plants surrounding the runner, and the sounds of nature - birds chirping, leaves rustling - adding to the immersive experience. Throughout the video, the teacher maintains a steady pace, their form suggesting a regular runner enjoying a peaceful jog in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The character's arm is twisted, the hand is distorted, and the foot is twisted."
}
] |
seed46_1019
|
videos/HRA_part2/1019.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly contrasting scene, a middle-aged, bespectacled teacher wearing a gray jacket, blue shirt, and khaki pants runs alongside a majestic, wild panther, both moving at full speed across a lush green field under a bright blue sky. The teacher, with short brown hair and a look of intense focus, matches strides with the powerful feline, its sleek black fur rippling in the wind as it sprints effortlessly beside him. The unlikely pair cuts through the vibrant grassland, the teacher's clothing billowing slightly from the momentum, creating an extraordinary and dynamic image of an educator and a panther in motion together.]"
},
{
"from": "gpt",
"value": "Bad. The running movements of the characters and animals in the video are not coordinated."
}
] |
seed42_2734
|
videos/HRA_part0/2734.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic, silver-furred wolf stands on a platform at the base of a colossal space elevator, its massive structure stretching into the starlit sky. The wolf gently caresses the sleek, metallic surface of the elevator with its snout, as if acknowledging a familiar presence. Its piercing golden eyes reflect the surrounding ethereal lights, adding an otherworldly touch to the interaction between the creature and the futuristic architecture. The platform is surrounded by a vast, moonlit landscape, with distant mountains silhouetted against the night sky, creating a dramatic contrast to the looming space elevator.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_325
|
videos/HRA_part1/325.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, distinguished by his gray beard and wearing a dark jacket, blue shirt, and khaki pants, interacts closely with a chimpanzee. The chimpanzee, positioned on a wooden structure in a spacious indoor setting, leaps energetically into the air, demonstrating its agility. The director observes intently, possibly guiding the action or assessing the performance, while standing on the same platform as the chimpanzee, which is enclosed within the large room. The scene captures the unique collaboration between human and animal in the context of filmmaking.]"
},
{
"from": "gpt",
"value": "Bad. The director's facial features in the video are generated disharmoniously, the fingers are deformed, and the chimpanzee's limbs are twisted and deformed."
}
] |
seed42_2206
|
videos/HRA_part0/2206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a yellow fire-resistant jacket, methodically mops the floor of a fire station common room, which features a pool table, a large flat-screen TV, and a couch. The mop bucket sits nearby, and the firefighter's focus and precision in cleaning contrast with the typically rugged image associated with firefighting. The scene highlights the everyday tasks and responsibilities of firefighters when they are not actively battling fires, emphasizing the importance of maintaining a clean and orderly living environment within the station.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2481
|
videos/HRA_part2/2481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, with curly brown hair and wearing a gray shirt, speaks directly to the camera with a smile, holding a small, unframed artwork in his hands. The focus is on his face and upper body, with the studio environment blurred in the background, including a large window and a partially visible sculpture. Throughout the clip, he maintains eye contact with the viewer, gesturing with his free hand as he passionately discusses his work. The atmosphere is warm and inviting, enhanced by the soft lighting that illuminates the artist and the artwork.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2544
|
videos/HRA_part0/2544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 space courtroom under the glow of neon lights, two children, a boy in a gray t-shirt and a girl in a pink dress, engage in a mock trial, surrounded by an audience of plush toys and action figures. The boy, acting as the judge, holds a gavel, while the girl, serving as the defendant, wipes away pretend tears with a small tissue, both participants fully immersed in their roles amidst the imaginative setting. Behind them, a large window reveals the vastness of outer space, complete with stars and planets, adding to the fantastical atmosphere of this unique children's play scenario.]"
},
{
"from": "gpt",
"value": "Normal. The boy's face and hands, the wooden hammer, and the girl's hands are generated with issues."
}
] |
seed44_2656
|
videos/HRA_part1/2656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green shirt and beige cargo pants, stands on set with a megaphone in hand, coordinating the action. Nearby, a majestic tiger leaps gracefully over a log, its muscles rippling and eyes intense, demonstrating the power and agility of the big cat. The scene is set in a lush, verdant forest, with sunlight filtering through the leaves, creating a dramatic interplay of light and shadow. The director's focused gaze and the tiger's dynamic leap are captured in high definition, highlighting the intensity and precision required for filming such a scene.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand, the megaphone in the hand, and the tiger's limbs were generated abnormally."
}
] |
seed42_1132
|
videos/HRA_part0/1132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged janitor, dressed in a gray jacket and khaki pants, gently caresses the trunk of a small, friendly mammoth. The creature, with its baby-blue fur and tiny tusks, stands docilely in a brightly lit room filled with cleaning supplies. The janitor, with a caring smile and a mop in one hand, tenderly strokes the mammoth's trunk, creating an unlikely yet heartwarming bond between the two. The room is warm and welcoming, with sunlight streaming in from a large window, casting a golden glow over the unlikely pair.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth in the video is not blue."
}
] |
seed44_2851
|
videos/HRA_part1/2851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown monkey walks purposefully across a lush green forest floor, sunlight filtering through the dense foliage above, casting dappled shadows on the ground. The monkey, with its fur ruffled by a gentle breeze, carries a small object in its mouth, possibly food, as it navigates the underbrush with agile movements. Its eyes, alert and curious, scan the surroundings, showcasing its adaptability in the wild. The scene is set against a backdrop of verdant vegetation, with the occasional sound of rustling leaves and chirping birds adding to the natural ambiance.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the small object mentioned in the caption that the monkey is supposed to be holding in its mouth."
