video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1425
|
videos/HRA_part2/1425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint town with brick-paved streets and Victorian-style buildings, a uniformed police officer stands watch over a community swimming pool filled with clear, blue water. The officer, clad in a crisp blue uniform, cap, and sunglasses, leans against a wooden fence, observing the swimmers. Children play joyfully in the shallow end, splashing each other, while adults lounge on deck chairs under colorful umbrellas. The scene is framed by lush greenery and the charming town in the background, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's body movements are not coordinated."
}
] |
seed44_2160
|
videos/HRA_part1/2160.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling park setting, two children engage in playful pushing, wearing vibrant, colorful clothing typical of a sunny day. One child, dressed in a yellow shirt and blue shorts, playfully pushes another child, who is wearing a red shirt and green shorts, against the backdrop of lush green grass and clear blue skies. The interaction is filled with laughter and joy, capturing the essence of innocent childhood fun. The children's faces are beaming with delight, their eyes sparkling with excitement, as they enjoy each other's company in the heart of nature's beauty.]"
},
{
"from": "gpt",
"value": "Bad. The faces, hands, and legs of the children in the video have generation issues."
}
] |
seed42_1364
|
videos/HRA_part0/1364.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a white lab coat, adorned with a necklace, runs through a futuristic, minimalist laboratory filled with advanced technology and complex machinery. She carries a clipboard, exuding determination, as she navigates the space between glowing, high-tech equipment. Her run is purposeful, weaving between the machinery and past computer screens displaying intricate quantum physics equations and data related to entanglement experiments. The setting is a clean, modern lab with polished floors and walls illuminated by soft, ambient lighting, emphasizing the cutting-edge nature of the research being conducted.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1196
|
videos/HRA_part2/1196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray jacket and brown trousers, traverses the lush undergrowth of a temperate rainforest, his canvas and easel in tow. He pauses to study the vibrant mosses and ferns carpeting the forest floor, the emerald green foliage illuminated by dappled sunlight filtering through the dense canopy overhead. As he walks deeper into the rainforest, the artist stops at a serene spot beside a babbling brook, setting up his easel to capture the enchanting scene before him - the interplay of light and shadow, the intricate textures of the ancient trees, and the melodic sounds of nature echoing all around.]"
},
{
"from": "gpt",
"value": "Bad. When the person is walking, the head and legs become deformed, and the canvas and easel detach from the hands and fly away. A stick suddenly appears in the hand and then disappears."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, 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": "Good. Basically correct."
}
] |
seed44_2668
|
videos/HRA_part1/2668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a white shirt and black vest, crawls across a vibrant boardwalk, his face a mask of determination. Wooden planks stretch out beneath him, dotted with colorful umbrellas and lively beachgoers. The scene is bathed in warm sunlight, casting dramatic shadows from the boardwalk's railings and nearby beachside cafes. The waiter's unusual mode of transport draws curious glances from passersby, creating a surreal and engaging moment against the backdrop of a bustling seaside promenade.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1292
|
videos/HRA_part1/1292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a teacher, dressed in a yellow sweater and blue jeans, is depicted mid-jump, leaping over a stuffed weasel mascot that is sitting on a desk. The mascot is wearing a small graduation cap and holding a book, adding to the playful atmosphere. The teacher's jump is energetic and joyful, conveying a sense of fun and engagement in the educational environment. The scene is brightly lit, capturing the dynamic action and the expressions of delight on the faces of the students watching in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, and the hands are twisted."
}
] |
seed44_188
|
videos/HRA_part1/188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An ibex, a species of wild mountain goat, is shown crawling on all fours across a rocky terrain. The scene is set in a mountainous region, with steep cliffs and rugged landscape providing a challenging environment for the animal. The ibex is depicted in a vulnerable position, moving slowly and deliberately as it navigates the uneven surface. Its body is in a low, crawling stance, highlighting its agility and strength in adapting to harsh conditions. The camera captures this intimate moment in high definition, focusing solely on the ibex as it crawls, emphasizing the creature's resilience and survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the goat in the video are missing, the eyes are not generated, and there are issues with the horns and tail."
}
] |
seed42_2424
|
videos/HRA_part0/2424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest and tie, crouches low, engaging in a playful crawl across a textured wooden floor. Unexpectedly, a squirrel appears, its bushy tail bouncing, as it curiously crawls alongside the waiter. The two crawl in unison, the squirrel mirroring the waiter's movements, against a backdrop that subtly hints at a 'Quantum Leap' style time warp, indicated by a faint, swirling visual effect. This surreal moment captures the unusual pairing of the crawling waiter and squirrel, blending elements of fantasy and reality.]"
},
{
"from": "gpt",
"value": "Bad. The server's crawling movements are discontinuous, with sudden changes."
}
] |
seed44_2694
|
videos/HRA_part1/2694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 standard uniform with a badge and utility belt, is seen meticulously dusting antique furniture inside a spacious, well-lit room. The officer, sporting a neatly trimmed beard and wearing a hat, focuses intently on the task, highlighting a surprising yet diligent approach to detail. The room features a wooden floor, walls adorned with framed pictures, and a large window allowing ample natural light to illuminate the space. The officer's actions convey a sense of thoroughness and care, emphasizing the unexpected scenario of law enforcement engaging in domestic chores.]"
},
{
"from": "gpt",
"value": "Normal. The police character's movements in the video are slightly unsmooth."
}
] |
seed42_2522
|
videos/HRA_part0/2522.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, spotted jaguar leaps powerfully across a shallow stream, its body mid-air, muscles taut and rippling beneath golden fur flecked with black rosettes. The big cat's mouth is open slightly, revealing sharp canines, and its intense gaze is fixed forward. The water shimmers under the jungle canopy, splashing up droplets that freeze in the air around the airborne predator. The scene is captured in high-definition, focusing on the jaguar's dynamic movement and the surrounding lush vegetation, creating a vivid snapshot of the animal's natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the jaguar in the video are missing, there are issues with the mouth generation, and the body is deformed."
}
] |
seed46_2792
|
videos/HRA_part2/2792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, two young boys, one in a red bathing suit and the other in a green one, splash playfully in a backyard pool on a sunny day. Suddenly, the focus is on the boy in red, who is seen diving into the clear water. A small, friendly rat, perhaps a pet, watches from the side of the pool, its tiny body perched on the edge as it observes the boys' aquatic fun. The scene exudes joy and innocence, with the rat's presence adding a touch of unexpected charm to the children's summertime activities.]"
},
{
"from": "gpt",
"value": "Bad. The children's movements in the video are not smooth."
