video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_309
|
videos/HRA_part2/309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kneels on a hardwood floor, wearing a grey turtleneck sweater, dark jeans, and brown boots, painting a vivid abstract artwork on a large canvas. A friendly dog, possibly a Golden Retriever, crawls playfully toward the artist, who gently pets it with a loving smile, both surrounded by the warm glow of a studio space filled with art supplies and natural light. The scene captures a tender moment between the artist and their canine companion, with the unfinished artwork providing a glimpse into the creative process.]"
},
{
"from": "gpt",
"value": "Bad. The dog's movements in the video are unsmooth."
}
] |
seed44_1723
|
videos/HRA_part1/1723.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, dressed in a spacesuit with the helmet removed, floats gracefully in zero gravity inside a space station, illuminated by the ethereal glow of Earth in the background. He gently caresses the inner wall of the station, adorned with complex machinery and wires, while looking out at the breathtaking view of our planet through the large circular window, conveying a sense of wonder and intimacy with the cosmos. The setting captures the essence of human achievement in space exploration, with the man's tender gesture toward the space station's interior wall highlighting a unique connection between humanity and its ventures beyond Earth.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight disharmony."
}
] |
seed44_3084
|
videos/HRA_part1/3084.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform and black pants, stands outdoors in a garden, holding a shovel. He is surrounded by various plants, including leafy greens, carrots, and herbs like rosemary, thyme, and sage. The chef has short brown hair and a neatly trimmed beard, and he is digging into the rich soil with determination, perhaps searching for fresh ingredients for his culinary creations. The scene is set against a backdrop of wooden crates and greenery, with a hint of sunlight filtering through the trees, casting dappled shadows on the chef and his gardening endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands appear deformed, and the shovel in his hand has also become distorted."
}
] |
seed42_2166
|
videos/HRA_part0/2166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A seasoned janitor, clad in a gray jumpsuit with a yellow utility vest over it, diligently wipes down a pristine, metallic surface within a bustling space station habitat. The vibrant blue and white Earth can be seen through a large window in the background, providing a stunning contrast to the industrial interior. As he works, the man pushes a cleaning cart filled with various supplies, emphasizing his commitment to maintaining the cleanliness of the space station. Nearby, two fellow crew members, wearing matching gray jumpsuits with red accents, are engaged in a conversation, adding to the lively atmosphere of the space habitat. Throughout the scene, the janitor continues his task with a focused determination, highlighting the importance of his role in the maintenance of the space station.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_22
|
videos/HRA_part2/22.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, bundled in a heavy coat, mittens, and a woolen cap, stands beside a friendly moose in a quaint village setting marked by wooden houses and snow-covered landscapes. The student gently wipes snowflakes from the moose's antlers, both gazing into the camera with a sense of camaraderie. Behind them, smoke rises from chimneys, indicating the warmth of homes in the cold environment. The scene is set during the golden hour, with soft, warm light casting long shadows across the snow, creating a cozy and welcoming atmosphere in the village.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, hand is distorted, face is contorted, and the moose's face is also twisted."
}
] |
seed44_1276
|
videos/HRA_part1/1276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European brown hare sits on a sandy shore, the vast ocean stretching to the horizon behind it, with rolling waves gently lapping at the sand. The hare, with its large ears and curious expression, appears to be contemplating the serene seascape. Suddenly, the hare leaps into the shallow waters, its powerful hind legs propelling it forward in an unexpected swimming motion. The water splashes around it, creating ripples that extend outward, as the hare continues to swim, defying expectations in the coastal scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3018
|
videos/HRA_part1/3018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a red jacket and khaki pants, races across a grassy field with a small, bushy-tailed fox hot on their heels. The student's face is full of determination and joy, their shoes kicking up clumps of grass as they sprint. The fox, equally playful, bounds alongside, its red fur matching the student's jacket. The scene is set against a backdrop of autumn trees, their leaves turning shades of gold and orange, with the sun casting long shadows across the landscape, highlighting the energetic chase between the student and the fox.]"
},
{
"from": "gpt",
"value": "Bad. There is deformation in his legs and hands. When the red fox runs, its legs also deform."
}
] |
seed46_185
|
videos/HRA_part2/185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, clad in a casual black jacket and gray trousers, runs energetically across a large, open room within a space-themed educational facility. The room is adorned with detailed models of the Apollo spacecraft and other historical rockets, highlighting the center's focus on space exploration. As he moves, the director passes by a group of attentive students seated at tables, each engaged with interactive exhibits about space missions. The vibrant atmosphere reflects the excitement and educational value of the space center, emphasizing its commitment to inspiring the next generation of astronauts and scientists.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1544
|
videos/HRA_part0/1544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a brown uniform, diligently wipes the glass enclosure of a wildlife exhibit, where a graceful gazelle is seen resting calmly inside. The enclosure is meticulously clean, save for a few lingering spots that the worker is addressing. The gazelle, displaying a relaxed demeanor, is positioned near the enclosure's entrance, its body language indicating a sense of security and comfort within its habitat. The scene captures the routine maintenance of the animal's living space, highlighting the careful interaction between the human caretaker and the wild creature in a shared environment.]"
},
{
"from": "gpt",
"value": "Bad. The human hand and arm appear deformed, and the gazelle's head is malformed."
}
] |
seed46_2103
|
videos/HRA_part2/2103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, clad in a spacesuit with a NASA logo, stands against the striking backdrop of a Martian sunset, characterized by its pinkish-blue hue. The director is captured mid-jump, with one arm raised in triumph, against the dramatic landscape of Mars. The sandy terrain stretches into the distance, dotted with rocks and craters, providing a stark contrast to the vibrant colors of the sunset. The director's silhouette is outlined by the warm glow of the setting sun, creating a powerful visual representation of human exploration and the beauty of the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, body, and legs of the person in the video are twisted."
}
] |
seed46_1189
|
videos/HRA_part2/1189.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 girls sit on a large, colorful rug, engrossed in crocheting a vibrant patchwork blanket. One girl, with short brown hair, wears a yellow T-shirt and blue jeans, focusing intently on her work. Beside her, a girl with long blonde hair, dressed in a pink dress, stitches away with determination. The room is filled with an array of yarn balls in various colors, scattered around them, and a white wooden table stands nearby, holding a cup of crayons and a half-finished coloring book, hinting at other creative activities. The atmosphere is warm and nurturing, with the girls' concentration and the colorful surroundings creating a scene of creativity and companionship.]"
},
{
"from": "gpt",
"value": "Normal. The girl's face and hands in the video have generation issues."
