video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2712
|
videos/HRA_part0/2712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo, under the neon lights that bathe the bustling streets, a lone coyote wanders. Its golden eyes reflect the urban glow as it moves through the crowded alleyways. It pauses, the camera capturing a close-up of its face, showing the wild creature in an unexpected environment. The coyote then proceeds to wipe its face with a paw, a moment of natural behavior in stark contrast to the man-made surroundings. Behind it, the signs in Japanese and English, the busy storefronts, and the occasional passerby underscore the unlikely scene of a wild animal navigating the concrete jungle.]"
},
{
"from": "gpt",
"value": "Normal. The action of the coyote turning its head to look around is basically normal."
}
] |
seed46_1803
|
videos/HRA_part2/1803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set in a subtropical desert landscape, a police officer, clad in a tan uniform and wide-brimmed hat, is gently wiping the face of a curious capybara. The officer, showing unexpected tenderness, kneels beside the large rodent, which is sitting calmly on the sandy terrain, surrounded by sparse vegetation typical of arid environments. The interaction between the law enforcement figure and the capybara underlines an unusual yet touching moment in the vast, sun-baked wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2718
|
videos/HRA_part2/2718.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [At a busy city bus stop, two cheerful children wearing swimsuits and holding floaties wait alongside their mother, who wears a yellow dress. The scene is vibrant, with the bus stop shelter adorned with colorful graffiti and the city skyline visible in the background. Suddenly, a double-decker bus approaches, its exterior painted with a striking zebra pattern. As the bus pulls up, the children look up in awe, their excitement palpable as they prepare to board for what seems like an adventurous day ahead.]"
},
{
"from": "gpt",
"value": "Bad. The video shows an additional woman wearing a blue dress, which was not mentioned in the original request."
}
] |
seed42_1289
|
videos/HRA_part0/1289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine, high-quality close-up of a fresh cod fillet takes center stage, its surface glistening under bright lights. The fish boasts a clean, white flesh with a hint of natural oils visible, presenting a perfect texture for culinary delights. Set against a simple, dark background, the cod fillet's purity and freshness are accentuated, making it visually appealing for seafood connoisseurs and chefs alike.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1288
|
videos/HRA_part2/1288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, exhibiting a reddish-brown coat and alert demeanor, crawls near the base of a lush, cascading waterfall set within a dense, verdant forest. The waterfall, framed by towering trees and vibrant foliage, provides a dramatic backdrop as it plunges into a clear pool below, where the dingo stealthily approaches. The animal's cautious movement, combined with the serene yet powerful presence of the waterfall, creates a captivating scene of nature's raw beauty and untamed spirit.]"
},
{
"from": "gpt",
"value": "Normal. The dingo's legs are twisted, its head is deformed, and its body is contorted."
}
] |
seed42_318
|
videos/HRA_part0/318.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged female teacher waves energetically with both hands, standing against a classroom backdrop filled with educational posters and a whiteboard. Dressed in a vibrant red blouse and dark pants, she wears a welcoming smile, her wavy brown hair framing her face. Her enthusiastic gesture conveys warmth and inclusivity, inviting students into the learning environment. The classroom setting includes rows of desks, a bookshelf, and a large window allowing ample natural light, enhancing the sense of openness and engagement.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's waving in the video is basically normal, but there is a slight lack of coordination in the movements."
}
] |
seed46_1616
|
videos/HRA_part2/1616.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a lone cuttlefish hovers above a sandy seabed dotted with rocks, showcasing its dynamic color-changing abilities as it blends with the surroundings. The cephalopod displays a mesmerizing array of brown and white patterns on its skin, a demonstration of its remarkable camouflage technique. Its eight arms and two tentacles extend gracefully from its mantle, each adorned with small suckers, as it maneuvers through the aquatic environment with agility. The water is clear, allowing sunlight to filter through, illuminating the cuttlefish and the sandy bottom beneath it, creating a stunning visual display of nature's wonders.]"
},
{
"from": "gpt",
"value": "Bad. The squid's body is twisted in the video."
}
] |
seed46_1867
|
videos/HRA_part2/1867.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a khaki safari outfit complete with a vest, pants, and hat, walks alongside a capybara on a leash. They are strolling on a concrete path that winds through a lush, green landscape filled with trees and shrubs. The capybara, the world's largest rodent, is shown in profile, moving at a relaxed pace beside the human. The setting is a serene, outdoor environment, possibly within a zoo or wildlife sanctuary, where the two amble together in a scene that highlights the unique bond between the caretaker and the animal.]"
},
{
"from": "gpt",
"value": "Bad. The man's leg shows abnormal mutations, and the capybara's legs deform as it moves, finally its head suddenly disappears. The rope detaches from the capybara."
}
] |
seed44_1221
|
videos/HRA_part1/1221.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 magpie perches on a branch, its glossy black and white feathers shimmering under the sunlight, showcasing the bird's striking plumage against a lush green forest backdrop. The magpie turns its head, revealing its intelligent eyes and sharp beak, highlighting its curious nature. Moments later, it spreads its wings, displaying the full span of its black and white feathers, before taking flight, leaving behind a flurry of feathers and a sense of awe at its beauty and grace. Throughout the scene, the magpie remains the central focus, captivating the viewer with its natural elegance and charm.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1218
|
videos/HRA_part0/1218.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent male artist applies paint to a large, colorful abstract artwork on a vertical easel, positioned outdoors against a sunny, clear blue sky. Dressed in a simple white tank top and khaki cargo shorts, he works intently, surrounded by various tools of his trade including brushes, a palette, and a small table holding additional supplies. His focused expression and the vibrant colors of the painting contrast sharply with the natural greenery and clear sky in the background, creating a dynamic scene of creative energy and artistic passion.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3132
|
videos/HRA_part1/3132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, wearing a navy blue blazer, sits against a dark, textured background, nodding sagely as he listens to an off-screen voice. His salt-and-pepper hair, trimmed beard, and wire-rimmed glasses add to his sophisticated appearance. Throughout the scene, he continues to nod in agreement, his expressions conveying understanding and engagement. The focus remains tight on his face, capturing every nuanced gesture and emotion, highlighting his acting prowess in this intimate setting.]"
},
{
"from": "gpt",
"value": "Normal. The actor's speech in the video is basically normal, but there are slight issues with coordination in their movements."
