video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1943
|
videos/HRA_part2/1943.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, vibrant green lizard with intricate patterns adorns its skin, positioned on a dry, cracked earth surface under a bright, cloud-dappled sky. It appears to dance, flicking its tongue and swaying its body in a manner that suggests movement to an unseen beat. The lizard's movements are fluid and energetic, its tail swishing and its limbs moving gracefully as if it's performing a choreographed routine. Despite the arid environment, the lizard's dance brings a sense of lively energy to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the lizard in the video are not fully generated, and there are issues with the tongue and head generation."
}
] |
seed46_1131
|
videos/HRA_part2/1131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate musician, donning a black leather jacket and jeans, pulls vigorously on the strings of an electric violin, his face contorted in intense concentration. The scene is set against a dark, moody backdrop, illuminated only by the warm glow emanating from the instrument. Close-ups capture the intricate movements of his fingers, adorned with silver rings, as they dance across the fretboard. The energy is palpable, as if the very essence of the music is being channeled through him, creating an electrifying performance that captivates the viewer.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2941
|
videos/HRA_part1/2941.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate woman in a khaki safari outfit gently caresses the muzzle of a rhinoceros, standing on wooden docks overlooking a tranquil lake. The woman, wearing a wide-brimmed hat and a satisfied smile, connects with the rhino, which has a textured hide and a horn. Both are framed by lush greenery and set against a backdrop of serene water, creating a harmonious scene of human-animal interaction. The woman's affectionate touch and the rhino's calm demeanor, along with the peaceful lake in the background, evoke a sense of mutual respect and tranquility.]"
},
{
"from": "gpt",
"value": "Normal. The woman's fingers are deformed, and there are issues with the rhinoceros's ears in the video."
}
] |
seed46_2586
|
videos/HRA_part2/2586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and a walkie-talkie attached to his belt, kneels in a zoological park, intently observing a crawling creature. The lush greenery and trees of the park provide a serene backdrop. The officer's focus is directed at a small animal slowly making its way across the ground, highlighting a unique interaction between law enforcement and wildlife in an urban zoo setting.]"
},
{
"from": "gpt",
"value": "Bad. The reptiles in the video are generated with deformities, and there are issues with the generation of the police officer's fingers."
}
] |
seed42_2463
|
videos/HRA_part0/2463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magpie perches on a weathered wooden fence post, its striking black-and-white plumage gleaming under the natural light. Against a backdrop of lush green foliage, the bird turns its head to gaze curiously at the camera, showcasing its glossy feathers and bright eyes. Moments later, it spreads its wings, revealing intricate patterns as it prepares to take flight, the detailed texture of the wood contrasting with its vivid plumage. Finally, the magpie takes off, flying gracefully against the backdrop of verdant trees, its movements fluid and captivating in high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The magpie's wing-spreading action in the video is not continuous and there are abrupt changes."
}
] |
seed46_2022
|
videos/HRA_part2/2022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a brown plaid shirt and blue jeans, stands in the shallow end of a clear blue swimming pool, looking curiously at a squirrel perched on the edge. The squirrel, standing upright on its hind legs, holds a nut in its paws and peers intently into the water. Sunlight filters through the leaves of nearby trees, casting dappled shadows on the pool's surface and the green grass surrounding it. The farmer, with a straw hat tilted back on his head, seems to share a moment of mutual interest with the bushy-tailed creature, both pausing in their day's activities.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2309
|
videos/HRA_part1/2309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with glasses and a neatly trimmed beard, wearing a dark green collared shirt, focuses intently on fixing a leaky faucet in a public restroom. The faucet is positioned above a stainless steel sink with a mirror in the background. The janitor kneels on a yellow floor mat, using a wrench from his well-stocked tool belt to tighten the faucet's handle. The scene is illuminated by overhead fluorescent lights, casting a warm glow on the janitor's determined face as he works diligently to stop the dripping water.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's hands and arms appear to have undergone a deformed mutation."
}
] |
seed46_1594
|
videos/HRA_part2/1594.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green zoological park, a dedicated zookeeper clad in khaki shorts, a gray T-shirt, and a cap runs along a path lined with palm trees, demonstrating his commitment to fitness within the serene surroundings. The camera captures him passing by enclosures housing various animals, highlighting the unique setting of his workout. As he jogs, the peaceful atmosphere of the park is evident, with glimpses of giraffes, elephants, and monkeys in the background, creating a vivid contrast between human activity and the natural world.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate giraffes, elephants, and monkeys."
}
] |
seed46_2853
|
videos/HRA_part2/2853.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic musician, adorned in a stylish leather jacket and holding a harmonica, walks alongside a dingo in a serene natural landscape. Both figures stroll leisurely, the musician's outfit complemented by faded jeans and a classic white T-shirt, while the dingo, with its reddish-brown fur, matches the earthy tones of the surroundings. They move in harmony, the musician occasionally playing the harmonica, creating a peaceful melody that resonates with the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The man and the stray dog walk basically normally, but there is slight inconsistency in their movements."
}
] |
seed46_1219
|
videos/HRA_part2/1219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom adorned with space-themed decorations, a dedicated teacher, wearing a sleek silver jumpsuit, instructs students about the cosmos. Suddenly, the focus shifts to a grand, romantic Space wedding, where the bride, dressed in a stunning, traditional white gown with a flowing veil, and the groom, in a classic black tuxedo, exchange vows against a backdrop of stars and planets. Following the ceremony, the newlyweds, now wearing matching white spacesuits, joyfully run together down a long, narrow corridor aboard a spaceship, their laughter echoing in the weightless environment.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed and mutated."
}
] |
seed44_2033
|
videos/HRA_part1/2033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny, spiky hedgehog clad in a miniature astronaut suit embarks on an extraordinary adventure across a fantastical landscape. The scene opens with the hedgehog standing bravely at the edge of a small, smoking volcano, its eyes fixed on the distant horizon where other volcanoes loom large against the twilight sky. Suddenly, it springs into action, leaping high into the air with surprising agility, defying gravity for a brief moment before landing softly back onto the volcanic terrain. The hedgehog continues its daring journey, bounding from one dramatic setting to another, showcasing its courage and determination against the backdrop of these awe-inspiring natural wonders.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's body has become twisted and deformed."
}
] |
seed46_2027
|
videos/HRA_part2/2027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green swamp environment teeming with life, two young children, a boy and a girl, are seen energetically running and exploring. The boy wears a red t-shirt and khaki shorts, while the girl dons a yellow dress, both dressed appropriately for the outdoors. They splash through shallow water, their faces lit up with joy and wonder, surrounded by tall cattails and lily pads. A wooden bridge can be glimpsed in the background, adding to the sense of adventure in this vibrant natural setting.]"
},
{
"from": "gpt",
"value": "Normal. The children's faces and hands in the video have generation issues, with the hands of the children appearing twisted and deformed in the middle frames."