}
] |
seed46_1657
|
videos/HRA_part2/1657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 living room filled with natural light, a diligent woman wearing a yellow apron over a floral dress meticulously dusts an ornate wooden dresser, her movements methodical and thorough. Beside her, a man in a white shirt and brown trousers assists, carefully wiping down a matching side table. The room is elegantly decorated with antique furniture and Persian rugs, creating a warm and inviting atmosphere. On the walls, framed paintings and family photographs add personal touches to the space. The couple works in harmony, their actions demonstrating a shared commitment to maintaining their cherished home environment.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video is distorted, with a twisted face, twisted arms, twisted legs, and twisted hands."
}
] |
seed44_1127
|
videos/HRA_part1/1127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate musician, donning a black beret, thick-rimmed glasses, and a patterned shirt, nods his head in time with the music he plays on his acoustic guitar. The scene is set in a dimly lit room, with the focus solely on the artist. His eyes are closed in concentration, lost in the melody, as he strums the guitar with skillful fingers. The atmosphere is intimate, capturing the essence of a solo performance, with the musician's nodding head emphasizing the rhythm of the song.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2402
|
videos/HRA_part2/2402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed firefighter, complete with helmet and yellow firefighting jacket, races through a lush, green forest, closely pursued by an animated beaver wearing a miniature firefighter uniform, also with a helmet and a small red cape. The firefighter leaps over a fallen log, demonstrating agility, while the beaver follows suit, mimicking every action with playful determination. Both characters run with purpose, the firefighter leading the charge and the beaver keeping pace, highlighting a fun, animated adventure set against the vibrant backdrop of a dense woodland.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1943
|
videos/HRA_part2/1943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant green lizard with intricate patterns adorns its skin, positioned on a dry, cracked earth surface under a bright, cloud-dappled sky. It appears to dance, flicking its tongue and swaying its body in a manner that suggests movement to an unseen beat. The lizard's movements are fluid and energetic, its tail swishing and its limbs moving gracefully as if it's performing a choreographed routine. Despite the arid environment, the lizard's dance brings a sense of lively energy to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The lizard's movements in the video are not smooth and are uncoordinated."
}
] |
seed42_2239
|
videos/HRA_part0/2239.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a quaint, dimly lit restaurant, a neatly dressed waiter, wearing a black apron over a crisp white shirt and black trousers, is seen wiping a table with a white cloth. Unexpectedly, a playful gray cat emerges, rubbing against the waiter's leg. The waiter pauses, gently bending down to pet the friendly feline before resuming his task, the cat now seated beside him, seemingly enjoying the attention in the cozy dining space.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm have undergone deformative mutations, and the kitten has also mutated."
}
] |
seed42_2425
|
videos/HRA_part0/2425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant parrotfish, distinguished by its yellow body and green head, swims gracefully near a coral reef, showcasing its unique features in stunning detail. The fish's eyes, positioned on the left side of its head, are clearly visible, and its beak-like mouth, used for feeding on coral, is prominent. Against a backdrop of colorful corals and underwater plants, the parrotfish's dynamic movements and distinctive appearance stand out, capturing the essence of life beneath the sea. The water around it shimmers with sunlight, adding to the beauty of the scene, as the parrotfish navigates its environment with ease.]"
},
{
"from": "gpt",
"value": "Normal. The pectoral fin generation of the parrotfish in the video has issues."
}
] |
seed42_2684
|
videos/HRA_part0/2684.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heroic firefighter, clad in full gear and a yellow helmet, stands in a lush, green forest near a majestic waterfall, holding a gerbil gently in his hands. He carefully wipes water from the small animal's face, ensuring its safety, as the waterfall cascades powerfully in the background, creating a dramatic contrast between the tender moment and the raw force of nature.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's fingers are deformed, the eyes are blurry, and the hamster is generally deformed."
}
] |
seed44_2465
|
videos/HRA_part1/2465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A curious brown monkey, with its fur ruffled by the breeze, is seen playfully paddling in a tranquil body of water, surrounded by lush green foliage. It uses its arms to splash about, moving gracefully through the clear blue water, with trees and plants in the background framing the scene. The monkey's expressive face shows delight as it swims, its limbs working rhythmically beneath the surface, and droplets of water scatter around it, capturing the joy of this unexpected aquatic adventure.]"
},
{
"from": "gpt",
"value": "Normal. The brown monkey in the video has uncoordinated movements."
}
] |
seed44_2453
|
videos/HRA_part1/2453.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vividly sunlit subtropical dry forest, a small, brownish-grey vole emerges from beneath the leaf litter, its fur blending seamlessly with the earthy tones of its surroundings. It pauses, nose twitching, before taking cautious steps forward, navigating the intricate network of twigs and leaves that carpet the forest floor. The vole's round ears and curious eyes are sharply focused, scanning the environment for both threats and opportunities as it walks through this arid woodland habitat, the sunlight filtering through the sparse canopy above.]"
},
{
"from": "gpt",
"value": "Normal. The mouse's legs appear deformed."