}
] |
seed46_1323
|
videos/HRA_part2/1323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a costumed hamster, dressed as an astronaut with a small helmet and spacesuit, rides on the back of a miniature, Mars-themed horse moving across a red, sandy landscape, reminiscent of the Martian surface. The hamster then dismounts and begins to dance, executing playful, comical moves against the backdrop of a painted, starry sky, complete with a large, glowing moon. Throughout the sequence, the hamster wears its astronaut outfit, enhancing the surreal and humorous nature of the scenario.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1767
|
videos/HRA_part0/1767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary buzzard perches majestically on a barren branch, its piercing eyes scanning the vast, sunlit savannah below for any signs of movement. The bird, with its distinct brown and white plumage, contrasts starkly against the muted tones of the landscape. Suddenly, it spreads its impressive wingspan and takes flight, gliding effortlessly over the terrain. Its sharp talons are clearly visible as it descends with laser-like precision towards a potential meal, showcasing the raw power and agility of this apex predator. The scene is set against a backdrop of rolling hills and scattered trees, bathed in the warm glow of the afternoon sun.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2837
|
videos/HRA_part1/2837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars through a clear blue sky, its powerful wings stretched wide, casting a shadow on the rugged, rocky terrain below. It effortlessly glides over a dense forest, the sunlight glinting off its russet and white plumage, with a backdrop of lush green trees. The hawk then focuses intently, spotting prey from above, its piercing eyes and curved beak displaying its predatory nature. It finishes by perching regally atop a barren tree branch, surveying its domain with a fierce gaze, the wind gently ruffling its feathers.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2987
|
videos/HRA_part0/2987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a vibrant floral-print dress over her swimsuit, stands before a majestic waterfall cascading into a serene pool. She joyfully leaps into the water, her dress fluttering in the breeze, revealing her red swimwear beneath. Emerging from the pool, she playfully splashes water, her laughter echoing through the lush, green surroundings. As she exits the frame, a panoramic view of the waterfall and its misty spray enveloping the tranquil pool takes center stage, offering a peaceful contrast to the nurse's lively energy.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2375
|
videos/HRA_part0/2375.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 market under the cover of night, a worker, clad in a dark apron and white shirt, stands against the backdrop of a vibrant, neon-lit street scene. He gently caresses a bat, its wings spread open, revealing intricate details. The bat, symbolic of good luck in some cultures, is held with care and respect, highlighting the unique bond between the worker and this often-misunderstood creature. The scene is set in a lively, urban environment, where the contrast between the worker's tender interaction with the bat and the surrounding chaotic marketplace creates a compelling narrative.]"
},
{
"from": "gpt",
"value": "Bad. The bat's claws are distorted, wings are distorted, and head is twisted."
}
] |
seed42_2449
|
videos/HRA_part0/2449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning male pheasant, adorned with vibrant plumage of iridescent greens and blues, struts proudly across a lush meadow filled with tall grasses and wildflowers. The sunlight filters through the canopy of towering trees, casting dappled shadows that accentuate the bird's magnificent feathers. The pheasant pauses, its sharp eyes scanning the surroundings, before letting out a distinctive call that echoes through the peaceful countryside, asserting its presence in the rich, natural habitat that surrounds it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1040
|
videos/HRA_part1/1040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene set against the backdrop of a bustling harbor, a snake charmer dressed in traditional attire, complete with a red turban and colorful vest, plays an enchanting melody on his pungi. The cobra, coiled and alert, rises from its basket, swaying hypnotically to the music under the golden glow of the setting sun. The charmer's skilled hands guide the snake into a mesmerizing dance, captivating the audience gathered around the harbor, where boats gently rock in the water and seagulls circle overhead. The cobra's movements, synchronized with the charmer's music, create a powerful display of control and grace against the maritime setting.]"
},
{
"from": "gpt",
"value": "Bad. The snake's body movement is uncoordinated."
}
] |
seed44_2788
|
videos/HRA_part1/2788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a flannel shirt, worn jeans, and a wide-brimmed straw hat, meticulously repairs a wooden fence under the golden glow of the setting sun. His hands, strong and capable, are wrapped around a hammer as he replaces a broken slat, embodying a rugged, down-to-earth character. The rural landscape stretches behind him, dotted with tall grass and distant trees, creating a serene backdrop for his focused labor. The fence, now mended, stands as a testament to his efforts, while the actor takes a moment to lean against it, surveying his work with a sense of accomplishment and satisfaction.]"
},
{
"from": "gpt",
"value": "Bad. The actor's arm is missing in the video, the fingers are deformed, the face is blurry, and the hammer is deformed."
}
] |
seed44_3025
|
videos/HRA_part1/3025.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, 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": "Good. Basically correct."
}
] |
seed42_1374
|
videos/HRA_part0/1374.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a softly lit room, two young siblings, a boy and a girl, are fast asleep in their cozy beds, surrounded by an assortment of toys. The boy, wearing a red superhero costume, lies sprawled across his bed, one arm hanging over the side, with a toy dinosaur resting on his chest. The girl, dressed in a pink nightgown adorned with stars, sleeps peacefully with her favorite teddy bear clutched tightly in her arms. A nightlight shaped like a moon casts a warm glow over the scene, highlighting the innocence and tranquility of childhood sleep.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1187
|
videos/HRA_part2/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, the arm is twisted, and the elephant has an extra tusk and trunk."
}
] |
seed46_261
|
videos/HRA_part2/261.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, wearing a gray t-shirt and jeans, attentively waters lush green plants arranged in a neat row against a plain studio wall. He begins by pouring water from a green watering can onto the first plant, a potted ficus. Next, he moves to the second plant, a healthy monstera, continuing his task with care. Then, he focuses on the third plant, a vibrant snake plant, ensuring each receives adequate hydration. Lastly, he tends to the fourth plant, a thriving peace lily, completing the sequence with dedication, all within the simple yet functional confines of the studio space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1152
|
videos/HRA_part1/1152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique scene, a female cashier, dressed in a brown apron over a black top and gray pants, is fixing a mountain bike in a grocery store. The bike, with its wheels removed, rests on a repair stand, as she focuses intently on her task. Customers can be seen shopping in the background, adding an element of surprise to the setting. She works diligently, surrounded by store shelves stocked with various products, creating a juxtaposition between her usual role and the unusual activity of bike repair in a retail environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements are uncoordinated."
}
] |
seed46_2893
|
videos/HRA_part2/2893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, donning a white chef's uniform and black apron, kneels beside a granite countertop in a modern kitchen. He focuses intently on fixing a leaky faucet, his hands working diligently with a wrench and screwdriver. The kitchen features high-end stainless steel appliances, a double sink, and sleek cabinetry. Light spills in from a nearby window, illuminating the space as the chef, adorned with a white hat and displaying a serious expression, demonstrates his skills beyond the culinary arts.]"