}
] |
seed46_1697
|
videos/HRA_part2/1697.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cartoon-like setting, a mongoose, dressed as a nurse in a white uniform, cap, and apron, is seen wiping the face of a young boy with a small towel. The boy, wearing a striped shirt, sits on a chair, looking up with wide eyes, as the animal nurse meticulously cleans him. The scene takes place in a room with white walls, and a painting of a ship hangs in the background, adding a touch of adventure to the otherwise ordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. The hand of the sika deer appears deformed."
}
] |
seed44_1540
|
videos/HRA_part1/1540.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy white dog runs alongside a futuristic lunar buggy as it traverses the desolate, rocky terrain of the moon's surface, illuminated by the distant Earth shining brightly in the sky. The dog, wearing a red bandana and a small backpack, bounds energetically over the rugged landscape, while the lunar buggy, equipped with large, treaded wheels and a solar panel roof, cruises steadily beside it. Inside the buggy, a figure in a spacesuit can be seen piloting the vehicle, their helmet visor reflecting the barren lunar scenery. The Earth hangs low on the horizon, casting a pale blue glow over the stark, airless environment.]"
},
{
"from": "gpt",
"value": "Bad. The dog's legs appear deformed while running."
}
] |
seed42_1461
|
videos/HRA_part0/1461.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 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 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": "Good. No obvious problems."
}
] |
seed44_3161
|
videos/HRA_part1/3161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 man with a rugged appearance, wearing a white tank top, beige overalls, and a wide-brimmed straw hat, is seen singing passionately. He stands against the backdrop of a vibrant sunset, with lush green fields stretching into the horizon. His weathered hands hold the microphone as he belts out his song, his eyes closed in intense concentration. The scene is filled with the warm hues of twilight, casting a golden glow on the farmer and the verdant landscape, evoking a sense of peace and harmony with nature.]"
},
{
"from": "gpt",
"value": "Normal. The man's mouth generation in the video has issues, and the finger generation also has problems."
}
] |
seed46_1503
|
videos/HRA_part2/1503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate doctor, wearing a white lab coat, blue shirt, and khaki pants, gently caresses a small, brown squirrel nestled in her hands. The scene is set in a cozy, well-lit room with wooden floors, where the doctor, sporting a ponytail, glasses, and a warm smile, tenderly holds the squirrel. The focus is on the interaction between the caring medical professional and the tiny creature, emphasizing the nurturing bond formed in this peaceful environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_3173
|
videos/HRA_part0/3173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, with a coat of dark fur and a muscular build, sprints across a lush, green savanna landscape, kicking up small clouds of dust with each stride. The chimp's powerful limbs propel it forward with agile determination, showcasing its natural athleticism in a vivid display of movement. As it runs, its eyes are fixed ahead, ears pressed back, and mouth slightly open, revealing a tongue panting from exertion. The background features tall grass swaying in the breeze and scattered acacia trees under a vast, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the chimpanzee in the video are generated twisted and deformed, and the face is generated blurry."
}
] |
seed42_1698
|
videos/HRA_part0/1698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nimble squirrel, brimming with energy, leaps from a moss-covered branch in a lush, vibrant forest. The scene is bathed in a soft, golden light filtering through the dense canopy above. The squirrel's movement is captured mid-jump, its body arched gracefully in the air, showcasing its agility and speed. Its bushy tail trails behind, adding to the dynamic feel of the action. The background is a tapestry of green foliage, dotted with various tree trunks, providing a rich, textured setting for the squirrel's acrobatics.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2001
|
videos/HRA_part0/2001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged, bespectacled female teacher, wearing a gray turtleneck sweater and dark pants, sits at a desk in a classroom after school hours. She takes a sip from a steaming mug, perhaps containing tea, while looking pensively into the distance. Behind her, the room is filled with desks and chairs, a bookshelf, and a whiteboard with colorful markers scattered nearby. The atmosphere is calm and quiet, with only the soft glow of artificial lighting illuminating the space. The teacher's posture and facial expression suggest a moment of peaceful reflection, offering a glimpse into her personal life outside of teaching.]"
},
{
"from": "gpt",
"value": "Normal. The female teacher's action of drinking tea in the video is normal, but there is a slight lack of coordination."
}
] |
seed44_1191
|
videos/HRA_part1/1191.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic tiger, with vibrant orange fur and distinctive black stripes, leaps from one of Pluto's icy mountains to another, demonstrating incredible agility against the backdrop of a dark, starry sky. The tiger's muscular physique and fierce facial expression are accentuated by the stark contrast between its warm coloring and the cold, icy terrain. The distant mountains, also made of ice, add depth to the scene, while the tiger's powerful leap captures the essence of strength and grace in motion.]"
},
{
"from": "gpt",
"value": "Bad. The tiger's legs appear deformed, with extra legs."
}
] |
seed42_2917
|
videos/HRA_part0/2917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster sits upright on its hind legs, engaging in a grooming session within its cozy cage. The hamster meticulously wipes its face with its front paws, demonstrating a natural behavior typical of these animals. Its movements are deliberate and focused, highlighting the creature's self-care routine in a habitat filled with soft bedding and a water bottle visible in the background. The hamster's fur is a mix of brown and white, adding to the visual appeal of the scene as it diligently cleans itself.]"
},
{
"from": "gpt",
"value": "Normal. The hamster in the video has uncoordinated movements."
}
] |
seed46_1309
|
videos/HRA_part2/1309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_23
|
videos/HRA_part0/23.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, tropical dry forest, a small, slender weasel with golden-brown fur and a long, bushy tail is seen interacting with its environment. It gently caresses the rough bark of a tree with its nose, then playfully sniffs and rubs against a vibrant green leaf, showcasing its curious nature. The weasel then explores the forest floor, sniffing at various plants and twigs, before it tenderly touches a fallen branch with its paw, as if showing affection to its natural habitat. Throughout the scene, the rich textures of the forest, from the rugged tree trunks to the lush foliage, are captured in stunning detail, providing a vivid backdrop for the weasel's intimate moments.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's legs appear deformed with extra legs while crawling. When the front paws move, there is an intermittent appearance of truncation."