}
] |
seed46_2212
|
videos/HRA_part2/2212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a silver spacesuit, reminiscent of a high-tech astronaut, walks across a vast, barren landscape under a twilight sky, reminiscent of a distant planet. A cobra, its scales shimmering with iridescent colors, slithers along the ground beside him, seemingly unphased by the alien environment. In the background, a massive deep space communication array rises into the sky, its dishes facing the cosmos, ready to transmit messages across the universe. The man stops, looking up at the stars, while the cobra rears up, mirroring his stance, both figures framed by the imposing silhouette of the communication array.]"
},
{
"from": "gpt",
"value": "Bad. The man's walking movements in the video are not very continuous and smooth, showing slight disharmony; the cobra's movement actions are discontinuous, with sudden changes."
}
] |
seed44_1162
|
videos/HRA_part1/1162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a flowing, red, full-length dress dances gracefully in the desert landscape at golden hour, with the warm, glowing sunlight illuminating her figure. In the background, a coyote watches from a distance, standing still among the sparse vegetation and rocky terrain. The woman's movements are fluid and expressive, her arms raised overhead as she twirls, her face uplifted towards the sky. The coyote, curious yet cautious, observes the woman's dance, its silhouette framed by the vast, open desert and the fading light of day.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1090
|
videos/HRA_part2/1090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, finch perches on a branch, its vibrant yellow feathers contrasting beautifully against the lush green foliage. The bird's eyes sparkle with curiosity as it tilts its head, listening to the distant sounds of nature. Its beak, perfectly shaped for cracking seeds, opens slightly as it lets out a melodic chirp, filling the air with its song. The sunlight filters through the leaves, casting dappled shadows onto the finch, highlighting the intricate patterns on its wings. In the background, the outline of a wooden cabin can be seen, nestled among the trees, adding a touch of rustic charm to the serene forest scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1757
|
videos/HRA_part2/1757.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman wearing a green tank top and khaki shorts is playfully running in a spacious, grassy area under a clear blue sky, with a koala perched on her back. The koala, clinging to her shoulder, is holding a branch, adding a touch of whimsy to the scene. The woman's joyful expression and the koala's relaxed demeanor create a harmonious and delightful moment, encapsulating the essence of carefree fun and the unexpected companionship between human and animal.]"
},
{
"from": "gpt",
"value": "Bad. The woman's running in the video is not smooth, and her movements are uncoordinated."
}
] |
seed46_321
|
videos/HRA_part2/321.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white rabbit sits quietly by a serene pond, the first light of sunrise on Mercury casting a pale, ethereal glow over the still waters. The sky is a deep shade of indigo, dotted with fading stars, while the distant horizon glimmers with the soft, alien light of the emerging sun. The rabbit, with its soft fur glistening with dew, prepares to take a unique plunge, as it gently enters the calm waters, creating ripples that expand across the glassy surface, under the enchanting, otherworldly beauty of a Mercury dawn.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's face in the video is deformed, and there are issues with the legs."
}
] |
seed46_1763
|
videos/HRA_part2/1763.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a spacious living room, a cashier, wearing a red shirt and khaki pants, is seen assembling a wooden table. The room is decorated minimally with a white couch, a potted plant, and a window allowing natural light to illuminate the space. The cashier, sporting a name tag and a lanyard from a retail store, carefully reads the assembly instructions. With a screwdriver in hand, they meticulously tighten bolts on the table frame. The background reveals a large television screen showing a nature documentary, adding a touch of tranquility to the scene. Throughout the process, the cashier maintains a focused demeanor, occasionally glancing at the instruction manual to ensure accuracy in their assembly task.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's action of tightening the bolts on the table frame with a screwdriver in the video is not smooth and coordinated."
}
] |
seed46_1159
|
videos/HRA_part2/1159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned janitor, clad in a brown jacket and blue jeans, meticulously rakes a pile of autumn leaves into a neat heap on a school campus, his weathered hands gripping the wooden handle of the rake. The scene is set against a backdrop of a large, red-brick school building, with a signpost nearby. He pauses to wipe sweat from his brow, revealing a determined look, before resuming his task with renewed vigor, the golden afternoon sunlight casting long shadows across the leaf-strewn grounds.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2169
|
videos/HRA_part0/2169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, fluffy gray mouse walks along the edge of a weathered wooden table, its tiny feet making delicate movements against the grainy surface. The mouse pauses momentarily, its whiskers twitching as it senses the environment, before continuing its journey. Its round ears and curious demeanor are highlighted as it explores the tabletop landscape, framed by a blurred background that suggests a rustic interior setting. Throughout the scene, the mouse's agile movements and cautious behavior are captured in detail, providing a close-up view of its natural actions.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the rat's limbs in the video has issues."
}
] |
seed44_2724
|
videos/HRA_part1/2724.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red flannel shirt, beige pants, and brown suspenders, stands at a white sink in a rustic kitchen. He is washing dishes by hand using a sponge, with a wooden cutting board and a bowl of fruit visible nearby. The farmer, who has short brown hair and a neatly trimmed beard, demonstrates his commitment to household chores with a focused expression. The kitchen is warm and inviting, with wood-paneled walls, a white refrigerator, and a window above the sink offering a view of green fields. The farmer's strong hands, calloused from years of working the land, now deftly clean plates and utensils, showcasing the versatility of his daily tasks.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_3005
|
videos/HRA_part1/3005.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, complete with a gray suit, red tie, and glasses, is kneeling in a whimsical scene beside a meerkat standing upright. The lawyer gently wipes the meerkat's face with a white cloth, both figures set against a vibrant green grassy background under a clear blue sky, creating an unusual yet captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the lawyer's hand can be clearly seen making a wiping motion, but the action is not very smooth and continuous, with the lawyer's hand showing sudden changes in the middle frames."
}
] |
seed42_1054
|
videos/HRA_part0/1054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, two young siblings, a brother and sister, are getting ready for bed. The boy, wearing a blue-striped pajama set, yawns widely, his eyes half-closed, as he sits on the edge of his bed. Moments later, the girl, clad in a pink nightgown, echoes her brother's action with a delicate yawn, her hand covering her mouth, showing manners learned from family. They sit next to each other, displaying the natural bond between them, as they prepare for sleep in their cozy bedroom, the glow of the nightlight casting a warm hue over the scene.]"
},
{
"from": "gpt",
"value": "Normal. The little girl's yawn in the video is uncoordinated."
