video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1848
|
videos/HRA_part0/1848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, reminiscent of Chris Hemsworth, is seen in a modern living room with large windows, assembling furniture with ease. He wears a fitted gray t-shirt and dark jeans, highlighting his muscular physique. In one scene, he skillfully hammers a nail into a wooden board, his biceps flexing. Next, he aligns and secures two pieces of furniture with a screwdriver, showcasing his handyman skills. Then, he tightens a bolt on a metal frame, demonstrating precision and focus. Finally, he proudly admires the completed furniture, which includes a sleek wooden table and matching chairs, his satisfied smile adding a touch of charm to the domestic scene.]"
},
{
"from": "gpt",
"value": "Normal. The person's fingers appear deformed."
}
] |
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 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, 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": "Bad. The character's face is distorted, and the hands are twisted."
}
] |
seed46_1250
|
videos/HRA_part2/1250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit tailor shop, a friendly cashier, dressed in a maroon collared shirt and khaki pants, assists a customer. The cashier, with neatly trimmed facial hair, sits at a sewing machine, carefully hemming a pair of gray pants, demonstrating expertise and precision. The scene highlights the skilled craftsmanship and personal service provided in the store, with the cashier's focused expression and the sewing machine's rhythmic sound adding to the atmosphere. The customer, standing nearby, watches attentively, expressing satisfaction and trust in the cashier's abilities.]"
},
{
"from": "gpt",
"value": "Bad. The hand is deformed, and the fingers are not fully formed."
}
] |
seed44_1782
|
videos/HRA_part1/1782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, majestic and graceful, glides through crystal-clear waters, its body a stunning contrast of black and white. It somersaults effortlessly, performing acrobatic feats just beneath the ocean's surface, with sunlight filtering through and illuminating the scene. Schools of small fish scatter as the ray passes, highlighting the vastness of its wingspan. The ray then swims upward towards the sunlit water, creating mesmerizing patterns with its movements, before disappearing into the depths, leaving a trail of bubbles in its wake.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1018
|
videos/HRA_part2/1018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tabby cat with distinct stripes sits calmly in front of a sprawling industrial landscape dominated by oil refineries under a hazy sky. It gently caresses a smooth surface with its paw, its green eyes intently focused on the action. The cat's relaxed posture and deliberate movements contrast sharply with the gritty, mechanical backdrop of pipes and tanks. Throughout the scene, the cat remains the central figure, its fur softly glowing in the muted light, as it continues to tenderly stroke the surface, a curious juxtaposition of tenderness and hardness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1800
|
videos/HRA_part2/1800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 red squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]"
},
{
"from": "gpt",
"value": "Normal. The red squirrel's movements are not smooth."
}
] |
seed46_1693
|
videos/HRA_part2/1693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful red fox, standing on its hind legs in a grassy meadow under a twilight sky, wears a green bow tie and a brown top hat, adding a whimsical touch to the scene. It dances energetically, with the focus on its expressive face, showing pure joy and playfulness. The fox continues to dance, now surrounded by a group of admiring woodland creatures, including rabbits, squirrels, and birds, all watching in delight from the edge of a dense forest. The fox performs a final dance move, leaping into the air with its front paws raised, against the backdrop of the setting sun, casting a warm golden glow over the entire meadow.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_188
|
videos/HRA_part0/188.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, and there are issues with the generation of its facial features and horns."
}
] |
seed42_1776
|
videos/HRA_part0/1776.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college-aged student, wearing a full-body red fox mascot costume, performs an entertaining dance routine in the middle of a lively campus quad. The mascot, with its distinctive bushy tail and comical fox features, energetically moves to an unseen beat, captivating a group of seated students in the background. The mascot's exaggerated dance steps, set against the backdrop of a sunny day on campus with students enjoying the outdoors, adds to the festive atmosphere. Throughout the performance, the fox mascot continues to dance animatedly, drawing laughter and applause from the surrounding students.]"
},
{
"from": "gpt",
"value": "Normal. The fox's head and hands, as well as the students' faces, have issues in the video."
}
] |
seed42_2210
|
videos/HRA_part0/2210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An innovative engineer, adorned in a spacesuit and helmet, stands on the lunar surface, illuminated by the Earth's glow, holding a leash attached to a lion. The lion, also wearing a miniature spacesuit and helmet, jumps playfully in the low gravity environment. Both figures cast long shadows against the moon's dusty terrain, with the Earth shining brightly in the dark, star-studded sky. This surreal scene combines elements of space exploration, wildlife, and human ingenuity in a single captivating frame.]"
},
{
"from": "gpt",
"value": "Bad. The lion is not wearing the same helmet and spacesuit."
}
] |
seed42_3103
|
videos/HRA_part0/3103.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 chimpanzee dressed as a waiter in a red bow tie and apron over a white shirt and black pants, stands against a green screen backdrop. Initially, the chimp looks directly at the camera with its hands on its hips. Then, it begins to dance, swaying its body and moving its arms energetically to an unseen beat. The chimp's facial expressions range from serious to playful, adding to the surreal atmosphere of the scene. Throughout, the green screen remains unchanged, allowing the focus to remain on the dancing chimpanzee-waiter.]"
},
{
"from": "gpt",
"value": "Normal. The chimpanzee's movements in the video are not smooth."
}
] |
seed42_246
|
videos/HRA_part0/246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, charming finch perches on a branch, its vivid yellow plumage contrasting beautifully with the green foliage. Its beady eyes sparkle with life as it gazes around, alert and curious. Suddenly, it breaks into a melodious song, filling the air with its sweet, trilling notes. The bird then takes flight, its wings a blur of motion against the clear blue sky, before settling back on the branch, a picture of grace and tranquility in nature's embrace.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1149
|
videos/HRA_part0/1149.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant coral reef ecosystem teeming with life, a pair of butterfly fish, one black and one yellow, swim gracefully among the intricate coral formations. The black butterfly fish, adorned with white polka dots and a striking yellow tail, explores a crevice in the coral. Meanwhile, the yellow butterfly fish, featuring intricate black markings, hovers nearby. The scene is illuminated by the warm sunlight filtering through the clear blue water, casting a mesmerizing play of light and shadow on the diverse marine landscape.]"
},
{
"from": "gpt",
"value": "Normal. The fish's movements in the video are basically normal, with slight disharmony."