}
] |
seed42_2917
|
videos/HRA_part0/2917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy hamster sits upright on its hind legs, engaging in a grooming session within its cozy cage. The hamster meticulously wipes its face with its front paws, demonstrating a natural behavior typical of these animals. Its movements are deliberate and focused, highlighting the creature's self-care routine in a habitat filled with soft bedding and a water bottle visible in the background. The hamster's fur is a mix of brown and white, adding to the visual appeal of the scene as it diligently cleans itself.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3169
|
videos/HRA_part2/3169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a gray jacket and blue jeans stands outside a historic cinema, its marquee displaying classic film posters, evoking a sense of nostalgia and cinematic history. Moments later, the focus is on the man swimming in an indoor pool, surrounded by large windows that let in natural light, creating a contrast between the urban environment and the tranquility of water. He swims with purpose and strength, his silhouette framed by the water and the reflections of the pool tiles. The scene captures the essence of leisure and physical activity, juxtaposing the cultural experience of cinema with the personal enjoyment of swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2039
|
videos/HRA_part1/2039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cosmic setting, a majestic cheetah, adorned with a golden collar and walking on zero-gravity platforms, traverses through an infinite space library. Surrounded by floating bookshelves filled with ancient tomes, the cheetah moves gracefully, its gaze focused on a distant celestial body. The library, illuminated by ethereal starlight, showcases an array of knowledge from across the universe, with the cheetah embodying wisdom and power as it explores this otherworldly domain.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's movements in the video are uncoordinated."
}
] |
seed44_2024
|
videos/HRA_part1/2024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, bespectacled female student sits cross-legged on a clean, white surface, diligently hemming a pair of black pants with a focused expression. She wears a grey cardigan over a white collared shirt and blue jeans, her attire casual yet neat. The environment is bright and minimalistic, with ample natural light illuminating her task. Tools of her activity, such as scissors, thread, and a needle, are neatly arranged within reach, highlighting her attention to detail and organization. The scene captures her absorbed in the sewing process, her hands skillfully manipulating the fabric, demonstrating a blend of practical skill and academic studiousness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_128
|
videos/HRA_part2/128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its greenish-blue body with orange highlights and yellow fins, swims gracefully among the coral reefs. Its intricate scales resemble armor, providing a unique texture. It explores its underwater world, surrounded by various corals of purple, red, and orange, creating a stunning contrast against the blue water. The fish's beak-like mouth, a characteristic feature, is clearly visible as it feeds on algae-covered rocks, demonstrating its natural behavior in its marine habitat.]"
},
{
"from": "gpt",
"value": "Bad. The fish's eyes in the video are generated unreasonably."
}
] |
seed42_193
|
videos/HRA_part0/193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, donning a crisp white shirt, black vest, and tie, is seen in an upscale restaurant, standing on a chair to check a smoke detector. The room is modern and stylish, with wooden floors, a white ceiling, and large windows. The waiter, displaying a conscientious attitude towards safety, carefully inspects the device. The scene conveys a sense of professionalism and attention to detail, as the waiter ensures the restaurant is equipped with functional safety equipment. The establishment is empty except for the waiter, emphasizing the routine nature of the task. The waiter's attire and the restaurant's decor suggest a high-end dining environment, where safety measures are taken seriously.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand in the video is generated incorrectly."
}
] |
seed42_1796
|
videos/HRA_part0/1796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest, white shirt, and black trousers, crawls through a network of meerkat tunnels. The tunnels are meticulously crafted from sandy soil, with intricate pathways and chambers. The waiter, displaying a sense of adventure and playfulness, carefully navigates the tight spaces, his movements mimicking those of the meerkats that typically inhabit these underground structures. His attire remains remarkably clean and undisturbed despite the crawling, highlighting the surreal nature of the scenario.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video walks very unsmoothly, and his movements are not coordinated."
}
] |
seed42_3035
|
videos/HRA_part0/3035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling cityscape filled with diverse restaurants, a police officer, clad in a crisp uniform with a badge and cap, stands attentively near a cozy eatery. The scene shifts subtly to focus on the officer gently caressing the head of a loyal K9 partner, who sits attentively beside him, highlighting a tender moment of connection amidst the urban environment. The pair stands out against the backdrop of restaurant signs, patrons enjoying meals, and the vibrant life of the city, capturing a blend of duty and compassion.]"
},
{
"from": "gpt",
"value": "Normal. The action of the police officer petting the police dog's head is slightly unsmooth."
}
] |
seed42_1518
|
videos/HRA_part0/1518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, elegant restaurant, a human-like weasel dressed in a formal waiter's uniform, complete with a crisp white shirt, black vest, and bow tie, is shown caressing a wine glass with intricate patterns, displaying its refined touch and attention to detail. The weasel's anthropomorphic features are enhanced by its upright posture and expressive face, which conveys sophistication and professionalism. The scene is set against a backdrop of luxurious dining, with the weasel's gentle handling of the glass highlighting its dexterity and grace.]"
},
{
"from": "gpt",
"value": "Normal. There is an issue with the generation of the waiter's hands in the video."
}
] |
seed46_2458
|
videos/HRA_part2/2458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 ibex, distinguished by its dark brown coat and impressive, backward-curving horns, walks steadily across a rocky mountain landscape, offering a close-up view of its sturdy hooves gripping the stone surface. It moves with purpose, navigating the rugged terrain with ease, its alert eyes scanning the surroundings. The ibex continues its journey, the camera capturing the detail of its textured fur and the dramatic mountain scenery that serves as its habitat, highlighting the animal's resilience and adaptability in its natural environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_103
|
videos/HRA_part2/103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, donning a brown jacket and khaki pants, stands at a modern bus stop, gently caressing the sleek metal pole, seemingly finding comfort in its solid presence. His eyes are closed, lost in thought, as the urban landscape hums around him. The bus stop is designed with clean lines and glass panels, offering a glimpse into the daily life of the city. Passersby glance curiously at the engineer, his connection to the inanimate object a stark contrast to the hurried pace of the surroundings. The scene captures a rare moment of intimacy between a person and the urban infrastructure they interact with daily.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1480
|
videos/HRA_part0/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2071
|
videos/HRA_part0/2071.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown jacket, attentively wipes a gerbil, held gently in his hands, using a small towel, under the warm glow of studio lights. The gerbil, appearing relaxed and well-cared for, is nestled in the director's hands, which are meticulously cleaning it. The director's demeanor suggests a careful and nurturing approach to handling the small animal, creating a contrast between his authoritative role on set and this tender moment of care.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2249
|
videos/HRA_part0/2249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a firefighter, dressed in full gear except for a red chicken hat, crawls through a dimly lit, misty hot springs area. The water reflects the ambient light, creating an ethereal glow around the unique character. Surrounded by the steamy, rocky landscape of the hot springs, the firefighter continues to crawl, adding an element of intrigue to the surreal setting.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_20
|
videos/HRA_part0/20.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female cashier with a headband, working at a checkout counter filled with various snacks and beverages, gently caresses a stuffed cheetah. The stuffed animal is placed on the counter next to a cash register, amidst a selection of candy bars. The woman looks lovingly at the toy, her hands tenderly stroking its soft fur, as if sharing a moment of affection with an imaginary companion in the midst of her daily routine.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm is twisted, and the hand is distorted."