}
] |
seed44_2501
|
videos/HRA_part1/2501.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cave, a police officer, wearing a uniform with a badge and a utility belt equipped with various tools, including a flashlight, gently caresses the rough stone wall, seemingly searching for hidden clues or evidence. The cave's textured walls, illuminated by the officer's flashlight, provide a dramatic backdrop for this intense moment of investigation. The officer's focused gaze and careful touch convey a sense of determination and meticulousness in uncovering secrets within the cave's depths.]"
},
{
"from": "gpt",
"value": "Bad. The officer's hand generation in the video has issues."
}
] |
seed44_2857
|
videos/HRA_part1/2857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant flamingo stands tall and proud on a sandy shore, its pink feathers glowing under the golden rays of the setting sun. Its long, slender legs elegantly support its body as it gazes out over the calm waters, creating a serene and picturesque scene. The flamingo's curved neck gracefully bends, while its beak rests gently on its chest, exuding a sense of tranquility and contentment. Surrounding palm trees sway gently in the breeze, adding to the idyllic atmosphere of this stunning coastal landscape.]"
},
{
"from": "gpt",
"value": "Normal. The flamingo's head was not generated in the video."
}
] |
seed46_1050
|
videos/HRA_part2/1050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dolphin breaches the surface of a turquoise ocean, its sleek gray body glistening in the sunlight, against a backdrop of a clear blue sky and calm seas. Moments later, it swims gracefully underwater, surrounded by the vibrant marine life of a coral reef, including colorful fish and swaying sea fans. Then, the dolphin leaps again, this time performing a stunning aerial maneuver with the sun illuminating its form from below, highlighting its agility and beauty. Finally, it returns to the depths, swimming alongside a school of shimmering silver fish, the underwater world coming alive around it, showcasing the dolphin's natural habitat in stunning detail.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2630
|
videos/HRA_part0/2630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lustrous, red-cooked lobster is presented on a simple white plate, its large, meaty tail curled gracefully. The claws, one broken open to reveal tender, succulent flesh, are garnished with fresh, green parsley. Steam gently rises from the hot shell, hinting at its recent emergence from boiling water. The setting is a rustic wooden table, adorned with a crisp, white cloth, where the lobster takes center stage under natural lighting, casting a subtle shadow that accentuates its texture and color. A small cup of clarified butter sits nearby, ready to enhance the rich, briny flavor of the lobster meat.]"
},
{
"from": "gpt",
"value": "Normal. The lobster's head was not generated in the video."
}
] |
seed46_2960
|
videos/HRA_part2/2960.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a blue jacket and jeans, walks purposefully across a vast, otherworldly landscape illuminated by the ethereal glow of a nearby galactic nebula. The scene opens with the student standing in the foreground, looking intently ahead, with the majestic nebula casting a soft, cosmic light over the terrain. As the student strides forward, the camera captures the detail of their journey, highlighting the unique features of the alien landscape. With each step, the student's determination is evident, their silhouette framed against the mesmerizing backdrop of the swirling nebula. The final shot lingers on the student's resolute figure, now further along the path, continuing their solitary trek under the watchful gaze of the celestial wonder above.]"
},
{
"from": "gpt",
"value": "Bad. The student's fingers in the video are deformed, the head generation is problematic, and the video style does not match reality."
}
] |
seed46_1439
|
videos/HRA_part2/1439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a small brown rat wearing swimming goggles and a red swim cap is seen floating in a pool, its limbs outstretched in a relaxed position. Behind it, the stunning rings of Saturn are visible, appearing as a backdrop in the night sky. The water is clear, reflecting the stars above, and the rat seems content in its unusual aquatic environment, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1800
|
videos/HRA_part2/1800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2670
|
videos/HRA_part2/2670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow safety vest, blue jeans, and brown work boots, sits on a wooden crate under a bright blue sky, with scaffolding and building materials in the background. He gently pets a brown and white dog lying on its back, belly-up, on a pile of gravel, showing a tender moment of connection between the worker and the animal. The worker's hands, rough from labor, contrast with the softness of the dog's fur, creating a touching scene of companionship amidst a rugged worksite.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2499
|
videos/HRA_part2/2499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, known for its brown fur and flat tail, swims underwater in a clear, glassy lake during the daytime. It surfaces, revealing its full body, including the distinctive markings on its face and body. The beaver then proceeds to swim along the bottom of the riverbed, showcasing its webbed hind feet propelling it forward. Throughout the video, the beaver remains submerged, occasionally coming up for air, with the tranquil water and lush green vegetation along the riverbank providing a serene backdrop for this aquatic mammal's natural behavior.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's limbs and tail generation in the video have issues."
}
] |
seed42_2912
|
videos/HRA_part0/2912.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit diner after hours, a weary waiter, attired in a crisp white shirt, black vest, and striped tie, rests his head on his hands atop a checkered tablecloth. He has removed his shoes and his black socks are visible, adding to the sense of weariness and relaxation. His nametag reads 'Eduardo', and he appears to have fallen into a peaceful slumber, surrounded by the quiet emptiness of the restaurant. A half-drunk cup of coffee sits beside him, a testament to the long night shift he's just completed. The scene is intimate and still, capturing a rare moment of rest for a hardworking individual.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed46_1972
|
videos/HRA_part2/1972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray spacesuit with a NASA logo, is seen running energetically across the barren, rocky landscape of a distant planet, with a large, complex space station visible in the background. His movements are dynamic, showing determination and purpose. The vast, alien terrain, dotted with craters and boulders, stretches out behind him, while the dimly lit space habitat, complete with solar panels and satellite dishes, looms large. The janitor's spacesuit bears a name tag and various patches, adding to the realism of this futuristic scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1593
|
videos/HRA_part1/1593.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a gray shirt and blue jeans stands on a green ladder, cleaning out debris from the clogged gutters of a two-story house with a red roof, set against a clear blue sky. His focus is intense as he uses a small garden trowel to scoop out leaves and dirt. The house facade, painted in a warm beige hue, contrasts with the lush greenery surrounding it. A pile of removed debris sits on the ground beneath him, indicating progress in his task. His gray shirt and blue jeans are slightly soiled from the work, highlighting the effort and dedication put into maintaining the home's exterior.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears deformed."
}
] |
seed44_1082
|
videos/HRA_part1/1082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal setting, a student, identifiable by their backpack and casual attire, is crawling through a crowded mall. This unusual behavior attracts the curious gaze of shoppers, who pause to watch. Unexpectedly, a hyena, also crawling and wearing a backpack, joins the student. Both crawl side by side, blending into the urban environment, creating a bizarre yet harmonious scene amidst the mall's vibrant storefronts and bustling pedestrian traffic.]"