}
] |
seed42_1020
|
videos/HRA_part0/1020.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, dressed in a navy pea coat, beige trousers, and brown shoes, is gracefully dancing in a large, empty room with polished wooden floors and high ceilings. In the background, a magnificent cat leaps playfully, its silhouette outlined by the warm glow of the rising sun, which streams through a window, casting a soft light on a potted plant. Mercury, visible as a bright star in the twilight sky outside, adds a celestial touch to the scene. The director's dance moves, captured in a series of fluid poses, convey a sense of joy and creative inspiration, while the cat's energetic jumps mirror the director's movements, creating a harmonious connection between the two.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is flying, an arm appears and disappears. The face appears deformed."
}
] |
seed42_199
|
videos/HRA_part0/199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, young female nurse, wearing a white uniform with a stethoscope around her neck, gently caresses the head of a golden retriever dog lying on the grass in a lush, green park. The nurse, with her hair tied back in a bun, interacts tenderly with the dog, who looks up at her adoringly. In another scene, she sits on a park bench, continuing to pet the dog affectionately, with trees and foliage visible in the background. The bond between the nurse and the dog is evident as they share a peaceful moment together in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The park bench mentioned in the caption does not appear in the video."
}
] |
seed46_3011
|
videos/HRA_part2/3011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, donning a traditional straw hat and overalls, embarks on an extraordinary space diplomatic mission, sprinting across a futuristic landscape. Surrounded by alien flora and fauna, he carries a small, symbolic sapling, aiming to establish intergalactic agricultural cooperation. The farmer, now in a spacesuit tailored for farming, runs alongside a diverse group of extraterrestrial diplomats, each representing their unique planetary cultures. Together, they race towards a monumental structure, blending elements of various architectural styles from across the universe, symbolizing unity and collaboration among different worlds.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hands, arms, feet, and legs are twisted in the video."
}
] |
seed44_2779
|
videos/HRA_part1/2779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull, standing solitary on a wooden pier post, looks out across the ocean with its yellow-rimmed eyes, reflecting determination and resilience. It wears a feathered coat of gray and white, with black wingtips, embodying the spirit of the seaside. Against a backdrop of a cloudy sky and the vast sea, it spreads its wings, preparing for flight, as the water gently laps against the pier. This iconic seashore bird, perched majestically, captures the essence of coastal life with its keen gaze and weathered feathers.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2406
|
videos/HRA_part1/2406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warbler perches on a thin branch, its vibrant yellow and olive-green feathers illuminated by the soft sunlight filtering through the dense foliage of a lush forest. Its bright yellow underparts contrast sharply with the olive-green upperparts, while its two wing bars and eyestripe add distinctive touches. The bird's sharp, dark eye is focused intently ahead, and its slender beak is slightly open, as if about to burst into song. The warbler's delicate feet grip the branch firmly, and its tail feathers fan out slightly, adding balance as it prepares to take flight or sing its melodic tune.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1186
|
videos/HRA_part1/1186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magpie perches on a weathered wooden fence post, its distinctive black-and-white plumage gleaming under the soft sunlight. Against a backdrop of lush green foliage and clear blue skies, the bird's eyes sparkle with curiosity. It tilts its head to the side, seemingly observing its surroundings with interest. The vibrant colors of nature serve as a striking contrast to the magpie's striking feathers, highlighting its unique beauty in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1478
|
videos/HRA_part2/1478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing her uniform consisting of a white collared shirt, black pants, and a name badge, takes a break from her duties to clean the gutters of the medical facility. She stands on a ladder, her gloved hands scooping out debris, with the sunny day highlighting her dedication beyond her regular responsibilities. The video showcases her multitasking abilities, as she balances her healthcare role with the practical needs of maintaining the clinic's infrastructure, all while dressed in her recognizable nursing attire.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_3170
|
videos/HRA_part0/3170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a white tank top, blue denim overalls, and a wide-brimmed straw hat, sprints across a lush, green landscape dotted with ancient cemeteries. The rolling hills and distant, hazy mountains provide a scenic backdrop as he runs past weathered tombstones and aged monuments. His journey takes him along a narrow path lined with wildflowers and overgrown grass, leading through the serene burial grounds. Amidst the tranquility of the cemeteries, the farmer's vigorous run adds a dynamic element to the otherwise peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's running movements in the video are uncoordinated."
}
] |
seed42_2423
|
videos/HRA_part0/2423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, dressed in a black leather jacket, dark jeans, and a white T-shirt, sings into a microphone against a dimly lit, blurred background, evoking a sense of depth. His eyes are closed as he belts out a powerful note, showcasing his emotional connection to the music. His left arm is raised, gripping the mic stand, while his right hand passionately strums an electric guitar, amplifying the intensity of the performance. The scene is set in a small, intimate venue, with the audience's silhouettes visible in the background, creating a captivating atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The musician's fingers are poorly generated, the face is slightly blurry, and the guitar is generated too small."
}
] |
seed46_2089
|
videos/HRA_part2/2089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative blend of scenes, two smiling children, a boy in a blue jacket and a girl in a pink jacket, walk alongside a life-sized zebra puppet, its distinctive black and white stripes vivid against a neutral background. The children hold hands, looking up in wonder, as the zebra puppet, operated by an unseen handler, walks alongside them. Behind them, a large, high-definition screen displays a captivating visualization of dark matter research, featuring swirling galaxies and complex data visualizations, seamlessly merging elements of nature, childhood innocence, and scientific exploration.]"
},
{
"from": "gpt",
"value": "Bad. The child's movements in the video are not smooth, and the zebra puppet's actions are also not smooth."
