video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1102
|
videos/HRA_part1/1102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a black jacket over a gray shirt and dark pants, is engaged in an intense scene where he skillfully catches a falling glass bottle with his right hand, displaying remarkable agility and precision. His focused gaze and the dynamic motion of the catch are highlighted against a dimly lit, gritty urban setting, adding to the dramatic effect of the moment. The scene is shot in high definition, capturing every detail of the actor's expression and the fluidity of his movements as he successfully intercepts the bottle mid-air.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show a glass bottle."
}
] |
seed42_1096
|
videos/HRA_part0/1096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space reality TV set, an antelope, wearing a small golden bell around its neck, stands calmly against a backdrop of stars and galaxies. The animal is gently caressed by a human figure dressed in a spacesuit, conveying a sense of comfort and companionship in the vastness of space. The astronaut's gloved hand softly touches the antelope's face, while the creature looks on serenely, the golden bell shining under the starlight, creating a surreal and touching moment in an extraterrestrial environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2592
|
videos/HRA_part0/2592.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 focused young student sits at a wooden desk in a well-lit classroom, diligently sewing a button onto a piece of light blue fabric using a thin needle and white thread. The student, wearing a gray hoodie and blue jeans, attentively works on the sewing project, which is placed atop a larger piece of white fabric. The room is filled with natural light from a nearby window, illuminating the task at hand and highlighting the student's concentration and skill in performing this traditional craft.]"
},
{
"from": "gpt",
"value": "Bad. The student's hands show signs of deformity and mutation."
}
] |
seed46_1839
|
videos/HRA_part2/1839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, prehistoric landscape under an orange sky, a group of Woolly Mammoths walk together in the distance, creating a sense of awe and grandeur. Meanwhile, in the foreground, a female caveman, dressed in furs and bearing a resemblance to a modern-day cashier, stands against a rocky outcropping, holding what appears to be ancient currency in her hand. She looks intently at the mammoths, which are walking away from her across the ancient terrain, conveying a narrative of survival and commerce in prehistoric times.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements are not smooth."
}
] |
seed44_2423
|
videos/HRA_part1/2423.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 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 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": "Good. No obvious issues."
}
] |
seed42_1882
|
videos/HRA_part0/1882.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated female nurse, clad in a white uniform and wearing her hair in a bun, attentively checks a smoke detector mounted on the ceiling in a modern hospital hallway. The space is pristine and well-lit, with pale green walls and white trim, exuding a sense of cleanliness and professionalism. The nurse, displaying her commitment to safety, uses a long, red-handled tool to test the device, ensuring it functions properly in the healthcare environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1047
|
videos/HRA_part0/1047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned farmer, wearing a white shirt, blue overalls, and a wide-brimmed hat, stands in a lush green field under a clear blue sky. He is in mid-throw, tossing hay bales with ease, his strong arms and focused expression showcasing his expertise. The hay bales are wrapped neatly in plastic, indicating a modern farming technique. The farmer's stance, with one leg forward for balance, adds dynamism to the scene, while the rolling hills and distant trees provide a picturesque rural backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2514
|
videos/HRA_part0/2514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space habitat designed to mimic Earth's savanna, a majestic rhinoceros, fitted with a specialized spacesuit, calmly walks on artificial grass under a simulated sky. Tourists, dressed in sleek, white spacesuits, observe from a safe distance behind transparent barriers, their expressions a mix of awe and curiosity. The rhino moves gracefully, its every step monitored by advanced technology to ensure its well-being in the zero-gravity environment. This unique scene captures the harmony between wildlife conservation and the boundless possibilities of space exploration, offering viewers a glimpse into a world where nature and technology coexist in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The person and the rhinoceros in the video have no movements."
}
] |
seed42_2894
|
videos/HRA_part0/2894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen with wooden cabinets and cream walls, two young children, a boy and a girl, stand on small stools by the sink, their sleeves rolled up. They are happily washing dishes together, the girl scrubbing a plate with a pink sponge, while the boy rinses a glass under the faucet. The room is filled with natural light from a window above the sink, casting a warm glow on the soap bubbles and wet surfaces. A few clean dishes are stacked neatly on a drying rack nearby, and a colorful dishcloth hangs over the tap, completing the scene of domestic harmony and teamwork.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2902
|
videos/HRA_part0/2902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinct black markings, is perched on a concrete ledge. It has a full, rounded body and is situated in an urban environment, as indicated by the presence of a streetlight nearby. The bird's head is turned to the side, revealing its detailed eye and beak. Its wings are folded neatly against its body, and its legs, with their characteristic pinkish hue, grip the ledge firmly. The setting is an everyday city scene, with the pigeon appearing comfortable and unperturbed in its surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2523
|
videos/HRA_part1/2523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a tailored gray suit, white shirt, and red tie, takes an unconventional break from his legal duties to clean windows on a busy city street. Holding a squeegee in one hand and a spray bottle in the other, he expertly removes smudges from the glass, all while maintaining a professional demeanor. Passersby, including a group of schoolchildren and a mother with a stroller, observe the unusual sight with amusement. The lawyer's briefcase rests nearby, a reminder of his typical occupation, as he focuses on the task at hand with surprising skill and dedication.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_300
|
videos/HRA_part0/300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic brown horse gallops across a lush, green meadow under a clear blue sky, its muscular body rippling with each powerful stride. The horse's mane and tail flow dramatically in the wind, creating a sense of speed and freedom. A pair of vibrant yellow flowers appear briefly in the foreground, adding a pop of color to the scene. The horse continues its run, hooves kicking up small clumps of earth, highlighting its strength and grace as it moves through the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Normal. The horse's head and hooves in the video have generation issues, and the video does not realistically represent reality."
}
] |
seed44_2565
|
videos/HRA_part1/2565.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, a young female cashier, clad in a green jumpsuit with a name tag, works diligently at a market specializing in hydroponic produce. She crawls under the counter, surrounded by vibrant, healthy greens growing vertically against the back wall, illuminated by LED grow lights. The space agriculture setting is evident from the lush plants and the advanced technology used for cultivation. The cashier's actions are focused and purposeful, highlighting the unique challenges and innovations of farming in space, all within the confines of a bustling space station market.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1946
|
videos/HRA_part0/1946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 brown rat is seen grooming itself meticulously, its paws lifting to wipe across its face and whiskers. Positioned against a neutral grey backdrop, the rat's actions are the focal point, as it carefully tends to its cleanliness, showcasing the natural behavior of self-care in rodents. The scene is intimate, with the rat's fur and whiskers detailed in high definition, emphasizing the texture and vibrancy of its coat against the monochromatic setting.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the wiping of the face and beard as mentioned in the caption."