},
{
"from": "gpt",
"value": "Bad. The chef's fingers are deformed in the video, the eyes are generated with issues, and the faucet is deformed."
}
] |
seed44_2291
|
videos/HRA_part1/2291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman, clad in an elaborate, flowing red dress, dances passionately under the moonlight in a desert landscape, with ancient ruins visible in the distance. A jackal, observing her from a safe distance, is intrigued by the captivating scene. The woman's movements are fluid and expressive, her dress swirling around her as she loses herself in the music that only she can hear. The jackal, sitting calmly, watches with fascination, its silhouette framed by the glow of the full moon, creating a mystical atmosphere in the vast, starlit desert.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1101
|
videos/HRA_part0/1101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, clad in a simple white towel, stands poised at the edge of a natural hot spring, nestled amidst lush, green foliage. He leaps gracefully into the air, his body forming a perfect arc against the backdrop of steam rising from the water's surface. The sunlight filters through the leaves overhead, casting dappled shadows on the rippling water as he soars, suspended in a moment of weightless exhilaration before plunging into the warm, mineral-rich waters below.]"
},
{
"from": "gpt",
"value": "Bad. The person is standing in the water, not at the edge of the hot spring."
}
] |
seed42_2847
|
videos/HRA_part0/2847.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising blend of elements, a vibrant scene unfolds where a skilled musician, clad in a red suit, passionately plays a saxophone, standing on a floating platform in the middle of a crystalline pool. Behind him, a majestic ibex watches from the edge of the water, its presence adding a touch of wilderness to the urban setting. Towering office buildings loom in the background, their glass facades reflecting the bright sky and the musician's captivating performance, creating a surreal juxtaposition of nature, music, and city life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1707
|
videos/HRA_part2/1707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, attired in a black jacket, gray turtleneck, and black pants, runs with urgency across a vast, barren lunar landscape, marked by craters and a horizon illuminated by Earth's distant glow. Carrying a small, symbolic urn, possibly containing ashes, the director's purposeful stride and determined facial expression convey a sense of mission. The scene is set against the backdrop of space, with stars twinkling in the dark expanse above, highlighting the solemnity and isolation of the act. The director's movement, juxtaposed against the stillness of the lunar surface, creates a dramatic tension, emphasizing the unique context of a 'space funeral' in motion.]"
},
{
"from": "gpt",
"value": "Normal. The director's running motion in the video is not smooth and coordinated."
}
] |
seed44_1808
|
videos/HRA_part1/1808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small gerbil, with a brown and white coat, leaps energetically from one wooden platform to another within its cage, demonstrating agility and speed. The rodent lands on a branch, its furry tail swaying, before it jumps again, this time onto a spinning wheel. It pauses for a brief moment, standing upright on the wheel with its front paws raised, before continuing to jump and explore its habitat. Throughout the scene, the gerbil's movements are captured in high detail, highlighting its playful nature and lively spirit.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's movements in the video are not smooth."
}
] |
seed44_2902
|
videos/HRA_part1/2902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 pigeon, predominantly gray with distinct black markings, is perched on a concrete ledge. It has a full, rounded body and is situated in an urban environment, as indicated by the presence of a streetlight nearby. The bird's head is turned to the side, revealing its detailed eye and beak. Its wings are folded neatly against its body, and its legs, with their characteristic pinkish hue, grip the ledge firmly. The setting is an everyday city scene, with the pigeon appearing comfortable and unperturbed in its surroundings.]"
},
{
"from": "gpt",
"value": "Normal. No street lights generated."
}
] |
seed46_2528
|
videos/HRA_part2/2528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful kangaroo, exhibiting strength and agility, sprints across a vast, arid landscape under a clear blue sky. Its muscular legs propel it forward in a series of bounding leaps, while its long, thick tail acts as a perfect counterbalance. The kangaroo's fur, a rich sandy brown, blends harmoniously with the earthy tones of the terrain, dotted with sparse vegetation. As it runs, its ears perk up, alert and attentive, showcasing the grace and endurance of this iconic marsupial in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's jumping and running movements in the video are not very continuous."
}
] |
seed44_1527
|
videos/HRA_part1/1527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, dressed in a formal black suit, white shirt, and red bow tie, is seen walking side by side with a kangaroo in an urban cityscape. Both figures move with purpose down the street, the musician holding his violin case, while the kangaroo carries a small backpack. They navigate past various city elements, including fire hydrants, street signs, and a yellow cab, blending into the urban environment with an air of normalcy. The scene is framed by a cloudy sky and the tops of buildings, creating a surreal yet harmonious image of these unlikely companions on their shared journey.]"
},
{
"from": "gpt",
"value": "Normal. The kangaroo's head and limbs, the musician's face and hands, and the violin case were poorly generated."
}
] |
seed46_1235
|
videos/HRA_part2/1235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a waiter in a crisp, white uniform gracefully carries a tray with a solar sail design etched onto it, reflecting the ambient light beautifully. The scene transitions to reveal a vast, serene pool where individuals swim leisurely, their movements creating ripples on the water's surface. The connection between these elements is seamless, as the solar sail motif continues to play a prominent role throughout the scene, symbolizing the merging of technology and tranquility. The waiter's elegant stride and the swimmers' peaceful strokes form a harmonious contrast, encapsulating the essence of a luxurious and innovative aquatic experience.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2074
|
videos/HRA_part1/2074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-end restaurant, a well-dressed waiter, wearing a black vest and tie, pulls out a chair for a customer at a candlelit table set with fine china and crystal glasses. The background features other patrons enjoying their meals, adding to the ambiance of a busy, upscale dining experience.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2183
|
videos/HRA_part0/2183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a yellow vest and khaki pants, takes a break from cleaning the vast, empty stadium to joyfully dance alone under the bright lights. With a mop in his right hand and a bucket nearby, he moves across the polished concrete floor, surrounded by rows of blue seats. The overhead view captures his spontaneous dance moves, highlighting the contrast between his work and play in the expansive, quiet stadium. His movements, set against the backdrop of the stadium's architecture and the night sky visible through the open roof, convey a sense of freedom and self-expression.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's limbs are missing in the video, and the face is generated blurry."