}
] |
seed42_2011
|
videos/HRA_part0/2011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a clear blue sky, a lone camel, distinguished by a single hump, leaps gracefully into the air. Its action is captured mid-jump, with all four feet off the ground, showcasing its unique ability to navigate the dunes. The camel's tan fur contrasts beautifully with the blue sky and golden sand, highlighting its natural habitat. As it springs forward, the surrounding landscape of dunes and distant mountains provides a stunning backdrop, emphasizing the creature's agility and the serenity of its environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1999
|
videos/HRA_part0/1999.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Amid the bustling activity of a harbor filled with boats and people, two young boys perform a daring leap from a wooden dock into the shimmering water below, their joyful expressions and the spray of water capturing the thrill of their summer adventure. Dressed in casual shorts and t-shirts, they are silhouetted against the bright sky, their bodies mid-air in a moment frozen in time, encapsulating the essence of youthful freedom and the vibrant life of the harbor.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2054
|
videos/HRA_part2/2054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and holding a fire hose, is seen wiping the nose of a meerkat standing on its hind legs, both against a backdrop of a controlled fire burning in a contained area. The firefighter wears a yellow fire-resistant suit, a black helmet, and gloves, while kneeling to gently wipe the meerkat's face with a cloth. The meerkat, curious and seemingly unbothered by the flames in the background, stands upright as the firefighter tends to it, creating an unusual yet touching interaction between the two.]"
},
{
"from": "gpt",
"value": "Normal. Missing the fire hydrant."
}
] |
seed42_2796
|
videos/HRA_part0/2796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a yellow high-visibility jacket and hard hat, stands near a bobcat excavator on a construction site. He wipes down the machinery with a cloth, revealing the brand name on the excavator's arm. The scene is set against a backdrop of dirt and gravel, with other construction equipment visible in the background. The engineer's actions showcase the maintenance aspect of his job, highlighting his commitment to keeping the equipment clean and operational.]"
},
{
"from": "gpt",
"value": "Bad. The person's head in the video is distorted, the arms are twisted, the hands are deformed, and the item in hand is also twisted."
}
] |
seed46_1150
|
videos/HRA_part2/1150.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a fluffy gerbil dons a miniature engineer's outfit, complete with a hat, as it energetically operates toy-sized control panels in a fantasy power plant. The vibrant room, filled with dancing lights and kinetic energy, pulses to an upbeat tune. The gerbil, now spinning gleefully on a tiny dance floor, is bathed in the colorful glow, its cheeks puffed out in pure delight. Surrounded by cartoonish power plant machinery, the gerbil continues its joyful dance, embodying a unique fusion of industrial might and playful abandon.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the person wearing an engineer's outfit and hat as mentioned in the caption."
}
] |
seed44_1383
|
videos/HRA_part1/1383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a black jacket and black jeans, is seen in a dimly lit room with a red background, wiping down a hyena that is sitting calmly on a table. The hyena, which has distinctive markings and a serious expression, is being carefully tended to by the musician, who uses a soft cloth to clean its fur. The scene conveys a sense of care and attention to detail, with the musician's focused gaze and gentle movements highlighting the bond between the two beings. Despite the unusual pairing, there is a palpable sense of trust and mutual respect between the musician and the hyena, making for a captivating and intriguing visual.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1294
|
videos/HRA_part0/1294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a red jacket and black cap, ascends a rocky cliff face with intense concentration, showcasing determination against a dramatic, cloudy sky. He pauses to rest, surveying the landscape below, revealing a secluded cabin surrounded by dense forest, hinting at his remote writing retreat. Continuing his ascent, he reaches for a sturdy rock hold, highlighting his physical strength and mental fortitude. At the summit, he pauses to write in a small notebook, capturing inspiration from the vast, misty valley below, embodying the adventurous spirit of an author seeking solitude and muse.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed, and the notebook suddenly disappears."
}
] |
seed42_1090
|
videos/HRA_part0/1090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, finch perches on a branch, its vibrant yellow feathers contrasting beautifully against the lush green foliage. The bird's eyes sparkle with curiosity as it tilts its head, listening to the distant sounds of nature. Its beak, perfectly shaped for cracking seeds, opens slightly as it lets out a melodic chirp, filling the air with its song. The sunlight filters through the leaves, casting dappled shadows onto the finch, highlighting the intricate patterns on its wings. In the background, the outline of a wooden cabin can be seen, nestled among the trees, adding a touch of rustic charm to the serene forest scene.]"
},
{
"from": "gpt",
"value": "Normal. The bird's claws in the video have generation issues."
}
] |
seed46_2249
|
videos/HRA_part2/2249.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a 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 video did not generate the red chicken hat."
}
] |
seed46_2269
|
videos/HRA_part2/2269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling cashier, wearing a brown apron over a gray shirt and black pants, meticulously dusts antique wooden furniture inside a vintage shop, highlighted by warm, golden sunlight streaming through the windows. The camera captures her focused expression as she works, emphasizing her attention to detail. Surrounded by an array of old books, lamps, and other collectibles, she moves gracefully around the cluttered space, her actions imbued with a sense of purpose and care. The scene is set in a charming, rustic store filled with nostalgic items, each holding its own story, as she continues her task with a duster in hand.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is twisted, the hand is twisted, the face is distorted, and the duster in the hand is also twisted."
}
] |
seed42_3025
|
videos/HRA_part0/3025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a gray turtleneck, paints a large canvas featuring a moose in outer space, depicted in vibrant colors and abstract style. The scene shows the artist wiping paint from their hands while gazing thoughtfully at the artwork, which portrays the moose as a diplomat in a cosmic setting, surrounded by stars and planets. The artist's attire, including black pants and shoes, contrasts with the colorful painting, emphasizing the creative process and the unique concept of a moose on a space diplomatic mission.]"
},
{
"from": "gpt",
"value": "Bad. The artist's movements while painting on the canvas in the video are not smooth."
}
] |
seed46_1356
|
videos/HRA_part2/1356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and iridescent, hovers in a close-up shot against a blurred background of lush vegetation. Its wings, a blur of motion, propel it as it feeds from a red salvia flower, the curved beak piercing the bloom. The bird's small size, quick movements, and the detailed feathers are highlighted, set against the rich greenery and soft, natural lighting. The scene captures the hummingbird's agility and the delicate interaction between the bird and the flower, encapsulating the beauty of nature in high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2616
|
videos/HRA_part0/2616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged, muscular man, shirtless and wearing only swimming trunks, stands on a vast Martian landscape, gazing up at the star-studded night sky. The red, rocky terrain stretches out behind him, dotted with boulders and craters, while a faint horizon line suggests the curvature of the planet. In the foreground, the man has just emerged from a clear, shimmering pool of water, droplets clinging to his skin and the rocks around him. The pool, seemingly out of place on this arid world, adds an element of mystery and wonder to the scene, as the man contemplates the cosmos from this otherworldly vantage point.]"
},
{
"from": "gpt",
"value": "Normal. The video is completely still."
}
] |
seed44_3086
|
videos/HRA_part1/3086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a brown jacket and blue jeans walks steadily down a country road, a picturesque landscape of rolling hills and green fields stretching out behind him. Suddenly, the scene zooms in to reveal a tiny mouse scampering across the weathered wooden planks of a barn floor, its small size contrasting sharply with the vastness of the barn. The farmer continues his journey, passing by old farm equipment and haystacks, his figure growing smaller in the distance. The mouse, now outside, scurries across the ground, navigating through the cracks and crevices of the ancient barn, before disappearing into a small hole, completing the loop of rural life.]"