}
] |
seed46_2310
|
videos/HRA_part2/2310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature man, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2771
|
videos/HRA_part2/2771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, dressed in a classic pinstripe suit, stands in a vast, dimly lit studio, skillfully orchestrating a surreal scene. Nearby, a Robot astronaut, adorned in a sleek silver spacesuit with gleaming gold accents, follows the director's guidance as it begins to dance. The robot's movements are fluid and precise, a captivating fusion of technology and artistry, set against the backdrop of cinematic equipment and the director's watchful gaze, creating a mesmerizing spectacle where reality meets imagination.]"
},
{
"from": "gpt",
"value": "Bad. The robot's hand is twisted, the arm is twisted, the leg is twisted, and the director's hand is twisted."
}
] |
seed44_260
|
videos/HRA_part1/260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a yellow t-shirt and khaki shorts, sits at a wooden desk in a rural backyard, typing on a laptop while referencing notes about wormhole travel. Nearby, a brown chicken pecks at the ground, seemingly curious about the writer's work. The scene then shifts to show the writer swimming in a clear blue pool, contemplating the mysteries of the universe and wormhole navigation. The camera captures the water droplets on the writer's face, hinting at the fluidity of time and space, while the chicken watches from the poolside, adding a touch of whimsy to the intellectual exploration.]"
},
{
"from": "gpt",
"value": "Bad. The writer's face and hands, as well as the laptop, in the backyard scene have generation issues."
}
] |
seed42_1268
|
videos/HRA_part0/1268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a brown jacket, beige pants, and carrying a sketchbook, walks through a surreal landscape inspired by a galactic nebula. The sky is a vivid swirl of cosmic colors - deep purples, electric blues, and fiery oranges, evoking the ethereal beauty of distant galaxies. Giant, floating rock formations, tinged with the same nebulous hues, tower above, while the ground beneath his feet is a shimmering, star-lit plane that reflects the celestial spectacle overhead. Despite the otherworldly setting, the artist strides purposefully, his form and clothing sharply detailed against the dreamlike backdrop, as if he's on a mission to capture the universe's wonders on paper.]"
},
{
"from": "gpt",
"value": "Normal. The character's head is distorted, and the legs are twisted."
}
] |
seed44_3153
|
videos/HRA_part1/3153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2724
|
videos/HRA_part0/2724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red flannel shirt, beige pants, and brown suspenders, stands at a white sink in a rustic kitchen. He is washing dishes by hand using a sponge, with a wooden cutting board and a bowl of fruit visible nearby. The farmer, who has short brown hair and a neatly trimmed beard, demonstrates his commitment to household chores with a focused expression. The kitchen is warm and inviting, with wood-paneled walls, a white refrigerator, and a window above the sink offering a view of green fields. The farmer's strong hands, calloused from years of working the land, now deftly clean plates and utensils, showcasing the versatility of his daily tasks.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's eyes in the video have generation issues, the fingers are malformed, and the sponge is distorted."
}
] |
seed42_3209
|
videos/HRA_part0/3209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 in a red t-shirt and black shorts is depicted running alongside a kangaroo on a dusty trail surrounded by lush vegetation, both appearing energetic and engaged in the activity. They run together on a dirt path amidst dense greenery, the kangaroo bounding effortlessly beside the man, who maintains a steady pace. The scene captures the unique companionship between the man, dressed casually in a red top and dark shorts, and the kangaroo, as they traverse the natural environment together. The duo continues their run through the vibrant landscape, the kangaroo's powerful legs propelling it forward in sync with the man's strides, highlighting their shared rhythm and connection amidst the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The man and kangaroo's running actions are not smooth."
}
] |
seed46_2510
|
videos/HRA_part2/2510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with gray hair and glasses sits in a cozy room filled with bookshelves, natural light, and warm tones. He wears a blue shirt and a brown cardigan, appearing thoughtful and engrossed in a thick hardcover book. Moments later, he looks up from reading, revealing a pensive expression. He then turns the page, his eyes scanning the text intently, before pausing again to reflect on what he has read. Throughout the scene, he remains seated in the same position, his attire and surroundings unchanged, creating a calm and intellectual atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_142
|
videos/HRA_part2/142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of a fresh, whole mackerel fish, glistening under bright lights, lies on a bed of ice. The fish features intricate, dark-blue stripes over a silver body, a hallmark of its species. Its eyes are clear and shiny, indicating freshness, while its mouth is slightly open. The tail fin is curled, and the dorsal fins stand erect, showcasing the fish's natural beauty and texture. Surrounding the mackerel are ice crystals, reflecting light and adding to the icy, clean presentation of the seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1846
|
videos/HRA_part0/1846.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, wearing a red flannel shirt, blue jeans, and brown boots, runs alongside a spirited golden retriever in a lush green park. Both the musician and the dog display expressions of pure joy and freedom. The musician, equipped with a backpack, is in mid-stride, while the dog bounds ahead, tail wagging. The scene captures the essence of a carefree day in the park, with the musician's attire and the dog's enthusiastic demeanor setting the tone for a playful and energetic outing.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_186
|
videos/HRA_part2/186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cheerful children, ranging from toddlers to preteens, are engaged in the task of cleaning windows on a bright, sunny day. They wear casual clothes, including t-shirts, shorts, and sneakers, and sport various hairstyles, from pigtails to afros. The kids use squeegees and rags to wipe down the glass, leaving streaks of water and soap behind. They work together, laughing and chatting, as they tackle the large window panes of a suburban home, with lush greenery visible through the transparent surfaces. The atmosphere is one of teamwork and fun, with the youngsters taking pride in their chores under the warm glow of the sun.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2916
|
videos/HRA_part0/2916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat crawls across a desolate volcanic landscape, featuring dark, rocky terrain and smoldering vents emitting wisps of smoke. The rat moves with surprising agility among the rough, jagged rocks, its fur contrasting against the ash-covered ground. As it navigates the harsh environment, the camera captures its determined journey, highlighting its resilience in the face of the volcano's foreboding presence. Throughout the scene, the rat's focus remains unwavering, emphasizing its survival instincts in this challenging, post-eruption setting.]"
},
{
"from": "gpt",
"value": "Bad. The brown mouse in the video has uncoordinated movements while walking."