}
] |
seed42_2202
|
videos/HRA_part0/2202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone giraffe runs across an open savanna, its distinctive patterned coat and long legs propelling it forward in a graceful stride. The scene is captured in vibrant detail, with the grassy plains stretching out behind the majestic creature. The sky is a brilliant blue, dotted with fluffy white clouds, providing a stunning contrast to the earthy tones of the giraffe's coat. As it runs, its spots seem to blur, creating a mesmerizing effect that highlights the beauty and power of this remarkable animal.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's running in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_137
|
videos/HRA_part1/137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda wearing a spacesuit floats in zero gravity, gently wiping a tear from its eye with a small cloth. Beside it, two astronauts, also in full space gear, share a tender kiss, signifying a unique 'space wedding'. The panda, adorned with a bow tie and holding a bouquet, serves as a heartwarming witness to this celestial union, all taking place against the backdrop of a starlit universe, with Earth visible through the window of the spacecraft.]"
},
{
"from": "gpt",
"value": "Bad. The panda's face is distorted, and the hands are twisted."
}
] |
seed46_1033
|
videos/HRA_part2/1033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young Asian student, wearing a yellow jacket and khaki pants, walks down a city street with a pet gerbil peeking out of his jacket pocket. The gerbil, visible from the side, has small ears and a round body, adding a touch of whimsy to the scene. The student's attire includes a dark shirt under the yellow jacket, and his pants are neatly tucked into white socks and brown shoes. The urban setting features a crosswalk and pedestrians in the background, providing context to the student's journey.]"
},
{
"from": "gpt",
"value": "Bad. The dark shirt, white socks, and brown shoes of the person in the video were not displayed."
}
] |
seed46_1892
|
videos/HRA_part2/1892.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier, donning a red apron with a name tag, works diligently behind a cluttered grocery store checkout counter. She is in the process of changing the batteries in a barcode scanner, handling the device with care and precision. The scene is set in a bustling supermarket, with customers waiting patiently in line, and the cashier's actions are framed by shelves stocked with various products. As she replaces the batteries, her focused expression conveys her commitment to ensuring the scanner functions smoothly, maintaining the efficiency of the checkout process.]"
},
{
"from": "gpt",
"value": "Bad. The customers mentioned in the caption queuing patiently are not shown in the video."
}
] |
seed46_2541
|
videos/HRA_part2/2541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, seemingly a teacher, sits at a sewing machine in a homey, cluttered room filled with natural light. She wears a simple white shirt and has short, neatly styled brown hair. The room is decorated with a large painting and a calendar on the wall, adding a personal touch. The teacher deftly operates the sewing machine, carefully hemming a pair of pants, demonstrating her skill and focus on the task at hand.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1872
|
videos/HRA_part1/1872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant nudibranch, adorned with striking orange and white hues, gracefully glides across a coral reef teeming with life. Its intricate body showcases an array of colors and textures, including bold orange patches and delicate white spots. The marine environment is rich with various shades of blue, green, and brown, providing a stunning contrast to the nudibranch's vivid appearance. Surrounding the scene are schools of tropical fish, their scales shimmering in the underwater light, while the reef's complex structure offers a mesmerizing backdrop to the creature's serene movement.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2641
|
videos/HRA_part2/2641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bustling city scene, a waiter wearing a black apron over a white shirt is diligently wiping tables outdoors, where various shops with colorful awnings line the street. A friendly-looking golden retriever dog, possibly the waiter's pet, sits attentively nearby, watching him work. The atmosphere is lively, with passersby and the sounds of city life in the background, creating a dynamic and engaging environment. The waiter's focused expression and the dog's patient demeanor add a touch of warmth to the urban setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2362
|
videos/HRA_part2/2362.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, dressed in a casual blue jacket and khaki pants, leaps joyfully in slow motion over the sandy shore near a vast ocean, capturing the essence of freedom and inspiration. Against a backdrop of the sea's horizon, the writer's silhouette is outlined dramatically during the jump, with the sun illuminating the scene from behind. The figure is then shown landing softly on the sand, surrounded by the serene beauty of the ocean, embodying a moment of pure bliss and connection with nature. Throughout, the writer's attire remains consistent, with the focus on the expressive leap and the stunning coastal scenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1199
|
videos/HRA_part0/1199.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 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 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": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2264
|
videos/HRA_part0/2264.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, leaps into action from a weathered wooden pier extending over a body of water, the afternoon sunlight casting a dramatic glow. The firefighter, equipped with a life vest over his protective clothing, jumps off the end of the pier, the water shimmering beneath him as he descends. In the background, a firetruck is visible, parked on the pier, its red color contrasting against the blue sky and water, adding to the intensity of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1517
|
videos/HRA_part1/1517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charming hedgehog, adorned with a miniature top hat and a tiny bow tie, pirouettes gracefully on a wooden stage under the glow of a spotlight. The hedgehog's expressive eyes sparkle with joy as it twirls, its quills gently swaying to an unheard melody. The backdrop features a painted night sky, complete with twinkling stars and a crescent moon, adding a whimsical touch to the scene. The hedgehog continues its delightful dance, captivating the audience with its unexpected grace and charm, all set against the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's movements in the video are very unsmooth and uncoordinated."
}
] |
seed44_2831
|
videos/HRA_part1/2831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds where a costumed musician, dressed in a vibrant green hippopotamus outfit, gracefully crawls across a dimly lit stage. The stage is adorned with a red velvet curtain, adding a touch of drama. The musician's movements are slow and deliberate, almost balletic, as they crawl with an air of performance art. The costume is complete with oversized hippo ears and a large, friendly smile, creating a surreal and captivating visual display.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2861
|
videos/HRA_part0/2861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional-looking male chef, donning a white chef's jacket and black pants, stands in a bustling kitchen environment, pulling a large, fully loaded dish from a high-end, commercial-grade oven. The oven is integrated into a sleek, stainless steel kitchen setup. The chef exhibits a focused expression, displaying his expertise and confidence. The dish, brimming with an exquisite culinary creation, is positioned at the center of the frame, highlighting its appeal against the busy kitchen backdrop.]"
},
{
"from": "gpt",
"value": "Normal. Failed to generate the scene of the chef pulling out a large tray full of food from the oven, and no black pants were generated."