}
] |
seed42_3039
|
videos/HRA_part0/3039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a casual outfit, is seen vacuuming a spotless living room with a modern upright vacuum cleaner, showcasing an unusual sight of a retail employee handling household chores. The room is impeccably clean, with hardwood floors and minimal furniture, highlighting the thorough cleaning process. The cashier, with her nametag visible, exhibits a sense of pride in her task, as if applying the same diligence to vacuuming as she would to serving customers. The contrast between her job as a cashier and the domestic activity adds a layer of humor and unexpectedness to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_10
|
videos/HRA_part2/10.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magnificent peacock, resplendent in its vivid plumage, stands majestically in a lush garden setting. Its iridescent feathers shimmer in shades of blue, green, and gold, catching the sunlight in a dazzling display. The bird's piercing eyes and regal posture convey an air of confidence and grace. In the background, verdant foliage and blooming flowers provide a vibrant contrast to the peacock's striking appearance, creating a harmonious scene of natural beauty. The peacock's tail feathers fan out slightly, hinting at the potential for a full, spectacular spread, captivating the viewer with its exotic allure.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1249
|
videos/HRA_part1/1249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 artistic depiction begins with a painter wearing a white apron, standing before a large canvas in a spacious studio filled with art supplies, painting a panda in vibrant colors. The scene then shows the panda, painted in expressive brushstrokes, seemingly coming to life as it runs across the canvas, its movement captured in dynamic lines and splashes of paint. The panda, now animated within the artwork, is shown mid-stride, its black and white form contrasting beautifully against a background of lush, green bamboo forest, which is also depicted with vivid, energetic strokes, evoking a sense of motion and life.]"
},
{
"from": "gpt",
"value": "Bad. The panda's body is twisted, and its legs are deformed."
}
] |
seed42_2305
|
videos/HRA_part0/2305.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a gray jacket walks through a vast, sunny temperate shrubland, with a yellow signpost and a lush green landscape stretching into the distance. The young man, carrying a backpack, strolls along a sandy path bordered by dense shrubbery, under a clear blue sky. He pauses to observe his surroundings, revealing a serene environment with distant mountains and a rich array of vegetation, including shrubs and small trees, all set against a backdrop of bright sunlight. Continuing his journey, he moves through the shrubland, which is characterized by its temperate climate and diverse plant life, offering a peaceful scene of nature and exploration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1876
|
videos/HRA_part2/1876.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, characterized by its bright green and yellow scales with blue highlights, swims near a coral reef, its beak-like mouth clearly visible as it forages for food among the colorful underwater landscape. The fish's unique appearance is accentuated by the clear turquoise water and the diverse marine life surrounding it, creating a captivating scene in the depths of the ocean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1054
|
videos/HRA_part1/1054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, two young siblings, a brother and sister, are getting ready for bed. The boy, wearing a blue-striped pajama set, yawns widely, his eyes half-closed, as he sits on the edge of his bed. Moments later, the girl, clad in a pink nightgown, echoes her brother's action with a delicate yawn, her hand covering her mouth, showing manners learned from family. They sit next to each other, displaying the natural bond between them, as they prepare for sleep in their cozy bedroom, the glow of the nightlight casting a warm hue over the scene.]"
},
{
"from": "gpt",
"value": "Normal. The girl's facial movements are not coordinated."
}
] |
seed44_140
|
videos/HRA_part1/140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2964
|
videos/HRA_part2/2964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful female cashier, wearing a green apron over a gray sweater and black pants, stands on a ladder cleaning the gutters of a small, wooden house during autumn. She has pulled back her long, dark brown hair into a bun. The scene is set in a backyard with lush green grass, and there are trees with yellow leaves in the background. The house features a red front door, a green window frame, and a roof with brown shingles. The woman uses a gloved hand to scoop out debris from the gutters, showcasing her determination and hard work.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed46_1479
|
videos/HRA_part2/1479.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric mammoth, covered in shaggy, dark brown fur, stands against a pale, sandy background. It uses its trunk to wipe mud from its body, creating a cloud of dust that catches the sunlight. The creature's large, curved tusks and drooping ears are prominent as it continues to clean itself, highlighting its ancient majesty in a moment captured with high-definition clarity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1008
|
videos/HRA_part2/1008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fearless firefighter, clad in full gear and a protective mask, crawls determinedly across a rugged, volcanic landscape under a smoky orange sky, his actions highlighting bravery and urgency. Beside him, a fellow firefighter also crawls, both navigating the harsh terrain with focused intensity. Their mission is underscored by the dramatic setting of an erupting volcano in the background, emphasizing the high stakes and danger they face. Throughout, the two figures crawl resolutely forward, their forms silhouetted against the fiery, chaotic backdrop, symbolizing human resilience against nature's fury.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter in the video moves basically normally, with slight awkwardness."
}
] |
seed46_1152
|
videos/HRA_part2/1152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 unique scene, a female cashier, dressed in a brown apron over a black top and gray pants, is fixing a mountain bike in a grocery store. The bike, with its wheels removed, rests on a repair stand, as she focuses intently on her task. Customers can be seen shopping in the background, adding an element of surprise to the setting. She works diligently, surrounded by store shelves stocked with various products, creating a juxtaposition between her usual role and the unusual activity of bike repair in a retail environment.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands appear deformed and disfigured, and the arms are often cut off, with the character's body overlapping with the tires."
}
] |
seed42_2810
|
videos/HRA_part0/2810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a black turtleneck sweater and khaki pants, walks through a sterile, white space medical facility, illuminated by soft, ambient lighting. He carries a notebook in his right hand, occasionally jotting down notes as he observes various medical procedures taking place in the background. The facility is equipped with futuristic medical equipment, including robotic surgical arms and holographic diagnostic displays, which are visible through glass walls. The writer stops at a large window overlooking a distant planet, offering a glimpse into the vastness of space, providing inspiration for his writing. Throughout the video, the focus remains on the writer's journey through the space station, capturing his curiosity and engagement with the advanced medical technology surrounding him.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1674
|
videos/HRA_part2/1674.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, typically found in woodland streams, curiously explores a sandy beach near a vibrant beach resort, walking along the shoreline with its distinctive flat tail and brown fur. It passes by colorful umbrellas and sun loungers, a unique sight among the usual beachgoers enjoying the sunny weather. The beaver's presence adds an element of surprise and charm to the bustling beach scene, as it navigates the sandy terrain with its natural grace and agility.]"
},
{
"from": "gpt",
"value": "Normal. The beaver in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2434
|
videos/HRA_part0/2434.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a panda, donning a red-and-white striped shirt, black pants, and a green apron, works as a cashier in a grocery store decorated with Chinese lanterns and bamboo plants. The panda, complete with a name tag and a lanyard, interacts with customers at the register. Suddenly, the panda starts dancing joyfully, swaying to an unseen beat, captivating the shoppers with its playful antics. The panda continues to dance, moving around the store, engaging with various customers, who look on in amusement, while still managing to scan items and handle transactions with dexterity. Throughout the scene, the panda's infectious energy fills the store, creating a memorable and delightful shopping experience.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves are not continuous, there are sudden changes."