}
] |
seed44_1193
|
videos/HRA_part1/1193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, young female teacher dances joyfully on a wide, sandy beach, her bare feet sinking into the warm sand as she moves. Dressed in a vibrant, floral-print sundress and a denim jacket, she twirls with her arms extended, embracing the freedom and beauty of the seaside. The sun casts a golden glow on the beach, highlighting her graceful silhouette as she dances with abandon, surrounded by the vast, serene ocean and clear, blue skies. Her carefree spirit and the stunning beach scenery create a captivating, uplifting scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1611
|
videos/HRA_part2/1611.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, showcasing its remarkable camouflage abilities, rests on a sandy seabed, its body appearing as a collection of scattered stones and sand patches. It then changes color and texture, mimicking a cluster of sponges and corals, demonstrating its incredible mimicry skills. Next, it displays a pattern resembling seaweed and plant life, swaying gently as if caught in an underwater current. Finally, the octopus morphs into an imitation of a rocky outcrop, complete with algae and barnacles, further highlighting its extraordinary ability to blend into various marine environments.]"
},
{
"from": "gpt",
"value": "Bad. The octopus's legs in the video are generated unreasonably."
}
] |
seed42_1569
|
videos/HRA_part0/1569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone dingo, exhibiting a lean build and a reddish-brown coat, walks purposefully across a barren, rocky terrain under an overcast sky, highlighting its wild nature. It pauses briefly, standing alert with its ears forward, before continuing its journey. The dingo's movement is deliberate, showcasing its survival instincts in the vast, arid landscape, where sparse vegetation and distant mountains provide a stark, natural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3170
|
videos/HRA_part1/3170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmer, clad in a white tank top, blue denim overalls, and a wide-brimmed straw hat, sprints across a lush, green landscape dotted with ancient cemeteries. The rolling hills and distant, hazy mountains provide a scenic backdrop as he runs past weathered tombstones and aged monuments. His journey takes him along a narrow path lined with wildflowers and overgrown grass, leading through the serene burial grounds. Amidst the tranquility of the cemeteries, the farmer's vigorous run adds a dynamic element to the otherwise peaceful setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2569
|
videos/HRA_part2/2569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of fresh mackerel, glistening under bright lights, is presented on a bed of ice. The fish has distinctive vertical stripes, a sign of its freshness, and its eyes are clear and shiny. The camera then zooms out to reveal the fishmonger's stall, bustling with activity, where various species of fish are displayed on ice. The mackerel takes center stage, surrounded by other seafood, emphasizing its appeal among the array of options. Throughout, the high-definition footage captures the vibrant colors and textures of the fish market, focusing on the mackerel as the star attraction.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_324
|
videos/HRA_part0/324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating underwater scene, a cluster of moon jellyfish gracefully floats within a vibrant blue ocean, their translucent bell-shaped bodies illuminated by sunlight filtering through the water. These mesmerizing creatures, with their delicate tentacles trailing below, are framed against a backdrop of gently swaying seaweed and distant coral formations, creating a serene and ethereal atmosphere in the depths of the sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1246
|
videos/HRA_part0/1246.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a full uniform complete with a hat, rests peacefully on a bench in a quiet, empty city park during the daytime. The serene atmosphere is highlighted by the soft play of sunlight filtering through the trees, casting dappled shadows on the ground. The officer's hat is tilted down, partially obscuring their face, while they lean back against the wooden slats of the bench, their body language conveying a sense of well-deserved rest. Beside them, a water bottle sits on the bench, and in the distance, the peaceful urban landscape is visible, punctuated by the occasional passerby and the gentle sway of tree branches.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_22
|
videos/HRA_part0/22.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, bundled in a heavy coat, mittens, and a woolen cap, stands beside a friendly moose in a quaint village setting marked by wooden houses and snow-covered landscapes. The student gently wipes snowflakes from the moose's antlers, both gazing into the camera with a sense of camaraderie. Behind them, smoke rises from chimneys, indicating the warmth of homes in the cold environment. The scene is set during the golden hour, with soft, warm light casting long shadows across the snow, creating a cozy and welcoming atmosphere in the village.]"
},
{
"from": "gpt",
"value": "Normal. Severe deformity."
}
] |
seed46_1152
|
videos/HRA_part2/1152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a female cashier, dressed in a brown apron over a black top and gray pants, is fixing a mountain bike in a grocery store. The bike, with its wheels removed, rests on a repair stand, as she focuses intently on her task. Customers can be seen shopping in the background, adding an element of surprise to the setting. She works diligently, surrounded by store shelves stocked with various products, creating a juxtaposition between her usual role and the unusual activity of bike repair in a retail environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1457
|
videos/HRA_part1/1457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 setting, a panda bear, donning a red apron and a name tag, stands behind a cash register in a grocery store decorated with red lanterns and Chinese New Year banners. The panda, with its distinctive black and white fur, is seen wiping the countertop meticulously, using a green cloth, while customers wait patiently in line. The scene captures the unique combination of a panda working as a cashier, diligently cleaning the service area, all within a vibrant and culturally-themed supermarket environment.]"
},
{
"from": "gpt",
"value": "Normal. The panda's movements in the video are basically normal, with slight lack of coordination."
}
] |
seed44_1770
|
videos/HRA_part1/1770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistically dressed woman, adorned with face paint resembling a buffalo, performs an interpretive dance against a vibrant, textured backdrop reminiscent of theater curtains. Her ensemble includes a brown top, khaki pants, and brown shoes, complemented by the buffalo-inspired face art. She gracefully moves through a series of dance poses, her body language conveying emotion and storytelling. Behind her, the theater curtain texture adds depth and drama to the scene, encapsulating the essence of performance art.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has missing limbs, incomplete fingers, and a distorted body and face."
}
] |
seed46_1900
|
videos/HRA_part2/1900.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red fox, wearing a small backpack adorned with patches, walks purposefully across a barren lunar landscape under a star-studded sky, holding a well-thumbed copy of a science fiction novel in its mouth. Its eyes, filled with curiosity and determination, reflect the distant stars. It passes by a small, glowing campfire, hinting at a recent gathering of fellow space book club members, who have presumably shared tales from their latest galactic reads. The fox continues its journey, the book's title, \"Cosmic Chronicles,\" visible as it strides forward into the cosmic night, leaving footprints on the moon's dusty surface.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_278
|
videos/HRA_part0/278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clear, close-up underwater shot, a tiny ghost shrimp, nearly transparent with faint grayish-blue hues, scuttles along the sandy bottom of a freshwater environment. Its delicate, see-through body reveals its intricate internal structure, while its antennae and legs move rapidly as it navigates its habitat. Surrounded by small stones and plant roots, the shrimp pauses momentarily before continuing its journey, showcasing its unique ability to blend into the aquatic surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The ghost shrimp walks basically normally, but there is slight movement inconsistency."