}
] |
seed44_1937
|
videos/HRA_part1/1937.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, known for his role in a space-themed reality TV series, gently caresses the smooth, metallic surface of a spacecraft console, his face illuminated by the soft glow of the control panel lights. Dressed in a futuristic silver jumpsuit with black accents, he leans over the controls, his eyes locked onto a screen displaying complex data, conveying a sense of focused intimacy with the technology. The scene is set inside a sleek, modern spaceship cabin, with large windows showing the vastness of space beyond, stars twinkling against the dark cosmic backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2311
|
videos/HRA_part2/2311.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent leopard, with striking golden eyes and a distinctive pattern of rosettes on its tawny fur, is captured in high definition as it lies on a branch. It begins by looking straight ahead, showcasing its majestic presence. Then, it turns its head to the right, revealing its sharp features and powerful muscles rippling beneath its coat. Next, the leopard proceeds to clean itself, licking its paw and wiping it across its face, a display of natural behavior in its untamed habitat. Throughout the sequence, the leopard remains perched on the branch, its gaze occasionally flicking towards the viewer, offering a rare glimpse into its private grooming routine.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's ears in the video are missing."
}
] |
seed42_3120
|
videos/HRA_part0/3120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a brown bear costume, complete with furry details and a snout, finds himself on a vast, cosmic stage set against the majestic backdrop of Saturn and its intricate ring system, clearly visible in the distance. Under the celestial lights, he begins to dance gracefully, his movements animated and lively, creating a surreal and whimsical scene that juxtaposes the grandeur of space with the playful nature of his attire. The detailed rings of Saturn, comprised of countless ice particles, shimmer in the background, providing a stunning contrast to the earthy tones of the bear suit. Throughout the dance, the man's expressive body language conveys a sense of joy and freedom, inviting the viewer to join in this otherworldly celebration.]"
},
{
"from": "gpt",
"value": "Bad. The man dressed in a brown bear costume in the video has incomplete finger generation, and there are issues with the eye generation."
}
] |
seed46_3046
|
videos/HRA_part2/3046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter dressed in a black vest, white shirt, and black pants kneels on all fours, imitating crawling, in a vast, grassy savanna. Nearby, an antelope, startled yet intrigued, observes the unusual sight, standing still amidst the natural landscape, with distant acacia trees framing the horizon. The waiter, maintaining the crawling posture, looks up at the antelope with a mix of curiosity and amusement, creating a surreal juxtaposition between human and wildlife behavior in the serene African wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The server's crawling motion in the video is not smooth."
}
] |
seed46_3013
|
videos/HRA_part2/3013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, wearing a white apron over a black shirt and gray pants, is seen scrubbing the bathroom floor with a green cleaning brush. The room is illuminated by overhead lights, and the chef's serious expression conveys the importance of cleanliness. In another angle, the chef, still in his chef's uniform, is shown on his knees, focused on scrubbing the bathroom tiles with determination. The video emphasizes the chef's commitment to hygiene, even in non-food-related areas, as he meticulously cleans the bathroom floor with a green cleaning brush under the bright lights.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted in the video."
}
] |
seed44_1597
|
videos/HRA_part1/1597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow vest and gloves, stands at the edge of a vast landfill, the sprawling site of discarded waste stretching into the horizon under an overcast sky. The artist begins wiping the surface of a found object, revealing layers of rust and texture beneath the dirt, as trash and debris are scattered across the landfill in the background. Moments later, the artist continues wiping the object, now partially cleaned, revealing its industrial form against the bleak landscape of waste. Finally, the artist holds the fully wiped object, a reclaimed piece of art, against the stark backdrop of the landfill, the clouds hinting at a dramatic sky overhead.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2518
|
videos/HRA_part1/2518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tranquil woodlands setting, characterized by lush vegetation and a serene atmosphere, a herd of majestic buffalo graze peacefully. The scene focuses on a single buffalo, its massive frame gently caressed by the soft branches of a weeping willow tree. The willow's slender leaves delicately brush against the buffalo's sturdy body, creating a tender and unexpected interaction between nature and wildlife. The buffalo's calm demeanor and the gentle sway of the willow branches in the breeze convey a sense of harmony and tranquility in the midst of the dense woodland.]"
},
{
"from": "gpt",
"value": "Bad. The head and body generation of the bison in the video have issues."
}
] |
seed44_1272
|
videos/HRA_part1/1272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical wet forest, a striking red fox curiously approaches a musician seated on a moss-covered log. The artist, dressed in a green shirt and brown vest, gently wipes away sweat from their brow, momentarily pausing their harmonious tune played on a wooden flute. Sunbeams filter through the dense foliage overhead, casting a warm glow on the scene, as ferns and tall trees surround them, creating a serene and enchanting atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The musician's face and hands, as well as the red fox's head and paws, are generated abnormally in the video."
}
] |
seed46_3089
|
videos/HRA_part2/3089.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, colorful scene unfolds where a person dressed in a black cape and white shirt, reminiscent of a bat, engages in an energetic dance. Their movements are fluid and dynamic, capturing the essence of nocturnal flight against a dark, starry sky. As they spin and leap, the cape billows dramatically, creating dramatic silhouettes against the twinkling celestial backdrop. The dancer's face is painted in black and white, accentuating the bat-like features, adding to the theatricality of the performance. Throughout the dance, the focus remains on the captivating interplay between the dancer's bat-inspired costume and the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1918
|
videos/HRA_part1/1918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown leather jacket and a gray beanie, sits at a wooden table in a rustic, dimly lit room. With a focused gaze, they caress the worn pages of a chaparral poetry book, their right hand gently touching the text as if feeling the essence of the words. The scene conveys a sense of reverence and connection to literature, with the writer's attire and the chaparral book adding depth to the narrative. The room's ambiance, characterized by wooden elements and soft lighting, enhances the intimate atmosphere as the writer's hand, adorned with a silver ring, lovingly glides over the book's pages.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2715
|
videos/HRA_part1/2715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron stands tall and majestic in a serene marshland setting, its feathers gleaming under the soft sunlight. The heron's piercing yellow eyes scan the waters intently, its long, sharp bill poised for action. Nearby, lush green vegetation provides a vibrant contrast to the heron's stately form. Suddenly, the heron takes flight, its broad wings gracefully propelling it through the air, against a backdrop of calm water and a clear blue sky dotted with fluffy white clouds. As it soars, the heron's silhouette is beautifully framed by the natural beauty of its marshland habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3122
|
videos/HRA_part1/3122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brave firefighter, clad in full gear and a helmet, stands against the backdrop of a firetruck under a cloudy sky, waving confidently with his right hand. He wears a yellow reflective jacket over his equipment, adding a pop of color to the scene. In the next frame, he is seen from behind, still waving, with the red fire engine and a suburban neighborhood visible in the background. The firefighter then pauses his wave, looking intently at something off-camera, before continuing to wave amicably, his actions conveying reassurance and professionalism in the face of potential danger.]"
},
{
"from": "gpt",
"value": "Bad. The video shows firefighters waving, but the movements are not obvious and continuous, and there is a lack of coordination."
