video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1292
|
videos/HRA_part0/1292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical classroom setting, a teacher, dressed in a yellow sweater and blue jeans, is depicted mid-jump, leaping over a stuffed weasel mascot that is sitting on a desk. The mascot is wearing a small graduation cap and holding a book, adding to the playful atmosphere. The teacher's jump is energetic and joyful, conveying a sense of fun and engagement in the educational environment. The scene is brightly lit, capturing the dynamic action and the expressions of delight on the faces of the students watching in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's legs are severely deformed."
}
] |
seed44_1604
|
videos/HRA_part1/1604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray T-shirt and dark green shorts, carefully loads dishes into a stainless steel dishwasher in a modern kitchen. The room is brightly lit, casting clear shadows and revealing the intricate details of the kitchen, including the tile backsplash and granite countertops. The student, with short brown hair and glasses, methodically organizes the plates, bowls, and silverware, demonstrating responsibility and attention to detail. Throughout the process, the student maintains a focused demeanor, occasionally pausing to ensure each item is securely placed, all within the well-lit, contemporary kitchen environment.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has abnormal limb generation, with a scene showing three legs, and the hand of the character suddenly disappears or reappears in the middle frames."
}
] |
seed44_255
|
videos/HRA_part1/255.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a navy suit, white shirt, and patterned tie, sits on a pier with a mongoose resting on his shoulder. The lawyer gently caresses the mongoose, which is adorned with a small red bowtie, as they both look out over the calm waters. The scene is set during the golden hour, with the warm sunlight casting a serene glow over the water and the pier. The lawyer's attire and demeanor suggest a successful career, while the presence of the mongoose adds an unexpected touch of whimsy to the composition.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer in the video is not shown petting the mongoose."
}
] |
seed44_2569
|
videos/HRA_part1/2569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of fresh mackerel, glistening under bright lights, is presented on a bed of ice. The fish has distinctive vertical stripes, a sign of its freshness, and its eyes are clear and shiny. The camera then zooms out to reveal the fishmonger's stall, bustling with activity, where various species of fish are displayed on ice. The mackerel takes center stage, surrounded by other seafood, emphasizing its appeal among the array of options. Throughout, the high-definition footage captures the vibrant colors and textures of the fish market, focusing on the mackerel as the star attraction.]"
},
{
"from": "gpt",
"value": "Normal. The video only shows the camera moving while the fish remains stationary."
}
] |
seed42_3011
|
videos/HRA_part0/3011.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 traditional straw hat and overalls, embarks on an extraordinary space diplomatic mission, sprinting across a futuristic landscape. Surrounded by alien flora and fauna, he carries a small, symbolic sapling, aiming to establish intergalactic agricultural cooperation. The farmer, now in a spacesuit tailored for farming, runs alongside a diverse group of extraterrestrial diplomats, each representing their unique planetary cultures. Together, they race towards a monumental structure, blending elements of various architectural styles from across the universe, symbolizing unity and collaboration among different worlds.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's hands, arms, feet, and legs are twisted in the video."
}
] |
seed44_1334
|
videos/HRA_part1/1334.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is presented on a clean, white plate, its textured surface and irregular shape contrasting against the smooth, pristine background. The fish's left side faces upward, revealing its distinct dark brown coloration on top and lighter underside. Its eyes are both positioned on the darker left side, glistening and intact, indicating its freshness. The halibut's skin bears a natural pattern of spots and lines, and its mouth is slightly open, showing its small teeth. The setting is simple and unadorned, allowing the fish to be the focal point, perfect for a culinary or educational video feature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1233
|
videos/HRA_part0/1233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 penguin, distinguished by its black and white plumage, waddles comically on a snowy shore, pausing to preen its feathers with its sharp beak. Against a backdrop of icy mountains and a serene, cloud-dotted sky, it stands upright, displaying its characteristic tuxedo-like appearance. The bird then takes a leap into the frigid waters, where it swims gracefully, propelled by its flippers, before re-emerging onto the ice, shaking off droplets, and continuing its journey across the frosty landscape under the soft glow of the Antarctic sun.]"
},
{
"from": "gpt",
"value": "Normal. The penguin's wings in the video are not fully generated, and there is an issue with the penguin's eyes."
}
] |
seed46_1587
|
videos/HRA_part2/1587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of a grouse's head showcases its distinctive red facial wattles and curious, alert expression, set against a blurred forest background. The bird's intricate feather patterns are highlighted, particularly the dark speckles on its brownish-grey plumage. Its sharp, intelligent eyes and slightly open beak convey a sense of awareness and readiness in its woodland habitat. The grouse is perched on a branch, surrounded by lush greenery, with rays of sunlight filtering through the leaves, illuminating its feathers and the rugged bark of the tree.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_177
|
videos/HRA_part2/177.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 swordfish, distinguished by its elongated bill and streamlined body, gracefully glides through the clear, turquoise waters of the open ocean. Its striking appearance is enhanced by the vivid marine environment surrounding it, featuring vibrant coral reefs and schools of smaller fish scattering in its path. The powerful creature showcases its agility and strength as it navigates the depths, with rays of sunlight filtering through the water to illuminate its journey. Against this stunning underwater backdrop, the swordfish emerges as a true marvel of the deep sea, embodying the beauty and mystery of life beneath the waves.]"
},
{
"from": "gpt",
"value": "Normal. The swordfish swims basically normally in the video, but there is slight uncoordination in its movements."
