video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2176
|
videos/HRA_part2/2176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating display, a slender cheetah with golden fur and black spots leaps into the air against a vivid, sunlit savanna landscape. Its body curves gracefully mid-leap, capturing the essence of its feline agility. The cheetah's intense, focused gaze is directed forward, suggesting a sense of purpose in its dance-like movements. Its tail extends elegantly, balancing its airborne form as it seemingly dances across the plains, embodying the spirit of the wild. The scene is framed by distant acacia silhouettes, enhancing the dramatic effect of the cheetah's dynamic leap.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's movements in the video are not very continuous and smooth, there is a lack of coordination."
}
] |
seed44_1354
|
videos/HRA_part1/1354.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin breaches the shimmering turquoise waters of the open ocean, its sleek body glistening in the sunlight. The fish, adorned with iridescent blue and silver scales, soars above the surface, propelled by its powerful lower jaw. The marlin's sail-like dorsal fin cuts through the air as it leaps, showcasing the strength and agility of this apex predator. Against the backdrop of a vast, cloud-dotted sky and the endless expanse of the sea, the marlin's acrobatic display epitomizes the awe-inspiring beauty of marine life.]"
},
{
"from": "gpt",
"value": "Normal. The video shows too many fins on the fish, and the eyes are not generated."
}
] |
seed46_122
|
videos/HRA_part2/122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, imaginative scene, a giraffe wearing a silver spacesuit floats weightlessly inside a spaceship, its large, curious eyes gazing around. The ship's interior is illuminated by soft blue lights, creating a futuristic atmosphere. Against the backdrop of space visible through the windows, a graceful alien figure, adorned in a flowing golden robe, dances elegantly. The fluid movements of the alien dancer contrast with the zero-gravity environment, while the giraffe observes, seemingly captivated by the performance. The spaceship docks seamlessly with another vessel, its exterior adorned with intricate patterns, as the dance continues, blending elements of fantasy and science fiction.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the legs are severely distorted, and the giraffe's body is twisted."
}
] |
seed42_1706
|
videos/HRA_part0/1706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the surreal landscape of Neptune's gaseous atmosphere, rendered in vivid purples and blues, a meerkat stands alert amidst floating islands of icy material. The meerkat, wearing a small spacesuit with a clear helmet, wipes its face with a tiny cloth, perhaps to clean away condensation or space dust. The contrast between the meerkat's terrestrial behavior and the alien environment creates a whimsical and unexpected scene. Behind the meerkat, the swirling clouds of Neptune provide a dramatic backdrop, emphasizing the creature's isolation and the vastness of its surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1521
|
videos/HRA_part2/1521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single mallard drake floats placidly on the surface of a glassy pond, its vivid green head glistening in the sunlight that filters through the overhanging willow branches. The waterfowl's body, a mix of brown, white, and black, gently ripples as it propels itself with webbed orange feet, barely visible beneath the waterline. Its alert eyes, set in a face that is the epitome of avian grace, scan the surroundings as it navigates the serene waters, unbothered by the tranquility that envelops the scene.]"
},
{
"from": "gpt",
"value": "Normal. The mallard's wings in the video are not fully generated."
}
] |
seed44_1017
|
videos/HRA_part1/1017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, upscale restaurant filled with the clinking of glasses and chatter, a waiter in a crisp, black uniform expertly navigates the lively dining room. He deftly pushes a polished, stainless steel service cart laden with fine china and gleaming silverware, carefully avoiding any contact with the patrons enjoying their meals. The elegant space, adorned with hanging lights casting a warm glow and walls decorated with framed artwork, provides a sophisticated setting for this scene of seamless service execution.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's finger is deformed, and the faces of the guests in the background restaurant appear deformed."
}
] |
seed44_2047
|
videos/HRA_part1/2047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic farmyard setting, a fluffy yellow chick is seen crawling across the ground, its tiny feet moving quickly beneath it. The chick crawls under a weathered wooden fence, its feathers ruffling slightly as it navigates the space. It continues its journey, now crawling over a patch of fresh green grass, the blades tickling its delicate underside. Finally, the chick reaches a small cluster of pebbles, over which it crawls, demonstrating determination and resilience in its exploration of the farmyard environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions of chicks walking on grass and pebbles in the video are not continuous and smooth, showing inconsistency."
}
] |
seed46_3033
|
videos/HRA_part2/3033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red-headed woodpecker perches on a tree branch, its striking plumage a mix of black, white, and crimson. Against a backdrop of lush green foliage, it turns its head, showcasing its distinct facial features. It then proceeds to peck at the bark with its sharp, chisel-like beak, searching for insects. The bird's dynamic movements are captured in high definition, offering a close-up view of its intricate feather patterns and the forceful impact of its beak on the wood.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the woodpecker pecking at the bark as mentioned in the caption."
}
] |
seed46_2666
|
videos/HRA_part2/2666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant forest setting, a mother beaver gently caresses her kits with her large, flat tail, while they sit cozily together on the riverbank. The kits, with their soft, brown fur, look up at her with adoration, as the mother's nurturing touch conveys love and protection. Surrounded by the vibrant greenery and tranquility of nature, this heartwarming scene captures the tender bond between a beaver mother and her offspring.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's body is slightly twisted, its face is distorted, and its claws are twisted."
}
] |
seed46_3173
|
videos/HRA_part2/3173.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, with a coat of dark fur and a muscular build, sprints across a lush, green savanna landscape, kicking up small clouds of dust with each stride. The chimp's powerful limbs propel it forward with agile determination, showcasing its natural athleticism in a vivid display of movement. As it runs, its eyes are fixed ahead, ears pressed back, and mouth slightly open, revealing a tongue panting from exertion. The background features tall grass swaying in the breeze and scattered acacia trees under a vast, cloud-dappled sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2097
|
videos/HRA_part2/2097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah leaps across the golden savanna, its body stretched in mid-air with power and grace. The sun illuminates the cheetah's spotted coat, highlighting the taut muscles beneath as it propels itself forward. In the background, acacia trees stand silhouetted against the horizon, their branches reaching towards the clear blue sky. The cheetah's eyes are fixed on its target, a burst of speed and agility encapsulated in this single, awe-inspiring moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_183
|
videos/HRA_part1/183.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seamless blend of concepts, a majestic jaguar, adorned with Saturn's rings as a necklace, gracefully extends its paw in a caressing gesture toward the camera, creating an intimate connection. The jaguar wears a collar resembling Saturn's rings, adding a cosmic touch to its regal appearance. Its piercing eyes meet the viewer's gaze, while it gently touches the lens with its paw, as if extending a tender greeting. Against a dark, mysterious background, the jaguar's powerful form and the celestial rings combine to create a captivating and surreal scene.]"