}
] |
seed42_3060
|
videos/HRA_part0/3060.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a white tank top, blue jeans, and black sneakers, meticulously cleans a car using a sponge and bucket filled with soapy water, under a clear blue sky. He begins by pouring water from a green hose nozzle onto the vehicle, the bubbles catching the sunlight. Next, he uses a sponge to scrub the car's hood, his focused gaze and dedicated posture conveying his commitment to the task. Then, he rinses the suds away with the hose, revealing the car's now gleaming surface. Lastly, he wipes down the clean car door with a cloth, the contrast between the dirty rag and the shiny paintwork highlighting the effectiveness of his efforts.]"
},
{
"from": "gpt",
"value": "Bad. The video does not generate a water pipe, and the human hand appears deformed."
}
] |
seed42_204
|
videos/HRA_part0/204.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged, bespectacled woman stands in a dimly lit classroom, adorned with scientific posters and models, wearing a blue shirt, black pants, and sneakers, holding a book titled 'Dark Matter'. She speaks passionately about dark matter research, gesturing toward a whiteboard filled with complex equations and diagrams. Suddenly, she transitions into a swimming instructor, standing poolside at an indoor swimming facility. Dressed in a blue swimsuit and cap, she demonstrates proper swimming techniques, her movements fluid and confident, as students watch attentively from the water. Throughout the scene, educational elements and swimming gear are prominently displayed, blending the worlds of academia and aquatic sports seamlessly.]"
},
{
"from": "gpt",
"value": "Normal. The middle-aged woman in the video stands and speaks in the classroom, and the movements are not very smooth and continuous."
}
] |
seed44_3139
|
videos/HRA_part1/3139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a blue shirt and apron, is seen in a well-lit kitchen, preparing an evening meal. The scene opens with a close-up of her face, framed by curly hair, as she smiles warmly while chopping vegetables on a wooden cutting board. She then proceeds to sauté the ingredients in a large pan on a gas stove, the flames casting a soft glow on her face. The camera captures her stirring the contents of the pan with a wooden spoon, her focus and passion for cooking evident in every movement. As the aroma of the sizzling food fills the room, she adds spices from a set of neatly arranged jars, her actions fluid and practiced, embodying the dual talents of writing and culinary artistry.]"
},
{
"from": "gpt",
"value": "Bad. The writer's movements while stir-frying the ingredients in the video are not smooth."
}
] |
seed44_2794
|
videos/HRA_part1/2794.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique and captivating scene, a small brown bat, identified as a Mexican free-tailed bat, swims across a body of water, its wings functioning as paddles. This unexpected sight unfolds against the backdrop of a calm lake, with lush greenery visible in the background. The bat's swimming action is emphasized, showcasing its survival instinct and adaptability in an unfamiliar environment. The video captures this rare moment in high definition, highlighting the bat's struggle and determination as it navigates the water.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2481
|
videos/HRA_part1/2481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, with curly brown hair and wearing a gray shirt, speaks directly to the camera with a smile, holding a small, unframed artwork in his hands. The focus is on his face and upper body, with the studio environment blurred in the background, including a large window and a partially visible sculpture. Throughout the clip, he maintains eye contact with the viewer, gesturing with his free hand as he passionately discusses his work. The atmosphere is warm and inviting, enhanced by the soft lighting that illuminates the artist and the artwork.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2411
|
videos/HRA_part2/2411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]"
},
{
"from": "gpt",
"value": "Normal. The bison's movements in the video are not smooth."
}
] |
seed46_317
|
videos/HRA_part2/317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical scene, two small children wearing vibrant space suits crawl across the rugged terrain of Pluto's icy mountains, their movements slow and deliberate due to the planet's low gravity. The landscape is dominated by towering, sparkling ice formations that reflect the dim, alien sunlight. One child looks back with wide-eyed wonder, their helmet visor fogging slightly from their breath. Beside them, a robust rover equipped with large wheels and advanced scientific instruments sits idle, providing a sense of scale to the vast, icy environment. The overall atmosphere is one of awe-inspiring isolation and the pure joy of exploration, encapsulated in the children's expressions and the vast, untouched beauty of Pluto's surface.]"
},
{
"from": "gpt",
"value": "Bad. Two children's legs and arms undergo abnormal mutations while walking, and the two children eventually merge into one child."
}
] |
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 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 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 movements in the video are not smooth."
}
] |
seed44_1930
|
videos/HRA_part1/1930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small brown rabbit crawls through the tall grass, its movements slow and deliberate. The camera captures this scene in high definition, focusing on the rabbit's textured fur and the vibrant vegetation surrounding it. The atmosphere is peaceful and serene, with the gentle swaying of the grass and the soft sounds of nature providing a calming backdrop. The rabbit continues its crawl, seemingly undisturbed by the presence of the camera, offering viewers an intimate glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's face is distorted, the ears are slightly twisted, and the legs are twisted."
}
] |
seed42_321
|
videos/HRA_part0/321.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit sits quietly by a serene pond, the first light of sunrise on Mercury casting a pale, ethereal glow over the still waters. The sky is a deep shade of indigo, dotted with fading stars, while the distant horizon glimmers with the soft, alien light of the emerging sun. The rabbit, with its soft fur glistening with dew, prepares to take a unique plunge, as it gently enters the calm waters, creating ripples that expand across the glassy surface, under the enchanting, otherworldly beauty of a Mercury dawn.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's movements in the video are not smooth."