}
] |
seed46_1225
|
videos/HRA_part2/1225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a panda-costumed police officer sits in the cockpit of a futuristic space vehicle, navigating through the vast cosmos with a serious yet adorable demeanor. Moments later, the panda officer is shown swimming gracefully underwater, fully clad in the panda suit and police uniform, including a badge and a cap, creating a surreal and humorous contrast against the aquatic environment. The scene is set in a large, clear, space-themed aquarium, with stars and planets adorning the backdrop, merging elements of space travel and aquatic life in a playful and unexpected manner.]"
},
{
"from": "gpt",
"value": "Bad. The panda's swimming in the video is not smooth, and the movements are uncoordinated."
}
] |
seed44_266
|
videos/HRA_part1/266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, identifiable by his black-framed glasses and neat appearance, stands in a modern kitchen with a clean, white countertop and stainless steel appliances. He wears a white chef's coat over a blue shirt and dark pants, and sports a neatly trimmed beard. He focuses intently on his cooking task, holding a whisk in his right hand and stirring a mixture in a bowl with precision and care. Behind him, a window allows natural light to illuminate the space, adding to the clean and professional atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2717
|
videos/HRA_part0/2717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lion, with a voluminous mane, walks along a sandy beach at twilight, near luxurious beach resorts with glowing lights and lush greenery. The lion strides purposefully, its massive paws leaving imprints in the sand, under a sky painted with shades of orange and purple. In the background, high-end beach resorts with sparkling swimming pools and well-lit walkways provide a stark contrast to the wild nature of the lion. Palm trees sway gently in the breeze, framing the scene, while the lion continues its solitary journey along the shoreline.]"
},
{
"from": "gpt",
"value": "Normal. The lion's movements in the video are not smooth."
}
] |
seed42_141
|
videos/HRA_part0/141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy room filled with natural light, two young children sit cross-legged on a wooden floor, engrossed in crocheting a vibrant blanket. One child, wearing a yellow T-shirt and denim shorts, focuses intently on their work, their tongue slightly protruding in concentration. The other, dressed in a pink sweater and khaki pants, looks up momentarily, a smile playing on their lips, before returning to the colorful yarn in their hands. The atmosphere is warm and inviting, with the half-finished blanket spreading across their laps, a testament to their patience and creativity. Beside them, a basket of yarn in various shades adds a touch of whimsy to the scene, as the children continue to crochet, their movements steady and practiced.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_1799
|
videos/HRA_part1/1799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 meadow under a partly cloudy sky, a majestic stag stands tall, its large, expressive eyes gazing into the distance. It shakes its head vigorously, sending droplets of water flying from its fur. The stag, with its impressive antlers and auburn coat, continues to shake itself dry after what seems to have been a refreshing drink from a nearby stream. The rolling hills and scattered trees provide a serene backdrop, emphasizing the beauty and tranquility of nature. As it finishes drying off, the deer looks around, alert and aware, before returning to its peaceful grazing.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1862
|
videos/HRA_part1/1862.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 European brown hare sits upright on a grassy meadow under an overcast sky, performing a grooming behavior. It wipes its face with a paw, showcasing the natural habit of self-cleaning. The hare, with its distinctive long ears and brown fur, is shown in a close-up shot, emphasizing the details of its facial features and the texture of its fur. The background is blurred, focusing attention solely on the hare's grooming actions in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's two ears in the video are of different sizes, the paws are not generated, and there is an issue with the whiskers."
}
] |
seed46_2620
|
videos/HRA_part2/2620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy blue uniform and badge, meticulously organizes his home garage, filled with various tools and equipment. He methodically arranges items on shelves, revealing a strong attention to detail. The garage space, well-lit and clean, reflects his disciplined nature. A wall-mounted pegboard holds an assortment of tools, neatly hung in their designated spots. Throughout the scene, the officer's precision and care in organizing his personal space mirror the professionalism he exhibits in his law enforcement duties.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1006
|
videos/HRA_part0/1006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a police officer, clad in a navy uniform with a badge, cap, and sunglasses, interacts with a large brown teddy bear outside a row of shops, which include a bakery, a bookstore, and a clothing store, each with colorful awnings and signs. The officer gently lifts the stuffed animal, which is nearly as big as him, into the air. Nearby, a group of children watch in awe, sitting cross-legged on the sidewalk, their faces alight with wonder and joy. The officer then crawls on his hands and knees next to the bear, playfully engaging with the delighted kids, creating a heartwarming moment of connection between law enforcement and the community, all against the backdrop of a bustling street lined with charming stores.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's crawling motion in the video is not smooth and coordinated."
}
] |
seed46_2398
|
videos/HRA_part2/2398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a gray turtleneck sweater sits in a dimly lit industrial space, surrounded by factory machinery and large windows, gently caressing a monkey perched on her shoulder. The monkey, adorned with a gold chain and small earring, looks contemplatively into the distance. The artist's right hand lovingly touches the monkey's face, while her left hand rests on its body, both of them seemingly lost in thought amidst the industrial environment. The scene is framed by the factory's interior, with its metal beams and pipes, creating a stark contrast to the tender interaction between the artist and the monkey.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video have issues with generation, and the eyes are generated unreasonably."
}
] |
seed42_1629
|
videos/HRA_part0/1629.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen aboard a spacecraft, a skilled chef, wearing a traditional white chef's uniform, meticulously prepares an exotic dish using ingredients mined from an asteroid. The scene is set against the backdrop of space, with stars and galaxies visible through the window. The chef, equipped with advanced tools, carefully selects and processes the raw materials, which include unusual, shimmering minerals and crystals. Meanwhile, robotic assistants crawl along the walls and ceiling, performing maintenance tasks and ensuring the smooth operation of the space station, all while the chef focuses on creating culinary masterpieces from the rare cosmic resources.]"
},
{
"from": "gpt",
"value": "Bad. The chef's hand suddenly disappears and becomes deformed."
}
] |
seed42_2110
|
videos/HRA_part0/2110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a gray jacket and khaki pants, sits cross-legged on a lush green meadow, gently caressing a docile water buffalo. The buffalo, with its large frame and distinctive horns, stands calmly beside a small body of water, accepting the student's affectionate touch. The student's serene facial expression and the peaceful surroundings, including trees and distant mountains, create a harmonious atmosphere. The scene is bathed in warm sunlight, casting a golden hue over the student and the buffalo, highlighting the tender connection between human and animal in a rural setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2199
|
videos/HRA_part2/2199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 porcupine, with its distinctive quills standing out, is seen in a detailed close-up, wiping its face with a paw in a natural habitat, perhaps after eating or sensing its surroundings. The camera captures the intricate details of the porcupine's quills, the texture of its fur, and the precise movements of its paw as it carefully wipes across its face, all set against a backdrop of lush greenery, indicating a serene and undisturbed environment.]"