}
] |
seed42_2925
|
videos/HRA_part0/2925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male musician, dressed in a black leather jacket, dark jeans, and sunglasses, walks purposefully down a busy city street, the iconic Flatiron Building visible in the background. Suddenly, the scene shifts to depict him walking at an extraordinary pace, a visual effect suggesting the concept of light-speed travel. He continues his brisk walk, now surrounded by blurs of color and light, evoking the sensation of moving at incredible velocities. Throughout this dynamic sequence, he maintains his cool demeanor, his outfit unchanged, embodying the fusion of urban style and science fiction themes.]"
},
{
"from": "gpt",
"value": "Bad. The male musician's face generation in the video is uncoordinated, and the hands and feet are deformed."
}
] |
seed42_1792
|
videos/HRA_part0/1792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 straw hat and denim overalls, stands on wooden docks by the water's edge, engaging in an impromptu dance with a mongoose. The mongoose, with its alert eyes and bushy tail, seems equally engaged in the dance, mirroring the farmer's playful steps. The docks, weathered and worn, creak under their movements, providing a rustic stage for this unlikely duo. The sun begins to set, casting a golden glow over the scene, adding a magical touch to the dance between the farmer and the mongoose.]"
},
{
"from": "gpt",
"value": "Normal. The person's feet are twisted in the video, the mongoose's body is twisted, the arms are twisted, the claws are twisted, and the face is twisted."
}
] |
seed42_1914
|
videos/HRA_part0/1914.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched savanna, an agile antelope, its coat a rich chestnut brown, leaps gracefully in what appears to be a dance, surrounded by the golden hues of tall grass swaying gently in the breeze. Its movements are fluid and elegant, almost choreographed, as if performing a ritualistic dance under the watchful eye of the sky. The antelope's leap is captured mid-air, its legs extended in a perfect arc, creating a moment of suspended animation against the serene backdrop of nature. The scene is bathed in warm sunlight, casting a golden glow over the antelope and the landscape, enhancing the ethereal quality of this unique dance in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The antelope's running in the video is not coordinated."
}
] |
seed46_2210
|
videos/HRA_part2/2210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An innovative engineer, adorned in a spacesuit and helmet, stands on the lunar surface, illuminated by the Earth's glow, holding a leash attached to a lion. The lion, also wearing a miniature spacesuit and helmet, jumps playfully in the low gravity environment. Both figures cast long shadows against the moon's dusty terrain, with the Earth shining brightly in the dark, star-studded sky. This surreal scene combines elements of space exploration, wildlife, and human ingenuity in a single captivating frame.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the lion wearing a mini spacesuit and helmet as mentioned in the caption."
}
] |
seed46_2939
|
videos/HRA_part2/2939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with distinctive ear tufts and a short tail, leaps over a checkout counter in slow motion, its muscles tensing and releasing with each bound. The cash register, with its glowing display and scattered coins, provides context to the setting. The cashier, wearing a red apron and a surprised expression, watches the wild cat jump, creating an unexpected and captivating moment. The bobcat's leap is captured in mid-air, highlighting its agility and grace, against the backdrop of a typical supermarket checkout area.]"
},
{
"from": "gpt",
"value": "Bad. The lynx's jumping in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_3100
|
videos/HRA_part2/3100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech laboratory setting, a professional lawyer, dressed in a sharp navy suit, consults with a dedicated nanobot repair crew. The crew, clad in matching silver jumpsuits, works diligently on a complex control panel. One crew member uses a microfiber cloth to carefully wipe down a row of advanced machinery, ensuring every surface is spotless. The lawyer observes closely, occasionally pointing to specific components and engaging in animated discussions with the crew about the intricacies of the nanobot technology. The scene is lit by the soft glow of the lab equipment, creating a futuristic and professional atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the group members in the video are very unsmooth and uncoordinated."
}
] |
seed42_1259
|
videos/HRA_part0/1259.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a museum hall with marble floors, an antelope taxidermy mount is displayed under a spotlight, its majestic form captured mid-leap. A diligent custodian wearing a green apron wipes the glass display case, ensuring the exhibit is pristine. The antelope, with its striking coat and alert posture, seems to leap over a miniature landscape within the display. The custodian, in a green uniform, carefully cleans the case, her reflection visible alongside the antelope's image. Throughout, the museum's grandeur is evident, with high ceilings, ornate moldings, and other exhibits surrounding the featured antelope.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_209
|
videos/HRA_part1/209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male musician, donning a white button-down shirt and khaki pants, meticulously dusts a vintage gramophone with a feather duster in a warmly lit, cluttered room filled with musical instruments. His attire includes a brown belt and brown shoes, adding to his polished appearance. The room is decorated with a variety of string instruments hanging from the walls, including violins and cellos, highlighting the musician's passion for music. Throughout the scene, he continues to dust various objects, showcasing his dedication to preserving his cherished belongings, all within the cozy, wood-paneled space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2033
|
videos/HRA_part1/2033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny, spiky hedgehog clad in a miniature astronaut suit embarks on an extraordinary adventure across a fantastical landscape. The scene opens with the hedgehog standing bravely at the edge of a small, smoking volcano, its eyes fixed on the distant horizon where other volcanoes loom large against the twilight sky. Suddenly, it springs into action, leaping high into the air with surprising agility, defying gravity for a brief moment before landing softly back onto the volcanic terrain. The hedgehog continues its daring journey, bounding from one dramatic setting to another, showcasing its courage and determination against the backdrop of these awe-inspiring natural wonders.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1421
|
videos/HRA_part1/1421.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, wearing a red checkered shirt, brown apron, and khaki pants, takes a break from cooking to rake leaves in a suburban backyard. He pauses for a moment, looking thoughtful, before continuing his task with determination. The chef, now smiling, rakes a large pile of autumn leaves into a heap, enjoying the crisp fall weather. Finally, he pauses again, this time looking pleased with his work, standing next to the sizable leaf pile, with his rake resting on his right shoulder, and a residential neighborhood visible in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, rake, and body are distorted in the video."
}
] |
seed46_2890
|
videos/HRA_part2/2890.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. No obvious issues."
}
] |
seed46_1444
|
videos/HRA_part2/1444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic scene unfolds, featuring a creative individual sitting at an easel, engrossed in painting a detailed landscape, with a curious squirrel perched on the artist's shoulder. Nearby, a tranquil pond offers a serene contrast, its glassy surface broken only by ripples as a squirrel, perhaps inspired by its surroundings, bravely ventures into the water, swimming with surprising grace. The artist, still absorbed in their work, occasionally glances at the unexpected swimmer, capturing the unique moment on canvas.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel's movements in the video are not smooth."