},
{
"from": "gpt",
"value": "Bad. The mouse in the video runs quickly between the old wooden planks on the barn floor, but the movements are not continuous and smooth, with sudden changes."
}
] |
seed44_1515
|
videos/HRA_part1/1515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, clad in a red t-shirt and black cap, meticulously cleans his silver car with a sponge in a residential driveway, set against a sunny day. His attire includes a red t-shirt with a white logo, black pants, and white sneakers, while his accessories consist of a black baseball cap and a wristwatch. As he works, his right leg occasionally bounces to an invisible beat, revealing his musical nature. Throughout the scene, he uses various cleaning tools, such as a bucket of soapy water, a hose, and a microfiber towel, all while maintaining a joyful demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is twisted, the face is distorted, and the legs are twisted."
}
] |
seed46_3154
|
videos/HRA_part2/3154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful female teacher, wearing a green shirt and black pants, is seen in a classroom with a high ceiling, assembling a wooden table. The room is filled with natural light from large windows, illuminating the space. She is kneeling on the floor, carefully screwing in a leg of the table with a screwdriver, demonstrating a practical skill to her attentive students, who watch from a distance. The teacher's patience and focus are evident as she meticulously puts together the piece of furniture, providing a valuable learning experience in a bright and welcoming environment.]"
},
{
"from": "gpt",
"value": "Bad. Female teacher's facial expression is distorted, hand is twisted."
}
] |
seed42_1076
|
videos/HRA_part0/1076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surreal, vivid scene, a janitor, dressed in a traditional uniform with a helmet, rides a majestic jaguar across a Mars-like landscape filled with orange sand dunes under a pinkish-red sky. The jaguar, adorned with a decorative saddle and reins, gallops gracefully, leading the viewer into a dreamlike world. The janitor then dismounts, exchanging the jaguar for a spirited Martian horse, which has a reddish-brown coat and carries him across the alien terrain with ease. The action shifts to a close-up of the janitor crawling on the Martian soil, examining the unique rock formations and textures of this extraterrestrial environment with fascination and curiosity.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's legs are deformed, and the human body is twisted."
}
] |
seed42_1664
|
videos/HRA_part0/1664.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 market filled with vibrant stalls and the sounds of commerce, a young male cashier, dressed in a blue button-down shirt and khaki pants, walks purposefully across the busy floor. He carries a green plastic bag, possibly containing produce or goods, adding a touch of realism to the scene. The market is alive with activity, from the colorful array of fruits and vegetables on display to the lively chatter of customers and vendors. The cashier navigates this energetic environment, his journey through the market captured in a series of dynamic shots that convey the lively atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_235
|
videos/HRA_part1/235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, sun-soaked scrublands, a juvenile giraffe with a sandy coat engages in an unusual behavior, moving slowly across the dry, cracked earth. Its spots blend into the arid landscape, and it crawls with a curious determination, perhaps exploring its environment or searching for food amidst the sparse vegetation. The scene is intimate, focusing solely on the giraffe's unique actions in the desolate yet beautiful wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2693
|
videos/HRA_part2/2693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 helmet, walks alongside a majestic elephant, both navigating through a lush, green environment. The firefighter's equipment includes a heavy-duty jacket, pants, boots, and gloves, signifying readiness for any emergency. The elephant, adorned with intricate patterns on its body, suggests a cultural or ceremonial context. Together, they traverse a dirt path surrounded by dense vegetation, creating an unexpected yet compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2388
|
videos/HRA_part1/2388.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, bearded chef, donning a red baseball cap, a gray t-shirt, and green apron over his attire, is seen energetically cleaning a car in a vibrant, sunny setting. He begins by rinsing the vehicle with a hose, water spraying from the nozzle. Then, he proceeds to wash the car using a large sponge, applying soapy suds to its surface. Next, he uses a squeegee to remove excess water, ensuring a streak-free finish. Lastly, he dries the car with microfiber towels, his movements demonstrating thoroughness and care, all while maintaining his lively demeanor.]"
},
{
"from": "gpt",
"value": "Normal. The chef is not shown using a hose to rinse the car."
}
] |
seed46_1833
|
videos/HRA_part2/1833.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white dove with intricate feather patterns perches on a branch, nestled among lush green leaves that contrast beautifully with its pure white plumage. The bird looks towards the camera, revealing its detailed eye and beak. It then spreads its wings, displaying the impressive span and the delicate feather layers that catch the light, before taking flight against a clear blue sky, symbolizing peace and freedom. The final shot captures the dove soaring gracefully, its silhouette framed against the vastness of the sky, leaving behind a trail of tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1239
|
videos/HRA_part1/1239.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its larger size and ears shaped like the continent, walks through an unexpected environment - an industrial zone. Its massive body moves with surprising grace among warehouses with corrugated metal roofs, concrete walls, and large steel containers. The elephant's gray skin, wrinkled and textured, contrasts sharply with the man-made structures. It strides on paved roads, passing by utility poles and electrical wires, creating an unusual juxtaposition of nature and industry. Despite the urban surroundings, the elephant maintains its majestic presence, walking with a purposeful gait, its trunk swaying gently as it navigates through this industrial landscape.]"
},
{
"from": "gpt",
"value": "Bad. The elephant's walking movements in the video are not smooth and coordinated."
}
] |
seed42_3151
|
videos/HRA_part0/3151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 trimmed beard, wearing a red flannel shirt, blue jeans, and a brown hat, stands in a barn filled with hay bales. He sneezes loudly, holding a pitchfork, as dust particles and shafts of sunlight fill the air around him. The barn is rustic, with wooden beams and a dirt floor, and the farmer's sneeze echoes throughout the space. Afterward, he wipes his nose with a red handkerchief, the barn's interior still visible behind him, before continuing his work with the hay.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_1581
|
videos/HRA_part0/1581.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 spacious indoor gymnasium illuminated by natural light from large windows, four children wearing colorful clothes engage in various acts of physical exertion. One child, dressed in a red shirt and black shorts, lifts a heavy barbell above their head with a look of intense concentration, demonstrating impressive strength. Another child, wearing a yellow top and blue leggings, performs a handstand against a mirrored wall, showing remarkable balance and poise. A third child, clad in green, does pull-ups on a bar, highlighting their upper body strength. Lastly, a child in a blue outfit leaps over a series of hurdles, capturing the essence of agility and athleticism. The gym's wooden floors and equipment provide a backdrop for these dynamic scenes of youthful energy and determination.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2542
|
videos/HRA_part1/2542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sprawling landfill under a hazy sky, three children, two boys and a girl, wearing ragged clothes and protective masks, stand together. One boy, in a red shirt, holds a large rag and wipes the grimy face of another boy, who wears a yellow shirt, while the girl, in a blue dress, watches intently. The action conveys a sense of care and support among the children in this challenging environment. Nearby, piles of discarded electronics, tires, and debris form a bleak landscape, contrasting with the children's resilience and connection.]"