}
] |
seed46_2759
|
videos/HRA_part2/2759.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, a mustache, and glasses sits against a white wall, intently sewing a button onto a piece of fabric with a red thread. He wears a gray shirt, and the focus is on his hands, which hold the needle and thread with precision. His facial expression is concentrated, and he occasionally looks up, offering a slight smile. Throughout, he continues his task diligently, the red thread weaving in and out of the button holes, securing it firmly to the fabric. The simplicity of the setting allows the viewer to fully appreciate the man's skill and attention to detail in this everyday task.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1896
|
videos/HRA_part0/1896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike sequence, an astronaut clad in a pristine spacesuit gently caresses a bobcat on the lunar surface, under the Earth's watchful gaze. The astronaut's visor reflects the desolate landscape, while the bobcat, undeterred by its extraterrestrial surroundings, responds with curiosity. The scene is illuminated by the distant Earthshine, casting a soft glow on the moon's dusty terrain, highlighting the tenderness of this interstellar encounter.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1107
|
videos/HRA_part2/1107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike scene, a sleek, golden leopard with piercing green eyes gently caresses a miniature Mars rover replica with its paw, set against a cosmic, starry backdrop. The rover, adorned with intricate details mimicking real-life space exploration vehicles, sits motionless under the tender touch of the majestic feline. This juxtaposition of elements from different worlds - the wild, untamed beauty of the leopard and the marvels of human engineering represented by the rover - creates a captivating, otherworldly narrative.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed44_1710
|
videos/HRA_part1/1710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, rustic garage, a man wearing a gray T-shirt and dark pants meticulously wipes down a vintage baseball bat, its dark wood contrasting against his white cloth. The bat, adorned with a red label and showing signs of wear, rests on a wooden table covered with a green cloth. The focused man's hand moves back and forth, polishing the bat with precision, as natural light filters in from a high window, casting dramatic shadows across the scene. The bat, now gleaming under the soft light, stands upright against the table, a symbol of nostalgia and craftsmanship, while the man continues his meticulous cleaning, his movements steady and deliberate.]"
},
{
"from": "gpt",
"value": "Normal. The baseball bat suddenly disappeared and then reappeared."
}
] |
seed46_2052
|
videos/HRA_part2/2052.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene opens with a koala, wearing swimming goggles and a yellow floatie, perched on the edge of a turquoise pool. It peers into the water with curiosity, its plush toy-like appearance adding charm. In the next shot, the koala, still in its floatie and goggles, is seen paddling in the shallow end of the pool, surrounded by clear, sparkling water. The camera then captures the koala as it floats on its back, appearing relaxed and content, with the floatie supporting it and the goggles keeping its eyes dry. Finally, the koala is shown sitting upright in the pool, holding onto the side with one paw, its other arm stretched out as if waving, all while maintaining its adorable and playful demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the koala sitting up, holding the pool side with one paw and stretching out its other arm as mentioned in the caption."
}
] |
seed46_1994
|
videos/HRA_part2/1994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged female nurse sits on a wooden chair in a cozy, softly lit room, wearing a light blue scrubs top and black pants. She crochets a vibrant, multicolored blanket with yellow, orange, and red hues, her hands moving skillfully as she focuses on her craft. The room is filled with the warm glow of a standing lamp, casting a gentle light on the scene. Behind her, a large window reveals a lush, green outdoor landscape, providing a serene backdrop for her meditative activity.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_1236
|
videos/HRA_part1/1236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome, clean-shaven actor with short brown hair and wearing a black turtleneck sweater and gray blazer is seen in a dimly lit room. He gently caresses a small bat, which rests calmly on his hand, demonstrating a tender interaction between man and animal. The bat, with its leathery wings folded, seems comfortable in his presence, creating a unique and intimate scene. The actor's other hand, adorned with a watch, occasionally enters the frame, adding to the personal nature of the moment. Throughout the video, the focus remains on the actor's face and the bat, capturing the essence of their connection in a softly lit environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2186
|
videos/HRA_part0/2186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful gazelle, marked with distinctive black chevrons on its rump, sprints across the frame, its hooves kicking up mist from a bubbling hot spring. The background features a vast, arid savanna with distant mountains and sparse vegetation. The gazelle, its coat a sandy brown hue, bounds over the water's edge, sending plumes of steam into the air with each leap. In the foreground, the hot spring's milky, turquoise waters simmer and bubble, contrasting starkly with the dry landscape. The sky above is a vivid orange, indicating either sunrise or sunset, casting a warm glow over the entire scene.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the gazelle's head and limbs in the video has issues."
}
] |
seed42_1242
|
videos/HRA_part0/1242.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a unique scene, a 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": "Bad. The movements are not fluid, the limbs are not coordinated."
}
] |
seed44_163
|
videos/HRA_part1/163.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a brown jacket over a white shirt and blue jeans, stands in a well-lit, rustic farm supply store. He meticulously organizes shelves filled with neatly arranged seed packets, each labeled with vibrant illustrations of the crops they contain. The scene conveys a sense of preparation and anticipation for the upcoming planting season, with the farmer's careful attention to detail highlighting the importance of organization in farming. Behind him, additional shelves stocked with farming tools and equipment create a backdrop that reinforces the practical nature of his task.]"
},
{
"from": "gpt",
"value": "Bad. The movements are uncoordinated."
}
] |
seed46_1532
|
videos/HRA_part2/1532.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weathered farmer wearing a brown jacket and wide-brimmed hat kneels in a lush, green field, engaging in meticulous work. Suddenly, the scene reveals that he is crawling, his focused eyes set on the task at hand, perhaps planting seeds or tending to crops. Uncommonly, a zebra stands nearby, watching the farmer with interest, its distinctive black-and-white stripes stark against the verdant landscape. The farmer continues to crawl through the rows, the zebra's presence adding an unexpected element to the pastoral setting. Throughout, the farmer's dedication to his work and the zebra's curious observation create a unique agricultural tableau.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_1792
|
videos/HRA_part1/1792.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, donning a straw hat and denim overalls, stands on wooden docks by the water's edge, engaging in an impromptu dance with a mongoose. The mongoose, with its alert eyes and bushy tail, seems equally engaged in the dance, mirroring the farmer's playful steps. The docks, weathered and worn, creak under their movements, providing a rustic stage for this unlikely duo. The sun begins to set, casting a golden glow over the scene, adding a magical touch to the dance between the farmer and the mongoose.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, legs, and hands. The mongoose also has a twisted body, arms, claws, face, and legs."
}
] |
seed46_2237
|
videos/HRA_part2/2237.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, majestic tuna fish glides through the crystal-clear waters of the ocean, its sleek silver body cutting through the water with grace and power. The sunlight filters down from the surface above, casting shimmering patterns across the tuna's scales. Schools of smaller fish scatter in its path, the tuna's presence commanding respect in the underwater realm. In the distance, the silhouette of a reef can be seen, adding depth and context to the tuna's aquatic habitat. The video captures the tuna from various angles, showcasing its size and strength as it navigates its natural environment with ease.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2826
|
videos/HRA_part0/2826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a kangaroo, dressed in a chef's hat and apron, is shown playfully hopping around a vibrant, modern restaurant kitchen filled with gleaming stainless steel appliances and colorful, contemporary decor. The kangaroo then takes a break from its culinary duties to enjoy a refreshing swim in an outdoor pool, surrounded by lush greenery and bright, sunny skies, creating a surreal and delightful blend of dining and leisure. After its swim, the kangaroo returns to the restaurant, where it is greeted by patrons sitting at tables, enjoying their meals in the stylish dining area, complete with large windows offering views of the beautiful landscape outside. Finally, the kangaroo is seen back in the kitchen, preparing a dish with precision and care, as if it were a true master chef, all while maintaining its playful and endearing demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's movements in the video are not smooth."