}
] |
seed44_269
|
videos/HRA_part1/269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, misty forest setting, a majestic bull moose with a full rack of antlers tenderly nuzzles a smaller female moose, both enveloped in the early morning light filtering through the trees. Their interaction is gentle and intimate, showcasing the softer side of these typically solitary creatures. The male's large, furry body and impressive antlers contrast with the delicate nature of their caress, highlighting the bond between them. The scene is set against a backdrop of lush vegetation and tall trees, creating a peaceful and private moment in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2131
|
videos/HRA_part2/2131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and safety goggles, carefully crawls across a rugged, volcanic landscape, examining a unique rock formation. Surrounded by steam vents and volcanic rocks, the doctor, complete with a backpack and protective gear, crawls through a narrow crevice, demonstrating determination and focus in the harsh environment. The scene highlights the doctor's adventurous spirit and scientific curiosity, as they navigate the challenging terrain, crawling under low-hanging rock formations, all set against the dramatic backdrop of an active volcano.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2973
|
videos/HRA_part0/2973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet suburban neighborhood, two young boys stand side by side, wearing casual clothes; one in a gray t-shirt and denim shorts, the other in a red shirt and khaki shorts. They are positioned against a backdrop of a white-painted wooden fence, with lush green bushes visible beyond. The boy in gray has his left foot raised, while the other boy leans forward, both engaged in a playful interaction. Their stance and attire are typical of summertime leisure, capturing a candid moment of childhood camaraderie against a backdrop of a sunny day.]"
},
{
"from": "gpt",
"value": "Bad. The boy's fingers and feet are deformed in the video, and there are missing parts in the generation of the arms and body."
}
] |
seed46_1462
|
videos/HRA_part2/1462.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and a light brown jacket, kneels in a modest living room to feed three domesticated cats. The room features a small, cluttered table, a beige couch, and a brown coffee table. The officer demonstrates kindness and care, pouring food into a green bowl as the cats eagerly surround him. Moments later, he gently pets one of the cats, showcasing a softer side of law enforcement, with the cats nestled around the bowl and the comforting interior of the home providing a backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the cat and the hands of the character in the video are missing, the face of the cat is distorted, and the police officer's face is generated blurry."
}
] |
seed44_2887
|
videos/HRA_part1/2887.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cheerful nurse in a traditional white uniform and cap leaps playfully across the muddy terrain of a swampy forest, surrounded by tall, lush green ferns and moss-draped trees. The scene is vibrant and lively, with splashes of mud adding a dynamic element to her joyful activity. She bounds from one spongy moss-covered log to another, her movements fluid and energetic, a stark contrast to the typically serene and still environment of the swamp. The nurse's actions are filled with a sense of adventure and freedom, her figure standing out brightly against the dark, rich greens of the swamp vegetation.]"
},
{
"from": "gpt",
"value": "Bad. The nurse in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed44_3188
|
videos/HRA_part1/3188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, wearing a white chef's uniform with black stripes and a matching hat, is seen in a small, empty room with white walls and a gray floor. He stands on a brown wooden ladder, holding a paintbrush in his right hand and a white roller brush in his left. The room is illuminated by a large window to his right, casting a soft glow over the space. The chef, with a full beard and a concentrated look on his face, is in the process of painting the wall a vibrant shade of green. The scene captures his transformation of the room, as he applies the paint with precision and care, highlighting his skills beyond the kitchen.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1
|
videos/HRA_part0/1.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden glow of twilight, a slender, reddish-brown jackal stands out against a sandy desert landscape, its piercing eyes and alert ears capturing the viewer's attention. It begins to move gracefully, its body swaying in a dance-like motion, as if responding to an unheard melody. The jackal's fluid movements are juxtaposed against the stillness of the desert, creating a mesmerizing scene where nature and rhythm intertwine. Its agile form, framed by the warm hues of the setting sun, tells a story of survival and spirit in the vast wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2569
|
videos/HRA_part1/2569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of fresh mackerel, glistening under bright lights, is presented on a bed of ice. The fish has distinctive vertical stripes, a sign of its freshness, and its eyes are clear and shiny. The camera then zooms out to reveal the fishmonger's stall, bustling with activity, where various species of fish are displayed on ice. The mackerel takes center stage, surrounded by other seafood, emphasizing its appeal among the array of options. Throughout, the high-definition footage captures the vibrant colors and textures of the fish market, focusing on the mackerel as the star attraction.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_135
|
videos/HRA_part2/135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown jacket, blue jeans, and a beige hat, walks down a street with a hare, which is hopping alongside. The artist, holding a large canvas, is seen from the back, moving purposefully. In another shot, the artist, wearing a brown jacket, blue jeans, and a beige hat, walks down the street, accompanied by the hare, which is leaping beside him. The artist, still carrying the large canvas, is shown from the front, revealing a face full of determination. Lastly, the artist, donning a brown jacket, blue jeans, and a beige hat, strolls down the street with the hare, which bounds playfully at his side, as the two continue their journey together.]"
},
{
"from": "gpt",
"value": "Bad. No scenes of the rabbit jumping off the artist's hand were generated."