}
] |
seed46_1171
|
videos/HRA_part2/1171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife sanctuary, a compassionate veterinarian, wearing a khaki shirt and cargo pants, gently wipes the face of a majestic cheetah lying on a checkered cloth, its gaze fixed on the vet. The scene is set outdoors, with lush greenery and wooden fences framing the backdrop, highlighting the unique bond between the medical professional and the wild animal. The vet's careful action, using a soft, white cloth, conveys a sense of tenderness and care, while the cheetah's calm demeanor suggests trust and familiarity.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the cheetah's head, the green plants were not lush enough, and the veterinarian's hand suddenly distorted and disappeared in the middle frame."
}
] |
seed44_1815
|
videos/HRA_part1/1815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 opens with a koala, typically terrestrial, surprisingly adept in water, swimming in a serene, clear blue pool. Its brown fur glistens as it paddles with determination, showcasing an unexpected talent. The koala, wearing a small yellow swim cap, navigates the water with surprising grace, its limbs moving rhythmically. Moments later, it emerges from the pool, shaking off droplets, revealing a cozy green towel wrapped around its body. The koala then sits on the edge of the pool, seemingly pleased with its aquatic adventure, the sunlight sparkling on the water behind it.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed46_2859
|
videos/HRA_part2/2859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal cinematic scene, a majestic buffalo leaps gracefully over a row of vintage cinema seats, its powerful muscles straining against the force of gravity. The buffalo, with its shaggy brown fur and large horns, seems unfazed by the unusual setting, focusing solely on the jump. The cinema seats, arranged neatly in rows, are old-fashioned, with red upholstery and gold accents, creating a striking contrast against the buffalo's wild nature. The room is dimly lit, casting dramatic shadows on the walls and floor, emphasizing the buffalo's impressive leap. The air is filled with tension and anticipation as the buffalo soars through the air, its hooves inches from touching the seat backs. This captivating scene combines elements of nature and culture in a way that challenges traditional boundaries and expectations.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1890
|
videos/HRA_part0/1890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green vest and khaki pants, walks purposefully down a dimly lit hallway, pushing a squeaky cleaning cart. On the wall, a badger mascot poster from a local college, Wausau Woodchucks, adds a touch of whimsy. The scene shifts slightly to reveal more of the hallway, showcasing the linoleum floor and overhead lights. The janitor continues his journey, passing a row of lockers adorned with stickers and graffiti, while the badger poster remains visible, adding a sense of character to the otherwise mundane setting. Finally, the focus is on the janitor's interaction with the environment, as he pushes the cart with determination, the badger poster serving as a silent observer in the background.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands in the video are slightly distorted."
}
] |
seed44_1057
|
videos/HRA_part1/1057.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit studio, an artist sits at a desk, engrossed in sketching detailed cosmic phenomena, specifically the explosive aftermath of a white hole, depicted on a large sheet of paper. On the desk, a gerbil runs playfully, its movements occasionally distracting the artist. The artist, wearing a black beret and glasses, looks up pensively, perhaps inspired by the gerbil's antics. Then, the artist gently caresses the gerbil, which is now sitting still, as if bonding with the small creature, all while the cosmic illustration continues to take shape in the background.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand and the hamster in the video have generation issues."
}
] |
seed46_2245
|
videos/HRA_part2/2245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning close-up of a Brook Trout fills the frame, its vibrant colors and intricate patterns mesmerizing. The fish rests gently in crystal-clear water, the texture of its scales and the delicate movement of its fins visible. Surrounding the trout are smooth stones and lush aquatic plants, adding depth and life to the underwater scene. Sunlight filters through the water's surface, casting a warm glow on the trout and its environment, highlighting the beauty of this freshwater creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1635
|
videos/HRA_part0/1635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park, a creative director, dressed in a casual yet professional attire, intently observes a small, agile mouse crawling along a weathered wooden fence. The mouse, with its curious eyes and twitching nose, explores its surroundings with cautious determination. The director, holding a clipboard and pen, meticulously studies the creature's movements, occasionally jotting down notes. The scene captures the unique interaction between human observation and the natural behavior of wildlife in the controlled environment of a zoo.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2683
|
videos/HRA_part2/2683.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 sits in a dimly lit room, her face softly illuminated by a single light source. She is wearing a simple white shirt, her brown hair falling gently over her shoulders. The camera focuses on her chest, rising and falling slowly as she takes deep, deliberate breaths. Each inhale is visible, drawing attention to the tranquility of the moment. Her eyes are closed, her lips slightly parted, as she finds peace in the rhythm of her breathing. The quiet atmosphere is punctuated only by the sound of her breath, creating a serene and intimate portrait of mindfulness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2588
|
videos/HRA_part2/2588.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair and glasses, wearing a gray shirt, sits at a desk cluttered with papers and pens. She is intently writing with a pen in her right hand, her focus evident on her face. Behind her, a large window reveals a bustling cityscape at twilight. A laptop and coffee mug sit on the desk beside her, while a bookshelf filled with engineering texts and a whiteboard covered in equations complete the scene, highlighting the intellectual environment. The engineer pauses briefly to look up, perhaps contemplating her next line of thought, before returning to her writing with renewed determination.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2165
|
videos/HRA_part0/2165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, ancient-looking turtle with a mossy, textured shell slowly moves across a lush, green forest floor, surrounded by vibrant ferns and fallen leaves. Its wise, gentle eyes and wrinkled skin reflect its age and resilience. Nearby, a small stream glistens in the dappled sunlight, while tall trees tower overhead, creating a serene, natural habitat for this majestic creature. The turtle continues its unhurried journey, embodying the peaceful, enduring spirit of the forest.]"
},
{
"from": "gpt",
"value": "Normal. The turtle's head and legs are distorted in the video."
}
] |
seed46_1241
|
videos/HRA_part2/1241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown vole wearing a miniature top hat and a tiny pair of spectacles stands on its hind legs atop a wooden stage, backdropped by a dark, starlit night. It begins to dance, performing a series of charming, unexpected moves that captivate the viewer. The vole's expressive face shows pure joy as it twirls and leaps, its tiny body moving gracefully to an unheard melody. Occasionally, the vole pauses, looking directly into the camera with a mischievous glint in its eye, before continuing its delightful solo performance under the twinkling stars.]"
},
{
"from": "gpt",
"value": "Normal. The vole is not wearing glasses."