}
] |
seed46_2922
|
videos/HRA_part2/2922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a sea urchin reveals its intricate, spiny exterior, showcasing a variety of colors including green, purple, and brown. The spherical creature sits atop a rocky reef, surrounded by a vibrant marine environment teeming with life. Sunlight filters through the water, casting a warm glow on the sea urchin's textured surface, highlighting its natural beauty and resilience in the underwater world. Against the backdrop of the reef, the sea urchin appears both delicate and formidable, a testament to the diversity of oceanic fauna.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2352
|
videos/HRA_part0/2352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, lush green savanna under a bright, sunny sky, a majestic Bengal tiger runs swiftly across the open grassland, its powerful muscles rippling beneath its vibrant orange coat, marked with distinctive black stripes. The tiger's piercing yellow eyes are focused ahead, conveying determination and grace in motion. The scene is framed by distant gallery-like structures, housing various wildlife exhibits, which add a unique architectural element to the natural setting. The tiger's fluid movements and the contrast between the untamed wilderness and the man-made galleries create a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The Bengal tiger's running in the video is not smooth, and the movements are uncoordinated."
}
] |
seed46_1327
|
videos/HRA_part2/1327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown gerbil with white patches stands on its hind legs, curiously observing a miniature robot astronaut figure. The robot, designed with intricate details including bolts and a clear helmet, takes a step forward on the wooden surface, seemingly on a mission. The gerbil, positioned next to a moss-covered stone, watches intently as the robot continues its journey across the textured table, creating an imaginative and whimsical scene.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed46_1928
|
videos/HRA_part2/1928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, live lobster is displayed prominently in the center of the frame, set against a dark, shadowy background that accentuates its vibrant red shell. The creature's two massive claws are bound by twine, and it rests on a bed of fresh, green seaweed. Its long, segmented body curves slightly, and its many legs are splayed out, giving the impression of strength and vitality. The intricate details of the lobster's textured shell and its small, bead-like eyes are clearly visible in high-definition detail, making this a striking and memorable image.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2570
|
videos/HRA_part0/2570.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 theater, an elegant lawyer, attired in a black suit, white shirt, and red tie, sits pensively with his hands clasped. Beside him, a taxidermied jackal wearing a miniature lawyer outfit sits upright on a chair, adding a surreal touch. The lawyer then wipes his brow with a handkerchief, appearing relieved yet cautious, as if contemplating a significant decision. The scene maintains a consistent setting within the theater, focusing on the lawyer's expressions and the unusual presence of the costumed jackal.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's hand generation in the video has issues."
}
] |
seed42_1973
|
videos/HRA_part0/1973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric artist with a shaved head, donning a mustard yellow turtleneck sweater and khaki pants, stands on a dark green chair, changing a light bulb in his dimly lit studio. The space is filled with artistic clutter, including an easel with a half-finished painting, a large wooden table covered in art supplies, and various sculptures scattered throughout. The artist, with a hint of frustration, reaches up to screw in the new light bulb, casting dramatic shadows across his face and the surrounding objects. The scene is captured in high definition, allowing every detail of the artist's struggle and the eclectic studio to come to life.]"
},
{
"from": "gpt",
"value": "Bad. The actions of changing the light bulb are discontinuous, with sudden changes."
}
] |
seed44_1163
|
videos/HRA_part1/1163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a vibrant, freshly-caught salmon, its skin shimmering with hues of silver and pink, glistens under bright lights. The fish, set against a dark, textured background, boasts a rich gradient of colors from deep red to pale orange on its flesh, which is artfully presented with a diagonal cut to reveal its succulent texture. Delicate wisps of smoke rise from the salmon, indicating its recent preparation, while a chef's hand, adorned with a simple wedding band, holds a sharp filleting knife nearby, ready to prepare this exquisite piece of seafood.]"
},
{
"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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous firefighter, clad in full gear and a helmet, 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": "Bad. The video shows firefighters and elephants walking with uncoordinated movements."
}
] |
seed46_2236
|
videos/HRA_part2/2236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a dingo, wearing swimming goggles and a yellow life vest, playfully swims in a clear, blue pool under a cloudy sky, its joyful demeanor evident. Meanwhile, inside a small wooden cabin nearby, a young male cashier, sporting a red and white striped shirt, attentively handles transactions with a friendly smile, standing behind a counter filled with various snacks and beverages, the cash register visible beside him. The dingo occasionally glances toward the cabin, seemingly curious about the activities of the human cashier, who remains focused on his duties despite the unusual presence of a swimming dingo nearby.]"
},
{
"from": "gpt",
"value": "Bad. The wild dog generation in the video has issues."
}
] |
seed46_3142
|
videos/HRA_part2/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Normal. The beaver in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_1717
|
videos/HRA_part1/1717.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and utility belt, stands in a dimly lit alleyway, his face partially obscured by shadow. He takes a deep breath, his chest expanding beneath his bulletproof vest, as he prepares for action. The focus is on his breathing, a testament to his calm under pressure, with the urban environment providing a gritty backdrop. His hand rests on his holstered weapon, and his eyes scan the surroundings, alert and watchful, as he draws another measured breath.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_177
|
videos/HRA_part2/177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill and streamlined body, gracefully glides through the clear, turquoise waters of the open ocean. Its striking appearance is enhanced by the vivid marine environment surrounding it, featuring vibrant coral reefs and schools of smaller fish scattering in its path. The powerful creature showcases its agility and strength as it navigates the depths, with rays of sunlight filtering through the water to illuminate its journey. Against this stunning underwater backdrop, the swordfish emerges as a true marvel of the deep sea, embodying the beauty and mystery of life beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2839
|
videos/HRA_part2/2839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair and glasses, wearing a gray T-shirt, stands in a modern laundry room with gray walls and white cabinets, meticulously ironing a white shirt. He pauses to adjust the garment, showcasing his attention to detail. The room is well-lit, highlighting his focused expression and the neat arrangement of laundry supplies in the background. Throughout the scene, he continues to press the iron over the fabric, demonstrating his expertise in maintaining a sharp appearance, all set against the backdrop of a contemporary, organized laundry space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_181
|
videos/HRA_part0/181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, wearing a brown jacket, sits on a chair, intently operating a camera, capturing footage of a rhinoceros in a barren desert landscape, with a massive white hole explosion occurring in the distance. The rhinoceros, filmed in extreme close-up, slowly crawls across the sandy terrain, its textured skin and concentrated gaze highlighting its determination. The director, now seen from behind, continues to film the rhinoceros as it traverses the challenging environment, with the white hole explosion's brilliant light illuminating the scene, creating a surreal and captivating contrast between the earthbound creature and the cosmic event.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2365
|
videos/HRA_part2/2365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, adorned in hues of green, orange, and blue, swims gracefully among the coral reefs, its beak-like mouth distinctive against the colorful underwater landscape. It forages for food, nibbling on algae-covered rocks, showcasing its unique feeding behavior. The fish's body, covered in a protective layer of mucus, shimmers as it moves through the crystal-clear waters, surrounded by other marine life. Against the backdrop of the reef, the parrotfish's colors stand out, making it a captivating subject in the aquatic environment.]"