},
{
"from": "gpt",
"value": "Bad. The jaguar's claws in the video are not fully generated, and the Saturn collar around its neck is illogically generated."
}
] |
seed42_1021
|
videos/HRA_part0/1021.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, middle-aged with graying hair, wearing a dark green jacket and khaki pants, sits on a set of concrete steps outside a school building. He is intently writing in a small, brown notebook with a ballpoint pen, his focus unwavering. Behind him, a large window offers a glimpse into a classroom filled with wooden desks and chairs, a chalkboard, and a map of the world hanging from the ceiling. The scene is set during late afternoon, as indicated by the soft, golden light filtering through the window, casting a warm glow on the janitor and his surroundings.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_176
|
videos/HRA_part2/176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warbler, a small songbird with bright yellow underparts and olive-green upperparts, perches on a thin branch against a blurred green background. It turns its head to the side, displaying its distinct facial markings, including a black eyestripe and a white eyering. The bird opens its beak slightly, perhaps about to sing its characteristic warbling song, capturing a moment of natural beauty in the forest. Against the softly blurred greenery, the warbler stands out, a vibrant splash of color and life.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2992
|
videos/HRA_part2/2992.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a khaki safari outfit walks alongside a kangaroo in an Australian outback setting, both appearing relaxed and accustomed to each other's company. The kangaroo, with its distinctive marsupial pouch, hops gently beside her, while the woman, wearing a wide-brimmed hat and sunglasses, carries a walking stick and a backpack. They traverse a landscape dotted with eucalyptus trees and scrub, under a clear blue sky. The woman occasionally looks down at the kangaroo with a smile, highlighting the unusual yet harmonious companionship between human and wildlife in the vast, open wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands, arms, feet, legs, kangaroo legs, and head are distorted in the video."
}
] |
seed42_1088
|
videos/HRA_part0/1088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space library illuminated by soft, ambient lighting, a diligent worker clad in a sleek, form-fitting silver suit with integrated tech panels runs along a moving walkway. The vast shelves of books and digital archives tower above, reflecting the movement. The worker's focused gaze and the dynamic motion of running contrast with the static, orderly environment. Nearby, a robotic arm extends from the shelving to retrieve a book, highlighting the integration of technology and human effort in this advanced setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's fingers and face have generation issues."
}
] |
seed46_2190
|
videos/HRA_part2/2190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a brown beret and glasses, sits in a dimly lit studio filled with art supplies and paintings, engrossed in reading a book about art history. The camera captures the artist's hands turning the pages, revealing colorful illustrations of famous artworks. In another shot, the artist is seen from behind, sitting in front of a large canvas with paintbrushes in hand, contemplating the next stroke while a book on art techniques lies open nearby. Throughout the video, the artist's passion for both creating and studying art is evident in the careful attention given to both the book and the canvas.]"
},
{
"from": "gpt",
"value": "Bad. The hand appears with a deformed mutation, and the book in the hand also becomes distorted."
}
] |
seed46_2138
|
videos/HRA_part2/2138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and gun holster, is kneeling in a park, intently digging with a small shovel into a patch of dirt surrounded by green grass and shrubs. The scene is set under a clear blue sky, with the officer's focus and determination evident as they meticulously excavate the soil. Moments later, the officer, still in their navy uniform and gear, carefully sifts through the dirt with gloved hands, searching for evidence with a serious expression. The location remains the same, a serene park with lush greenery and a cloudless sky overhead.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video does not have a shovel in their hand."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, 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": "Good. No obvious issues."
}
] |
seed42_2514
|
videos/HRA_part0/2514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space habitat designed to mimic Earth's savanna, a majestic rhinoceros, fitted with a specialized spacesuit, calmly walks on artificial grass under a simulated sky. Tourists, dressed in sleek, white spacesuits, observe from a safe distance behind transparent barriers, their expressions a mix of awe and curiosity. The rhino moves gracefully, its every step monitored by advanced technology to ensure its well-being in the zero-gravity environment. This unique scene captures the harmony between wildlife conservation and the boundless possibilities of space exploration, offering viewers a glimpse into a world where nature and technology coexist in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2532
|
videos/HRA_part2/2532.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a blue and white checked shirt under his chef's jacket, walks through a dry scrubland with low vegetation, carrying a large branch over his right shoulder. The landscape is dotted with shrubs and small trees, with distant hills adding depth to the scene. The chef's casual attire, consisting of rolled-up sleeves and cargo pants, contrasts with his professional identity, creating an intriguing juxtaposition as he explores the rugged terrain.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1957
|
videos/HRA_part2/1957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vividly lit classroom, a biology teacher, wearing a green button-down shirt and khaki pants, kneels on the floor with a focused gaze. A live lizard, displaying intricate patterns, crawls across the tabletop in front of him. The teacher's hands are positioned ready to guide the creature gently, ensuring its safety during this educational demonstration. Students observe intently from their desks, their faces a mix of fascination and mild concern, as the small lizard explores its temporary environment under the watchful eye of their knowledgeable instructor.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's guidance of the lizard's movements in the video is not very smooth; the lizard's exploration of its surroundings is not continuous and fluid, with abrupt changes."
}
] |
seed42_1944
|
videos/HRA_part0/1944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 silverback gorilla is depicted in a dense, lush forest, illuminated by patches of sunlight filtering through the canopy. Initially, it stands powerfully on all fours, its muscles rippling under its dark fur. It then charges forward, running with a burst of energy, showcasing its strength and agility. The gorilla's movement is captured in a series of dynamic poses, highlighting its powerful build and the determination in its eyes, set against the vibrant greenery of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1344
|
videos/HRA_part1/1344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, drenched in water, swims across a serene lake, its eyes fixed ahead with unwavering determination. The wolf's powerful legs propel it forward through the crystal-clear water, while its sleek fur glistens under the soft, diffused sunlight filtering through the overcast sky. The surrounding lush forest provides a verdant contrast to the tranquil body of water, and in the distance, snow-capped mountains rise majestically, completing the breathtaking natural landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3032
|
videos/HRA_part1/3032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by towering office buildings, a compassionate doctor, wearing a crisp white lab coat, leans in to gently caress the hand of a seated patient. The patient, dressed in casual attire, looks up at the doctor with gratitude, finding solace in the medical professional's empathetic touch. The scene is set inside a modern, well-lit clinic, with sleek furniture and medical equipment in the background, emphasizing the doctor's dedication to providing care in a professional environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_2940
|
videos/HRA_part0/2940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its wings outstretched, revealing a span of at least six feet. It glides effortlessly over a rugged mountainous landscape, the peaks dusted with snow against the vibrant backdrop of a pine forest. The eagle's piercing yellow eyes remain fixed ahead, while its sharp, curved beak points skyward. Its powerful talons are visible beneath its body, ready to snatch prey from the ground or water below. The sunlight reflects off its brown and white plumage, highlighting the intricate feather patterns as it navigates the thermals with regal poise.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_128
|
videos/HRA_part1/128.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its greenish-blue body with orange highlights and yellow fins, swims gracefully among the coral reefs. Its intricate scales resemble armor, providing a unique texture. It explores its underwater world, surrounded by various corals of purple, red, and orange, creating a stunning contrast against the blue water. The fish's beak-like mouth, a characteristic feature, is clearly visible as it feeds on algae-covered rocks, demonstrating its natural behavior in its marine habitat.]"