}
] |
seed44_1980
|
videos/HRA_part1/1980.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a cloudless blue sky, a lone brown camel slowly crawls across the dunes, its large, expressive eyes looking straight ahead. The animal's body is positioned low to the ground, its right front leg extended forward in a crawling motion, and its left hind leg bent beneath it. The texture of the camel's fur is detailed, showing the natural variations in color and the dryness of the skin. The sand dunes form dramatic curves and ridges, with soft shadows highlighting the contours created by the sun's light. In the distance, more dunes stretch to the horizon, emphasizing the camel's solitary journey through this expansive landscape.]"
},
{
"from": "gpt",
"value": "Normal. The camel's movements are not smooth."
}
] |
seed44_1515
|
videos/HRA_part1/1515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a red t-shirt and black cap, meticulously cleans his silver car with a sponge in a residential driveway, set against a sunny day. His attire includes a red t-shirt with a white logo, black pants, and white sneakers, while his accessories consist of a black baseball cap and a wristwatch. As he works, his right leg occasionally bounces to an invisible beat, revealing his musical nature. Throughout the scene, he uses various cleaning tools, such as a bucket of soapy water, a hose, and a microfiber towel, all while maintaining a joyful demeanor.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1071
|
videos/HRA_part1/1071.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge and a radio, stands guard at a large, bustling sports stadium filled with cheering spectators, the sounds of excitement echoing throughout. Moments later, the focus is on the officer patrolling the perimeter of an Olympic-sized swimming pool, the water shimmering under the bright lights, capturing the intense competition of swimmers slicing through the water with powerful strokes. The officer's presence ensures safety and security, maintaining order amidst the thrilling aquatic events.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's face is distorted in the video, and the athlete in the pool is also twisted and deformed."
}
] |
seed44_2209
|
videos/HRA_part1/2209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed doctor, wearing a white coat and a stethoscope around his neck, finds himself in a vibrant restaurant filled with lively music. Surprisingly, he is accompanied by a monkey dressed in miniature clothing, sitting on a chair beside him. As the captivating beat takes over, the doctor and the monkey begin to dance together, their movements synchronized in a comical yet endearing manner. The other patrons, seemingly unfazed, continue dining, providing a backdrop of casual elegance to this unusual dance spectacle.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2014
|
videos/HRA_part0/2014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a sea urchin reveals its intricate, symmetrical structure as it clings to a rocky surface underwater. Sunlight filters through the clear, blue water, casting a soft glow on the urchin's spines, which are a striking contrast to the dark rocks. The camera captures the water gently swaying the urchin, emphasizing its resilience in the marine environment. The scene is framed by the rocky crevices of the seabed, highlighting the creature's natural habitat, while the muted colors of the rocks and sand provide a serene backdrop for the brightly colored sea urchin.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1821
|
videos/HRA_part2/1821.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mongoose, exhibiting resilience and adaptability, is seen walking through a vast, sunlit landfill. The creature, with its sandy brown fur and alert eyes, navigates the discarded human debris, from plastic bottles to broken electronics. It pauses on a pile of waste, scanning its surroundings with curiosity and survival instinct, highlighting the animal's presence in an unlikely habitat. The mongoose then continues its journey across the landfill, its small figure contrasting against the expansive landscape of garbage under the open sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1674
|
videos/HRA_part2/1674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, typically found in woodland streams, curiously explores a sandy beach near a vibrant beach resort, walking along the shoreline with its distinctive flat tail and brown fur. It passes by colorful umbrellas and sun loungers, a unique sight among the usual beachgoers enjoying the sunny weather. The beaver's presence adds an element of surprise and charm to the bustling beach scene, as it navigates the sandy terrain with its natural grace and agility.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's legs showed deformities, and its tail suddenly disappeared at the end."
}
] |
seed44_177
|
videos/HRA_part1/177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill and streamlined body, gracefully glides through the clear, turquoise waters of the open ocean. Its striking appearance is enhanced by the vivid marine environment surrounding it, featuring vibrant coral reefs and schools of smaller fish scattering in its path. The powerful creature showcases its agility and strength as it navigates the depths, with rays of sunlight filtering through the water to illuminate its journey. Against this stunning underwater backdrop, the swordfish emerges as a true marvel of the deep sea, embodying the beauty and mystery of life beneath the waves.]"
},
{
"from": "gpt",
"value": "Normal. The swordfish's swimming motion in the video is basically normal, with slight inconsistency."
}
] |
seed46_3100
|
videos/HRA_part2/3100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech laboratory setting, a professional lawyer, dressed in a sharp navy suit, consults with a dedicated nanobot repair crew. The crew, clad in matching silver jumpsuits, works diligently on a complex control panel. One crew member uses a microfiber cloth to carefully wipe down a row of advanced machinery, ensuring every surface is spotless. The lawyer observes closely, occasionally pointing to specific components and engaging in animated discussions with the crew about the intricacies of the nanobot technology. The scene is lit by the soft glow of the lab equipment, creating a futuristic and professional atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The fingers of the group members in the video are deformed, there are missing parts in the generation of the arms, there are issues with the facial generation, and only the fingers of the lawyer were generated."
}
] |
seed46_1415
|
videos/HRA_part2/1415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid close-up of a Rainbow Trout, showcasing its shimmering silver scales speckled with vibrant pink stripes, fills the frame. The fish's large, expressive eyes and intricate patterns on its fins are clearly visible, set against a dark, blurred aquatic environment. The water around it gently swirls, revealing bubbles and fine particles, while the trout remains remarkably still, allowing for a detailed examination of its stunning features.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1485
|
videos/HRA_part2/1485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, distinguishable by his classic black vest and white button-down shirt, is shown shoveling snow with determination. His attire is uniquely juxtaposed with the wintry task at hand, as he clears a path in front of a charming, snow-covered cottage. Snowflakes gently fall from a cloudy sky, accumulating on the roof and surrounding trees, while the waiter, wearing black gloves and sensible shoes for traction, focuses on his unexpected duty. Despite the cold, he works diligently, the snow creating a picturesque setting that contrasts with his formal waiter's uniform.]"
},
{
"from": "gpt",
"value": "Bad. The server's facial features were not generated in the video, and there is a missing arm."