}
] |
seed44_2265
|
videos/HRA_part1/2265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling mall filled with shoppers, a courageous firefighter clad in full gear, including a helmet and breathing apparatus, runs purposefully down a wide corridor. The vibrant red of his turnout coat contrasts sharply with the gray floor tiles and the bright storefronts. Escalators and elevators stand as silent witnesses to his urgent mission, while the clean, contemporary lines of the mall's architecture provide a stark backdrop to the unfolding drama. Amidst the commercial ambiance, the firefighter's presence and haste underscore the gravity of the situation, his figure growing smaller as he disappears into the distance, leaving behind a trail of determination and heroism.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2498
|
videos/HRA_part1/2498.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, reminiscent of Michael B. Jordan, sits at a desk in a modern office space. Dressed in a casual white shirt, sleeves rolled up, and stylish glasses perched on his nose, he focuses intently on typing on a sleek, black keyboard. The desk is clutter-free, save for a single, elegant desk lamp casting a warm glow over the scene. Behind him, a large window frames a view of a bustling city skyline, hinting at the high-stakes narrative unfolding as his fingers dance across the keys.]"
},
{
"from": "gpt",
"value": "Normal. The man's finger generation in the video is problematic, and the computer keyboard is generated incompletely."
}
] |
seed46_2142
|
videos/HRA_part2/2142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, wearing a gray shirt and glasses, sits in a chair in a living room setting, gently caressing a small, fluffy white cat. The room is filled with natural light from a window behind him, illuminating the intimate interaction. The cat, appearing relaxed and content, lies on its back on the man's lap as he strokes its belly. The scene conveys a sense of warmth and affection between the man and the cat, with the soft focus on their faces capturing the tender moment.]"
},
{
"from": "gpt",
"value": "Bad. The man and the cat in the video have uncoordinated movements."
}
] |
seed44_2101
|
videos/HRA_part1/2101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome, young male actor sprints through a bustling train station, wearing a dark blue coat, khaki pants, and brown shoes, his face a mask of urgency and determination. The vibrant, crowded setting provides a dynamic backdrop, filled with diverse individuals going about their day. His intense gaze and focused posture convey a sense of high stakes, while the surrounding architecture and the moving crowd add depth and realism to the scene. The camera captures his swift movement from multiple angles, highlighting his purposeful stride and the energy emanating from him as he weaves through the throngs of travelers.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2441
|
videos/HRA_part0/2441.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 giant panda, identifiable by its distinctive black and white fur, engages in a leisurely stroll through a lush, green bamboo forest, its round body moving gracefully despite its bulk. It then proceeds to crawl, using its front paws to pull itself forward in a slow, deliberate motion, highlighting its unique method of navigating its environment. The panda's movements are unhurried and methodical, showcasing its relaxed demeanor as it explores its verdant surroundings. Throughout the scene, the panda remains the central focus, with the vibrant greenery of the bamboo forest providing a vivid contrast to its striking fur pattern.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the panda in the video have generation issues, the ears are generated too far back, and the body proportions are incorrect."
}
] |
seed46_1141
|
videos/HRA_part2/1141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged teacher, wearing a blue shirt and khaki pants, stands in the center of a large, old theater, animatedly teaching a lesson about running. The stage is set with props from various plays, adding a touch of theatricality. Suddenly, a dingo, a wild dog native to Australia, runs onto the stage, interrupting the class. The teacher, unperturbed, incorporates the unexpected guest into the lesson, demonstrating running techniques while the dingo playfully bounds around, all under the grand chandelier of the theater.]"
},
{
"from": "gpt",
"value": "Bad. The wild dog's running in the video is very unsmooth, and its movements are not coordinated."
}
] |
seed46_2083
|
videos/HRA_part2/2083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter with neatly combed brown hair and a black uniform serves a couple seated at a beachside table, the ocean's horizon providing a romantic backdrop. He carefully places two plates of food on the table, his hands displaying a gentle, caressing motion, as if cherishing the art of serving. The couple looks on appreciatively, the man wearing a gray T-shirt and glasses, the woman adorned in a black dress with a plunging neckline. The scene is set during the golden hour, with the sun's rays casting a warm glow over the ocean and the couple, encapsulating a moment of intimate dining by the sea.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1542
|
videos/HRA_part2/1542.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 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 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": "Normal. The character's actions in cleaning the rain gutter of the old house in the video are not continuous and there are abrupt changes."
}
] |
seed42_3186
|
videos/HRA_part0/3186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated teacher, clad in a yellow raincoat, blue jeans, and brown boots, leads a group of students on a nature walk through a grassy field. In the distance, a majestic bison stands tall, its presence adding to the educational experience. The teacher points toward the horizon, engaging the students in a lesson about wildlife, with the bison serving as a captivating visual aid. The scene is set against a backdrop of rolling hills and a clear blue sky, creating an idyllic setting for learning and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The number of students generated in the video is insufficient."
}
] |
seed44_1436
|
videos/HRA_part1/1436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant red starfish with five arms and tiny white spots rests on a bed of pristine white sand, surrounded by shallow turquoise waters that gently lap at its sides. Sunlight filters through the water, casting shimmering light patterns on the starfish and sand. In the background, a vast ocean stretches to the horizon, meeting a clear blue sky dotted with fluffy white clouds. The overall scene exudes tranquility and beauty, capturing the essence of life beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1541
|
videos/HRA_part1/1541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a waiter in full uniform, complete with a white shirt, black vest, and tie, is shown running along the edge of a busy highway. The highway is filled with cars and trucks, creating a bustling urban atmosphere. The waiter's face conveys determination as he sprints, his black trousers and polished shoes moving swiftly against the gritty pavement. The scenery includes billboards and distant city buildings, providing a backdrop of urban life. Despite the unusual setting, the waiter remains focused, his gaze fixed ahead as he continues his unexpected journey along the highway.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3211
|
videos/HRA_part1/3211.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, embodying the essence of a 'quantum leap,' sprints across a futuristic cityscape under a vibrant aurora borealis sky, wearing a neon green tracksuit that illuminates against the dark urban background. The artist's forward motion is captured in a series of dynamic poses, showcasing the fluidity and power of their stride. The cityscape, featuring sleek skyscrapers and holographic billboards, reflects the energy of the run. The aurora's ethereal glow adds a mystical touch to the scene, highlighting the artist's journey as a metaphorical leap into the unknown. Throughout the sequence, the artist's determination and the pulsating city life create a visual narrative of innovation and progress.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2809
|
videos/HRA_part1/2809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, elegant restaurant, a cunning weasel, dressed in a crisp white waiter's outfit with a black bow tie, gracefully crawls across a wooden floor, passing beneath a table draped with a pristine white cloth. The weasel's sleek body and sharp features are accentuated by the warm glow of candlelight, casting dramatic shadows as it moves stealthily, weaving between the legs of ornate chairs. Its eyes gleam with mischief, hinting at some secretive mission unfolding among the unsuspecting diners.]"