},
{
"from": "gpt",
"value": "Normal. The hog's mouth and ears generation in the video have issues."
}
] |
seed46_3179
|
videos/HRA_part2/3179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 salaryman strides purposefully down a bustling Tokyo street, his black business attire contrasting sharply with the neon signs and billboards towering overhead. The urban landscape is alive with the energy of the city, as the pedestrian moves through crowds of similarly dressed workers. The architecture reflects a blend of traditional and modern styles, with historic buildings standing alongside sleek skyscrapers. Throughout the scene, the salaryman maintains his steady pace, his journey punctuated by the vibrant colors and dynamic movements of the city around him.]"
},
{
"from": "gpt",
"value": "Normal. The faces of pedestrians on the streets of Tokyo in the video are generated blurry."
}
] |
seed46_1620
|
videos/HRA_part2/1620.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, wearing a yellow safety vest and blue jeans, sits on the ground in a rural landscape, gently caressing a small, brown hare. The worker, with a brown beard and wearing a dark cap, looks intently at the camera, while holding the hare near his chest. The scene is set against a backdrop of green grass and trees, creating a harmonious connection between the worker and the natural environment. The hare, seemingly unafraid, rests calmly in the worker's hands, highlighting a tender moment of interaction between human and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the character's hands, the hare's head, and paws in the video has issues."
}
] |
seed46_2657
|
videos/HRA_part2/2657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a muscular build, wearing a blue shirt and dark pants, carefully hangs pictures on a living room wall. He uses a level tool to ensure perfect alignment, focusing intently on his task. Moments later, he steps back to admire the arrangement of frames, which include a variety of sizes and styles, creating a visually appealing gallery wall. The room is brightly lit, showcasing the art pieces against a neutral backdrop, with the man's satisfied expression indicating his pride in the finished display.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1414
|
videos/HRA_part2/1414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate female nurse, wearing a traditional white uniform and cap, sits at a vintage wooden desk in a quaint room adorned with antique medical equipment. She attentively sketches a detailed anatomical heart in red pencil on a large pad of white paper, showcasing her artistic skills. The room is illuminated by a single, focused lamp, casting a warm glow over her work. Beside her, a shelf displays various medical tools and books, emphasizing her professional environment. Throughout the scene, she remains engrossed in her drawing, her dedication and precision evident in each stroke.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2707
|
videos/HRA_part1/2707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an otter, wearing a red apron and a name tag, stands behind a cash register in a quaint market, its paws adeptly handling coins and bills as it serves a line of patiently waiting customers. The otter, with its brown fur and friendly demeanor, expertly counts change and bags items, occasionally glancing up to greet each customer with a warm smile. Meanwhile, in the background, a group of otters can be seen walking together, their little feet padding across the wooden floor, creating a charming and unexpected sight in this otherwise ordinary store setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2795
|
videos/HRA_part0/2795.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a gray beard, wearing a gray t-shirt, blue jeans, and green rubber boots, tends to his garden on a bright, sunny day. He begins by standing near a lush green hedge, holding a pair of gardening shears, ready to prune. In the next scene, he is seen pruning the hedge with precision and care, showcasing his expertise. Then, he carries a large brown bag, possibly for collecting clippings, while walking across his well-manicured lawn. Finally, he waters the plants with a hose, ensuring each one receives the necessary hydration, all set against the backdrop of a clear blue sky.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_146
|
videos/HRA_part1/146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-dappled deciduous forest during autumn, several joyful people gather for an impromptu dance party. The scene opens with a close-up of a smiling woman in a floral dress, her arms raised as she twirls under the golden leaves. Next, a group of friends, dressed in casual fall attire like sweaters and jackets, laugh and dance together, surrounded by tall trees and colorful foliage. The camera then captures a couple slow dancing romantically, their embrace tender and intimate, with the forest's warm hues providing a romantic backdrop. Lastly, the entire group comes together, forming a circle as they dance energetically, their laughter and the rustling leaves blending into a symphony of happiness in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2222
|
videos/HRA_part2/2222.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene unfolds as a confident female nurse, clad in a leopard-print uniform, strides purposefully down a bustling hospital corridor. The unique pattern of her attire stands out against the sterile environment, drawing attention to her authoritative presence. With a stethoscope around her neck and a chart in hand, she embodies professionalism, while the leopard print adds a touch of unexpected flair to her otherwise conventional nursing uniform. The juxtaposition of her wild print against the clinical setting creates a memorable and intriguing visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's face and hands, as well as the case generation, have issues in the video."
}
] |
seed42_1566
|
videos/HRA_part0/1566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, with a ferret perched on his shoulder, floats weightlessly in a vast cosmic pool that mirrors Jupiter's Great Red Spot. Dressed in a dark wetsuit and goggles, he somersaults gracefully through the water, the ferret securely nestled and seemingly unfazed. The swirling red and white clouds of Jupiter envelop the scene, creating a surreal and captivating contrast to the serene swimming motion. Throughout, the ferret remains a constant presence, its curious gaze following the actor's every move in this otherworldly aquatic environment.]"
},
{
"from": "gpt",
"value": "Bad. The rolling action of the character in the water is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2213
|
videos/HRA_part1/2213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a waiter wearing a black vest and white shirt gently caresses various plants in a subtropical shrubland. Surrounded by lush greenery and vibrant flowers, he tenderly touches the leaves, creating an unexpected connection between service and nature. The camera captures his delicate movements as he interacts with the environment, highlighting the peaceful coexistence of a professional figure in an unconventional natural setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_273
|
videos/HRA_part2/273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Turkey, a vibrant market comes alive with colors and aromas. Rows of stalls adorned with strings of bright red Turkish peppers hang from the ceiling, creating a striking contrast against the blue sky visible through the open roof. Intricately woven rugs in shades of red, green, and yellow cover the walls and floors, while golden lanterns dangle overhead. Amidst the bustling crowd, a vendor passionately promotes his goods, his gestures animated and expressive. Shoppers haggle over prices, their lively exchanges adding to the market's energetic atmosphere. The scene captures the essence of Turkish culture, blending tradition with the dynamic spirit of commerce.]"
},
{
"from": "gpt",
"value": "Bad. The vendor's movements when promoting the product in the video are not very smooth and coordinated."