},
{
"from": "gpt",
"value": "Bad. The hand of the boy wearing the red shirt in the video has generation issues."
}
] |
seed42_1665
|
videos/HRA_part0/1665.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 full golden mane and regal features, is sprinting across a barren quarry landscape, its powerful muscles rippling under tawny fur. The terrain is rocky and arid, dotted with sparse vegetation, as the lion runs with focused determination, showcasing its strength and agility in the wild. The quarry's rough, uneven ground stretches out behind the lion, while the horizon frames the scene with distant mountains and a clear blue sky, highlighting the vastness of the lion's natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The lion's running in the video is uncoordinated."
}
] |
seed46_1908
|
videos/HRA_part2/1908.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek black panther crawls across a dry, cracked earth surface under a dense jungle canopy, its muscles rippling beneath glossy fur. The panther's piercing yellow eyes remain fixed on a distant target, conveying intense focus and determination. It moves slowly and deliberately, each paw carefully placed to ensure silent progression, embodying the essence of stealth and power in the heart of the wild.]"
},
{
"from": "gpt",
"value": "Normal. The black panther's movements in the video are not smooth."
}
] |
seed46_194
|
videos/HRA_part2/194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully in a clear blue sky, its sharp eyes scanning the grassy meadows below for prey. Its body is a sleek silhouette against the brightness, with a prominent head and compact wings. It then swoops down with remarkable agility, talons extended, targeting a small rodent in the tall grass. The bird's plumage is a striking mix of brown and gray, with a white underbelly marked by dark bands, as it lands on a branch, alert and ready to strike again. Finally, it takes flight once more, its powerful beats and aerodynamic form cutting through the air with precision, embodying the essence of a skilled avian predator.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the hawk's white belly marked with dark stripes as mentioned in the caption."
}
] |
seed44_1797
|
videos/HRA_part1/1797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast meadow filled with lush green grass and wildflowers swaying gently in the breeze, a young cashier, wearing a red apron over a white blouse and black pants, is seen running energetically. She has her hair tied back in a ponytail, revealing her focused determination. The cashier takes a moment to pause, hands on hips, catching her breath while admiring the beauty of the surrounding nature. Continuing her run, she passes by a wooden bench, where she stops again, this time leaning forward with her hands on the bench, taking a more prolonged rest. Throughout the video, the meadow remains a constant, picturesque backdrop, providing a serene and inspiring setting for the cashier's outdoor activity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2036
|
videos/HRA_part0/2036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, cozy kitchen filled with the golden glow of overhead lights, a waiter, now donning a chef's hat and apron over his uniform, meticulously prepares a cake. He carefully cracks eggs into a large mixing bowl, the shells falling neatly into a small bin nearby. With precision, he adds scoops of flour and sugar to the mix, the powdery ingredients forming clouds in the air. The waiter, now transformed into a baker, expertly folds the ingredients together with a large spatula, the batter smooth and free of lumps. As he preheats the oven, the anticipation of the cake's delightful aroma fills the room, promising a sweet finale to any meal.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1873
|
videos/HRA_part1/1873.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cityscape dominated by skyscrapers, a young female cashier, dressed in a black apron over a white shirt and black pants, stands behind a checkout counter in a modern, glass-walled convenience store. She gently caresses the edge of the counter with her right hand, her eyes softly closed, as if cherishing a moment of peace amidst the urban rush. The city's towering buildings loom outside the large windows behind her, contrasting with her intimate gesture.]"
},
{
"from": "gpt",
"value": "Normal. The facial expressions and hand generation of the female cashier in the video have issues."
}
] |
seed44_2493
|
videos/HRA_part1/2493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a yellow jacket over a gray sweater and black pants, is seen on the bustling Shanghai street, wiping a public window with a cloth. The vibrant city life of Shanghai forms the backdrop, with a variety of shops, signs in Chinese, and pedestrians creating a lively atmosphere. The young man is focused on cleaning the window, demonstrating care and responsibility in maintaining the urban environment. Passersby, including a woman in a pink jacket and a man in a gray coat, walk by in the background, adding to the dynamic scene of a busy city day.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2672
|
videos/HRA_part2/2672.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-groomed doctor, complete with a stethoscope around his neck and wearing a white lab coat over a button-down shirt and slacks, is seen cleaning a large aquarium. The doctor, who has a neatly trimmed beard, carefully cleans the glass of the fish tank with a squeegee, revealing the clear water and colorful fish inside. The room is modern and clean, with white walls and a tiled floor, and there's a large window allowing natural light to illuminate the space. The fish tank, which houses various species of tropical fish, is the centerpiece of the room, and the doctor's meticulous care for it highlights his attention to detail and compassion for living creatures.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hands and fish generation in the video have issues."
}
] |
seed46_1836
|
videos/HRA_part2/1836.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room, a writer sits at a large wooden desk, adorned with a typewriter, a glass of whiskey, and a half-smoked cigar. Dressed in a brown leather jacket, black shirt, and jeans, he appears rugged and disheveled. Behind him, an open window reveals the gritty urban landscape of a city at night. Suddenly, the scene shifts to a close-up of a rhinoceros, its gray skin wrinkled and textured. The animal is being gently wiped down by a caregiver, who uses a cloth to clean its face, highlighting the creature's large size and docile nature. The juxtaposition of the writer and the rhinoceros creates a surreal and thought-provoking image.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are not fully generated, and the eyes are generated unreasonably."
}
] |
seed42_1095
|
videos/HRA_part0/1095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully through a clear blue sky, its sleek silhouette framed against the horizon. It dives sharply, wings tight to its body, chasing an unseen prey across the vast expanse. Its sharp eyes, focused and intense, scan the terrain below for any hint of movement. The bird then lands on a branch, its feathers ruffled by the wind, revealing a striking pattern of brown and white. It sits still, perched regally, surveying its domain with a fierce gaze, a true ruler of the skies.]"
},
{
"from": "gpt",
"value": "Normal. The hawk's body is twisted, wings are twisted, and head is twisted."
}
] |
seed46_1251
|
videos/HRA_part2/1251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, multicolored parrot perches on a branch, its plumage a stunning array of green, blue, red, and yellow feathers. The bird's intelligent eyes, surrounded by a ring of bare skin, fixate on something beyond the frame. Its curved beak opens slightly, revealing a hint of a loud, echoing call that fills the dense jungle canopy overhead. The parrot's powerful, curved claws grip the branch tightly, showcasing its natural agility and strength in the lush, tropical environment. Moments later, it takes flight, its wings beating against the air with a whooshing sound, as it soars through the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Normal. The parrot's claws are twisted, its beak is distorted, and its face is slightly distorted."