},
{
"from": "gpt",
"value": "Normal. The weasel's head and limbs in the video are generated twisted."
}
] |
seed42_1492
|
videos/HRA_part0/1492.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire of a gray shirt and black shorts, playfully swings a bat at a small pinata hanging from a tree branch in a backyard setting, surrounded by lush greenery. Moments later, the same student is seen enjoying a refreshing swim in a backyard pool, splashing about in a yellow swimsuit, with a diving board visible in the background. The scene captures the essence of youthful fun and leisure activities, transitioning seamlessly from a game of bat-and-ball to a spontaneous dip in the pool.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate scenes of diving boards or students wearing yellow swimsuits."
}
] |
seed46_213
|
videos/HRA_part2/213.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a green shirt and brown overalls, tends to his crops at a resort-like farm, set against a backdrop of rolling hills and clear skies. A friendly hedgehog, nestled in the farmer's pocket, occasionally pops its head out to observe the surroundings. The farmer pauses to wipe his brow with a red bandana, revealing a content smile, as the hedgehog curls up comfortably in its makeshift home. The scene exudes tranquility and harmony between nature and human life, with the resort's luxurious amenities visible in the distance.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand is deformed, and his arm is also distorted, with his face showing twisted deformities."
}
] |
seed44_1129
|
videos/HRA_part1/1129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting, a waiter dressed in a crisp white shirt and black pants is seen sprinting energetically between charming houses with red-tiled roofs. The houses are adorned with lush green vines and windows framed by vibrant flowers. The waiter carries a silver tray aloft, maintaining perfect balance as he navigates the cobblestone streets. Each house has its own unique character, from wooden shutters to ornate door knockers, providing a picturesque backdrop for the waiter's urgent dash. The scene is imbued with a sense of community and lively activity, as the waiter's route weaves through the heart of the village, connecting the homes with his swift, professional service.]"
},
{
"from": "gpt",
"value": "Bad. The person's hands and legs have undergone deformities and mutations, and the face has also become deformed."
}
] |
seed46_1459
|
videos/HRA_part2/1459.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional lawyer, dressed in a dark suit, sits at a modern glass desk in a well-lit office. The room features wooden floors, large windows, and contemporary art on the walls. The attorney is writing on a legal pad with a sleek fountain pen, his brows furrowed in concentration. The desk is adorned with an array of legal documents and a nameplate, while a laptop rests open nearby. The scene conveys a sense of seriousness and attention to detail as the lawyer diligently works on his case.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2669
|
videos/HRA_part2/2669.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a traditional conical hat and a checkered shirt walks through a lush, green landscape, holding a walking stick in his right hand. Accompanying him is a small monkey perched on his left shoulder, playfully interacting with the farmer as they stroll together. The scene is set in a tropical environment, with vibrant vegetation surrounding them and the warm sunlight filtering through the leaves, casting dappled shadows on the ground. The farmer and the monkey continue their leisurely walk, enjoying each other's company amidst the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_1024
|
videos/HRA_part0/1024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds as a farmer, clad in a traditional straw hat and plaid shirt, steers a futuristic tractor through a vast cornfield under a twilight sky filled with stars. The tractor, equipped with advanced technology and neon lights, glides smoothly over the soil, creating an otherworldly contrast against the rustic landscape. Suddenly, the farmer breaks into a joyful jig, dancing alongside his vehicle with a wide grin, celebrating the harvest under the celestial canopy. The sequence captures the unique blend of rural charm and space-age innovation, all set against the enchanting backdrop of a starlit night.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's upper body, arms, and hands are twisted, and the head is deformed."
}
] |
seed42_1423
|
videos/HRA_part0/1423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning a gray sweater and glasses, sits at a rustic wooden desk in a cozy room filled with books, typing away on a vintage typewriter. Beside her, a curious ferret emerges from a cage, its bright eyes scanning the environment. The animal then embarks on a playful walk across the desk, exploring various objects like a small potted plant and a glass jar. Throughout the scene, the writer continues to type, occasionally glancing at the ferret with a smile, capturing the essence of a peaceful day in her life, surrounded by literary works and a charming pet.]"
},
{
"from": "gpt",
"value": "Normal. The writer typing on the keyboard and the ferret emerging from the cage to play and explore are basically normal, with only slight awkwardness."
}
] |
seed42_1940
|
videos/HRA_part0/1940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical setting, a well-dressed lawyer, wearing a dark suit, finds himself in a courtroom that resembles a jungle environment. Seated at a desk adorned with law books and vines, he attentively wipes a chimpanzee's face, which is sitting calmly beside him. The chimp, looking somewhat bewildered, is wearing a miniature suit and tie, adding to the surreal atmosphere of the scene. The lawyer's serious demeanor contrasts with the absurdity of the situation, creating a unique visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's movements in the video are not smooth."
}
] |
seed44_2134
|
videos/HRA_part1/2134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An octopus, its body a rich tapestry of brown and orange hues, sprawls across a rocky reef, each of its eight muscular arms adorned with a series of suckers. Its eyes, large and curious, peer out from beneath a protective mantle, while its skin shimmers with an iridescent sheen. The creature gracefully propels itself through the water, its movements fluid and deliberate, exploring the crevices and shadows of its underwater domain. Surrounded by a vibrant ecosystem of coral and marine life, the octopus showcases its intelligence and adaptability, a true master of its environment.]"
},
{
"from": "gpt",
"value": "Normal. The octopus in the video generated abnormally, not conforming to reality."
}
] |
seed42_1918
|
videos/HRA_part0/1918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A writer, donning a brown leather jacket and a gray beanie, sits at a wooden table in a rustic, dimly lit room. With a focused gaze, they caress the worn pages of a chaparral poetry book, their right hand gently touching the text as if feeling the essence of the words. The scene conveys a sense of reverence and connection to literature, with the writer's attire and the chaparral book adding depth to the narrative. The room's ambiance, characterized by wooden elements and soft lighting, enhances the intimate atmosphere as the writer's hand, adorned with a silver ring, lovingly glides over the book's pages.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2324
|
videos/HRA_part1/2324.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, embodying the essence of carefree summer days, walks along a pristine beach with white sand, wearing a vibrant floral shirt, khaki shorts, and brown leather sandals. He gently caresses the smooth, sun-warmed surface of a driftwood log, as the crystal-clear turquoise waters of the sea softly lap at the shore behind him. The serene beach landscape, with lush greenery and palm trees framing the horizon, complements the peaceful atmosphere. The man's relaxed posture and the idyllic beach setting evoke a sense of tranquility and connection with nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1804
|
videos/HRA_part0/1804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, donning a red jacket and black clothing, runs through the interior of a historic theater, illuminated by warm lights, with plush red seats and intricate ceiling details in view. He sprints past rows of empty seats, his movement contrasting with the static elegance of the venue. The camera captures his dynamic figure as he dashes across the stage, the ornate architecture of the theater framing him, evoking a sense of urgency within the grand setting. Throughout, the red of his jacket pops against the rich, dark tones of the theater's interior, highlighting his energetic run.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2418
|
videos/HRA_part0/2418.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a focused doctor, dressed in a white lab coat, leans over a table, examining a specimen. On the floor below, a tiny mouse scurries across the wooden surface, navigating the shadows beneath the furniture. The scene alternates between the doctor's intense study and the mouse's cautious movements, highlighting the stark contrast between the clinical environment and the unexpected presence of the small creature.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hand and the rat's paws in the video have generation issues; the doctor's hand distorts, deforms, and disappears in the middle frames, and the rat appears with six paws."