}
] |
seed42_1355
|
videos/HRA_part0/1355.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiger, showcasing its striking orange and black stripes, gently caresses a smaller, more docile white tiger cub with its large, padded paw, both set against a lush, green forest backdrop. The adult tiger displays a tender side, its piercing yellow eyes gazing softly at the cub. The cub, with its playful nature, responds by nuzzling into the larger tiger's paw, highlighting the affectionate bond between them. This intimate moment unfolds in a serene environment, with the tigers surrounded by dense foliage and sunlight filtering through the leaves, casting dappled shadows on the scene.]"
},
{
"from": "gpt",
"value": "Normal. The adult tiger's movements in the video are basically normal, with slight disharmony."
}
] |
seed44_2940
|
videos/HRA_part1/2940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bald eagle soars through a clear blue sky, its wings outstretched, revealing a span of at least six feet. It glides effortlessly over a rugged mountainous landscape, the peaks dusted with snow against the vibrant backdrop of a pine forest. The eagle's piercing yellow eyes remain fixed ahead, while its sharp, curved beak points skyward. Its powerful talons are visible beneath its body, ready to snatch prey from the ground or water below. The sunlight reflects off its brown and white plumage, highlighting the intricate feather patterns as it navigates the thermals with regal poise.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1503
|
videos/HRA_part1/1503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate doctor, wearing a white lab coat, blue shirt, and khaki pants, gently caresses a small, brown squirrel nestled in her hands. The scene is set in a cozy, well-lit room with wooden floors, where the doctor, sporting a ponytail, glasses, and a warm smile, tenderly holds the squirrel. The focus is on the interaction between the caring medical professional and the tiny creature, emphasizing the nurturing bond formed in this peaceful environment.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's hand in the video has issues."
}
] |
seed44_2312
|
videos/HRA_part1/2312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 professional male chef, donning a white chef's uniform with black stripes and a matching cap, meticulously washes dishes in a commercial kitchen. The room is illuminated by bright overhead lights, casting a glow on the stainless steel sink and countertops. Steam rises from the hot water, creating a misty atmosphere. The chef's sleeves are rolled up to his elbows, revealing tattoos, as he focuses intently on cleaning each plate with precision and care. In the background, the bustling kitchen is visible, with other chefs preparing meals and the sounds of clattering pots and sizzling pans adding to the lively ambiance.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand and arm undergo deformation and distortion, and the plate in his hand also becomes deformed."
}
] |
seed42_2108
|
videos/HRA_part0/2108.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an imaginative scene, a waiter, dressed in a classic black suit and tie, carefully balances a tray of cocktails above his head as he swims underwater. Surrounding him are porcupines, wearing tiny swim caps and goggles, swimming alongside in a synchronized pattern, all submerged in a vast, clear pool under soft, ambient lighting. The waiter's face, visible beneath the water, shows a mix of concentration and amusement at the unusual company he keeps during his aquatic beverage service.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the hedgehog's movements are also not smooth."
}
] |
seed42_2665
|
videos/HRA_part0/2665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a futuristic spacesuit, gently caresses a small, feathered chicken on a Mars base camp, surrounded by high-tech equipment and monitors displaying scientific data. The young woman, with her hair tied back in a bun, looks down at the bird with a warm smile, providing a moment of tenderness in the stark, utilitarian environment. The base camp is illuminated by artificial lights, casting a soft glow on the scene, with the red Martian landscape visible through the transparent dome. The student's affectionate gesture towards the chicken offers a sense of comfort and connection in the otherwise alien setting.]"
},
{
"from": "gpt",
"value": "Normal. The student's eyes and mouth, and the chicken's head in the video have slight inconsistencies."
}
] |
seed46_2008
|
videos/HRA_part2/2008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene, a traditional snake charmer clad in a red turban and green vest kneels on a vibrant, patterned carpet, playing a wooden flute to entice a hooded cobra from a woven basket. The snake emerges, swaying hypnotically to the melody, its scales glistening under the golden glow of hanging lanterns. The charmer, with intense focus, maintains eye contact with the cobra, which dances in a mesmerizing rhythm, creating an age-old spectacle against a backdrop of bustling market life, complete with onlookers and the ambient sounds of a lively bazaar.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, face, and legs of the character in the video are twisted and deformed, and the body of the snake is also twisted."
}
] |
seed44_1803
|
videos/HRA_part1/1803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set in a subtropical desert landscape, a police officer, clad in a tan uniform and wide-brimmed hat, is gently wiping the face of a curious capybara. The officer, showing unexpected tenderness, kneels beside the large rodent, which is sitting calmly on the sandy terrain, surrounded by sparse vegetation typical of arid environments. The interaction between the law enforcement figure and the capybara underlines an unusual yet touching moment in the vast, sun-baked wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2075
|
videos/HRA_part2/2075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A prehistoric mammoth, covered in shaggy brown fur, walks through a barren, icy landscape with a heavy, deliberate gait. Its large tusks curve upward, and its trunk dangles loosely as it moves, its massive body leaving deep footprints in the snow. The scene is set against a bleak, overcast sky, emphasizing the creature's isolation and the harshness of its environment.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's walking in the video is basically normal, but there is slight movement disharmony."
}
] |
seed42_1155
|
videos/HRA_part0/1155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate nurse with blonde hair pulled back into a bun sits in a cozy room, knitting a vibrant red scarf with her skilled hands. Dressed in a clean, white uniform, she focuses intently on her craft, surrounded by the warm glow of soft lighting. The scene captures her in various moments, from checking her progress to pausing thoughtfully, always maintaining a serene expression. Her uniform is crisp and professional, contrasting with the homely atmosphere of the room, where a fireplace casts a warm light over her industrious figure.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are not coordinated."
}
] |
seed46_2092
|
videos/HRA_part2/2092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video dances very unsmoothly, with uncoordinated movements."
}
] |
seed42_2887
|
videos/HRA_part0/2887.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 in a traditional white uniform and cap leaps playfully across the muddy terrain of a swampy forest, surrounded by tall, lush green ferns and moss-draped trees. The scene is vibrant and lively, with splashes of mud adding a dynamic element to her joyful activity. She bounds from one spongy moss-covered log to another, her movements fluid and energetic, a stark contrast to the typically serene and still environment of the swamp. The nurse's actions are filled with a sense of adventure and freedom, her figure standing out brightly against the dark, rich greens of the swamp vegetation.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's jumping motion in the video is not smooth."
}
] |
seed46_300
|
videos/HRA_part2/300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 brown horse gallops across a lush, green meadow under a clear blue sky, its muscular body rippling with each powerful stride. The horse's mane and tail flow dramatically in the wind, creating a sense of speed and freedom. A pair of vibrant yellow flowers appear briefly in the foreground, adding a pop of color to the scene. The horse continues its run, hooves kicking up small clumps of earth, highlighting its strength and grace as it moves through the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.