},
{
"from": "gpt",
"value": "Bad. The crawling movements of the student and the hyena in the video are not smooth and continuous, there are abrupt changes."
}
] |
seed42_1157
|
videos/HRA_part0/1157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station pool, a courageous nurse, wearing a protective spacesuit with a clear helmet, fearlessly swims alongside a non-venomous cobra, which has been specially adapted for space travel. The nurse's spacesuit is adorned with patches representing various medical organizations, highlighting her dedication to healthcare even in the cosmos. The cobra, now a docile companion, glides effortlessly through the water, its scales reflecting the artificial lighting of the space station. This extraordinary scene showcases the integration of healthcare, exotic animals, and space tourism in a serene aquatic environment, encapsulating the essence of adventure and innovation in the final frontier.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's face and hands, as well as the cobra's head, are generated abnormally in the video."
}
] |
seed42_1798
|
videos/HRA_part0/1798.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a green shirt and khaki shorts, tends to a lush garden filled with vibrant flowers and greenery. He strums his acoustic guitar, creating a melodic soundtrack for his gardening endeavors. The garden is brimming with life, featuring an array of colorful flowers such as daisies, roses, and tulips. The musician, wearing a wide-brimmed straw hat and sunglasses, works diligently, watering plants and trimming bushes. As he gardens, he occasionally pauses to play his guitar, seamlessly blending his passions for music and nature in a harmonious outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_242
|
videos/HRA_part2/242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [On a vibrant boardwalk by the seaside, two young girls, one in a red dress and the other in a pink floral dress, dance joyously under a clear blue sky. They move energetically, their carefree spirits captured in the glow of the afternoon light. Around them, the bustling boardwalk is filled with the sights and sounds of summer: families walking, vendors selling colorful balloons and cotton candy, and the distant music from a carousel. The girls, however, are lost in their own world, their laughter and twirls creating a heartwarming scene against the backdrop of the lively boardwalk.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1514
|
videos/HRA_part0/1514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, windswept grassland under a partly cloudy sky, a janitor wearing a yellow vest, blue jeans, and a white shirt is seen wiping a transparent, rectangular window that floats in front of him. The serene landscape stretches to the horizon, dotted with distant trees, while the janitor diligently cleans the window with a cloth, revealing the pristine clarity of the glass. The peaceful scene is punctuated by the gentle sway of the tall grass and the solitude of the janitor's task, emphasizing the unexpected context of maintenance in the midst of nature.]"
},
{
"from": "gpt",
"value": "Bad. The man's arm in the video is generated too long, his facial features are not generated, there are issues with the fingers, and the cloth is deformed."
}
] |
seed44_2272
|
videos/HRA_part1/2272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a hat, rakes leaves in a community garden, his gold nametag gleaming under the sunlight. He pauses to smile warmly at the camera, his friendly demeanor evident. Wearing a dark blue police uniform complete with a name badge and a cap, he continues raking, surrounded by piles of autumn leaves in various shades of orange, red, and brown. The video closes with him raking diligently, highlighting the unexpected sight of a law enforcement officer engaging in a domestic chore, fostering a sense of community and service.]"
},
{
"from": "gpt",
"value": "Bad. The police officer in the video has uncoordinated movements."
}
] |
seed46_1910
|
videos/HRA_part2/1910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, donning a yellow safety vest, orange hard hat, and blue jeans, sits on a wooden beam, holding a hammer in his right hand and resting his left elbow on his knee, against a backdrop of a partially built structure with blue skies visible through the gaps. Moments later, he takes a break, sitting on the same beam with his legs crossed, now holding a water bottle and looking directly at the camera. Then, he is shown sitting with his legs dangling, his right arm resting on a higher beam, and his left hand holding the hammer, with the half-constructed building and clear blue sky in the background. Lastly, he sits with his back straight, both hands on his knees, and a focused expression, still clad in his yellow vest, orange helmet, and denim pants, the unfinished building and open sky framing him.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3167
|
videos/HRA_part0/3167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, clad in a simple black one-piece swimsuit, swims calmly in a vast, prehistoric lake, with a woolly mammoth standing watchfully nearby on the shore, its massive frame and shaggy coat a stark contrast against the serene water. The setting sun casts a warm glow over the scene, highlighting the woman's strokes and the mammoth's still form, creating a captivating juxtaposition of ancient and modern elements in a natural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The person's head and arms are distorted in the video."
}
] |
seed44_1502
|
videos/HRA_part1/1502.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, subtropical woodland setting, a majestic tiger lies on the rich forest floor, its coat blending harmoniously with the dappled sunlight filtering through the dense foliage above. The camera captures the intimate moment as a gentle hand caresses the tiger's head, conveying an unexpected sense of trust and connection between the wild animal and the unseen human presence. The tiger's eyes are closed, its expression one of pure bliss, indicating a rare bond formed within the natural habitat of the subtropical woodlands.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2386
|
videos/HRA_part1/2386.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, intricate fish with blue fins and a yellow body swims serenely in a clear, turquoise underwater environment, surrounded by lush green seaweed gently swaying in the current. Nearby, a school of smaller, silvery fish dart and weave, their movements synchronized and graceful, creating a mesmerizing display of aquatic life against the vivid backdrop of the underwater world. Above, rays of sunlight filter through the water's surface, casting dappled light on the scene below, highlighting the beauty and tranquility of the ocean depths.]"
},
{
"from": "gpt",
"value": "Normal. The fish's head is distorted in the video."
}
] |
seed42_1034
|
videos/HRA_part0/1034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 buzzard soars through the sky, its broad wings spread wide as it glides over a rugged, rocky landscape. The bird's sharp eyes scan the ground below, searching for prey among the boulders and sparse vegetation. Its feathers catch the sunlight, revealing shades of brown and white, while its powerful talons remain ready to strike at a moment's notice. The scene is set against a vast, open sky, emphasizing the buzzard's freedom and dominance over its territory.]"
},
{
"from": "gpt",
"value": "Bad. The flying motion can be seen, but the movements are not continuous, there are sudden changes, and the wings detach from the body."
}
] |
seed42_1904
|
videos/HRA_part0/1904.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A casually dressed 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": "Normal. The man's limbs in the video are missing, and his facial features are distorted."
}
] |
seed46_1268
|
videos/HRA_part2/1268.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket, 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": "Good. Basically correct."