}
] |
seed42_2064
|
videos/HRA_part0/2064.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of people are gathered at a pristine lake nestled in the heart of a lush, green forest, engaging in various activities. Some are wiping their feet on a large, sandy beach, preparing to enter the clear, inviting waters. Others are seated on the shore, enjoying the serene surroundings as they wipe sand from their hands and feet. The scene is peaceful, with the sound of water lapping against the shore and birds singing in the trees overhead. The lake, framed by towering pines and dotted with small boats, provides a stunning backdrop for this tranquil moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1494
|
videos/HRA_part0/1494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful young student, dressed in casual attire, gently caresses a chimpanzee seated beside her, both looking straight ahead. The scene is set against the backdrop of a busy industrial area, with large oil refineries visible in the background, emitting plumes of smoke into the hazy sky. Despite the industrial setting, the focus remains on the tender interaction between the student and the chimpanzee, conveying a sense of connection and empathy amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2175
|
videos/HRA_part1/2175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, golden hamster in swimwear, including water goggles and a miniature life jacket, floats on a raft in a clear, gently flowing river surrounded by lush greenery. It paddles with its tiny paws, navigating through the serene waters with determination. The hamster then jumps into the river, swimming energetically, its little body moving gracefully through the water. Finally, it rests on a rock near the riverbank, basking in the sunlight, wearing a happy expression, all set against the peaceful backdrop of a forest and a calm river.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1986
|
videos/HRA_part0/1986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, donning a gray t-shirt and black tactical pants, meticulously assembles a wooden dresser in a sparsely decorated room. Sunlight filters through a nearby window, casting warm shadows across the scene. The firefighter, complete with a gray tank top, dark tactical pants, and a muscular build, expertly constructs the furniture piece, showcasing his versatility beyond firefighting. The focus is on his hands as they skillfully tighten screws and align panels, revealing a side of firefighters' capabilities often unseen. Against a backdrop of a partially painted wall, the firefighter continues to assemble the dresser, demonstrating precision and care typically associated with his primary occupation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3200
|
videos/HRA_part0/3200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone jackal leaps through the air, its body stretched in mid-jump, against the backdrop of a desolate volcanic landscape. The creature, with its sandy fur and alert expression, bounds over rugged terrain as steam rises from vents in the ground. The jackal lands and pauses, ears pricked, silhouetted against the smoldering volcano that fills the horizon, its eyes reflecting the fiery glow. Moments later, it springs into action again, bounding away across the rocky, moon-like surface, leaving plumes of dust in its wake.]"
},
{
"from": "gpt",
"value": "Bad. The jackal's body is twisted, its head is twisted, and its legs are twisted."
}
] |
seed42_1193
|
videos/HRA_part0/1193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young female teacher dances joyfully on a wide, sandy beach, her bare feet sinking into the warm sand as she moves. Dressed in a vibrant, floral-print sundress and a denim jacket, she twirls with her arms extended, embracing the freedom and beauty of the seaside. The sun casts a golden glow on the beach, highlighting her graceful silhouette as she dances with abandon, surrounded by the vast, serene ocean and clear, blue skies. Her carefree spirit and the stunning beach scenery create a captivating, uplifting scene.]"
},
{
"from": "gpt",
"value": "Bad. The female teacher in the video has issues with limb generation, facial defects, and bodily deformities."
}
] |
seed42_2223
|
videos/HRA_part0/2223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unexpected scene, a mongoose, typically found in natural habitats, explores an industrial zone with caution, navigating through rusty pipes and concrete structures. Suddenly, it encounters a small pool of water, possibly from a recent rain, and surprisingly dips its paw in, showing curiosity about the liquid in this unusual environment. The mongoose then proceeds to swim gracefully, defying expectations of its usual terrestrial behavior, amidst the backdrop of industrial decay and urban grit. This juxtaposition highlights the animal's adaptability and resilience in an unorthodox setting.]"
},
{
"from": "gpt",
"value": "Bad. The mongoose's legs show deformities."
}
] |
seed46_3161
|
videos/HRA_part2/3161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a rugged appearance, wearing a white tank top, beige overalls, and a wide-brimmed straw hat, is seen singing passionately. He stands against the backdrop of a vibrant sunset, with lush green fields stretching into the horizon. His weathered hands hold the microphone as he belts out his song, his eyes closed in intense concentration. The scene is filled with the warm hues of twilight, casting a golden glow on the farmer and the verdant landscape, evoking a sense of peace and harmony with nature.]"
},
{
"from": "gpt",
"value": "Good. The man's singing in the video is basically normal."
}
] |
seed46_2305
|
videos/HRA_part2/2305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 student wearing a gray jacket walks through a vast, sunny temperate shrubland, with a yellow signpost and a lush green landscape stretching into the distance. The young man, carrying a backpack, strolls along a sandy path bordered by dense shrubbery, under a clear blue sky. He pauses to observe his surroundings, revealing a serene environment with distant mountains and a rich array of vegetation, including shrubs and small trees, all set against a backdrop of bright sunlight. Continuing his journey, he moves through the shrubland, which is characterized by its temperate climate and diverse plant life, offering a peaceful scene of nature and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The student's walking in the video is basically normal, but there are movements that are not coordinated."
}
] |
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 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 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 man's running in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed44_1326
|
videos/HRA_part1/1326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a dark, rugged outfit, crawls across a desolate landscape marked by the aftermath of a white hole explosion, which illuminates the scene with an eerie glow. The actor's face is partially obscured by shadows, adding to the suspense. As he moves, the ruins of a futuristic city can be seen in the background, hinting at a catastrophic event. The actor's intense gaze and strained posture convey a sense of urgency and survival in this post-apocalyptic setting. The scene is framed by the remnants of advanced technology and the haunting beauty of the white hole's light, creating a dramatic contrast between destruction and awe.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand generation in the video has issues."