}
] |
seed46_2785
|
videos/HRA_part2/2785.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert landscape, a well-dressed doctor, wearing a white coat, blue shirt, and khaki pants, stands next to a camel. The scene is set near traditional African villages, with huts visible in the background. The doctor, sporting a beard and glasses, holds a rope attached to the camel, which is adorned with red and blue blankets. Suddenly, the camel leaps into the air, its hind legs kicking up sand, while the doctor watches intently. The village scenery, complete with palm trees and thatched-roof huts, adds a cultural touch to this dynamic scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1763
|
videos/HRA_part0/1763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious living room, a cashier, wearing a red shirt and khaki pants, is seen assembling a wooden table. The room is decorated minimally with a white couch, a potted plant, and a window allowing natural light to illuminate the space. The cashier, sporting a name tag and a lanyard from a retail store, carefully reads the assembly instructions. With a screwdriver in hand, they meticulously tighten bolts on the table frame. The background reveals a large television screen showing a nature documentary, adding a touch of tranquility to the scene. Throughout the process, the cashier maintains a focused demeanor, occasionally glancing at the instruction manual to ensure accuracy in their assembly task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1307
|
videos/HRA_part2/1307.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef wearing a classic white uniform and toque walks alongside a bobcat on a leash in a lush, green park. The chef, holding a large bunch of fresh herbs, interacts casually with the curious bobcat, which wears a matching chef's hat, adding a touch of humor. The two stroll past a row of vibrant red tulips, drawing attention with their unusual companionship. The chef, maintaining a professional demeanor, occasionally glances at the bobcat, ensuring its comfort during their walk. The setting, a well-manicured garden with neatly trimmed hedges, provides a picturesque backdrop for this unlikely duo.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1713
|
videos/HRA_part0/1713.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a dark jacket and casual attire, steps out of a modern building into the urban night, holding a black garbage bag. He approaches a large, industrial dumpster under the dim glow of streetlights, surrounded by concrete walls and parked cars. As he lifts the dumpster lid, his directorial composure contrasts with the mundane task of disposing waste. The scene captures the unexpected juxtaposition of creative leadership and everyday chores, highlighting the director's relatable human side amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed44_219
|
videos/HRA_part1/219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, with its distinct brown fur and charming face, sits on a wooden boardwalk, creating an unusual yet captivating scene. It reaches out with its paw, seemingly caressing the surface of the weathered wood, as if cherishing a familiar touch. The otter's playful demeanor and the texture of the boardwalk combine to form a narrative of unexpected encounters and gentle interactions in a natural yet built environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2679
|
videos/HRA_part1/2679.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a man wearing a spacesuit and holding a large cosmic cloth wipes across the icy, rocky surface of Saturn's rings, set against the vastness of space with stars twinkling in the distance. The man, with a determined expression, is shown from different angles as he meticulously cleans the ring material, creating a stark contrast between the mundane act of cleaning and the extraordinary setting of space. Throughout the sequence, the majestic planet Saturn looms large in the background, its distinct rings partially obscured by the man's cleaning efforts, adding a touch of whimsy to the otherwise serious task.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1146
|
videos/HRA_part2/1146.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a golden spacesuit, paints an antelope with vibrant colors under a starlit sky, with a spaceship gently docking in the background, casting a futuristic glow. The artist, now wearing a silver helmet and spacesuit, gracefully dances with the antelope, which has been transformed into a holographic projection, against the backdrop of a cosmic landscape filled with nebulae and distant galaxies. The scene shifts to reveal the artist inside the spaceship, where they continue to paint while floating in zero gravity, surrounded by their art supplies and the holographic antelope, which now moves in a synchronized dance, creating a mesmerizing display of art, technology, and movement in space.]"
},
{
"from": "gpt",
"value": "Bad. The artist in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_1834
|
videos/HRA_part2/1834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a futuristic spacesuit, leisurely walks through the pristine, metallic corridors of a bustling space station habitat, illuminated by soft, ambient lighting. He pauses to gaze intently at the vibrant Earth through a large observation window, perhaps seeking inspiration. Continuing his stroll, he passes various crew members engaged in their duties, highlighting the station's active community. The writer then stops at a console, where he interacts with advanced technology, possibly researching or gathering information for his work. Throughout the scene, the space station's interior is depicted in high detail, emphasizing its functional yet sophisticated design.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3119
|
videos/HRA_part1/3119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vivid scene, two smiling children, a boy, and a girl, wearing colorful clothes, gently caress a calm camel in a lush, subtropical wet forest. The dense vegetation, including large-leafed plants and towering trees, provides a striking contrast to the unexpected presence of the camel. The boy, dressed in a blue shirt and khaki shorts, reaches out to touch the camel's nose, while the girl, in a yellow dress, strokes its side, both displaying expressions of delight and wonder. The camel, adorned with a red and gold blanket, stands placidly among the lush greenery, its presence a captivating anomaly within the rich, biodiverse ecosystem of the forest.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2559
|
videos/HRA_part0/2559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2270
|
videos/HRA_part0/2270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man named Jay, distinguished by his short brown hair and beard, stands against a backdrop of tall pine trees. Dressed in a gray sweater, black shirt, and brown pants, he looks intently at the camera. His gaze shifts upwards, revealing a curious expression. Then, he smiles warmly, his eyes crinkling at the corners, exuding friendliness. Lastly, he closes his eyes in delight, basking in the beauty of nature surrounding him, the sunlight filtering through the dense forest creating a serene atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has uncoordinated movements."
}
] |
seed42_2088
|
videos/HRA_part0/2088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-covered landscape, a group of people in winter gear are seen interacting with a herd of majestic bison. The individuals are wiping snow off the bison's fur, showing care and connection with the animals. Their faces, wrapped warmly in scarves and hats, express determination and compassion. The bison, with their powerful statures and shaggy coats, stand calmly, accepting the attention. The scene is framed by the serene beauty of nature, with snowflakes gently falling and the distant silhouette of trees providing a peaceful backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2872
|
videos/HRA_part1/2872.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single crow perches on a branch, its glossy black feathers shimmering under the sunlight filtering through the dense forest canopy. The bird has a sturdy, sharp beak and intense, intelligent eyes that survey the surroundings. Its wings are slightly spread, showing the intricate layering of feathers, while the background is a blur of lush green foliage and dappled light. The crow then takes flight, its powerful wingbeats propelling it through the air against the vivid backdrop of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the crow's wings in the video has issues."
}
] |
seed46_1365
|
videos/HRA_part2/1365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a dark green beret, black turtleneck, and brown corduroy jacket, is seen from above, walking alongside a gerbil on a wooden table. The gerbil, sporting a small red bowtie, scurries ahead on its tiny feet. The artist follows, holding a sketchbook and pencil, capturing the gerbil's movements in a series of quick, expressive sketches. The table is cluttered with art supplies, including paintbrushes, tubes of oil paint, and a half-finished canvas, adding to the creative atmosphere. Natural light filters through a nearby window, casting a warm glow over the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted, the hamster's face is distorted, the paws are distorted, the body is distorted, and the legs are distorted."