}
] |
seed44_1319
|
videos/HRA_part1/1319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jeans, sits cross-legged on a wooden deck by a lake, gently stroking a small brown beaver. The scene is set during the golden hour, with the student's face showing affection and the beaver seemingly comfortable with the interaction. The student, with tousled hair and a warm smile, holds the beaver with both hands, providing a sense of safety and care, while the creature, with its distinctive flat tail and sharp teeth, appears relaxed and unafraid in this peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2076
|
videos/HRA_part1/2076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful nurse, wearing a white uniform and a badge, is seen running through a lush, green landscape dotted with tall trees and vibrant vegetation. In the distance, a serene hot springs oasis comes into view, its steam gently rising against the backdrop of a clear blue sky. The nurse, with a backpack and running shoes, continues her jog towards this peaceful destination, her movements fluid and energetic. Upon arrival, she pauses to enjoy the tranquil atmosphere, the steam from the hot springs swirling around her, before continuing her run along the scenic path that meanders through the verdant scenery.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2873
|
videos/HRA_part1/2873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet futuristic scene, a giant panda, wearing a spacesuit and helmet adorned with antennas, sits against a backdrop of stars and galaxies, symbolizing deep space communication. The panda is seen wiping its paw across the visor of its helmet, perhaps to clear condensation, while floating in zero gravity, surrounded by the vastness of space. This unique juxtaposition of elements - the panda representing Earthly innocence, the spacesuit and helmet signifying human exploration, and the cosmic background evoking a sense of wonder - creates a captivating and surreal visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_163
|
videos/HRA_part2/163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, and the face is deformed."
}
] |
seed46_1461
|
videos/HRA_part2/1461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 deciduous forest, a local worker wearing a straw hat and khaki clothing kneels near a serene riverbank. Suddenly, a jaguar stealthily emerges from the dense foliage, its golden eyes fixed on the water. The wild cat, exhibiting grace and power, leaps into the river for a refreshing swim, its sleek body cutting through the water effortlessly. The worker watches in awe, a harmonious moment captured between human and nature, all set against the backdrop of the vibrant deciduous forest.]"
},
{
"from": "gpt",
"value": "Bad. The person's legs are deformed, and the stray cat is missing two legs."
}
] |
seed44_1813
|
videos/HRA_part1/1813.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and khaki pants, stands in the midst of a vast desert landscape, the golden sand stretching to the horizon under a clear blue sky. Holding a paintbrush in one hand, he wipes it across a large canvas, which rests on an easel, revealing strokes of orange and yellow that mirror the fiery sunset in the background. The artist's face is intense, his eyes fixed on the canvas as he captures the essence of the desert's beauty, with the sun's last rays casting long shadows across the dunes.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed42_1910
|
videos/HRA_part0/1910.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, donning a yellow safety vest, orange hard hat, and blue jeans, sits on a wooden beam, holding a hammer in his right hand and resting his left elbow on his knee, against a backdrop of a partially built structure with blue skies visible through the gaps. Moments later, he takes a break, sitting on the same beam with his legs crossed, now holding a water bottle and looking directly at the camera. Then, he is shown sitting with his legs dangling, his right arm resting on a higher beam, and his left hand holding the hammer, with the half-constructed building and clear blue sky in the background. Lastly, he sits with his back straight, both hands on his knees, and a focused expression, still clad in his yellow vest, orange helmet, and denim pants, the unfinished building and open sky framing him.]"
},
{
"from": "gpt",
"value": "Normal. Missing the shot of holding the water bottle."
}
] |
seed42_3102
|
videos/HRA_part0/3102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a fantastical prehistoric scene, a massive woolly mammoth leaps over a frozen log in a snow-covered forest during the Ice Age, with tall pine trees framing the action. The mammoth, complete with shaggy brown fur and impressive tusks, is captured mid-air, its large body defying expectations as it clears the obstacle with surprising agility. The icy landscape, dotted with ancient conifers, adds to the dramatic effect of this unlikely jump, highlighting the creature's strength and adaptability in its harsh environment.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's walking in the video is basically normal, but there is slight movement inconsistency."
}
] |
seed46_1635
|
videos/HRA_part2/1635.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 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 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": "Bad. No pen generated, the character's hand is missing; there's an issue with the rat's claws in the video."
}
] |
seed46_1857
|
videos/HRA_part2/1857.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, named Bingo, energetically jumps onto a wooden platform in a spacious outdoor enclosure, surrounded by lush greenery and trees. Dressed in a tiny red jacket, Bingo displays his strength and agility, with the sunlight filtering through the leaves highlighting his movement. He then leaps from the platform onto a thick branch, showcasing his natural climbing skills. Next, he swings from a hanging tire, his joyful expressions and animated body language capturing the essence of playfulness. Finally, he bounds across the enclosure, his powerful legs propelling him forward, as he explores his environment with boundless energy and curiosity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1086
|
videos/HRA_part2/1086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of an ibis's face, its piercing yellow eye set against a backdrop of dark feathers, commands attention. The bird's distinctive curved bill, a striking contrast to its plumage, adds character. Its textured feathers, a mix of brown and black, envelop the head, while the yellow iris and bill tip pop against the dark plumage. The ibis's head tilts slightly, revealing a patch of bare red skin, and its textured feathers frame the captivating facial features, capturing the essence of this unique bird species.]"
},
{
"from": "gpt",
"value": "Normal. The bird in the video is basically normal, with slightly uncoordinated movements."
}
] |
seed44_1972
|
videos/HRA_part1/1972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, clad in a gray spacesuit with a NASA logo, is seen running energetically across the barren, rocky landscape of a distant planet, with a large, complex space station visible in the background. His movements are dynamic, showing determination and purpose. The vast, alien terrain, dotted with craters and boulders, stretches out behind him, while the dimly lit space habitat, complete with solar panels and satellite dishes, looms large. The janitor's spacesuit bears a name tag and various patches, adding to the realism of this futuristic scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2127
|
videos/HRA_part0/2127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wild dingo, characterized by its sandy coat, alert ears, and bushy tail, walks purposefully across a rocky terrain, surrounded by arid scrubland and distant, hazy mountains, evoking a sense of freedom and survival in the Australian wilderness. The dingo moves with a steady gait, its eyes scanning the environment, showcasing its natural instincts and resilience in a harsh landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1594
|
videos/HRA_part1/1594.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green zoological park, a dedicated zookeeper clad in khaki shorts, a gray T-shirt, and a cap runs along a path lined with palm trees, demonstrating his commitment to fitness within the serene surroundings. The camera captures him passing by enclosures housing various animals, highlighting the unique setting of his workout. As he jogs, the peaceful atmosphere of the park is evident, with glimpses of giraffes, elephants, and monkeys in the background, creating a vivid contrast between human activity and the natural world.]"