}
] |
seed46_1075
|
videos/HRA_part2/1075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket and khaki pants, stands in a lush, green forest clearing, gently wiping mud off the antlers of a majestic deer using a soft cloth. The deer, with large, inquisitive eyes, tolerates the man's ministrations, standing still as the man carefully cleans each tine of the impressive antlers. Sunlight filters through the canopy above, casting dappled shadows on the scene below, highlighting the tender interaction between the man and the wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The action of the character wiping the deer's antlers in the video is not continuous and has abrupt changes."
}
] |
seed44_1901
|
videos/HRA_part1/1901.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged teacher, wearing rectangular glasses and a blue button-down shirt with a maroon sweater, sits at a desk in a classroom filled with wooden desks and chairs. She leans over to replace the batteries in a digital timer used for classroom activities, demonstrating resourcefulness and attention to detail. The room is decorated with a whiteboard covered in colorful marker scribbles and motivational posters, adding a vibrant touch to the educational environment. The teacher's focused expression and the act of replacing the batteries in the timer, which is placed next to a stack of papers, highlight her commitment to ensuring the smooth operation of classroom tools.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the teacher changing the sub-timer battery, and the action is basically normal but somewhat uncoordinated."
}
] |
seed42_2860
|
videos/HRA_part0/2860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown mouse, with large ears and a long tail, crawls across a wooden surface, its movements quick and cautious. The mouse pauses momentarily, its nose twitching as it sniffs the air, before continuing on its path. The texture of the wood grain is visible beneath the mouse's tiny feet, which grip the surface as it navigates its environment. The scene is captured in high definition, allowing every detail of the mouse's fur and the wooden surface to be seen clearly. The background is a soft, neutral tone, ensuring the focus remains on the mouse as it crawls.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the mouse's paws and mouth in the video has problems."
}
] |
seed42_1907
|
videos/HRA_part0/1907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 solitary vulture, with its distinctive bald head and dark, rugged feathers, perches on a branch in a barren tree set against a cloudy sky. The bird's sharp eyes scan the surroundings, while its large wings remain folded, ready for flight. In the next scene, the vulture takes off, its powerful wings propelling it into the air as it begins to circle above the landscape, searching for carrion. The video then focuses on the vulture in mid-flight, its wings spread wide, gliding effortlessly through the air with a backdrop of rolling hills and distant mountains. Finally, the bird lands gracefully on a rocky outcropping, where it stands alert, surveying its territory with a commanding presence.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2664
|
videos/HRA_part1/2664.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a brown jacket over a white shirt and khaki pants, walks through a temperate deciduous forest during autumn. The trees are predominantly bare, with scattered leaves covering the ground. The forest floor is carpeted with a thick layer of dry, brown leaves, creating a crunching sound underfoot. The doctor occasionally stops to observe his surroundings, showcasing his appreciation for nature. Throughout the scene, the forest remains dense and the trees tall, with occasional glimpses of sunlight filtering through the canopy, highlighting the serenity of the environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1811
|
videos/HRA_part1/1811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and black leggings, walks briskly across a campus path, holding textbooks and a coffee cup. Suddenly, a coyote appears in the frame, walking parallel to the path, about ten feet away from the student. The coyote, seemingly unbothered by the human presence, has a gray and brown coat, alert ears, and a bushy tail. It continues to walk alongside the path, offering a unique encounter between urban wildlife and a busy student on the go.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2481
|
videos/HRA_part2/2481.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, with curly brown hair and wearing a gray shirt, speaks directly to the camera with a smile, holding a small, unframed artwork in his hands. The focus is on his face and upper body, with the studio environment blurred in the background, including a large window and a partially visible sculpture. Throughout the clip, he maintains eye contact with the viewer, gesturing with his free hand as he passionately discusses his work. The atmosphere is warm and inviting, enhanced by the soft lighting that illuminates the artist and the artwork.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands show signs of deformity and mutation."
}
] |
seed44_1854
|
videos/HRA_part1/1854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown leather jacket and jeans, walks alongside a cheetah in a natural savanna setting, both figures dwarfed by the vast, open landscape. The writer, wearing a beige hat, sunglasses, and holding a pen and notebook, looks thoughtful as they stroll together. The cheetah, sporting a tracking collar, walks parallel to the writer, its gaze forward, reflecting a sense of purpose and freedom. Together, they traverse the grassy terrain, the writer occasionally jotting down notes, while the cheetah remains vigilant, embodying the spirit of the wild.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's limbs are uncoordinated while walking."
}
] |
seed44_3043
|
videos/HRA_part1/3043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, attired in a crisp white shirt, black vest, and trousers, strolls through dense, lush green thickets, carrying an empty silver tray. The vibrant flora envelops him as he walks, the sunlight filtering through the leaves creating a dappled effect on his path. The setting, reminiscent of an English garden, is filled with various plants and trees, providing a rich, textured backdrop for his leisurely walk. Despite the wild surroundings, the waiter maintains a professional demeanor, his attire and posture suggesting a formal occasion amidst nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1800
|
videos/HRA_part1/1800.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 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 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": "Good. No obvious problems."