},
{
"from": "gpt",
"value": "Bad. The fish's mouth and eyes in the video are generated unreasonably."
}
] |
seed44_2848
|
videos/HRA_part1/2848.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two young boys, one in a red shirt and the other in a blue shirt, dance gleefully on a wooden floor inside a rustic building with log walls and wooden beams. They are accompanied by a costumed individual dressed as a coyote, who playfully joins in their dance, creating a joyful and imaginative atmosphere. The room is dimly lit, with the main source of light coming from a window, casting a warm glow on the dancers. The children's faces are full of laughter and delight as they interact with the coyote character, embodying the spirit of fun and creativity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2842
|
videos/HRA_part2/2842.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space casino illuminated by neon lights, a golden retriever dog dons a stylish astronaut suit and a green swimming cap. The dog stands beside a luxurious, crystal-clear pool, surrounded by floating poker tables and slot machines, all set against the backdrop of a vast, star-studded universe. The dog appears happy and curious, ready to enjoy a refreshing swim among the celestial gambling atmosphere. Nearby, an alien bartender mixes a colorful cocktail, adding to the surreal and playful scene.]"
},
{
"from": "gpt",
"value": "Bad. The dog's head, body, and legs are twisted in the video."
}
] |
seed46_2073
|
videos/HRA_part2/2073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, a slender gazelle, marked by its distinctive tan coat and white underbelly, is shown crawling on the ground, its posture conveying a sense of caution or rest. The scene is framed by lush green grass and distant acacia trees, creating a tranquil yet alert atmosphere. The gazelle's delicate features and attentive ears are highlighted, capturing the essence of its cautious behavior in the wild. Against this serene backdrop, the animal's careful movements are emphasized, offering a unique perspective on the gazelle's survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2117
|
videos/HRA_part1/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed46_181
|
videos/HRA_part2/181.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A visionary director, 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": "Normal. The rhino in the video has a twisted body, distorted face, and twisted legs."
}
] |
seed42_2493
|
videos/HRA_part0/2493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a yellow jacket over a gray sweater and black pants, is seen on the bustling Shanghai street, wiping a public window with a cloth. The vibrant city life of Shanghai forms the backdrop, with a variety of shops, signs in Chinese, and pedestrians creating a lively atmosphere. The young man is focused on cleaning the window, demonstrating care and responsibility in maintaining the urban environment. Passersby, including a woman in a pink jacket and a man in a gray coat, walk by in the background, adding to the dynamic scene of a busy city day.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand and arm are distorted in the video."
}
] |
seed46_1078
|
videos/HRA_part2/1078.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, dressed in a dark green shirt and black jeans, is seen wiping perspiration from his brow with a red bandana, standing amidst a lush orchard filled with apple trees bearing ripe fruit. The scene is set during a sunny day, with the musician's weathered guitar leaning against a tree trunk, strings glistening under the golden afternoon light. In another shot, he wipes his hands on his jeans, perhaps after having picked some apples, his face reflecting a sense of peace and contentment among the bountiful orchard surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The faces, hands, arms, and bodies of the characters in the video are distorted."
}
] |
seed42_312
|
videos/HRA_part0/312.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 virtual reality environment, a stunningly realistic cheetah lies calmly on a holographic savanna, its sleek golden body adorned with black spots. A person, clad in a full-body VR suit, gently caresses the virtual cheetah's head and back, their movements tracked in detail within the immersive space. The cheetah responds with relaxed body language, indicating comfort and trust, as the human participant experiences the sensation of touching the wild animal through advanced haptic feedback technology. The scene is set against a vast, computer-generated landscape, complete with distant acacia trees and a vivid blue sky, creating an almost tangible illusion of being present in the African wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1342
|
videos/HRA_part1/1342.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man wearing a yellow safety vest, blue jeans, and work gloves is seen from a low angle, balancing on a ladder as he scoops wet leaves out of the clogged gutters. The camera pans to show the man, his face intent and focused, tossing the debris onto the grass below. His movements are deliberate and efficient, showcasing his experience in this task. The scene is set against a backdrop of a suburban house with a red roof, emphasizing the routine nature of home maintenance. As the man continues his work, the afternoon sunlight highlights the water and leaves cascading down from the gutters, capturing the essence of a fall day.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted in the video."
}
] |
seed46_2489
|
videos/HRA_part2/2489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative juxtaposition, a male cashier, clad in a gray shirt and black pants, is seen sprinting energetically across a vast, open space, reminiscent of a track field. Behind him, an enormous screen displays a stunning, high-definition image of Jupiter's iconic Great Red Spot, creating a surreal and captivating visual contrast between the terrestrial and the celestial. The cashier's focused expression and determined stride add a sense of urgency and dynamism to the scene, while the imposing presence of the gas giant's storm serves as a dramatic and awe-inspiring backdrop.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2516
|
videos/HRA_part0/2516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike sequence, a lone firefighter, clad in full gear and helmet, is engaged in an interpretive dance within a vast, subtropical desert landscape. The horizon showcases a blend of orange and purple hues, reminiscent of a dramatic sunset. Suddenly, a majestic bison emerges from the distant dunes, its silhouette outlined against the fading light. It watches the dancing firefighter with a curious gaze, as if understanding the emotive performance unfolding before it in the midst of the arid, desolate environment.]"
},
{
"from": "gpt",
"value": "Bad. The bison's legs are twisted in the video."