},
{
"from": "gpt",
"value": "Bad. No giraffes, elephants, or monkeys were generated."
}
] |
seed46_2105
|
videos/HRA_part2/2105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 shirt and dark pants, attentively sorts colorful laundry in a busy laundromat filled with vibrant washing machines and dryers. He meticulously folds a yellow shirt, revealing a sense of pride in his work. Next, he checks the laundry, holding up a pair of red socks, demonstrating his thoroughness. Then, he loads the washer with various garments, including a green sweater and blue jeans, his actions methodical and precise. Finally, he closes the washer door, presses the start button, and turns to face the camera, his expression conveying satisfaction in a job well done, all within the bustling environment of the laundromat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1894
|
videos/HRA_part1/1894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lawyer, dressed in a navy suit, white shirt, and striped tie, races through a lush green forest, holding a koala in one arm. The koala, clinging tightly, wears a tiny barrister's wig and round spectacles, adding a whimsical touch to the scene. They run past tall trees, ferns, and flowers, with the lawyer's facial expressions alternating between determination and a smile, highlighting the unusual yet playful nature of the chase. The vibrant forest setting, complete with sunlight filtering through the leaves, enhances the dynamic and surreal atmosphere of the scenario.]"
},
{
"from": "gpt",
"value": "Normal. The running motion of the character in the video is not smooth."
}
] |
seed44_2659
|
videos/HRA_part1/2659.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 under a clear blue sky, a man wearing a brown jacket and khaki pants kneels on lush green grass, observing a small weasel. The weasel, with its distinct brown fur and white underbelly, crawls along the edge of a weathered stone wall that separates neatly arranged houses from the garden. The man watches intently as the weasel explores its surroundings, highlighting the unexpected encounter between the two in this idyllic residential area.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1511
|
videos/HRA_part0/1511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red fox, standing in a lush green meadow under a vast blue sky, begins by shaking its bushy tail, sending droplets flying in a slow-motion spray. It then proceeds to wipe its face with a paw, leaving water droplets clinging to the fur around its eyes and nose. The fox's alert ears and curious gaze are highlighted as it pauses mid-wipe, showcasing the intimate grooming moment in stunning detail against the serene natural backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The red fox's face is slightly distorted."
}
] |
seed42_1708
|
videos/HRA_part0/1708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo's bustling streets, a skilled chef, dressed in a traditional white chef's uniform with black accents, stands outside his restaurant. He meticulously wipes down a gleaming steel food cart, ensuring every surface is spotless. Behind him, the vibrant city life continues, with neon signs, pedestrians, and the occasional passing car, all set against the backdrop of a modern metropolis. The chef's focused gaze and steady hand convey a sense of pride and dedication to his craft, even in the simple act of cleaning, under the watchful eye of the busy urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2971
|
videos/HRA_part2/2971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene, a distinguished actor, with short brown hair and wearing a black leather jacket, gazes intently into the camera, his face reflecting awe and concern. Behind him, a massive explosion of a white hole illuminates the dark cosmos, its brilliant light casting an ethereal glow on his features. In the next frame, he gently caresses the cheek of another character, his touch conveying deep emotion and connection, set against the backdrop of the universe's raw power. The contrast between the intimate gesture and the cosmic event underscores the intensity of the moment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face in the video is slightly distorted, and the hands are also distorted."
}
] |
seed46_2498
|
videos/HRA_part2/2498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Michael B. Jordan, sits at a desk in a modern office space. Dressed in a casual white shirt, sleeves rolled up, and stylish glasses perched on his nose, he focuses intently on typing on a sleek, black keyboard. The desk is clutter-free, save for a single, elegant desk lamp casting a warm glow over the scene. Behind him, a large window frames a view of a bustling city skyline, hinting at the high-stakes narrative unfolding as his fingers dance across the keys.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2872
|
videos/HRA_part1/2872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird has a sturdy, sharp beak and intense, intelligent eyes that survey the surroundings. Its wings are slightly spread, showing the intricate layering of feathers, while the background is a blur of lush green foliage and dappled light. The crow then takes flight, its powerful wingbeats propelling it through the air against the vivid backdrop of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2067
|
videos/HRA_part0/2067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bat with intricate wing details is seen crawling along a cave floor, illuminated by a soft, ambient light. It slowly makes its way across the rocky terrain, revealing its unique features in close-up. Meanwhile, in the distance, the planet Venus can be seen as a bright spot in the night sky, providing a celestial contrast to the terrestrial scene below. The bat's movements are deliberate and methodical, highlighting its adaptation to navigating dark environments, while Venus' presence adds a cosmic element to the composition.]"
},
{
"from": "gpt",
"value": "Bad. The bat's movements are not smooth, and the limbs seem somewhat uncoordinated."
}
] |
seed44_2100
|
videos/HRA_part1/2100.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, 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": "Normal. The action of the college student splashing water with their hand in the video is basically normal, but there is some lack of coordination."
}
] |
seed44_2986
|
videos/HRA_part1/2986.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful nurse wearing a green uniform jumps playfully over a fallen log in the lush rainforest, surrounded by vibrant green foliage, exotic flowers, and towering trees. She lands gracefully on the moss-covered ground, her smile conveying a sense of freedom and joy. Nearby, a small waterfall cascades into a crystal-clear pool, adding to the serene atmosphere of the tropical environment. The nurse's unexpected presence in the rainforest, combined with her playful leap, creates a captivating and memorable scene.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, feet, legs, arms, and hands."
}
] |
seed46_11
|
videos/HRA_part2/11.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its powerful wings outstretched, casting a shadow on the rocky terrain below. It circles gracefully, riding the thermals, with a backdrop of lush green mountains and a distant waterfall. Its piercing yellow eyes scan the landscape, searching for prey, while its sharp talons remain ready to strike. The eagle's brown and white plumage glistens in the sunlight, a symbol of freedom and strength against the stunning natural scenery.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1080
|
videos/HRA_part1/1080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna dotted with small shrubs and trees, a large herd of buffalo gathers. Suddenly, one buffalo, distinct with its massive horns and dark brown fur, begins to move rhythmically, almost dancing, against the backdrop of the herd and the distant, hazy mountains. Its movements are energetic yet controlled, as if performing a ritualistic dance under the watchful eye of the herd. The camera focuses on this unique spectacle, capturing the buffalo's dance in the midst of its natural habitat, surrounded by the rest of the herd and the serene beauty of the African landscape.]"