}
] |
seed42_2399
|
videos/HRA_part0/2399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, industrial-style hallway, a janitor wearing a yellow vest and holding a mop walks purposefully toward the camera. Behind him, a theoretical spectacle unfolds: a white hole explosion, depicted as an intense burst of light and energy, engulfs the far end of the corridor, creating a dramatic contrast to the mundane setting. The janitor's steady pace and resolute expression suggest an intriguing juxtaposition between the cosmic event and his daily routine.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2554
|
videos/HRA_part0/2554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a gray sweater and brown pants, is seen painting en plein air in a lush green forest. Suddenly, a squirrel scurries into the frame, running along the forest floor, its bushy tail bouncing behind it. The artist pauses, observing the squirrel's movements with fascination, capturing the essence of the woodland creature in motion on the canvas. The squirrel, now aware of the artist's presence, stops briefly to look back before continuing its hurried journey, providing a perfect subject for the artist's brushstrokes.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1107
|
videos/HRA_part1/1107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, dreamlike scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's actions of touching the Mars rover in the video are basically normal, with slight inconsistency."
}
] |
seed46_1505
|
videos/HRA_part2/1505.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, plump quail with brown and black speckled feathers stands prominently in the foreground, nestled among lush green foliage that includes leaves, ferns, and tall grasses. It faces left, its head turned slightly toward the camera, revealing its distinctive facial features, including a small beak and alert eyes. The bird's textured feathers are intricately detailed, and its legs are visible as it perches on the forest floor, surrounded by the vibrant flora.]"
},
{
"from": "gpt",
"value": "Normal. The quail's movements in the video are basically normal, with slight inconsistency."
}
] |
seed42_1516
|
videos/HRA_part0/1516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrious male engineer, wearing a blue button-down shirt and glasses, meticulously irons his clothes in a modestly furnished room with a wooden floor and cream walls. He stands at an ironing board covered with a white cloth, carefully smoothing out wrinkles in a garment. The room is illuminated by natural light from a window behind him, casting a warm glow over the scene. On the wall to his right, a large painting in shades of green adds a splash of color to the otherwise simple space. Beside the window, a desk with a laptop and engineering blueprints hints at his professional life, while a shelf filled with books and a houseplant brings a personal touch to the environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's ironing movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed44_2295
|
videos/HRA_part1/2295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant underwater scene, an array of coral formations thrives, illuminated by the dappled sunlight filtering through the clear blue water. A variety of corals, from branching staghorn to massive brain corals, creates a textured landscape. Nearby, a school of tropical fish, featuring yellows, blues, and oranges, swims gracefully among the corals, adding life and movement to the tableau. The water is crystal clear, allowing every detail of the coral and marine life to be visible, making it a stunning display of the beauty found beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2620
|
videos/HRA_part2/2620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy blue uniform and badge, meticulously organizes his home garage, filled with various tools and equipment. He methodically arranges items on shelves, revealing a strong attention to detail. The garage space, well-lit and clean, reflects his disciplined nature. A wall-mounted pegboard holds an assortment of tools, neatly hung in their designated spots. Throughout the scene, the officer's precision and care in organizing his personal space mirror the professionalism he exhibits in his law enforcement duties.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_129
|
videos/HRA_part0/129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, with wet brown fur and a charming face, is seen grooming itself in its natural habitat. It wipes its paw across its face in a cute and meticulous manner, showcasing its daily cleaning ritual. The otter is positioned against a backdrop of lush greenery and water, highlighting its wild environment. Throughout the scene, the otter continues to groom its whiskers and face, occasionally pausing to look around, offering a captivating glimpse into its world.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2369
|
videos/HRA_part2/2369.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman wearing a yellow shirt and blue jeans stands on a wooden chair, her right hand holding a new light bulb, her left hand unscrewing the old one. She has short brown hair and wears glasses, her face showing concentration as she works against a background of a white ceiling and pale green walls. Moments later, she screws in the new bulb, her tools, a screwdriver and pliers, rest on the chair next to her. The room is sparsely furnished, featuring a wooden table and chairs, and a window covered by white curtains, as she completes her task with skill and determination.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes and the light bulb and screwdriver in her hand suddenly disappear."
}
] |
seed42_1054
|
videos/HRA_part0/1054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, two young siblings, a brother and sister, are getting ready for bed. The boy, wearing a blue-striped pajama set, yawns widely, his eyes half-closed, as he sits on the edge of his bed. Moments later, the girl, clad in a pink nightgown, echoes her brother's action with a delicate yawn, her hand covering her mouth, showing manners learned from family. They sit next to each other, displaying the natural bond between them, as they prepare for sleep in their cozy bedroom, the glow of the nightlight casting a warm hue over the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2345
|
videos/HRA_part2/2345.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a doctor, clad in a crisp white lab coat, stands in a vibrant jungle setting, complete with lush green foliage and exotic flowers. Accompanied by a dingo, the duo begins to dance gracefully, the doctor's stethoscope swinging rhythmically as they move. The dingo, surprisingly elegant, prances alongside, its fur glistening under the golden sunlight filtering through the canopy above. The two continue their dance, the doctor's glasses catching the light and the dingo's tail swishing in time, creating a surreal and joyful spectacle in the heart of the jungle.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the wild dog's actions are also not smooth."
}
] |
seed44_2853
|
videos/HRA_part1/2853.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic musician, adorned in a stylish leather jacket and holding a harmonica, walks alongside a dingo in a serene natural landscape. Both figures stroll leisurely, the musician's outfit complemented by faded jeans and a classic white T-shirt, while the dingo, with its reddish-brown fur, matches the earthy tones of the surroundings. They move in harmony, the musician occasionally playing the harmonica, creating a peaceful melody that resonates with the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The musician's hands are distorted, the object in hand is distorted, the face is distorted, the feet are distorted, the dingo's face is distorted, and the legs are distorted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.