}
] |
seed42_1650
|
videos/HRA_part0/1650.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jacket and dark pants, walks through a grassy campus area, holding a small, fluffy rabbit in their hands. They gently cradle the rabbit, which has white fur and black ears, as they stroll under a clear blue sky. The student occasionally looks down at the rabbit with a smile, while passersby glance curiously at the unusual sight. The scene is peaceful, with the student and rabbit seemingly enjoying each other's company in the outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1583
|
videos/HRA_part2/1583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, neon-lit diner from another dimension, a badger, dressed in a crisp waiter's outfit complete with a bow tie and apron, is seen energetically tap dancing. The animated badger performs intricate dance steps on a checkered floor, surrounded by surreal, cosmic decor, creating an otherworldly atmosphere. This captivating scene is enhanced by the vibrant, pulsating lights that illuminate the peculiar space, giving it an electrifying, interdimensional vibe. The badger's expressive face and lively movements convey a sense of joy and wonder in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2255
|
videos/HRA_part2/2255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer, clad in a brown jacket, gray beanie, and khaki pants, dances gleefully in a grassy field under a partly cloudy sky, with rolling hills in the background. An ibex, standing nearby, observes the farmer's antics with curiosity. The farmer, his face etched with lines from years of hard work, performs a series of playful dance moves, his boots kicking up tufts of grass. The ibex, its horns curving gracefully upward, seems to mimic the farmer's movements, creating an unexpected yet charming duet between man and animal. Throughout the scene, the farmer's joyful expressions and the ibex's inquisitive gaze capture the essence of an unlikely friendship forged in the midst of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's face and hands in the video have generation issues."
}
] |
seed44_3100
|
videos/HRA_part1/3100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech laboratory setting, a professional lawyer, dressed in a sharp navy suit, consults with a dedicated nanobot repair crew. The crew, clad in matching silver jumpsuits, works diligently on a complex control panel. One crew member uses a microfiber cloth to carefully wipe down a row of advanced machinery, ensuring every surface is spotless. The lawyer observes closely, occasionally pointing to specific components and engaging in animated discussions with the crew about the intricacies of the nanobot technology. The scene is lit by the soft glow of the lab equipment, creating a futuristic and professional atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2100
|
videos/HRA_part0/2100.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning swimming trunks and a baseball cap, playfully interacts with a bobcat cub at a serene, secluded lake. The student, showing a friendly smile, gently splashes water as the curious cub watches from the sandy shore. Both the young man and the bobcat cub seem at ease in each other's company, sharing a moment of innocent fun amidst the peaceful natural surroundings, with the clear blue sky and lush greenery framing the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2587
|
videos/HRA_part1/2587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and whimsical scene, a Bactrian camel with two humps, typically found in desert environments, is seen swimming in crystal-clear waters. The camel, with its shaggy brown coat and large, curious eyes, moves gracefully through the water, its head held high above the surface. The backdrop features lush greenery and palm trees, contrasting the camel's usual habitat. The setting sun casts a warm glow over the landscape, creating a surreal and captivating moment where desert meets sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2779
|
videos/HRA_part0/2779.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": "Normal. The gull's claws and wings in the video have generation issues."
}
] |
seed44_2559
|
videos/HRA_part1/2559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1564
|
videos/HRA_part2/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Normal. The lama in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_1392
|
videos/HRA_part2/1392.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dimly lit room, a doctor dressed in a white lab coat and stethoscope hangs around his neck, kneels on the floor, examining a jaguar cub. The cub, with its distinctive golden fur and black spots, is crawling on the checkered tile floor, exploring its surroundings with curiosity. The room is filled with medical equipment, indicating it's likely an animal clinic. The jaguar cub's small size and playful behavior contrast sharply with the doctor's professional demeanor, creating a unique and touching scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_158
|
videos/HRA_part0/158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, well-lit room, two young children sit attentively at a wooden table, each engaged in the meticulous task of hemming pants. One child, a boy with short brown hair wearing a blue t-shirt and jeans, carefully measures the fabric with a silver ruler, ensuring precise folds. Beside him, a girl with long pigtails, dressed in a yellow dress, threads a needle with focused determination, her tongue slightly poking out in concentration. Both use matching white sewing machines placed on either side of the table, their small feet reaching down to operate the pedals. The atmosphere is one of diligent learning, with the children's expressions showing a mix of seriousness and occasional smiles, highlighting their engagement in this practical skill.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed42_2190
|
videos/HRA_part0/2190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown beret and glasses, sits in a dimly lit studio filled with art supplies and paintings, engrossed in reading a book about art history. The camera captures the artist's hands turning the pages, revealing colorful illustrations of famous artworks. In another shot, the artist is seen from behind, sitting in front of a large canvas with paintbrushes in hand, contemplating the next stroke while a book on art techniques lies open nearby. Throughout the video, the artist's passion for both creating and studying art is evident in the careful attention given to both the book and the canvas.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2615
|
videos/HRA_part1/2615.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, plump hedgehog with distinctively sharp, brown spines traverses a lush, green garden, walking determinedly over mossy stones. It pauses briefly, its round body and curious face framed by the vibrant greenery. The hedgehog continues its journey, navigating the garden's textured path, with a wooden fence and hanging ivy leaves providing a natural, earthy backdrop. Throughout the walk, the hedgehog's spines glisten under the sunlight, highlighting its unique texture against the verdant setting.]"
},
{
"from": "gpt",
"value": "Normal. The hedgehog's face is distorted, and its claws are twisted."
}
] |
seed44_2892
|
videos/HRA_part1/2892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, softly lit room, two young children sit at a wooden table, intently working on hemming pants. One child, wearing round glasses and a striped shirt, carefully measures the fabric with a ruler, while the other, dressed in a yellow top, attentively pins the hem in place. Both children display a sense of pride and focus, their actions revealing a quiet determination. The scene is filled with natural light, casting warm shadows across the tabletop, as they engage in this practical task, surrounded by the tools of sewing—scissors, thread, and needles—all neatly arranged within reach.]"
},
{
"from": "gpt",
"value": "Bad. The child's face and arm are distorted in the video."
}
] |
seed42_2858
|
videos/HRA_part0/2858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whole, fresh cod fish is presented on a bed of ice, its body glistening under bright lights. The fish has a distinct silver hue, with large, clear eyes and tightly closed gills, indicating its freshness. Its scales reflect the light, and the texture of the skin is smooth yet firm. In the background, other seafood items can be seen, hinting at a bustling market setting where various fish are displayed on ice. The focus remains on the cod, which takes center stage, showcasing its size and quality in vivid detail.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_124
|
videos/HRA_part1/124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with glasses and a neat beard sits at a wooden desk, intensely pushing letters on a vintage typewriter, surrounded by piles of books and papers. The room is dimly lit by a standing lamp, casting shadows that emphasize his focused expression. Wearing a green military-style jacket, he leans forward, completely absorbed in his work, as if battling to translate his thoughts into words. The cluttered environment reflects his creative process, with the typewriter positioned center-stage, highlighting the act of writing as both a physical and mental endeavor.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2158
|
videos/HRA_part0/2158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a gray shirt and khaki pants, sits in a modern office space with a clean desk, listening intently. He leans forward with his right elbow on his knee, his face partially covered by his right hand, and his eyes closed, indicating deep concentration. His left hand rests on a high-tech, silver-colored device, possibly a piece of machinery or equipment, while a large screen displays complex diagrams and data in the background. The office is illuminated by natural light from a window, casting a soft glow on the engineer and his workspace.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's face and right hand in the video have generation issues."