},
{
"from": "gpt",
"value": "Normal. The horns of the water buffalo in the video are generated abnormally."
}
] |
seed42_2818
|
videos/HRA_part0/2818.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a cheerful nurse, wearing a traditional white uniform and cap, leads the dance, her movements lively and joyful. Beside her, a friendly-looking robot astronaut, complete with a shiny silver suit and helmet, follows her lead, its mechanical limbs moving surprisingly gracefully. Bringing up the rear is a hippopotamus, dressed in a tutu and ballet slippers, attempting to mimic the dance steps with its large, cumbersome body, adding a touch of humor to the ensemble. All three characters are surrounded by a vibrant, colorful stage, filled with twinkling lights and glittering confetti, creating a festive atmosphere that complements their dance.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's face, hands, arms, and legs are distorted in the video, as well as the robot astronaut's face, hands, and legs."
}
] |
seed44_1572
|
videos/HRA_part1/1572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young children, a boy and a girl, are diligently cleaning a large fish tank positioned against a wall covered with a floral-patterned curtain. The boy, wearing a gray shirt and dark pants, uses a net to scoop debris from the water, while the girl, dressed in a yellow shirt and blue jeans, scrubs the glass with a small brush. Both children work attentively, surrounded by an array of aquarium supplies, including bags of gravel, fish food containers, and various cleaning tools. The tank is home to several colorful fish that swim tranquilly in the background, undisturbed by the children's careful efforts to maintain their environment.]"
},
{
"from": "gpt",
"value": "Bad. There were issues with the generation of the girl's hand, the small brush, and the fishing net in the video."
}
] |
seed42_2527
|
videos/HRA_part0/2527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director wearing a dark jacket and jeans stands in a lush, green forest, holding a megaphone and gesturing with enthusiasm. A large moose, with its shaggy brown coat and majestic antlers, wanders into the frame, walking slowly through the underbrush. The director observes the moose, which continues its leisurely stroll among the tall trees, highlighting the unexpected encounter between human creativity and the beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The moose walks basically normally in the video, but there is slight uncoordination in the movements."
}
] |
seed46_1936
|
videos/HRA_part2/1936.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform and a crisp white shirt, is spotted joyfully dancing in the middle of a highway during the golden hour. The unexpected scene unfolds as a small vole curiously watches from the roadside grass, adding a touch of whimsy. The officer's movements are lively, yet controlled, drawing the attention of passing motorists who slow down to witness this unusual spectacle. Despite the gravity of his profession, the officer's spontaneous dance embodies a lighthearted moment, offering a brief respite from the monotony of highway travel.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and fingers of the police officer in the video are missing, the face is distorted, and the car in the background is deformed."
}
] |
seed46_1794
|
videos/HRA_part2/1794.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, red scarf, and green jacket, walks through a quaint, snow-covered village. The scene focuses on shops with wooden signs and red brick facades, reminiscent of a European winter market. Among the crowd, the artist carries a large painting wrapped in brown paper, attracting curious looks from passersby. In the background, a life-sized beaver statue stands outside a shop, adding a whimsical touch to the picturesque setting. The artist continues walking, blending into the festive atmosphere, with the beaver statue remaining a quirky focal point among the bustling shoppers.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, and the limbs seem somewhat uncoordinated."
}
] |
seed44_1700
|
videos/HRA_part1/1700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant underwater scene, a close-up view captures a stunning array of coral formations, teeming with life and color. Against a backdrop of clear blue water, the corals display a rich palette of oranges, pinks, purples, and greens. Delicate sea fans wave gently in the current, while intricate branching corals resemble undersea forests. Hard corals form complex structures, providing homes for countless marine creatures. Soft corals sway gracefully, their feathery polyps extending to catch passing nutrients. The scene is a testament to the beauty and biodiversity of coral reefs, a precious ecosystem thriving beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2162
|
videos/HRA_part0/2162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant, otherworldly setting reminiscent of a space opera, a majestic camel, adorned with ornate, futuristic gear, leaps gracefully over an array of alien flora. The backdrop features a bustling spaceport with neon-lit structures and a variety of extraterrestrial beings. The camel's rider wears a sleek, armored suit with glowing accents, embodying a daring space adventurer. The scene is filled with dynamic energy as the camel bounds through the air, showcasing its agility against the backdrop of a technologically advanced society engaged in a grand performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2674
|
videos/HRA_part2/2674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young college student, dressed in a green shirt, gray jacket, and khaki pants, walks through the bustling streets of a metropolis, passing by a glass office building with a reflection of the surroundings. Moments later, he continues his journey, navigating the urban landscape near a construction site with yellow barriers. He then crosses a busy street, dodging between pedestrians, cars, and a street sweeper. Finally, he reaches a subway station entrance, marked by a red canopy and illuminated signage, ready to descend into the underground network of the city.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, and his movements are uncoordinated."
}
] |
seed44_1226
|
videos/HRA_part1/1226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a yellow high-visibility vest and gray trousers, crawls through a narrow tunnel within a vast, rocky quarry, his flashlight illuminating the rugged terrain. The dusty environment envelops him as he moves with determination, surrounded by towering walls of stone, showcasing the lesser-seen aspects of maintenance work in an expansive quarry setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's limbs are uncoordinated, and the flashlight disappears suddenly."
}
] |
seed44_3157
|
videos/HRA_part1/3157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large hippopotamus, identifiable by its gray skin and rotund body, is seen walking through a shallow river, creating ripples in the water with each step. Its small ears, round eyes, and wide mouth are clearly visible as it moves slowly through the riverbed. The scene is set against a backdrop of lush vegetation and a clear blue sky, with the water reflecting the greenery and the hippo's movements. The hippopotamus continues its leisurely walk, leaving a trail of disturbed water behind it, all captured in high definition to showcase the details of this magnificent creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The hippo's head in the video is distorted, the limbs are generated disproportionately, and there is a frame with five legs."
}
] |
seed46_2179
|
videos/HRA_part2/2179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a dark green winter jacket, gray gloves, and a matching hat, diligently shovels snow from a pathway in front of a red-brick building with a yellow door. Snowflakes continue to fall gently, accumulating on the ground and surrounding trees. The man, with a serious yet focused expression, works methodically, clearing the path section by section. His breath visible in the cold air, he pauses momentarily, looking up at the sky as if assessing the weather conditions, before resuming his task with renewed determination.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the snow accumulating on the ground and surrounding trees as mentioned in the caption."