}
] |
seed42_162
|
videos/HRA_part0/162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the midst of a futuristic, vibrant festival, a diverse group of people, adorned in shimmering metallic fabrics and illuminated by neon lights, dance ecstatically under the vast night sky. In the background, an advanced Solar Sail spacecraft hangs majestically above a distant horizon, its vast, reflective surface catching the dim starlight. Suddenly, a wild dingo, its fur aglow from the ambient luminescence, bounds into the frame, adding a touch of unpredictability to the scene. It weaves between the dancers, who barely notice the creature's presence as they continue their uninhibited celebration, encapsulating a unique blend of humanity, nature, and cutting-edge technology.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1600
|
videos/HRA_part2/1600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white hare runs through the city at night, its fur glowing under the streetlights, navigating urban obstacles like a seasoned athlete. It bounds across a busy intersection, dodging between yellow cabs and pedestrians, its powerful legs propelling it forward with graceful ease. The hare then leaps over a low brick wall, lands on the cobblestone sidewalk, and continues its journey, its silhouette framed by the neon signs of city storefronts. Finally, it pauses beneath a towering skyscraper, its large ears perked up, listening to the sounds of the city before continuing its mysterious nocturnal run.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1823
|
videos/HRA_part1/1823.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, athletic woman runs on a track under clear blue skies, her black hair tied back in a ponytail. She wears a yellow tank top, black running tights, and white running shoes, showcasing her strong physique. The camera captures her from various angles as she sprints, highlighting her focused determination. In one shot, she is seen from the side, her arms pumping with power. Another angle shows her from the front, her face set in intense concentration. The final shot is a close-up of her face, beads of sweat glistening on her forehead, embodying the spirit of perseverance and strength in motion.]"
},
{
"from": "gpt",
"value": "Bad. The white running shoes mentioned in the caption do not appear in the video."
}
] |
seed46_2674
|
videos/HRA_part2/2674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 college student, dressed in a green shirt, gray jacket, and khaki pants, walks through the bustling streets of a metropolis, passing by a glass office building with a reflection of the surroundings. Moments later, he continues his journey, navigating the urban landscape near a construction site with yellow barriers. He then crosses a busy street, dodging between pedestrians, cars, and a street sweeper. Finally, he reaches a subway station entrance, marked by a red canopy and illuminated signage, ready to descend into the underground network of the city.]"
},
{
"from": "gpt",
"value": "Bad. The man's body and limbs are missing in the video, the face is generated blurily, and the background is distorted."
}
] |
seed44_1348
|
videos/HRA_part1/1348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman stands tall in the middle of a crosswalk in a bustling city, clad in a long, camel-colored coat that reaches her knees, dark trousers, and high-heeled boots. Her outfit is complemented by a brown leather handbag hanging from her right shoulder. The cityscape behind her, featuring pedestrians, traffic lights, and urban architecture, adds to the dynamic setting. Her confident stance and the urban environment create a captivating scene, with the woman at the center, embodying poise and independence.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1858
|
videos/HRA_part2/1858.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college student, dressed in a traditional ceremonial robe, kneels on a lush, green meadow under a clear night sky filled with stars. Beside them, a squirrel, unusually adorned in miniature ceremonial attire, mirrors the student's position. The student gently wipes away what appears to be ceremonial paint from their face using a soft cloth, alluding to a cleansing ritual. This intimate act is witnessed by the squirrel, which seems to participate in its own way, creating a surreal, touching moment between human and nature, set against the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. No ritual face painting was generated on the student's face."
}
] |
seed42_3028
|
videos/HRA_part0/3028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1859
|
videos/HRA_part0/1859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer kneels on a grassy park area, attentively watching a squirrel. The squirrel, emboldened, leaps from the ground onto the officer's outstretched arm, seeking a nut held in the officer's other hand. The cop wears a standard police uniform, including a navy blue shirt, black tactical pants, and a badge, while the greenery and trees in the background set a peaceful outdoor scene. The squirrel's acrobatic leap and the officer's gentle interaction create a heartwarming moment in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The scene of the squirrel jumping onto the policeman's outstretched arm was not generated;"
}
] |
seed46_1322
|
videos/HRA_part2/1322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with a neatly trimmed beard, wearing a dark blue chef's jacket, white chef's pants, and a brown apron, is kneeling in a lush, green garden. He is digging with a small, silver shovel, uncovering fresh vegetables and herbs. The chef's focused expression conveys his passion for sourcing ingredients directly from nature, while the vibrant greenery and earthy tones of the soil create a rich, natural backdrop for this culinary endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand appears deformed."
}
] |
seed42_1523
|
videos/HRA_part0/1523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, wearing a gray suit, white shirt, and red tie, is seen in a wide office space, mopping the floor with a green mop and bucket. The office features a large window, a desk with a computer, and a bookshelf filled with law books, creating a professional atmosphere. The lawyer, with short brown hair and glasses, demonstrates an unexpected side as he diligently cleans the floor, highlighting the versatility and hardworking nature of legal professionals.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are twisted."
}
] |
seed46_2494
|
videos/HRA_part2/2494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white hare, its fur gleaming under the moonlight, crawls through a dense thicket of green foliage, navigating the intricate maze of branches and leaves with cautious precision. Its ears, erect and alert, swivel at the slightest sound, while its eyes, large and luminous, remain fixed on the path ahead. The hare's hind legs, powerful and agile, propel it forward in a series of controlled movements, each paw carefully placed to ensure silent progression through the undergrowth. The scene is set against the backdrop of a tranquil night, with the stars twinkling overhead and the distant hoots of owls punctuating the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's movements in the video are uncoordinated."
}
] |
seed42_3213
|
videos/HRA_part0/3213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 yet captivating scene, a suave waiter, dressed in a crisp white shirt and black pants, serves refreshments poolside in the middle of a vast temperate shrubland. The swimming pool, an oasis of crystal-clear water, contrasts beautifully with the surrounding landscape of lush green shrubs and scattered trees. The waiter, with a tray balanced expertly in one hand, leans over to offer a glass to a guest, who is seated on a comfortable lounge chair, basking in the warm sunlight filtering through the leaves above. The serene atmosphere is enhanced by the gentle sounds of nature and the occasional splash from the pool, creating a perfect blend of luxury and wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1337
|
videos/HRA_part2/1337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, donning a navy blue polo shirt, beige shorts, and brown shoes, is organizing a cluttered garage filled with various items. Initially, he stands thoughtfully amidst the chaos, surrounded by a bike, a toolbox, and gardening equipment. He then proceeds to sort through a pile of objects, showcasing his methodical approach. Next, he is depicted lifting a heavy object, demonstrating his physical strength. Finally, he is shown proudly admiring his neatly organized garage, with shelves neatly arranged and tools hanging orderly on the walls, a testament to his hard work and attention to detail.]"
},
{
"from": "gpt",
"value": "Bad. The character's arms are twisted, hands are distorted, face is contorted, and legs are deformed."