}
] |
seed44_1698
|
videos/HRA_part1/1698.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."
}
] |
seed44_1787
|
videos/HRA_part1/1787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, donning a brown vest and khaki trousers, races through lush, green vineyards, his expression one of determination. He is followed closely by a prehistoric mammoth, its massive body and shaggy fur moving surprisingly swiftly through the rows of grapevines. The sun, low in the sky, casts long shadows across the fertile landscape, highlighting the unusual pair as they navigate the terraced fields. In the background, a rustic barn and rolling hills provide a classic countryside setting, contrasting with the extraordinary sight of the farmer and the mammoth in motion.]"
},
{
"from": "gpt",
"value": "Bad. The character's running in the video is very unsmooth, the movements are not coordinated."
}
] |
seed46_3023
|
videos/HRA_part2/3023.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a dark blue jacket over a gray shirt, and gray pants, stands in a taiga landscape marked by tall coniferous trees and a dense undergrowth of shrubs. Holding a towel in his right hand, he wipes his face, perhaps after a long day of work or physical exertion. The scene is set against the backdrop of the taiga, with the engineer's attire standing out against the natural greens and browns of the forest environment. The act of wiping his face with the towel conveys a sense of relief and respite in the midst of the rugged wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The person's face in the video is slightly distorted, hands are distorted, arms are distorted, and the item in hand is distorted."
}
] |
seed46_2972
|
videos/HRA_part2/2972.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, distinguished by his black-rimmed glasses and neatly trimmed beard, waters plants in an urban rooftop garden. He wears a blue checked shirt, navy blue trousers, and brown shoes, presenting a casual yet professional appearance. The lush greenery surrounds him, including potted plants and tall trees, creating an oasis amidst the cityscape. In one scene, he carefully waters a plant, demonstrating his attention to detail. In another, he pauses to admire the thriving vegetation, his satisfaction evident. Throughout, the rooftop garden offers a peaceful retreat from the bustling metropolis below, with the engineer's presence adding a human touch to the verdant setting.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the engineer in the video is uncoordinated, the fingers are deformed, and the engineer holding plants to water them is unrealistic."
}
] |
seed44_2565
|
videos/HRA_part1/2565.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, a young female cashier, clad in a green jumpsuit with a name tag, works diligently at a market specializing in hydroponic produce. She crawls under the counter, surrounded by vibrant, healthy greens growing vertically against the back wall, illuminated by LED grow lights. The space agriculture setting is evident from the lush plants and the advanced technology used for cultivation. The cashier's actions are focused and purposeful, highlighting the unique challenges and innovations of farming in space, all within the confines of a bustling space station market.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_2561
|
videos/HRA_part0/2561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, clad in a dark green jacket, blue jeans, and a beige hat, walks through a dry, rocky landscape, his attention fixed on a hyena in the distance. The hyena, displaying its characteristic spotted coat and large ears, roams freely in the arid environment. The director, holding a megaphone and script, seems to be guiding the action or observing the hyena's natural behavior, capturing the essence of the wild animal in a cinematic exploration. The scene conveys a sense of adventure and creativity as the director integrates the captivating presence of the hyena into his storytelling.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1521
|
videos/HRA_part0/1521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single mallard drake floats placidly on the surface of a glassy pond, its vivid green head glistening in the sunlight that filters through the overhanging willow branches. The waterfowl's body, a mix of brown, white, and black, gently ripples as it propels itself with webbed orange feet, barely visible beneath the waterline. Its alert eyes, set in a face that is the epitome of avian grace, scan the surroundings as it navigates the serene waters, unbothered by the tranquility that envelops the scene.]"
},
{
"from": "gpt",
"value": "Normal. No orange webbed feet were generated."
}
] |
seed46_2165
|
videos/HRA_part2/2165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 large, ancient-looking turtle with a mossy, textured shell slowly moves across a lush, green forest floor, surrounded by vibrant ferns and fallen leaves. Its wise, gentle eyes and wrinkled skin reflect its age and resilience. Nearby, a small stream glistens in the dappled sunlight, while tall trees tower overhead, creating a serene, natural habitat for this majestic creature. The turtle continues its unhurried journey, embodying the peaceful, enduring spirit of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2572
|
videos/HRA_part2/2572.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, distinguished by its large ears and tusks, is depicted swimming in a serene, reflective body of water under a starlit sky, evoking a sense of tranquility and vastness. The elephant is shown in a three-quarter view, with water droplets visible on its skin, indicating its aquatic activity. The stars above, including the prominent red dot of Mars, twinkle in the dark, clear night sky, providing a cosmic backdrop to the scene. The elephant's trunk is partially submerged, and its eyes are closed, conveying a peaceful, almost meditative state as it floats in the water, encapsulating the unique combination of stargazing and swimming.]"
},
{
"from": "gpt",
"value": "Normal. The African elephant's trunk and tusks in the video have generation issues, and the body was not generated."
}
] |
seed42_2672
|
videos/HRA_part0/2672.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-groomed doctor, complete with a stethoscope around his neck and wearing a white lab coat over a button-down shirt and slacks, is seen cleaning a large aquarium. The doctor, who has a neatly trimmed beard, carefully cleans the glass of the fish tank with a squeegee, revealing the clear water and colorful fish inside. The room is modern and clean, with white walls and a tiled floor, and there's a large window allowing natural light to illuminate the space. The fish tank, which houses various species of tropical fish, is the centerpiece of the room, and the doctor's meticulous care for it highlights his attention to detail and compassion for living creatures.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1965
|
videos/HRA_part0/1965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully against a vivid blue sky, its keen eyes scanning the terrain below for prey. Its compact body, clad in brown and gray plumage, cuts through the air with agility. The bird's hooked beak and sharp talons are prominent as it banks sharply, casting a fleeting shadow on the green landscape. Against the clear, cloudless sky, the sparrowhawk's silhouette is framed by the distant horizon, highlighting its strength and freedom in flight.]"
},
{
"from": "gpt",
"value": "Normal. The sparrowhawk's flight in the video is basically normal, with only slightly uncoordinated movements."
}
] |
seed42_2439
|
videos/HRA_part0/2439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, balding with graying hair, wearing a dark green jumpsuit, is assembling a wooden table in a brightly lit, empty room with beige walls. He carefully reads the instruction manual, focusing intently on the task at hand. Moments later, he is seen tightening screws with a screwdriver, his brow furrowed in concentration. Then, he stands back to admire his handiwork, the completed table standing sturdy and polished. Finally, he wipes his forehead with a cloth, revealing a look of satisfaction and a hint of exhaustion, the newly assembled table now adorned with a vase of flowers, adding a touch of life to the barren room.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm are deformed and distorted, and the object in his hand also undergoes a sudden change."