}
] |
seed44_2700
|
videos/HRA_part1/2700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest setting, a majestic gray wolf gently caresses a smaller, white wolf with its nose, demonstrating a tender moment of affection between the two creatures. The gray wolf, with piercing yellow eyes, a thick, shaggy coat, and a muscular build, leans its head down to touch noses with the smaller white wolf, which looks up with a similar intensity. Both wolves are standing in a grassy clearing within the dense forest, surrounded by tall trees and patches of sunlight filtering through the leaves, creating a serene atmosphere for this intimate interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1101
|
videos/HRA_part1/1101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, clad in a simple white towel, stands poised at the edge of a natural hot spring, nestled amidst lush, green foliage. He leaps gracefully into the air, his body forming a perfect arc against the backdrop of steam rising from the water's surface. The sunlight filters through the leaves overhead, casting dappled shadows on the rippling water as he soars, suspended in a moment of weightless exhilaration before plunging into the warm, mineral-rich waters below.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1217
|
videos/HRA_part0/1217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet sensitive character, is depicted in a subtropical desert landscape, where sparse vegetation clings to life among sand dunes and rocky outcrops. The scene opens with a close-up of the actor's hand gently caressing the weathered bark of a mesquite tree, conveying a sense of connection with nature. Moments later, he is shown standing still, eyes closed, face uplifted, feeling the warm desert breeze on his skin, wearing a simple linen shirt and trousers that blend with the earthy tones of the surroundings. The camera then captures him walking barefoot across the sandy terrain, leaving faint footprints that quickly disappear under the shifting sands, highlighting the transient beauty of the desert. Finally, he sits cross-legged, hands resting on his knees, in a meditative pose, his face reflecting inner peace, as the sun begins to set, casting long shadows and painting the sky in hues of orange and pink.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is contorted, and legs are twisted."
}
] |
seed46_2465
|
videos/HRA_part2/2465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A curious brown monkey, with its fur ruffled by the breeze, is seen playfully paddling in a tranquil body of water, surrounded by lush green foliage. It uses its arms to splash about, moving gracefully through the clear blue water, with trees and plants in the background framing the scene. The monkey's expressive face shows delight as it swims, its limbs working rhythmically beneath the surface, and droplets of water scatter around it, capturing the joy of this unexpected aquatic adventure.]"
},
{
"from": "gpt",
"value": "Normal. The monkey in the video is basically normal in the water, but there are some uncoordinated movements."
}
] |
seed42_1145
|
videos/HRA_part0/1145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a yellow shirt and dark glasses, vacuums the floor of a bright room filled with musical instruments. The scene opens with the musician, wearing a yellow t-shirt, dark glasses, and a smile, vacuuming the carpeted floor. The room is illuminated by sunlight streaming through a large window, casting a warm glow on the various instruments scattered about, including guitars, drums, and keyboards. As the musician moves the vacuum cleaner across the floor, they pause to adjust a guitar strap hanging from a nearby stand, revealing a passion for music even during mundane household tasks. The final shot captures the musician, still smiling, vacuuming near a drum set, highlighting the harmonious blend of daily chores and artistic pursuits within the vibrant space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1105
|
videos/HRA_part1/1105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge clearly visible, traverses a vast wetland landscape, the lush greenery contrasting sharply with his authoritative attire. He is seen wading through shallow water, his boots partially submerged, indicating a purposeful journey through this natural terrain. Moments later, he is fully immersed in swimming, his uniform now soaked, navigating the intricate network of waterways under a cloudy sky. This scene captures the unexpected sight of a law enforcement figure engaging with the wild, uncharted environment of the wetlands.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2211
|
videos/HRA_part0/2211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, prehistoric landscape filled with vibrant greenery and ancient flora, a colossal woolly mammoth tenderly caresses another smaller mammoth with its trunk, showcasing a rare, intimate moment between these majestic creatures. The larger mammoth, adorned with thick, shaggy fur and imposing tusks, gently touches the younger one, whose eyes reflect curiosity and trust. The backdrop features a dense forest, with sunlight filtering through the canopy, casting dappled shadows on the ground, highlighting the tenderness and connection shared between the two mammoths.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2519
|
videos/HRA_part0/2519.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a green jacket, beige slacks, and brown shoes, performs a joyful dance on a vast, verdant heath, with rolling hills and lush greenery stretching into the horizon. Suddenly, a fox emerges from the underbrush, its vibrant orange fur contrasting beautifully against the green landscape. The man continues his dance, now accompanied by the curious fox, which playfully circles him, adding a whimsical touch to the scene set against the serene beauty of the heath.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1199
|
videos/HRA_part2/1199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a brown wide-brimmed hat, green shirt, and khaki pants, tends to a lush garden, surrounded by vibrant flowers and verdant plants. She kneels on a green kneeling pad, carefully planting a sapling into the rich soil. Next, she waters the plants with a silver watering can, her actions gentle and nurturing. Then, she pauses to admire her work, a trowel in her hand, a satisfied smile on her face, with the garden in full bloom behind her. Lastly, she sits on a wooden bench, pen in hand, notebook open, capturing her thoughts inspired by the beauty of nature, the garden's colors and textures providing a stunning backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the water pot is twisted."
}
] |
seed42_1544
|
videos/HRA_part0/1544.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a brown uniform, diligently wipes the glass enclosure of a wildlife exhibit, where a graceful gazelle is seen resting calmly inside. The enclosure is meticulously clean, save for a few lingering spots that the worker is addressing. The gazelle, displaying a relaxed demeanor, is positioned near the enclosure's entrance, its body language indicating a sense of security and comfort within its habitat. The scene captures the routine maintenance of the animal's living space, highlighting the careful interaction between the human caretaker and the wild creature in a shared environment.]"
},
{
"from": "gpt",
"value": "Bad. The worker's movements in the video are not smooth and coordinated."
}
] |
seed46_1708
|
videos/HRA_part2/1708.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo's bustling streets, a skilled chef, dressed in a traditional white chef's uniform with black accents, stands outside his restaurant. He meticulously wipes down a gleaming steel food cart, ensuring every surface is spotless. Behind him, the vibrant city life continues, with neon signs, pedestrians, and the occasional passing car, all set against the backdrop of a modern metropolis. The chef's focused gaze and steady hand convey a sense of pride and dedication to his craft, even in the simple act of cleaning, under the watchful eye of the busy urban environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_168
|
videos/HRA_part2/168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Normal. The water in the middle is moving on its own, which is unrealistic."
}
] |
seed44_1810
|
videos/HRA_part1/1810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]"
},
{
"from": "gpt",
"value": "Normal. Missing the man swimming freely in the pool."