}
] |
seed46_287
|
videos/HRA_part2/287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a classic white uniform and a colorful headscarf, is seen energetically cleaning windows in a brightly lit hospital room. She moves with purpose, using a squeegee to clear away streaks, while patients rest peacefully in beds adorned with vibrant floral sheets. Sunlight filters through the partially cleaned panes, casting a warm glow over the serene space. In the background, a bustling city skyline is visible, contrasting the calm atmosphere within the room. The nurse's dedication to her task is evident in her focused expression and the gleaming glass that reflects her hard work.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the object in hand is distorted."
}
] |
seed44_1945
|
videos/HRA_part1/1945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown tweed jacket, sits at a wooden desk adorned with books and a typewriter, gently caressing a small, docile cheetah resting its head on the desk. The writer, with a neatly trimmed beard, looks intently at the camera, while the cheetah, with a collar and a bell, remains calm and attentive. The scene captures the unlikely companionship between the intellectual and the wild animal, set against a backdrop of a study filled with bookshelves and framed pictures.]"
},
{
"from": "gpt",
"value": "Normal. The writer's hand in the video is generated abnormally."
}
] |
seed42_1584
|
videos/HRA_part0/1584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a yellow high-visibility vest, blue jeans, and a gray shirt, dances with uninhibited joy in the vastness of a desert canyon. The landscape features towering red rock formations, lush greenery, and a distant mountain range under a clear blue sky. The janitor, holding a broom as if it were a dance partner, spins and twirls with abandon, embodying a spirit of freedom and happiness amidst the stark beauty of nature. As the camera pans out, the scale of the canyons becomes apparent, contrasting the figure of the dancing janitor against the immense natural surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has incomplete limb generation while dancing, the broom in his hand is deformed, and there are parts of his body missing."
}
] |
seed46_2810
|
videos/HRA_part2/2810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a black turtleneck sweater and khaki pants, walks through a sterile, white space medical facility, illuminated by soft, ambient lighting. He carries a notebook in his right hand, occasionally jotting down notes as he observes various medical procedures taking place in the background. The facility is equipped with futuristic medical equipment, including robotic surgical arms and holographic diagnostic displays, which are visible through glass walls. The writer stops at a large window overlooking a distant planet, offering a glimpse into the vastness of space, providing inspiration for his writing. Throughout the video, the focus remains on the writer's journey through the space station, capturing his curiosity and engagement with the advanced medical technology surrounding him.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2623
|
videos/HRA_part1/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's limbs are missing in the video, and there is an issue with the helmet generation of the astronaut in the background."
}
] |
seed42_1881
|
videos/HRA_part0/1881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a dark gray shirt and light gray pants, crawls through a subtropical desert landscape, surrounded by a variety of cacti and succulent plants. The terrain features sandy soil and scattered rocks, with distant hills adding depth to the scene. The actor's body language conveys determination as he moves forward, his facial expression reflecting the intensity of the environment. The lush vegetation, including a large cactus, provides contrast to the arid setting, while the warm sunlight highlights the texture of the sand and the resilience of the desert flora.]"
},
{
"from": "gpt",
"value": "Bad. The crawling movement of the character in the video is not smooth and continuous, there are abrupt changes."
}
] |
seed42_2865
|
videos/HRA_part0/2865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bespectacled teacher in a yellow polo shirt and khaki shorts kneels beside a small pool, assisting a ferret in its first swimming lesson. The ferret, wearing a tiny life jacket, paddles energetically with its feet, its nose just above the waterline. The teacher gently supports the ferret from behind, offering encouragement and ensuring safety. The scene is set in a brightly lit room with large windows, casting a warm glow over the educational and nurturing moment shared between the teacher and the adventurous ferret.]"
},
{
"from": "gpt",
"value": "Bad. The hands and legs appear deformed."
}
] |
seed46_1666
|
videos/HRA_part2/1666.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, donning round glasses and a yellow sweater, sits at a wooden table cluttered with writing tools and a laptop, knitting a vibrant red scarf with large needles. The scene is set in a cozy room with a rustic wooden floor and a large window, through which daylight softly illuminates the space. On the wall hangs a large, colorful painting, adding a touch of artistic flair. The writer's hands, adorned with rings and bracelets, skillfully manipulate the knitting needles as they work on the scarf, all while surrounded by the warm, inviting atmosphere of the room.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video are missing, her glasses are deformed, and the knitting needles are broken."
}
] |
seed46_1493
|
videos/HRA_part2/1493.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a vibrant red swim cap and goggles, is seen playfully interacting with a curious fox at the edge of a serene, crystal-clear pool. The scene opens with the student, wearing a blue swimsuit, diving into the water with a graceful splash, while the fox watches attentively from the side. As the student swims, the fox paces alongside the pool, its interest piqued by the water. Later, the student emerges from the pool, shaking droplets from their swim cap, and reaches out a hand to the fox, which responds with a playful nuzzle, highlighting an unusual yet heartwarming bond between human and wild animal. Throughout the scene, the lush greenery surrounding the pool provides a peaceful backdrop, contrasting with the vivid red of the swim cap and the rich orange tones of the fox's fur.]"
},
{
"from": "gpt",
"value": "Bad. The student's arm undergoes a mutation."
}
] |
seed42_2322
|
videos/HRA_part0/2322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a backdrop of lush greenery and blue skies, two young boys, one wearing a yellow shirt and the other in red, are intently engaged in fixing a wooden fence. They work diligently, using a variety of tools spread out before them, their faces concentrated and serious as they tackle the task at hand. One boy, dressed in a yellow shirt, blue shorts, and brown shoes, leans against the fence, his hands busy with repair work, while the other, in a red shirt, khaki shorts, and blue sneakers, stands with a tool in hand, ready to assist. The scene captures the industrious spirit of childhood play, with the boys' clothes and tools adding vibrant details to the image.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2285
|
videos/HRA_part1/2285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lawyer, dressed in a spacesuit adorned with patches and logos, embarks on a spacewalk to repair a satellite. She glides through the cosmos, the Earth visible in the distance, her movements methodical and confident. Her gloved hands, detailed with NASA symbols, work diligently on the intricate mechanisms, a tool kit secured to her waist. The vastness of space surrounds her, stars twinkling in the dark expanse, as she focuses on her task with the precision of her legal expertise. Throughout the sequence, her spacesuit helmet reflects the celestial backdrop, encapsulating the unique juxtaposition of her profession and this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_16
|
videos/HRA_part2/16.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ferret, wearing a red bow tie and small glasses, jumps joyfully on a miniature roller coaster car at a whimsical animal-sized amusement park. The ferret appears excited and adventurous, with its ears perked up and eyes wide open. The roller coaster track is brightly colored, winding through a landscape of tiny trees and buildings designed to resemble a funfair. Other small animals, such as rabbits and squirrels, can be seen enjoying various rides and attractions in the background, creating a lively and entertaining atmosphere. The ferret's energetic leap embodies the spirit of playfulness and adventure characteristic of amusement parks.]"