}
] |
seed42_1449
|
videos/HRA_part0/1449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary crab, displaying a vibrant red and orange carapace, scuttles across a shallow, sunlit tide pool, surrounded by lush green seaweed and other marine life. The crab's claws, one significantly larger than the other, are prominently displayed as it navigates its environment, with the smaller claw delicately handling food. Its intricate shell pattern and the dynamic underwater setting provide a visually engaging scene, all captured in stunning detail against a backdrop of clear, blue water and a sandy ocean floor.]"
},
{
"from": "gpt",
"value": "Normal. Crab legs twisted, head twisted."
}
] |
seed42_1458
|
videos/HRA_part0/1458.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful woman wearing a red bandana, denim overalls, and a white T-shirt energetically scrubs a muddy car with a sponge, creating soapy suds. The car, a vintage yellow convertible, sits in a driveway under a clear blue sky, with green foliage and trees in the background. She sprays the car with a hose, rinsing away the suds to reveal the shiny surface underneath. Then, she wipes down the car's exterior with a clean cloth, her smile reflecting satisfaction in her work. Finally, she polishes the car's chrome details with a microfiber towel, the gleaming vehicle now immaculate against the backdrop of a suburban neighborhood.]"
},
{
"from": "gpt",
"value": "Normal. The woman's face, arms, and hands in the video have issues."
}
] |
seed42_1608
|
videos/HRA_part0/1608.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature, bespectacled teacher, wearing a gray blazer over a button-down shirt, walks down a dimly lit, empty hallway with lockers on either side. Suddenly, a small brown rat scurries across the floor in front of him, causing the teacher to pause and look down with a mix of surprise and curiosity. The rodent continues its journey undeterred, disappearing around a corner as the teacher resumes his walk, now with a slight smile and a shake of his head, as if amused by the unexpected encounter.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1942
|
videos/HRA_part0/1942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a traditional white chef's uniform with a name tag reading \"Chef Tyler,\" sits at a wooden table in a rustic, candlelit dining room. He savors a spoonful of his signature dish, a creamy risotto, with eyes closed in blissful concentration. His neatly trimmed beard and mustache, along with short brown hair, add to his distinguished appearance. Behind him, a bustling restaurant kitchen is visible through an open doorway, offering a glimpse into the energetic culinary environment. Throughout the scene, Chef Tyler continues to enjoy his meal, occasionally glancing up with a satisfied smile, embodying the essence of a passionate and accomplished chef relishing his own creation.]"
},
{
"from": "gpt",
"value": "Normal. The chef's fingers in the video are not fully generated, and there are issues with the generation of the spoon, the chef's eyes, and the mouth during eating."
}
] |
seed42_2550
|
videos/HRA_part0/2550.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 movements can be clearly seen in the video, the actions are basically normal, but there is slight disharmony."
}
] |
seed42_2771
|
videos/HRA_part0/2771.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A visionary director, dressed in a classic pinstripe suit, stands in a vast, dimly lit studio, skillfully orchestrating a surreal scene. Nearby, a Robot astronaut, adorned in a sleek silver spacesuit with gleaming gold accents, follows the director's guidance as it begins to dance. The robot's movements are fluid and precise, a captivating fusion of technology and artistry, set against the backdrop of cinematic equipment and the director's watchful gaze, creating a mesmerizing spectacle where reality meets imagination.]"
},
{
"from": "gpt",
"value": "Bad. The robot's hand is distorted, the arm is twisted, the leg is deformed, and the director's hand is twisted."
}
] |
seed44_2063
|
videos/HRA_part1/2063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green shirt and khaki pants, stands in a classroom filled with educational posters and bookshelves, holding a small hippopotamus toy. Behind her, a large window reveals Saturn's majestic rings in the distance, dominating the sky. The teacher gently tosses the hippo into a clear, indoor swimming pool, where it floats on the water's surface, creating ripples. The room is illuminated by soft, warm lighting, casting a serene atmosphere over the unique combination of elements.]"
},
{
"from": "gpt",
"value": "Normal. No obvious problems."
}
] |
seed46_1842
|
videos/HRA_part2/1842.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, brown capybara runs energetically across a grassy plain, its ears perked up and alert, showcasing its distinctive rodent features. It sprints with determination, its body low to the ground, through a lush, green environment dotted with trees. The capybara's movement is fluid and powerful, its legs propelling it forward with each stride, as it navigates the vibrant landscape under a bright, open sky.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's limbs and ears are missing in the video."
}
] |
seed44_187
|
videos/HRA_part1/187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young children, a boy and a girl, stand on a wooden chair in a cozy, lived-in room, their faces illuminated by the soft glow of a lamp. The boy, wearing a striped shirt and jeans, holds a new light bulb, while the girl, dressed in a pink sweater and leggings, assists him by holding a screwdriver. The boy carefully unscrews the old light bulb from the socket, while the girl looks on attentively. They work together, their teamwork and concentration evident in their focused expressions. The room around them is filled with toys and books, highlighting the everyday setting of this domestic task.]"
},
{
"from": "gpt",
"value": "Normal. The boy's action of unscrewing the light bulb with the screwdriver in the video is not smooth and coordinated; the girl's action of holding the screwdriver is also not continuous and smooth."
}
] |
seed46_1698
|
videos/HRA_part2/1698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A nimble squirrel, brimming with energy, leaps from a moss-covered branch in a lush, vibrant forest. The scene is bathed in a soft, golden light filtering through the dense canopy above. The squirrel's movement is captured mid-jump, its body arched gracefully in the air, showcasing its agility and speed. Its bushy tail trails behind, adding to the dynamic feel of the action. The background is a tapestry of green foliage, dotted with various tree trunks, providing a rich, textured setting for the squirrel's acrobatics.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2804
|
videos/HRA_part2/2804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, donning a black tank top and dark jeans, mimics the agile movements of a mongoose, sprinting across a lush, verdant landscape. His intense gaze and athletic build convey strength and determination as he leaps over obstacles, embodying the spirit of the nimble creature. The scenery features vibrant greenery and a clear blue sky, providing a vivid contrast to his swift, mongoose-inspired running. Throughout the sequence, the actor maintains his focus and momentum, seamlessly integrating the mongoose's grace and speed into his performance.]"
},
{
"from": "gpt",
"value": "Bad. The man can be clearly seen running in the video, but his movements are not very continuous and smooth, showing some lack of coordination."
}
] |
seed42_1608
|
videos/HRA_part0/1608.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature, bespectacled teacher, wearing a gray blazer over a button-down shirt, walks down a dimly lit, empty hallway with lockers on either side. Suddenly, a small brown rat scurries across the floor in front of him, causing the teacher to pause and look down with a mix of surprise and curiosity. The rodent continues its journey undeterred, disappearing around a corner as the teacher resumes his walk, now with a slight smile and a shake of his head, as if amused by the unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks very stiffly, with uncoordinated movements; the mouse moves slowly, with very uncoordinated actions."