}
] |
seed42_1957
|
videos/HRA_part0/1957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lit classroom, a biology teacher, wearing a green button-down shirt and khaki pants, kneels on the floor with a focused gaze. A live lizard, displaying intricate patterns, crawls across the tabletop in front of him. The teacher's hands are positioned ready to guide the creature gently, ensuring its safety during this educational demonstration. Students observe intently from their desks, their faces a mix of fascination and mild concern, as the small lizard explores its temporary environment under the watchful eye of their knowledgeable instructor.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears deformed and distorted."
}
] |
seed42_1301
|
videos/HRA_part0/1301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of four young children, two boys and two girls, are joyfully splashing in a clear blue swimming pool, their laughter echoing in the bright, sunny day. One boy, wearing green swim trunks, playfully jumps into the water from the side of the pool, creating a splash. Meanwhile, a small, curious brown mouse peers over the edge of the pool, its tiny head poking out, seemingly intrigued by the commotion and the splashing water. The children, unaware of the mouse's presence, continue to swim and play, their faces full of delight and energy, encapsulating the essence of carefree childhood summers.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is twisted, the face is twisted, the mouse's face is twisted, the claws are twisted."
}
] |
seed42_1930
|
videos/HRA_part0/1930.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 and there is an extra ear in the video."
}
] |
seed42_3091
|
videos/HRA_part0/3091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sits at a desk, bathed in the warm glow of a table lamp, surrounded by books and papers. He is wearing a gray t-shirt and dark glasses, and has a full beard. He yawns widely, stretching his arms above his head, showing signs of fatigue. His computer screen reflects the light, partially obscuring his face, as he leans back in his chair, the room's atmosphere conveying a sense of late-night writing and contemplation.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video does not have generated eyes, the face generation is uncoordinated, and the fingers are deformed."
}
] |
seed42_2607
|
videos/HRA_part0/2607.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting, a cheerful female cashier, wearing a yellow apron over a casual outfit, dances joyfully behind the counter of a rustic wooden market stall. The stall is adorned with colorful decorations and surrounded by vibrant greenery, enhancing the festive atmosphere. She moves energetically to an unseen beat, her smile contagious, as she momentarily pauses her duties to revel in the music. The village backdrop includes traditional architecture, bustling locals, and a lively community gathering, all contributing to the sense of celebration and unity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1904
|
videos/HRA_part1/1904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed man in a white shirt and dark pants walks through a lush, green meadow dotted with vibrant wildflowers under a bright, clear blue sky. He strides purposefully, his hands clasped behind his back, exuding a sense of peace and connection with nature. The tall grass sways gently in the breeze around him, and in the distance, a range of rolling hills provides a picturesque backdrop, enhancing the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2797
|
videos/HRA_part2/2797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, embodying a rugged explorer, traverses a dense tropical dry forest, wiping beads of sweat from his brow. Surrounded by towering trees with gnarled roots and sparse foliage, he navigates the arid landscape, dressed in khaki cargo pants, a beige tank top, and a wide-brimmed hat. The scene is illuminated by the golden glow of late afternoon sunlight filtering through the canopy, casting dappled shadows on the ground. The explorer pauses, wiping away perspiration with a cloth, revealing a map in his hands, hinting at his quest for hidden treasures within the unforgiving yet enchanting wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, arms, and the item in their hand are distorted in the video."
}
] |
seed42_1261
|
videos/HRA_part0/1261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, brown capybara swims through a clear, tranquil body of water, its ears and nose poking above the surface. It propels itself forward with powerful kicks from its webbed hind feet, showcasing its natural swimming abilities. The scene is set against a lush, green forest backdrop, highlighting the capybara's natural habitat. As it continues to swim, droplets of water scatter around it, creating a peaceful and captivating underwater perspective.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are basically normal, with slight clumsiness."
}
] |
seed44_2586
|
videos/HRA_part1/2586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a badge and a walkie-talkie attached to his belt, kneels in a zoological park, intently observing a crawling creature. The lush greenery and trees of the park provide a serene backdrop. The officer's focus is directed at a small animal slowly making its way across the ground, highlighting a unique interaction between law enforcement and wildlife in an urban zoo setting.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's hand undergoes a deformed mutation when making movements."
}
] |
seed42_2583
|
videos/HRA_part0/2583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 full uniform complete with a badge, gun, and hat, is tending to a lush garden in a public park. He begins by weeding around vibrant flowers, his actions gentle yet purposeful. Next, he waters the plants with a hose, the mist from the water creating a small rainbow in the sunlight. Then, he plants a new shrub, digging a hole with a small shovel and carefully placing the plant inside. Finally, he prunes a bush into shape, his movements precise as he shapes the greenery, all while maintaining his authoritative yet approachable demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The facial features and hands of the police officer in the video were generated abnormally."
}
] |
seed46_1256
|
videos/HRA_part2/1256.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vivid scene, a writer, presumably the main character, runs along a sandy path at a luxurious resort, set against a backdrop of lush greenery and palm trees. Dressed in a gray tank top, black shorts, and black running shoes, he wears a determined expression as he focuses ahead. Accompanying him is a black jackal, resembling a wild dog, which runs alongside him, adding a sense of companionship and adventure to the narrative. The resort's opulent buildings and facilities are visible in the background, highlighting the contrast between nature and luxury.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1195
|
videos/HRA_part0/1195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dingo, standing on its hind legs, dons a yellow tutu and green ballet slippers, dancing energetically in a grassy field under a bright blue sky. It leaps and twirls gracefully, its movements fluid and expressive, showcasing its unexpected talent for dance. The dingo's joyful expression and animated body language convey a sense of freedom and delight in its unusual activity, captivating the viewer with its unique performance.]"
},
{
"from": "gpt",
"value": "Bad. The dancing moves of the dingo in the video are not smooth."