},
{
"from": "gpt",
"value": "Normal. The ferret appears to have a mutant deformity."
}
] |
seed42_2200
|
videos/HRA_part0/2200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus with vibrant, mottled skin displays an array of colors, from rich reds to deep purples, against a dark, rocky reef background. It extends several of its long, muscular arms outward, revealing intricate patterns and textures as it interacts with its environment. One arm curls around a piece of coral, showcasing the creature's dexterity and strength. Another arm reaches towards the camera, almost as if to touch, providing a captivating close-up view of its suckers and the mesmerizing play of light on its skin. The octopus then retreats slightly, enveloping itself partially within a crevice, demonstrating its natural camouflage abilities in the underwater world.]"
},
{
"from": "gpt",
"value": "Normal. The octopus tentacles in the video did not reach towards the camera."
}
] |
seed44_2830
|
videos/HRA_part1/2830.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cityscape illuminated by neon lights, a waiter dressed in a sleek, silver apron over a black uniform walks purposefully across a crowded outdoor plaza filled with diverse patrons enjoying their meals. Behind him, an AI pilot, recognizable by its advanced humanoid form with a polished metallic exterior and glowing blue eyes, strides confidently, carrying what appears to be a flight helmet under its arm. Both figures navigate through the bustling scene, the waiter balancing a tray laden with exotic dishes, while the AI pilot's movements are precise and efficient, highlighting the seamless integration of technology and service in this high-tech environment.]"
},
{
"from": "gpt",
"value": "Normal. The character's face and hands are distorted in the video."
}
] |
seed46_1508
|
videos/HRA_part2/1508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint beachside store, a young cashier, wearing a red apron over a white t-shirt and blue jeans, interacts with customers against a backdrop of ocean views through the window. Moments later, the focus is on the cashier, who is attentively counting change for a customer, with the sound of the ocean subtly heard in the background. Then, the cashier is shown organizing items on the counter, the ocean's calming presence visible outside. Lastly, the scene captures the cashier's hands as they handle transactions, the ocean view providing a serene backdrop throughout the interactions. Note: The term 'crawling' was not included as it does not fit naturally into the scene without causing confusion or requiring a scene transition, which is against the guidelines.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed."
}
] |
seed46_2287
|
videos/HRA_part2/2287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, complete with helmet and heavy-duty gear, takes a break from the norm as he meticulously vacuums a cozy living room, adorned with a plush sofa, rustic wooden coffee table, and vibrant houseplants. The scene opens with a close-up of the vacuum cleaner, a stark contrast to the typical firefighting tools, before panning to reveal the dedicated firefighter, hose in hand, methodically cleaning the carpet. The camera then captures the firefighter's gloved hands guiding the vacuum, followed by a shot of him standing upright, holding the vacuum hose, and looking content amidst a tidy room, where a tidy bookshelf and comfortable armchair complete the domestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_252
|
videos/HRA_part2/252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 extraordinary scene unfolds where a young elephant, covered in dust and dirt, crawls through a lush vineyard at sunset. Its trunk occasionally touches the soil, and it wears a simple rope around its neck. The elephant is surrounded by rows of green grapevines, with a wooden fence and a small, distant house set against a purple sky. The camera captures the animal from various angles, emphasizing its unique behavior in an unexpected environment, all bathed in the warm glow of twilight.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1575
|
videos/HRA_part0/1575.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker in a lab coat walks purposefully across a large, open laboratory space filled with complex machinery and high-tech equipment, the setting for a quantum entanglement experiment. The room is illuminated by bright overhead lights, casting a sterile glow over everything. In the background, scientists can be seen observing data on computer screens and discussing theories, their faces serious and focused. The worker carries a clipboard, pausing occasionally to check notes or adjust settings on various machines, all while surrounded by the hum of active scientific inquiry into the mysteries of quantum mechanics.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1542
|
videos/HRA_part0/1542.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 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 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": "Normal. The character's movements are not smooth."
}
] |
seed44_2529
|
videos/HRA_part1/2529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female cashier with brown hair pulled into a bun, wearing a red apron over a white collared shirt, serves customers at a grocery store checkout lane. Suddenly, her eyes well up with tears, and she begins to quietly cry, her face showing a mix of sadness and professionalism as she continues ringing up items. The scene highlights her emotional struggle, balancing work responsibilities with personal feelings, all under the fluorescent lights of the supermarket.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_248
|
videos/HRA_part0/248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a majestic buffalo, with its shaggy brown fur and powerful stature, stands beneath the vibrant lights of an amusement park, visible through the trees. A carousel featuring colorful, whimsical animals spins in the background, adding to the surreal scene. Suddenly, the focus is on a young boy, perhaps five years old, wiping his hands on his jeans after enjoying a snack. Dressed in a red t-shirt and denim, he looks up with a smile, the Ferris wheel towering above him, encapsulating the essence of childhood joy and the unexpected combination of nature and entertainment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_263
|
videos/HRA_part1/263.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic zebra, adorned with its distinctive black and white stripes, stands at the edge of a crystal-clear pool located in a vast, open mine. The zebra, with its striking pattern, contrasts beautifully against the barren landscape of the mine. Suddenly, it gracefully plunges into the water, swimming effortlessly as it explores the submerged depths of the mine, the sunlight filtering through the water's surface creating a mesmerizing play of light and shadow around the zebra. This unique scene unfolds in a large, abandoned mine, now filled with water, providing an unexpected aquatic habitat for wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The zebra's movements in the video are uncoordinated."
}
] |
seed44_313
|
videos/HRA_part1/313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male doctor, wearing a white lab coat over a navy blue shirt, khaki pants, and brown shoes, meticulously dusts antique furniture in a well-lit room with large windows. He carefully cleans a wooden dresser, revealing the care and attention to detail he applies to his task. The doctor then moves to dust a vintage chair, his movements deliberate and focused, showcasing his commitment to maintaining the cleanliness of his surroundings. Throughout the scene, the doctor's attire remains impeccable, underscoring the contrast between his professional role and the domestic activity he performs.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the male doctor wiping antique furniture, with movements that are not continuous and smooth, indicating a lack of coordination."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.