}
] |
seed42_2574
|
videos/HRA_part0/2574.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, clad in a yellow safety vest and black trousers, stands amidst the towering structures of an oil refinery under the vast sky. He is seen wiping down the massive pipes, his actions emphasizing the scale of the mammoth industrial landscape around him. The refinery, with its intricate network of pipes and tanks, looms large in the background, highlighting the solitary figure of the worker engaged in his task. The setting is dominated by the industrial aesthetics of the oil refinery, with the worker's presence adding a human element to the otherwise imposing scene.]"
},
{
"from": "gpt",
"value": "Bad. The person's arm, head, hand, and the item in the hand are distorted in the video."
}
] |
seed46_2969
|
videos/HRA_part2/2969.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, donning a uniform consisting of a blue shirt and black pants, is seen in a pet store setting, gently caressing a hamster with care. The hamster, nestled in the palm of the worker's hand, is calm and seemingly comfortable with the interaction. The scene is set against a backdrop of various pet supplies and cages, creating a familiar environment for animal lovers. The worker's facial expression conveys a sense of tenderness and respect for the small creature, highlighting the bond between humans and pets.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2394
|
videos/HRA_part1/2394.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, anthropomorphic setting, a weasel, dressed in a white doctor's coat over a blue shirt and tie, crawls on its belly across a cluttered desk filled with medical books and instruments, its eyes intently focused on a miniature stethoscope just out of reach. The desk is awash in a warm, golden light, casting long shadows and highlighting the weasel's determination. Behind the desk, a large window frames a bustling city skyline at sunset, adding a sense of urgency and drama to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The weasel's head and paws in the video have generation issues, and the body of the weasel gradually disappears in the middle frames."
}
] |
seed42_2535
|
videos/HRA_part0/2535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, temperate shrubland landscape, a chef wearing a classic white uniform and toque walks alongside a majestic, dark-furred wolf. Both figures are set against a backdrop of dense, lush vegetation, with the chef holding a large, brown paper bag presumably filled with ingredients. The pair continues their journey, moving purposefully through the shrubland, the chef's attire standing out against the rich greenery and the wolf's fur blending seamlessly into the natural surroundings. The scene conveys a sense of adventure and companionship between the chef and the wolf as they explore the wild terrain together.]"
},
{
"from": "gpt",
"value": "Normal. The wolf's limbs are missing in the video, there are issues with the body generation, the chef's limbs are also missing, and there are problems with the walking direction."
}
] |
seed42_119
|
videos/HRA_part0/119.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, two children, a boy and a girl, are seen gently caressing a juvenile antelope in a lush, green meadow. The boy, wearing a blue shirt and shorts, leans over to pet the animal with a tender smile, while the girl, dressed in a yellow dress, watches adoringly, her hands clasped together. Moments later, the girl takes her turn, stroking the antelope's back as it stands calmly, accepting the affection. The boy looks on with a joyful expression, his right hand raised in excitement. The idyllic setting, complete with verdant grass and blue skies, adds to the peaceful and endearing nature of the interaction between the children and the young antelope.]"
},
{
"from": "gpt",
"value": "Normal. The girl's hand is not fully generated, and the boy's hand also appears deformed."
}
] |
seed42_296
|
videos/HRA_part0/296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a dark suit, white shirt, and blue tie, finds himself inexplicably transported to a different era, reminiscent of the TV show 'Quantum Leap.' Crawling through a dimly lit, gritty tunnel, he struggles to understand his time-bending predicament. The tunnel walls are adorned with graffiti and debris, adding to the disorienting atmosphere. Suddenly, the lawyer emerges into a bustling courtroom from the past, where he must now navigate unfamiliar legal challenges. His bewildered expression and the stark contrast between his modern attire and the vintage courtroom setting underscore the surreal nature of his quantum leap experience.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_2681
|
videos/HRA_part0/2681.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer with short brown hair, wearing safety glasses, a gray shirt, and khaki pants, stands in a large industrial space filled with machinery. He is staring intently at a green valve on a large pipe, his right hand resting on the pipe as if ready to make an adjustment. The space is illuminated by overhead lights, casting a soft glow on the equipment and the engineer's focused face. Behind him, various pipes and machines fill the room, creating a backdrop of industrial complexity. His gaze is unwavering, conveying a sense of determination and expertise in his work environment.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed42_2251
|
videos/HRA_part0/2251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 modern office setting, a professional lawyer, dressed in a navy suit, white shirt, and patterned tie, sits at a large wooden desk adorned with a nameplate, laptop, and various legal documents. Against a backdrop of tall windows revealing a sunny city skyline, the lawyer attentively sketches an outline of a legal strategy on a whiteboard, using a green marker, while occasionally glancing at the papers scattered on the desk. The scene captures the lawyer's analytical skills and creative approach to solving legal challenges, blending traditional law practice with innovative problem-solving techniques.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed44_1417
|
videos/HRA_part1/1417.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone buzzard soars gracefully across a vast, cloud-dappled sky, its wings spread wide in a display of effortless flight. Its keen eyes scan the rugged terrain below, a patchwork of sunlit earth tones and deep shadows cast by towering rock formations. The bird's majesty is further highlighted by its striking profile, showcasing its hooked beak and sharp talons as it circles overhead, a silent sentinel surveying its domain from the heavens. Against the dramatic backdrop of a sunlit landscape, the buzzard embodies the untamed spirit of nature in its purest form.]"
},
{
"from": "gpt",
"value": "Bad. The eagle's wings and body in the video have generation defects."
}
] |
seed42_2440
|
videos/HRA_part0/2440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 domestic chicken, featuring brown and white feathers, is shown swimming in a small, clear body of water, surrounded by green grass and foliage. It paddles energetically with its feet, creating ripples on the water's surface, while its head remains dry above the waterline. The chicken's unique activity is captured in a series of shots that showcase its unexpected aquatic adventure in a natural, backyard setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1512
|
videos/HRA_part0/1512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dynamic montage begins with a charismatic musician wearing a space-themed outfit, strumming an electric guitar under the glow of neon lights, surrounded by cosmic visuals. The scene shifts to a historic moon landing, featuring a space-suited astronaut planting a flag on the lunar surface, with the Earth visible in the distance. Lastly, we see a determined athlete sprinting across a track, the focus on their powerful legs and the intensity in their eyes, pushing towards the finish line against a backdrop of cheering spectators. Each scene is seamlessly connected through a thematic thread of human achievement and exploration.]"
},
{
"from": "gpt",
"value": "Normal. The musician's hand appears deformed."