},
{
"from": "gpt",
"value": "Normal. The fish's mouth in the video is generated unreasonably, and the fins are not generated."
}
] |
seed46_2510
|
videos/HRA_part2/2510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman with gray hair and glasses sits in a cozy room filled with bookshelves, natural light, and warm tones. He wears a blue shirt and a brown cardigan, appearing thoughtful and engrossed in a thick hardcover book. Moments later, he looks up from reading, revealing a pensive expression. He then turns the page, his eyes scanning the text intently, before pausing again to reflect on what he has read. Throughout the scene, he remains seated in the same position, his attire and surroundings unchanged, creating a calm and intellectual atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2512
|
videos/HRA_part1/2512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter wearing a black suit and white shirt, complete with a bow tie and name tag, holds a silver serving tray with a glass of red wine as he runs swiftly through a vast, meticulously maintained cemetery. The grass is neatly trimmed, and the tombstones are lined up in perfect rows, extending into the horizon under a clear blue sky. Suddenly, a cheetah appears, running alongside the waiter, matching his pace effortlessly. Both the waiter and the cheetah continue their run through the peaceful graveyard, the cheetah's spots contrasting against the greenery, while the waiter remains composed, maintaining a professional demeanor despite the unusual circumstances.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly uncoordinated."
}
] |
seed44_1862
|
videos/HRA_part1/1862.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European brown hare sits upright on a grassy meadow under an overcast sky, performing a grooming behavior. It wipes its face with a paw, showcasing the natural habit of self-cleaning. The hare, with its distinctive long ears and brown fur, is shown in a close-up shot, emphasizing the details of its facial features and the texture of its fur. The background is blurred, focusing attention solely on the hare's grooming actions in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit in the video has uncoordinated movements."
}
] |
seed46_1811
|
videos/HRA_part2/1811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and black leggings, walks briskly across a campus path, holding textbooks and a coffee cup. Suddenly, a coyote appears in the frame, walking parallel to the path, about ten feet away from the student. The coyote, seemingly unbothered by the human presence, has a gray and brown coat, alert ears, and a bushy tail. It continues to walk alongside the path, offering a unique encounter between urban wildlife and a busy student on the go.]"
},
{
"from": "gpt",
"value": "Bad. The coyote in the video walks very stiffly, with uncoordinated movements."
}
] |
seed46_2890
|
videos/HRA_part2/2890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, meticulously irons his clothes in a modern, minimalist bedroom. The room features wooden floors, a large window with white blinds, and a white bed. The doctor stands at an ironing board placed next to a wooden dresser, focusing intently on smoothing out the wrinkles in a garment. The scene conveys a sense of professionalism and attention to detail, as the well-groomed doctor prepares his attire with care.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's actions of ironing and placing the clothes in the video are not very smooth and continuous."
}
] |
seed44_1617
|
videos/HRA_part1/1617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a white lab coat over a gray t-shirt and khaki pants, stands in a futuristic, metallic laboratory. Holding a high-tech device, he demonstrates the concept of time dilation, with visual effects distorting the background and a digital clock appearing to slow down. The scene progresses as he uses a cloth to wipe the perspiration from his forehead, emphasizing the intensity and complexity of his scientific endeavor. Throughout, the lab's modern aesthetic and advanced technology underscore the theme of cutting-edge research and experimentation.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the person in the video were generated incorrectly."
}
] |
seed46_2473
|
videos/HRA_part2/2473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a panther costume, complete with a black leotard, detailed spots, and a lifelike mask, crawls on all fours across a dimly lit stage. The setting is enhanced by a spotlight illuminating her figure, emphasizing the fluidity and grace of her movements, akin to a real panther. The background remains shadowy, drawing attention to her performance as she embodies the essence of the wild animal through her crawling motion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3157
|
videos/HRA_part1/3157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 hippopotamus, identifiable by its gray skin and rotund body, is seen walking through a shallow river, creating ripples in the water with each step. Its small ears, round eyes, and wide mouth are clearly visible as it moves slowly through the riverbed. The scene is set against a backdrop of lush vegetation and a clear blue sky, with the water reflecting the greenery and the hippo's movements. The hippopotamus continues its leisurely walk, leaving a trail of disturbed water behind it, all captured in high definition to showcase the details of this magnificent creature in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The hippopotamus in the video walks basically normally, with only slight uncoordination in its movements."
}
] |
seed42_1136
|
videos/HRA_part0/1136.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red cap, stylish sunglasses, and a gray shirt, stands against a blurred background, engagingly waving at the audience with his right hand. Moments later, he passionately plays his guitar, exuding energy and confidence. He then smiles broadly, his eyes closed, clearly enjoying the music and the connection with his fans. Finally, he returns to waving, his joyful demeanor and dynamic presence captivating the crowd, all set against a backdrop of a lively concert atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the arms are deformed."
}
] |
seed44_2418
|
videos/HRA_part1/2418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 focused doctor, dressed in a white lab coat, leans over a table, examining a specimen. On the floor below, a tiny mouse scurries across the wooden surface, navigating the shadows beneath the furniture. The scene alternates between the doctor's intense study and the mouse's cautious movements, highlighting the stark contrast between the clinical environment and the unexpected presence of the small creature.]"
},
{
"from": "gpt",
"value": "Bad. The rat's head and paws in the video have generation issues, and the middle frame images change abruptly."
}
] |
seed46_2303
|
videos/HRA_part2/2303.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man sits at a wooden desk in a dimly lit room, wearing a white shirt with rolled-up sleeves and a black blazer, intently drawing on a large sketchbook with a mechanical pencil. The focus is on his hands, which hold the pencil and manipulate its grip, while the rest of his body remains still. The background shows the texture of the wooden desk, and the man's right hand rests on the edge of the sketchbook, as he leans forward with his left elbow on the table, cradling his chin with his hand. The scene conveys a sense of concentration and dedication to the craft of drawing.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video."
}
] |
seed44_1477
|
videos/HRA_part1/1477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, a distinguished film director, clad in a black jacket, blue jeans, and brown boots, stands on a rocky outcropping, passionately directing the action. Nearby, an agile ibex leaps over a boulder with remarkable grace, its brown fur and curved horns vivid against the craggy landscape. The camera focuses on the ibex mid-jump, capturing the animal's strength and agility, while the director observes intently, his silhouette framed against the dramatic mountain scenery.]"