}
] |
seed44_1424
|
videos/HRA_part1/1424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray jacket and khaki pants, unloads a large, industrial dishwasher in a busy school cafeteria during lunchtime. He wears yellow rubber gloves and a face mask, and carries a mop and bucket, indicating his role in maintaining cleanliness. The scene captures him pausing for a moment, holding a clean tray, with students visible in the background, emphasizing the bustling environment. The janitor then continues his task, placing trays on a metal shelf, demonstrating his routine duty amidst the lively atmosphere of the cafeteria.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2815
|
videos/HRA_part1/2815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male cashier with short brown hair and glasses, wearing a gray T-shirt and black pants, is seen lifting a large box of soda cans with both hands from a shopping cart onto a checkout counter. The store is busy with customers and products, adding to the bustling atmosphere. Moments later, he lifts another box of similar size with ease, demonstrating his strength and efficiency. The action takes place under bright fluorescent lights, highlighting the cashier's focused expression and determination as he manages the physical demands of his job.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1541
|
videos/HRA_part0/1541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a waiter in full uniform, complete with a white shirt, black vest, and tie, is shown running along the edge of a busy highway. The highway is filled with cars and trucks, creating a bustling urban atmosphere. The waiter's face conveys determination as he sprints, his black trousers and polished shoes moving swiftly against the gritty pavement. The scenery includes billboards and distant city buildings, providing a backdrop of urban life. Despite the unusual setting, the waiter remains focused, his gaze fixed ahead as he continues his unexpected journey along the highway.]"
},
{
"from": "gpt",
"value": "Normal. The man's limbs in the video are generated disharmoniously, fingers are not generated, and the face is blurry."
}
] |
seed46_2284
|
videos/HRA_part2/2284.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a brown jacket, blue shirt, and green trousers, promenades leisurely through a vast cornfield, the golden stalks towering over him as he walks. He pauses to observe a crawling caterpillar on a large, lush green leaf, its vibrant colors contrasting beautifully against the foliage. The farmer kneels down, his worn hands gently touching the leaf, as he watches the caterpillar slowly inching forward, exploring its world. The camera captures this intimate moment between man and nature, highlighting the farmer's connection to the land and the simple pleasures it offers.]"
},
{
"from": "gpt",
"value": "Normal. The farmer and caterpillar's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed44_2458
|
videos/HRA_part1/2458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its dark brown coat and impressive, backward-curving horns, walks steadily across a rocky mountain landscape, offering a close-up view of its sturdy hooves gripping the stone surface. It moves with purpose, navigating the rugged terrain with ease, its alert eyes scanning the surroundings. The ibex continues its journey, the camera capturing the detail of its textured fur and the dramatic mountain scenery that serves as its habitat, highlighting the animal's resilience and adaptability in its natural environment.]"
},
{
"from": "gpt",
"value": "Normal. The goat's hooves are missing in the video, and there are issues with the goat horns."
}
] |
seed46_2961
|
videos/HRA_part2/2961.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow vest and hard hat, finds a moment of joy as he dances alone in the vast, sun-baked expanse of a subtropical desert. The dunes stretch endlessly under a cloudless sky, the horizon melding seamlessly into the distance. His movements, expressive and free, contrast sharply with the stillness of the arid landscape. The golden sands ripple beneath his boots, each step a fleeting imprint in the relentless expanse. As he twirls and leaps, the desert becomes his stage, the unyielding sun his spotlight, capturing a fleeting moment of uninhibited happiness in an otherwise harsh environment.]"
},
{
"from": "gpt",
"value": "Bad. The faces, hands, and feet of the workers in the video are distorted and deformed, and the worker's feet suddenly appear or disappear in the middle frames."
}
] |
seed46_1815
|
videos/HRA_part2/1815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene opens with a koala, typically terrestrial, surprisingly adept in water, swimming in a serene, clear blue pool. Its brown fur glistens as it paddles with determination, showcasing an unexpected talent. The koala, wearing a small yellow swim cap, navigates the water with surprising grace, its limbs moving rhythmically. Moments later, it emerges from the pool, shaking off droplets, revealing a cozy green towel wrapped around its body. The koala then sits on the edge of the pool, seemingly pleased with its aquatic adventure, the sunlight sparkling on the water behind it.]"
},
{
"from": "gpt",
"value": "Normal. The koala in the video is not wearing a yellow swimming cap."
}
] |
seed42_2580
|
videos/HRA_part0/2580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, captured in high definition, is seen grooming itself by wiping its face with a flipper. The otter, with its brown fur and small, round ears, sits upright on a rocky shore, the surface speckled with white stones. The background features a lush green forest, with tall trees standing majestically against a bright sky. The otter pauses, looking directly at the camera with curious eyes, before continuing its self-cleaning ritual, creating a captivating moment in nature.]"
},
{
"from": "gpt",
"value": "Normal. The otter's paws are missing in the video, and there are too many legs generated."
}
] |
seed44_1221
|
videos/HRA_part1/1221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 branch, its glossy black and white feathers shimmering under the sunlight, showcasing the bird's striking plumage against a lush green forest backdrop. The magpie turns its head, revealing its intelligent eyes and sharp beak, highlighting its curious nature. Moments later, it spreads its wings, displaying the full span of its black and white feathers, before taking flight, leaving behind a flurry of feathers and a sense of awe at its beauty and grace. Throughout the scene, the magpie remains the central focus, captivating the viewer with its natural elegance and charm.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2939
|
videos/HRA_part2/2939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a bobcat, with distinctive ear tufts and a short tail, leaps over a checkout counter in slow motion, its muscles tensing and releasing with each bound. The cash register, with its glowing display and scattered coins, provides context to the setting. The cashier, wearing a red apron and a surprised expression, watches the wild cat jump, creating an unexpected and captivating moment. The bobcat's leap is captured in mid-air, highlighting its agility and grace, against the backdrop of a typical supermarket checkout area.]"
},
{
"from": "gpt",
"value": "Normal. The cat's tail in the video is not short."
}
] |
seed44_2322
|
videos/HRA_part1/2322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a backdrop of lush greenery and blue skies, two young boys, one wearing a yellow shirt and the other in red, are intently engaged in fixing a wooden fence. They work diligently, using a variety of tools spread out before them, their faces concentrated and serious as they tackle the task at hand. One boy, dressed in a yellow shirt, blue shorts, and brown shoes, leans against the fence, his hands busy with repair work, while the other, in a red shirt, khaki shorts, and blue sneakers, stands with a tool in hand, ready to assist. The scene captures the industrious spirit of childhood play, with the boys' clothes and tools adding vibrant details to the image.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a distorted body, head, feet, legs, and arms."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.