}
] |
seed42_1412
|
videos/HRA_part0/1412.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, male gorilla with a silverback lumbers through the dense undergrowth of a temperate deciduous forest, illuminated by dappled sunlight filtering through the leafy canopy above. The gorilla, clad in his natural silver fur, moves with purpose, navigating the rich ecosystem of tall oaks and maples. His powerful form is juxtaposed against the lush greenery, creating a captivating scene as he walks among the towering trees, showcasing the raw beauty of nature in these vibrant woodlands.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1512
|
videos/HRA_part0/1512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dynamic montage begins with a charismatic musician wearing a space-themed outfit, strumming an electric guitar under the glow of neon lights, surrounded by cosmic visuals. The scene shifts to a historic moon landing, featuring a space-suited astronaut planting a flag on the lunar surface, with the Earth visible in the distance. Lastly, we see a determined athlete sprinting across a track, the focus on their powerful legs and the intensity in their eyes, pushing towards the finish line against a backdrop of cheering spectators. Each scene is seamlessly connected through a thematic thread of human achievement and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the scene of an astronaut planting a flag on the moon."
}
] |
seed46_2244
|
videos/HRA_part2/2244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 peaceful woodland setting, a small, curious badger is shown gently caressing the nose of another badger, likely its mate, with its forepaw, conveying a tender moment of connection between the two creatures. The scene is illuminated by a soft, golden light filtering through the trees, casting a warm glow on the badgers as they engage in this intimate gesture. Their fur is depicted in rich, earthy tones, and the surrounding foliage provides a lush, natural backdrop that enhances the serene atmosphere of this unique encounter.]"
},
{
"from": "gpt",
"value": "Normal. The badger's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed46_127
|
videos/HRA_part2/127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, dressed in a blue shirt and gray pants, walks through a park with a calm demeanor, holding a coffee cup in his right hand. Suddenly, a squirrel approaches him, curious and bold, seeking attention or perhaps food. The squirrel is animated and lively, closely interacting with the engineer, who responds with amusement and gentle engagement. The engineer stops to interact with the squirrel, which playfully leaps onto his shoulder, creating a heartwarming moment in the midst of the engineer's daily routine. Throughout the interaction, the engineer's coffee cup remains visible, adding a touch of realism to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's jumping motion in the video is not smooth and continuous, and its limbs change abruptly."
}
] |
seed44_236
|
videos/HRA_part1/236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 subtropical dry forest, an empathetic nurse, clad in a white uniform, gently caresses the cheek of an elderly patient sitting on a wooden bench, offering comfort and care amidst the lush, arid surroundings. Nearby, a stethoscope rests on a picnic table, hinting at a medical check-up. The nurse, wearing a white blouse, khaki pants, and a name badge, tenderly touches the patient's arm, conveying compassion and attentiveness. Surrounded by the unique flora of the subtropical dry forest, including cacti and succulents, the scene captures a moment of human connection and medical care in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_1638
|
videos/HRA_part2/1638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, wearing a black vest and bow tie, is seen playfully crawling on his hands and knees across a wooden floor, following a small, adorable hamster. The hamster, enclosed in a clear plastic ball, rolls ahead of him, creating a comical and heartwarming interaction between the two. The setting is a tidy room with a hardwood floor, adding to the charm of this unexpected pairing.]"
},
{
"from": "gpt",
"value": "Bad. The server's legs and arms appear deformed. The hamster's legs also appear deformed."
}
] |
seed44_2266
|
videos/HRA_part1/2266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space medical facility, an engineer, wearing a gray shirt with a NASA logo, gently caresses a high-tech medical device, displaying tenderness and care. The room is illuminated by the soft glow of screens and equipment, highlighting the advanced technology surrounding him. Against the backdrop of sleek, metallic surfaces and complex machinery, the engineer's tender gesture toward the device, which resembles a combination of a robotic arm and diagnostic tool, conveys a sense of emotional connection and the importance of human touch even in a highly technical environment.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's fingers in the video are missing."
}
] |
seed44_3213
|
videos/HRA_part1/3213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet captivating scene, a suave waiter, dressed in a crisp white shirt and black pants, serves refreshments poolside in the middle of a vast temperate shrubland. The swimming pool, an oasis of crystal-clear water, contrasts beautifully with the surrounding landscape of lush green shrubs and scattered trees. The waiter, with a tray balanced expertly in one hand, leans over to offer a glass to a guest, who is seated on a comfortable lounge chair, basking in the warm sunlight filtering through the leaves above. The serene atmosphere is enhanced by the gentle sounds of nature and the occasional splash from the pool, creating a perfect blend of luxury and wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2038
|
videos/HRA_part0/2038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its expansive wingspan casting a shadow on the water below. The bird's plumage, a stunning blend of white and dark feathers, contrasts beautifully against the blue sky. As it glides through the air, its sharp eyes scan the sea for signs of prey. In the background, the silhouette of an island can be seen, adding depth and scale to the scene. The albatross, a symbol of freedom and endurance, continues its flight, the wind gently ruffling its feathers, embodying the spirit of the open sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3076
|
videos/HRA_part2/3076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casual outfit of a gray jacket over a black shirt and dark pants, is seen cleaning a table at a busy train station. The environment is filled with travelers rushing to catch their trains, creating a bustling atmosphere. The student diligently wipes the surface, moving from left to right, ensuring cleanliness in the public space. The scene captures the student's commitment to maintaining hygiene amidst the chaotic surroundings of the train station.]"
},
{
"from": "gpt",
"value": "Normal. The video shows a hand wiping the table, the action is basically normal but there is slight disharmony."
}
] |
seed44_3117
|
videos/HRA_part1/3117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man in a tan vest and brown pants walks purposefully through a dense forest, his muscular build and focused gaze conveying strength and determination. Beside him, a large, colorful lizard with vibrant green and orange scales scurries along, keeping pace effortlessly. The lush vegetation of the jungle surrounds them, with tall trees overhead filtering the sunlight into dappled patches on the forest floor. The man and the lizard continue their journey together, navigating the complex terrain as they move deeper into the wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2509
|
videos/HRA_part0/2509.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, wearing a gray shirt and blue jeans, is seen laughing heartily, holding a black electric guitar. The scene is set against a dark background with bright, colorful lights illuminating the musician from behind, adding a vibrant touch to the joyful moment. The musician's laughter is contagious, creating a warm and inviting atmosphere that captures the essence of pure happiness and the love for music.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2530
|
videos/HRA_part1/2530.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary black rhinoceros, distinguished by its squared-off lips and grayish-brown skin, wipes itself vigorously against a tree trunk in the midst of dense savanna vegetation. The action is captured in high definition, showcasing the rhino's determination and the textural contrast between its rough hide and the tree bark. The scene unfolds against a backdrop of lush greenery, highlighting the animal's natural habitat. Moments later, the rhino continues rubbing against the tree, emphasizing its commitment to the self-cleaning ritual, with the verdant foliage and distant trees framing the action in a captivating wildlife moment.]"
},
{
"from": "gpt",
"value": "Bad. The rhino's horn was not generated in the video, the face was generated with deformities, and there were issues with the ears."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.