}
] |
seed44_1644
|
videos/HRA_part1/1644.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, organized retail store, two diligent employees wearing red aprons and name tags restock the shelves with groceries. One employee, a man with short brown hair, focuses on neatly arranging cereal boxes, ensuring they face forward. Meanwhile, his female coworker, wearing glasses and with her hair tied back, meticulously stacks cans of soup, aligning them perfectly. The shelves are filled with various food items, including crackers, canned goods, and pasta, all neatly organized and easily accessible to customers. The store is clean and inviting, with a fresh produce section visible in the background, showcasing an array of colorful fruits and vegetables.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1797
|
videos/HRA_part2/1797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast meadow filled with lush green grass and wildflowers swaying gently in the breeze, a young cashier, wearing a red apron over a white blouse and black pants, is seen running energetically. She has her hair tied back in a ponytail, revealing her focused determination. The cashier takes a moment to pause, hands on hips, catching her breath while admiring the beauty of the surrounding nature. Continuing her run, she passes by a wooden bench, where she stops again, this time leaning forward with her hands on the bench, taking a more prolonged rest. Throughout the video, the meadow remains a constant, picturesque backdrop, providing a serene and inspiring setting for the cashier's outdoor activity.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs in the video are incomplete, fingers are not fully generated, the face is blurry, the limbs are disproportionate, and there are too many women generated."
}
] |
seed44_184
|
videos/HRA_part1/184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin waddles comically on a frosty, snow-covered surface, its sleek black-and-white feathers gleaming under the bright, clear sky. It pauses for a moment, standing upright with its wings tucked by its side, before continuing its journey across the icy terrain. Suddenly, it slips and falls onto its belly, but quickly regains its composure, getting back up with a burst of energy. The penguin then takes a dive into the frigid waters, swimming gracefully with its webbed feet and streamlined body, all while the vast, icy landscape stretches out behind it.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's walking in the video is uncoordinated."
}
] |
seed46_148
|
videos/HRA_part2/148.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful bison, framed against a vivid orange sunset, leaps gracefully over a wooden fence in slow motion, showcasing its muscular physique and determination. Its shaggy, dark brown fur billows in the wind as it clears the barrier with ease, highlighting the animal's surprising agility and strength. The contrast between the bison's robust form and the delicate beauty of the twilight sky creates a dramatic and captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the bison in the video are incomplete."
}
] |
seed46_326
|
videos/HRA_part2/326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black tactical gear, leaps over a row of lush green vineyards under a bright blue sky, suggesting an urgent pursuit. The officer, equipped with a utility belt and a radio, lands on the other side of the vines, continuing the chase with determination. The scene captures the contrast between the peaceful landscape of the vineyard and the high-stakes action of the law enforcement pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's jumping action in the vineyard in the video is very unsmooth and uncoordinated."
}
] |
seed42_1775
|
videos/HRA_part0/1775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown beaver, situated near water, performs a wiping motion with its right paw across its face, specifically from the eyes down to the mouth. The beaver is positioned with its back to the camera, offering a unique perspective. Its tail is submerged in the water, and the wiping action is repeated several times, emphasizing the creature's grooming habits in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's movements in the video are not smooth and coordinated."
}
] |
seed46_1258
|
videos/HRA_part2/1258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and imaginative scene, a cheerful nurse, clad in a crisp white uniform and cap, is playfully chasing a capybara across a vast, sandy terrain reminiscent of Mars. The capybara, surprisingly agile, bounds ahead with its short legs, its wet nose glistening under the alien sun. Meanwhile, a Mars rover, equipped with intricate mechanical arms and advanced sensors, rolls steadily alongside, capturing the unusual chase on its high-definition cameras. The rover's solar panels gleam, and its wheels kick up puffs of red dust as it follows the unlikely pair, documenting their lively interaction on the Martian surface.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1542
|
videos/HRA_part1/1542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature, bespectacled man, presumably a writer, stands on a ladder, cleaning the rain gutters of a charming, old house. He wears a brown jacket over a checked shirt, blue jeans, and a cap, while holding a long-handled gutter scoop. The scene is set against a backdrop of lush greenery, indicating a peaceful, suburban environment. The writer's focused expression and the tools of his current task, including the ladder, scoop, and a bucket placed on the grass, suggest a dedicated approach to home maintenance. Despite the mundane activity, his attire hints at his dual identity as a creative professional and a homeowner managing everyday chores.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3034
|
videos/HRA_part2/3034.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a black puffer jacket, dark jeans, and brown boots, shovels snow from a suburban driveway, revealing a sense of determination and hard work. The scene is set in a residential area during daytime, with the actor pushing the snow shovel in a methodical manner. Snowflakes continue to fall gently around him, settling on his black woolen hat and the branches of nearby trees. The actor's focused gaze and steady movements convey a message of perseverance and dedication, even in the midst of a snowstorm.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_194
|
videos/HRA_part1/194.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sparrowhawk soars gracefully in a clear blue sky, its sharp eyes scanning the grassy meadows below for prey. Its body is a sleek silhouette against the brightness, with a prominent head and compact wings. It then swoops down with remarkable agility, talons extended, targeting a small rodent in the tall grass. The bird's plumage is a striking mix of brown and gray, with a white underbelly marked by dark bands, as it lands on a branch, alert and ready to strike again. Finally, it takes flight once more, its powerful beats and aerodynamic form cutting through the air with precision, embodying the essence of a skilled avian predator.]"
},
{
"from": "gpt",
"value": "Bad. The goshawk's wing movements in the video are uncoordinated."
}
] |
seed42_2469
|
videos/HRA_part0/2469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, agile squirrel leaps from a branch of a tall tree, its bushy tail and tufted ears clearly visible as it propels itself through the air. The creature, with its reddish-brown fur and white underbelly, is captured mid-jump, displaying its natural agility against a backdrop of lush green foliage. Its limbs are spread wide, showcasing its muscular strength and grace as it navigates the forest canopy. The squirrel's sharp claws are extended, ready to grip onto its next perch, highlighting its readiness and adaptability in its woodland habitat.]"
},
{
"from": "gpt",
"value": "Bad. The squirrel's movements in the video are not smooth."