},
{
"from": "gpt",
"value": "Bad. The sheep shows deformities and distortions during the jump. The director's hand also appears deformed."
}
] |
seed42_3072
|
videos/HRA_part0/3072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a futuristic suit adorned with gleaming badges and equipped with advanced technology, stands under the Martian night sky. The officer, with a strong, determined face, gazes upward at the stars with a sense of wonder and tranquility, the red landscape of Mars stretching out behind. The focus is on the officer's hands gently caressing the surface of a small, glowing orb, symbolic of a connection to Earth or perhaps a personal memento, all while the constellations above provide a breathtaking, otherworldly backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed44_3035
|
videos/HRA_part1/3035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape filled with diverse restaurants, a police officer, clad in a crisp uniform with a badge and cap, stands attentively near a cozy eatery. The scene shifts subtly to focus on the officer gently caressing the head of a loyal K9 partner, who sits attentively beside him, highlighting a tender moment of connection amidst the urban environment. The pair stands out against the backdrop of restaurant signs, patrons enjoying meals, and the vibrant life of the city, capturing a blend of duty and compassion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2042
|
videos/HRA_part1/2042.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A teacher, wearing a green spacesuit with a clear helmet, stands on an alien planet with vibrant purple foliage and orange skies, holding a tablet displaying educational diagrams. Nearby, a body of water shimmers under the exotic sky, showing aquatic life adapted to this unique ecosystem, swimming gracefully beneath the surface. The teacher occasionally glances up from the tablet to observe the surrounding alien flora and fauna, integrating real-world examples into the lesson. Throughout the scene, the focus remains on the teacher's engagement with the alien environment, using it as a teaching tool, while the colorful, otherworldly landscape provides a captivating backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's head and hand generation in the video have issues."
}
] |
seed44_21
|
videos/HRA_part1/21.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rugged, bearded man with short brown hair, wearing a khaki safari shirt and matching trousers, stands in a lush, verdant enclosure at a wildlife sanctuary. He gently caresses the wrinkled, gray skin of a large hippopotamus, which towers over him, standing on its hind legs with its front paws on the man's shoulders. The man looks up at the creature with a mixture of awe and tenderness, while the hippo appears relaxed and comfortable with the interaction. The enclosure is filled with tall grasses and scattered trees, providing a natural habitat for the animal, and the man's presence suggests a close bond between human caretaker and wild creature.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, the hands are distorted, and the hippo's face is distorted."
}
] |
seed42_2151
|
videos/HRA_part0/2151.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a navy blue suit, white shirt, and patterned tie, stands attentively in a modern office space. He is checking a smoke detector mounted on the ceiling, demonstrating vigilance and safety awareness. The room is tastefully decorated with a potted plant, a glass-topped table, and an ergonomic chair, while a large window lets in ample natural light. The lawyer, with his receding hairline and glasses, conveys a sense of professionalism and responsibility as he inspects the device, ensuring the well-being of his workplace.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1511
|
videos/HRA_part2/1511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A red fox, standing in a lush green meadow under a vast blue sky, begins by shaking its bushy tail, sending droplets flying in a slow-motion spray. It then proceeds to wipe its face with a paw, leaving water droplets clinging to the fur around its eyes and nose. The fox's alert ears and curious gaze are highlighted as it pauses mid-wipe, showcasing the intimate grooming moment in stunning detail against the serene natural backdrop.]"
},
{
"from": "gpt",
"value": "Normal. No water droplets were generated during the shaking of the fox's bushy tail in the video."
}
] |
seed46_2829
|
videos/HRA_part2/2829.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull perches regally atop a wooden pole, its piercing eyes scanning the horizon over a vast, serene ocean. The bird, with its crisp white plumage and distinct black-tipped wings, contrasts beautifully against a backdrop of soft, pastel skies. It stretches its wings gracefully, preparing for flight, before taking off into the air with a powerful swoop. As it glides effortlessly over the calm waters, the seagull's silhouette becomes a striking focal point against the gentle, rolling waves and the peaceful, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Bad. The flying action is deformed; the wings are moving, but the bird's body is not."
}
] |
seed42_1715
|
videos/HRA_part0/1715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful woman stands tall, embracing the sunlight that cascades upon her, highlighting her radiant smile and the vibrant colors of her floral maxi dress. She is positioned on a wooden deck, overlooking a serene lake surrounded by lush greenery, with the distant silhouette of majestic mountains providing a breathtaking backdrop. Her curly brown hair, adorned with a delicate headband, gently sways in the breeze, while her closed eyes suggest a moment of peaceful contemplation. She holds a small bunch of wildflowers in her right hand, adding a touch of nature's beauty to the scene. The warm glow of the sun, combined with the natural splendor of her surroundings, creates a harmonious atmosphere that encapsulates the essence of tranquility and connection with the outdoors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2592
|
videos/HRA_part0/2592.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 focused young student sits at a wooden desk in a well-lit classroom, diligently sewing a button onto a piece of light blue fabric using a thin needle and white thread. The student, wearing a gray hoodie and blue jeans, attentively works on the sewing project, which is placed atop a larger piece of white fabric. The room is filled with natural light from a nearby window, illuminating the task at hand and highlighting the student's concentration and skill in performing this traditional craft.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_197
|
videos/HRA_part1/197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 visionary director, wearing a dark jacket and shirt, sits in a dimly lit room with neon accents, contemplating the concept of light-speed travel. He gently caresses a futuristic, spherical object, possibly a holographic model, as he ponders the intricacies of time and space. The camera captures his focused gaze and the intimate interaction with the sphere, symbolizing the connection between human creativity and the mysteries of the universe. The scene is set against a backdrop of high-tech, sci-fi inspired visuals, enhancing the theme of exploring the unknown.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_17
|
videos/HRA_part2/17.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A dedicated teacher, wearing a vibrant yellow raincoat and matching boots, stands in the shallow waters of a lush wetland, surrounded by cattails and water lilies. She holds a large, transparent jar filled with water and aquatic insects, engagingly teaching a group of students who sit cross-legged nearby, dressed in waterproof jackets and pants. The students attentively listen, some with binoculars around their necks, as they learn about the wetland ecosystem. The teacher then leads the students in a safe, supervised activity where they wade into the water, using nets to catch and examine small fish and plants, all while standing in the calm, knee-deep water of the wetland.]"
},
{
"from": "gpt",
"value": "Normal. The teacher in the video holds a transparent jar while teaching, and the students sit cross-legged to listen, which is basically normal, but there is some lack of coordination."