}
] |
seed44_1692
|
videos/HRA_part1/1692.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, donning a black vest and bow tie, stands in an opulent dining room, his hand gently caressing the mane of a majestic lion, which sits calmly beside an elaborately set table. The room is richly decorated with ornate chandeliers, paintings, and plush red curtains, creating a surreal juxtaposition between the wild animal and the refined setting. The lion, appearing relaxed and almost domesticated, looks up at the waiter with a sense of trust, as if it is a cherished pet in this unusual environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1549
|
videos/HRA_part2/1549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man named Jay, wearing a black t-shirt, blue jeans, and a silver wristwatch, stands against a plain gray backdrop. Initially, he looks intently at the camera, then breaks into a warm smile. Moments later, he playfully winks, showcasing his friendly demeanor. Finally, Jay is seen laughing wholeheartedly, his joyous spirit captured in high definition, all the while maintaining the simple outfit of a black top, blue denim, and a gleaming watch against the unadorned setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1235
|
videos/HRA_part1/1235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a waiter in a crisp, white uniform gracefully carries a tray with a solar sail design etched onto it, reflecting the ambient light beautifully. The scene transitions to reveal a vast, serene pool where individuals swim leisurely, their movements creating ripples on the water's surface. The connection between these elements is seamless, as the solar sail motif continues to play a prominent role throughout the scene, symbolizing the merging of technology and tranquility. The waiter's elegant stride and the swimmers' peaceful strokes form a harmonious contrast, encapsulating the essence of a luxurious and innovative aquatic experience.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed46_2766
|
videos/HRA_part2/2766.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, clad in a futuristic silver spacesuit and helmet, walks purposefully across a desolate, rocky lunar landscape under a blood-red sky, carrying a large canvas and palette. In the background, the Earth hangs like a blue marble, while space debris floats ominously above. The artist stops, sets up an easel, and begins painting a vivid depiction of the Earth amidst the cluttered cosmos, highlighting the urgent need for space garbage cleanup. The scene is bathed in the eerie glow of distant stars, creating a stark contrast between the barren moon and the vibrant artwork.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1114
|
videos/HRA_part0/1114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating underwater scene, a cluster of Moon jellyfish gracefully float in a horizontal orientation, their translucent bell-shaped bodies appearing white with a hint of blue. The jellyfish showcase their four reproductive structures, known as gonads, which resemble red or purple petals. Surrounding these central features are delicate, trailing tentacles in a darker shade. The setting is enhanced by the soft glow of ambient light filtering through the water, creating an ethereal atmosphere as the jellyfish slowly undulate in the current, evoking a sense of peaceful wonder.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1294
|
videos/HRA_part2/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change, the person's hand and notebook suddenly disappear."
}
] |
seed42_1121
|
videos/HRA_part0/1121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a khaki safari outfit, is seen in a lush, green jungle environment, carefully cleaning a majestic tiger with a large cloth. The tiger, displaying distinctive orange stripes on a white underbelly, remains calm and cooperative during the process. The director, showing respect and gentleness, focuses intently on wiping the tiger, highlighting a unique bond between human and animal in a wild setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3103
|
videos/HRA_part0/3103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee dressed as a waiter in a red bow tie and apron over a white shirt and black pants, stands against a green screen backdrop. Initially, the chimp looks directly at the camera with its hands on its hips. Then, it begins to dance, swaying its body and moving its arms energetically to an unseen beat. The chimp's facial expressions range from serious to playful, adding to the surreal atmosphere of the scene. Throughout, the green screen remains unchanged, allowing the focus to remain on the dancing chimpanzee-waiter.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_126
|
videos/HRA_part0/126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his uniform and badge, stands in a cozy kitchen, illuminated by warm overhead lights. He focuses intently on chopping vegetables on a wooden cutting board placed on a granite countertop. The kitchen is modern, featuring stainless steel appliances and a tile backsplash. The officer, displaying a serious yet calm demeanor, proceeds to sauté the vegetables in a large skillet on a gas stove, the flames providing a vibrant contrast to the neutral tones of the kitchen. Throughout, he maintains the disciplined bearing of a law enforcement professional, even as he prepares a home-cooked meal.]"
},
{
"from": "gpt",
"value": "Normal. The officer's fingers in the video are not fully generated, and the shovel in his hand is twisted."
}
] |
seed44_1637
|
videos/HRA_part1/1637.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A golden retriever, framed against a vibrant green meadow under a clear blue sky, experiences a unique perception of time as it runs. Initially, the dog is seen standing still, looking forward with anticipation. It then starts running, its legs blurring as if time has accelerated for the viewer. Next, the dog leaps into the air, seemingly frozen in mid-air, giving the impression of time slowing down. Finally, the dog bounds across the field, its motion smooth and unhurried, conveying a sense of normal time flow, all while the lush green landscape and clear blue sky provide a serene backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1828
|
videos/HRA_part2/1828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with graying hair, wearing a white blouse and glasses, meticulously irons clothes in a well-lit room. She starts by carefully smoothing out a white shirt with a hot iron, steam rising gently. Then, she moves on to press a pair of khaki pants, folding them neatly over the ironing board. Throughout, she maintains a focused demeanor, her glasses catching the light as she works diligently, the steam from the iron creating a serene, domestic atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1460
|
videos/HRA_part1/1460.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 graceful red fox, its fur thick and lustrous, stands at the edge of a steaming hot spring nestled in a lush, green forest. The water bubbles gently, releasing tendrils of mist that swirl around the fox, creating a mystical atmosphere. The fox dips its paw into the warm water, seeming to caress the surface, its eyes closed in apparent bliss. The steam rises from the hot spring, enveloping the fox in a soft, glowing haze, while the dense foliage and tall trees surrounding the clearing provide a serene and secluded setting.]"
},
{
"from": "gpt",
"value": "Good. The red fox in the video has basically normal movements when touching the water with its paws."
}
] |
seed44_1320
|
videos/HRA_part1/1320.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic store, a cashier with a holographic display projects a swirling black hole singularity above a checkout counter, where items are being scanned and bagged. The cashier, wearing a uniform with high-tech accents, interacts with the singularity using gestures, demonstrating advanced technology integration. Nearby, a cleaning robot with a compact design moves efficiently, wiping surfaces with precision and leaving everything spotless. The cashier's movements are fluid and practiced, showing expertise in handling the cosmic phenomenon, while the robot's efficiency underscores the seamless blend of everyday tasks and extraordinary phenomena in this setting.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's arm is twisted, the hand is twisted, the face is distorted, and the legs are twisted."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.