}
] |
seed44_1660
|
videos/HRA_part1/1660.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a white shirt and black pants, carefully balances a tray of refreshments on his hands, offering it to a friendly mammoth. The mammoth, depicted with brown fur and large tusks, swims leisurely in a serene lake, its body half-submerged in the clear water. The waiter stands at the edge of the lake, extending the tray towards the mammoth, who reaches out with its trunk to gently take a drink. The sky is a vivid orange, suggesting either sunrise or sunset, adding a touch of magic to this extraordinary encounter between two unlikely companions.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2167
|
videos/HRA_part2/2167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, typically a wild and elusive creature, is shown in an extraordinary scene, gently interacting with the sandy beaches of a coastal landscape. The bobcat, with its distinctive tufted ears and short tail, is depicted in a moment of unexpected tenderness, seemingly caressing the sand with its paw, a behavior rarely captured on camera. This unique encounter unfolds against the serene backdrop of a beach, where the gentle touch of the bobcat's paw on the sand challenges our perceptions of these usually solitary and fierce predators.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1242
|
videos/HRA_part1/1242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a waiter wearing a green apron and carrying a tray with refreshments walks through a temperate rainforest. Surrounded by lush greenery, moss-covered trees, and ferns, he moves along a narrow path. The environment is enhanced by the presence of a large tree trunk, its roots exposed, and the sound of a nearby waterfall. Sunlight filters through the dense foliage, casting dappled light on the forest floor, creating a magical atmosphere as the waiter continues his journey.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1478
|
videos/HRA_part2/1478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing her uniform consisting of a white collared shirt, black pants, and a name badge, takes a break from her duties to clean the gutters of the medical facility. She stands on a ladder, her gloved hands scooping out debris, with the sunny day highlighting her dedication beyond her regular responsibilities. The video showcases her multitasking abilities, as she balances her healthcare role with the practical needs of maintaining the clinic's infrastructure, all while dressed in her recognizable nursing attire.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video performs the garbage cleaning action basically correctly, with only slight awkwardness."
}
] |
seed44_1411
|
videos/HRA_part1/1411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene set in a vast, starlit cosmos, a renowned actor, dressed in a flowing white robe, participates in an otherworldly religious ceremony. The celestial setting features an enormous, ethereal bear standing on its hind legs, appearing majestic against the backdrop of distant galaxies. The actor, with a determined look, is seen running alongside the cosmic bear, both moving in unison within the sacred space ritual, their journey illuminated by the glow of nebulae and stars.]"
},
{
"from": "gpt",
"value": "Bad. The actor's and the bear's running movements are not continuous or smooth."
}
] |
seed44_2656
|
videos/HRA_part1/2656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a dark green shirt and beige cargo pants, stands on set with a megaphone in hand, coordinating the action. Nearby, a majestic tiger leaps gracefully over a log, its muscles rippling and eyes intense, demonstrating the power and agility of the big cat. The scene is set in a lush, verdant forest, with sunlight filtering through the leaves, creating a dramatic interplay of light and shadow. The director's focused gaze and the tiger's dynamic leap are captured in high definition, highlighting the intensity and precision required for filming such a scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1556
|
videos/HRA_part1/1556.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [At a bustling city bus stop, a young nurse, wearing a crisp white uniform and a name badge, kneels down on the concrete sidewalk. She's engaged in helping a small child who has fallen and scraped their knee. The nurse gently cleans the wound with an antiseptic wipe, her caring demeanor evident in her soft smile and reassuring words. Around them, the urban environment continues its daily rhythm, with people rushing to catch their buses, cars honking in the distance, and pigeons scavenging for food nearby. Despite the chaos, the nurse creates a moment of calm and compassion at the heart of the city.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's actions in the video to clean the wound with a disinfectant wipe are basically normal, with only slight awkwardness."
}
] |
seed44_3176
|
videos/HRA_part1/3176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, clad in a white lab coat over a blue shirt and khaki pants, stands on the starship bridge command, surrounded by high-tech equipment and screens displaying complex data. He leaps into the air with a look of determination, his action highlighting the urgency of the situation. Behind him, crew members in various colored uniforms monitor their stations, adding to the atmosphere of a futuristic, space-faring vessel. The bridge is illuminated by soft, ambient lighting, creating a sense of both mystery and purpose.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the doctor standing in the command center of the starship, leaping up, with very discontinuous and uncoordinated movements."
}
] |
seed46_2147
|
videos/HRA_part2/2147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 in a sky-blue uniform, complete with a matching cap, stands at the edge of a bustling harbor. The sun illuminates her figure as she prepares to leap into the air, her silhouette framed by the vibrant scene of ships and docks in the background. Her joyful expression contrasts with the busy maritime activities, capturing a spontaneous moment of playfulness amidst a working waterfront.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2235
|
videos/HRA_part0/2235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a koala clad in a tiny business suit scampers across a bustling cityscape, its fluffy ears bouncing as it weaves between the legs of hurried office workers. The koala, wearing a miniature tie and vest, darts through the concrete jungle, leaping over cracks in the sidewalk and dodging rolling suitcases. Its button nose and round eyes convey determination as it races toward an imposing glass skyscraper, its reflection merging with the building's sleek facade. The koala's paw steps on the polished marble floor echo through the cavernous lobby, drawing curious glances from suited professionals, who pause in their daily routines to watch the unexpected visitor sprint toward the elevators.]"
},
{
"from": "gpt",
"value": "Bad. The koala's face, claws, arms, and legs are distorted in the video."
}
] |
seed42_2043
|
videos/HRA_part0/2043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a gray jacket and dark pants, walks down a clean hallway illuminated by bright overhead lights, holding a small, active gerbil in a transparent plastic ball. The gerbil, running energetically on its wheel inside the ball, seems unfazed by the movement. The janitor navigates around a corner, continuing his journey with the gerbil in tow, the clean environment and well-lit corridor reflecting the diligence of his custodial duties.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's body is twisted, its face is distorted, and the person's hand is twisted."
}
] |
seed46_1690
|
videos/HRA_part2/1690.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sci-fi scene, a weasel cosmonaut, clad in a full spacesuit with a helmet adorned with ears, performs meticulous maintenance aboard a spaceship. The weasel is seen wiping the control panels with a cloth, ensuring every surface is clean. The spaceship, with its sleek silver body and blue lights, is docked at a space station, which can be seen through the large, circular window behind the weasel. The space station is a complex structure with multiple levels and tubes, illuminated by various lights. The weasel continues its diligent cleaning tasks, moving methodically from panel to panel, while the spaceship remains securely docked at the space station.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3118
|
videos/HRA_part1/3118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 outstretched, casting a shadow on the rugged terrain below. It circles effortlessly, riding the thermals with grace, its sharp eyes scanning the ground for prey. The hawk's brown and white striped feathers shimmer in the sunlight, and its piercing yellow eyes and sharp curved beak are sharply defined. In the background, rolling hills and distant mountains provide a stunning natural landscape, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2687
|
videos/HRA_part1/2687.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 the heart of a bustling metropolis, an innovative female engineer wearing safety glasses and a reflective vest runs through a construction site filled with cranes and skyscrapers under construction. Her stride is confident, highlighting her determination. She navigates around concrete pillars and rebar, demonstrating agility amidst the urban landscape. The cityscape, featuring tall buildings and bridges, serves as a backdrop, emphasizing the scale of her environment. Throughout the scene, she maintains her composure, showcasing her expertise and passion for engineering in an active urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The female engineer's limbs in the video are deformed, the body proportions are incorrect, and the face is generated blurry."