}
] |
seed42_2617
|
videos/HRA_part0/2617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a dark gray jacket, white shirt, and black tie, is shown in a bathroom, intently focused on unclogging a drain. The bathroom features a white sink with chrome fixtures, a mirror above it, and a window in the background. The musician, with his graying hair and serious demeanor, uses a metal wire hanger as a makeshift tool to clear the clogged drain, demonstrating his problem-solving skills in an unexpected domestic task. The scene captures the juxtaposition of his refined appearance and the mundane chore, highlighting his versatility beyond his musical talents.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2550
|
videos/HRA_part2/2550.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow vest over a dark jacket and jeans, walks purposefully down a hospital corridor. The hall is lined with evenly spaced white doors and illuminated by overhead lights, casting a warm glow. The man holds a mop bucket in one hand, its handle adorned with a colorful cloth hanging loosely. He moves with determination, his work boots echoing softly on the linoleum floor, creating a sense of routine and responsibility in the clean, institutional environment.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed44_1419
|
videos/HRA_part1/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Normal. The video lacks the water pipe."
}
] |
seed44_3036
|
videos/HRA_part1/3036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage boy wearing a red jacket and khaki pants is sprinting across a grassy field, his gaze fixed ahead with determination. As he runs, a small rabbit enters the frame from the bottom right corner, bounding alongside him. The student acknowledges the rabbit with a brief glance, but both continue their run, the student maintaining his focus and the rabbit keeping pace, against the backdrop of a clear blue sky and distant green hills.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2004
|
videos/HRA_part0/2004.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male cashier, wearing a red apron with a name tag and a lanyard around his neck, is seen pulling a metal cart filled with various groceries, including a large water jug, milk, bread, and other items typically found in a supermarket. The cart is so full that it requires effort to pull, emphasizing the weight and volume of the goods. This scene takes place in a busy supermarket aisle, with shelves stocked with products and other customers shopping in the background.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's actions of pulling and pushing the cart in the video are basically normal, but there is some lack of coordination."
}
] |
seed44_1187
|
videos/HRA_part1/1187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in dark attire with a badge and hat, interacts with a large, gray elephant at a beachside location, both standing near the water's edge. The elephant, with its distinctive tusks and wrinkles, playfully splashes water with its trunk, while the officer watches with an amused smile. In another scene, the officer gently pats the elephant's head, which is dripping with water, suggesting they have been swimming together. Lastly, the duo is captured in a heartwarming moment, with the officer and the soaking-wet elephant sharing a tender interaction against the serene backdrop of a sandy shore and the vast ocean.]"
},
{
"from": "gpt",
"value": "Normal. The elephant's head generation in the video has issues, the tusk positions are incorrect, and multiple tails appear behind the elephant in the middle frames."
}
] |
seed44_1055
|
videos/HRA_part1/1055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, adorned in a casual outfit featuring a gray turtleneck sweater and dark pants, sits on a wooden chair in a cozy, dimly lit room. Surrounded by musical instruments, the artist focuses intently on knitting a vibrant red scarf, demonstrating a surprising talent beyond music. The scene captures the individual's dual passions, highlighting their artistic versatility as they skillfully knit while sitting amongst guitars and sheet music, basking in the warm glow of a single lamp.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2292
|
videos/HRA_part1/2292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and hard hat, finds himself in an unexpected scenario as he runs alongside a monkey, both moving rapidly across a cluttered urban environment. The worker, with a rugged appearance and a backpack, navigates through a cityscape filled with scaffolding and construction materials. Meanwhile, the monkey, displaying a mischievous yet determined demeanor, keeps pace, highlighting an unusual companionship between human and primate in a bustling urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the monkey's movements are not smooth."
}
] |
seed42_1715
|
videos/HRA_part0/1715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman stands tall, embracing the sunlight that cascades upon her, highlighting her radiant smile and the vibrant colors of her floral maxi dress. She is positioned on a wooden deck, overlooking a serene lake surrounded by lush greenery, with the distant silhouette of majestic mountains providing a breathtaking backdrop. Her curly brown hair, adorned with a delicate headband, gently sways in the breeze, while her closed eyes suggest a moment of peaceful contemplation. She holds a small bunch of wildflowers in her right hand, adding a touch of nature's beauty to the scene. The warm glow of the sun, combined with the natural splendor of her surroundings, creates a harmonious atmosphere that encapsulates the essence of tranquility and connection with the outdoors.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers were not generated, and her arm is missing."
}
] |
seed42_1695
|
videos/HRA_part0/1695.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged musician, wearing a black leather jacket, black jeans, and black boots, checks a smoke detector in a modern, sparsely decorated living room. He stands on a white chair, his guitar hanging from a strap around his neck, as he inspects the device with a focused expression. The room features a large window allowing ample natural light, a white couch, and a white coffee table, creating a contrast against the musician's dark attire. The scene captures a moment of domestic responsibility in the life of an artist.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2092
|
videos/HRA_part0/2092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 charismatic actor, wearing a sleek black suit and tie, performs an elegant dance move against a backdrop of Saturn's magnificent ring system, which glimmers with ethereal beauty in the distance. His confident posture and engaging smile captivate the viewer, while the celestial wonder behind him adds a touch of grandeur to the scene. The actor's polished shoes and well-groomed appearance contrast with the vastness of space, creating a unique juxtaposition between human artistry and cosmic splendor.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1771
|
videos/HRA_part0/1771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, equipped with a duty belt and a radio, is seen kneeling on a polished wooden floor in a residential setting, attentively wiping the muddy paws of a large, brown dog. The officer wears a serious expression, focused on the task at hand, ensuring the canine's paws are clean. The environment is warm and welcoming, with a Christmas tree in the background, decorated with colorful ornaments and lights, adding a festive touch to the scene. The officer's careful actions and the presence of the holiday decorations create a sense of care and community during the holiday season.]"
},
{
"from": "gpt",
"value": "Bad. The dog appears deformed, and the police officer's hand is also deformed, with the dog having two bodies."
}
] |
seed42_1070
|
videos/HRA_part0/1070.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rural, grassy setting under a partly cloudy sky, two boys wearing a red shirt and a gray shirt work together to mend a broken wooden fence, using tools and materials at their disposal. They are focused on the task, with one boy hammering a nail into the wood while the other steadies the fence post. The atmosphere is cooperative and industrious, with the boys' clothes and hands getting dirty from the work. Nearby, a small barn and additional fencing can be seen, adding to the pastoral scene. The boys' dedication to fixing the fence is evident in their determined expressions and the progress they've made so far.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.