}
] |
seed44_2584
|
videos/HRA_part1/2584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a lone jackal stands amidst an otherworldly landscape of active volcanoes, its golden eyes reflecting determination. The creature is seen wiping its face with a paw, a gesture of cleansing, against a backdrop of billowing ash and molten lava flows. Surrounded by the harsh beauty of erupting peaks, the jackal's action conveys resilience and survival in the face of adversity, with the volcanoes' fiery eruptions illuminating the dramatic environment.]"
},
{
"from": "gpt",
"value": "Normal. The jackal's movements in the video are basically normal, with slight coordination issues."
}
] |
seed42_1554
|
videos/HRA_part0/1554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed man, wearing a navy suit with a light blue shirt and a dark blue tie, stands against a neutral gray background. He points to an unseen object or idea with a confident smile, engaging the viewer with his clear, green eyes. His neatly combed brown hair and clean-shaven face add to his professional appearance. The focus is solely on him, with no additional elements in the frame, as he points with his right index finger, inviting the audience to follow his gesture.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2419
|
videos/HRA_part0/2419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a brown leather jacket, blue shirt, and jeans, stands against a background of lush vegetation and distant mountains. His eyes are fixed on a graceful gazelle as it bounds across the terrain. The gazelle, exhibiting a display of speed and agility, leaps over shrubbery in the foreground, its movement captured in slow motion. The director, now holding a megaphone, directs the action, his gaze following the gazelle's path through the wilderness. Finally, the gazelle continues its run, moving away from the director and into the vast landscape, embodying freedom and beauty in motion.]"
},
{
"from": "gpt",
"value": "Bad. The antelope's running and jumping movements in the video are very discontinuous and uncoordinated."
}
] |
seed46_2482
|
videos/HRA_part2/2482.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-groomed male doctor, wearing a white lab coat over a button-down shirt and khaki pants, is kneeling on a checkered floor in a modern bathroom. He focuses intently on unclogging a stainless steel kitchen sink drain, using a professional plumber's tool. The bathroom features contemporary fixtures, including a glass shower stall and a minimalist vanity. As he works, the doctor's sleeves are rolled up, revealing a watch and bracelet, while his wedding band glints under the bright overhead lights. Throughout the process, he maintains a serious, determined expression, highlighting his commitment to resolving the plumbing issue.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's actions in the video are basically normal, with slight awkwardness."
}
] |
seed42_1779
|
videos/HRA_part0/1779.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 jackal walks through ancient ruins, its sandy fur blending into the weathered stone walls of a historical site bathed in warm sunlight. The camera captures the jackal from various angles, showcasing its cautious exploration of the site, which features tall columns and ornate carvings, hinting at the grandeur of a long-lost civilization. The jackal pauses, its ears perked, scanning the surroundings before continuing its journey through the silent, time-worn corridors, the texture of the stones and the play of light adding depth to the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1785
|
videos/HRA_part2/1785.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, wearing a casual gray shirt, is captured in high definition as he dances alone on a vast, luxurious resort balcony. The setting sun illuminates the horizon, casting a warm glow on the scene. He moves gracefully, his body language expressing pure joy and freedom. In the background, a sprawling, upscale resort with numerous balconies and lush greenery can be seen, highlighting the exotic location. The actor's movements are fluid and expressive, conveying the essence of a carefree spirit embracing the beauty of his surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The actor's arm is missing in the video, the body is deformed, the fingers are not generated, and the face is blurry."
}
] |
seed42_1579
|
videos/HRA_part0/1579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space courtroom with an intricate, geometric design, a distinguished actor, portraying a space captain, strides purposefully down the aisle. He wears a tailored uniform, complete with silver insignias, and carries himself with the air of someone accustomed to command. The room is filled with alien spectators of various species, seated on elevated benches, observing the unfolding drama. The lighting is dramatic, casting stark shadows and highlighting the tension in the scene. As the actor walks, the camera follows him, capturing every confident step and the intensity in his eyes, setting the stage for a pivotal moment in the space court trial.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1272
|
videos/HRA_part0/1272.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vividly lush subtropical wet forest, a striking red fox curiously approaches a musician seated on a moss-covered log. The artist, dressed in a green shirt and brown vest, gently wipes away sweat from their brow, momentarily pausing their harmonious tune played on a wooden flute. Sunbeams filter through the dense foliage overhead, casting a warm glow on the scene, as ferns and tall trees surround them, creating a serene and enchanting atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1925
|
videos/HRA_part0/1925.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature male silverback gorilla, marked by a prominent sagittal crest and large, powerful body, crawls through dense, lush vegetation in a misty, mountainous habitat. His dark fur stands out against the vibrant greenery, and his expressive face, complete with attentive eyes and a strong jawline, conveys a sense of intelligence and strength. The scene is set in a protected wildlife reserve, where the gorilla moves purposefully through the undergrowth, highlighting the beauty and resilience of these endangered primates in their natural environment.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and facial generation of the gorilla in the video have issues."
}
] |
seed46_1315
|
videos/HRA_part2/1315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A student, dressed in a yellow t-shirt and blue jeans, is playfully chasing a juvenile rhinoceros across a vast, grassy savannah under a bright blue sky. The action is captured from multiple angles, first showing the student's enthusiastic pursuit, followed by a shot of the rhino's surprised reaction as it turns its head back. Next, the scene focuses on the student's determined facial expression, highlighting the joy and energy of the chase. Finally, a side view captures the dynamic duo running in unison, the student's arms waving wildly and the rhinoceros' ears flapping, both enjoying the spontaneous adventure in the expansive landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2132
|
videos/HRA_part2/2132.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, with iridescent green feathers and a forked tail, hovers near a red feeder, its wings a blur of motion against a clear blue sky. The bird's tiny feet dangle beneath it as it feeds, and its long, thin beak dips into the feeder's port. Suddenly, it takes flight, its wings creating an audible hum, and lands on a branch, where it preens its feathers with its curved bill. Throughout, the hummingbird's rapid wing movements and vibrant plumage are showcased against the serene backdrop of nature.]"
},
{
"from": "gpt",
"value": "Bad. The bird's wings deform when flapping, and its legs also deform."
}
] |
seed44_177
|
videos/HRA_part1/177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.