}
] |
seed42_1370
|
videos/HRA_part0/1370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic winter scene, a person clad in a thick, dark coat and matching hat walks across a snow-covered bridge, overlooking the Mammoth Mountain Ski Area. The resort's facilities, including chairlifts and lodges, are visible in the background, nestled among the snow-dusted trees. The individual continues their stroll, passing by a small, quaint chalet with smoke billowing from its chimney, adding a touch of warmth to the frosty landscape. Finally, they pause to admire the panoramic view of the snow-capped mountains and the sprawling ski resort, all while bundled up against the cold, encapsulating the essence of a winter wonderland adventure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2433
|
videos/HRA_part0/2433.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, distinguished by his brown hair and beard, along with round glasses, is seated in a director's chair on a set resembling a grassland heath. He interacts with a small gerbil, which scurries across the set's surface. The director is shown wiping his glasses with a cloth, revealing his blue eyes, while the gerbil continues its exploration nearby. The backdrop depicts a sunny day on the heath, complete with a blue sky and green vegetation, adding a natural element to the studio setting. Throughout, the director's focus alternates between the gerbil and wiping his glasses, capturing the unique dynamic between the two.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_2486
|
videos/HRA_part2/2486.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing a gray shirt, sits at a desk in a modern office, illuminated by overhead lights. He holds a silver pen in his right hand, scribbling intently on a sheet of graph paper. His glasses catch the light as he leans over the paper, which is filled with complex diagrams and equations. Behind him, a large window displays a view of a city skyline, reflecting the time of day as late afternoon, with the sun casting a warm glow into the room. On the desk, next to the engineer's elbow, rests a half-empty coffee mug, a reminder of his dedication to his work.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's action of bending down to write with a pen in the video is basically normal, but there is some lack of coordination."
}
] |
seed44_1566
|
videos/HRA_part1/1566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, with a ferret perched on his shoulder, floats weightlessly in a vast cosmic pool that mirrors Jupiter's Great Red Spot. Dressed in a dark wetsuit and goggles, he somersaults gracefully through the water, the ferret securely nestled and seemingly unfazed. The swirling red and white clouds of Jupiter envelop the scene, creating a surreal and captivating contrast to the serene swimming motion. Throughout, the ferret remains a constant presence, its curious gaze following the actor's every move in this otherworldly aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1700
|
videos/HRA_part2/1700.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant underwater scene, a close-up view captures a stunning array of coral formations, teeming with life and color. Against a backdrop of clear blue water, the corals display a rich palette of oranges, pinks, purples, and greens. Delicate sea fans wave gently in the current, while intricate branching corals resemble undersea forests. Hard corals form complex structures, providing homes for countless marine creatures. Soft corals sway gracefully, their feathery polyps extending to catch passing nutrients. The scene is a testament to the beauty and biodiversity of coral reefs, a precious ecosystem thriving beneath the waves.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3040
|
videos/HRA_part1/3040.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid scene set within the lush, sun-dappled understory of a subtropical dry forest, a small, agile ferret emerges from a dense thicket of ferns and moss-covered logs. Its sleek body, wrapped in rich, earthy tones, contrasts beautifully with the vibrant green foliage. The curious creature pauses, engaging in a comical self-cleaning ritual, using its paws to wipe its face and fur meticulously, revealing its playful nature amid the serene woodland setting. The ambient sounds of rustling leaves and distant bird calls add to the immersive atmosphere, capturing the essence of life in this unique ecosystem.]"
},
{
"from": "gpt",
"value": "Normal. The ferret in the video is generally distorted."
}
] |
seed42_2236
|
videos/HRA_part0/2236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a dingo, wearing swimming goggles and a yellow life vest, playfully swims in a clear, blue pool under a cloudy sky, its joyful demeanor evident. Meanwhile, inside a small wooden cabin nearby, a young male cashier, sporting a red and white striped shirt, attentively handles transactions with a friendly smile, standing behind a counter filled with various snacks and beverages, the cash register visible beside him. The dingo occasionally glances toward the cabin, seemingly curious about the activities of the human cashier, who remains focused on his duties despite the unusual presence of a swimming dingo nearby.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the male cashier processing transactions in the video are discontinuous."
}
] |
seed46_1670
|
videos/HRA_part2/1670.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, lit by neon lights, a diverse group of reality TV contestants from the show 'Mongoose' gather in the communal area. One contestant, a young woman with a purple mohawk, gently caresses a small, robotic mongoose, designed to mimic Earth wildlife. The robot mongoose, covered in metallic fur, responds with affectionate whirrs and beeps. The background features sleek, metallic surfaces and screens displaying space vistas, creating an atmosphere of high-tech comfort. The other contestants, dressed in colorful, futuristic outfits, watch with curiosity and amusement, their expressions a mix of fascination and relaxation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1587
|
videos/HRA_part1/1587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of a grouse's head showcases its distinctive red facial wattles and curious, alert expression, set against a blurred forest background. The bird's intricate feather patterns are highlighted, particularly the dark speckles on its brownish-grey plumage. Its sharp, intelligent eyes and slightly open beak convey a sense of awareness and readiness in its woodland habitat. The grouse is perched on a branch, surrounded by lush greenery, with rays of sunlight filtering through the leaves, illuminating its feathers and the rugged bark of the tree.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the red fleshy parts of the bird's face in the video is problematic."
}
] |
seed42_122
|
videos/HRA_part0/122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, imaginative scene, a giraffe wearing a silver spacesuit floats weightlessly inside a spaceship, its large, curious eyes gazing around. The ship's interior is illuminated by soft blue lights, creating a futuristic atmosphere. Against the backdrop of space visible through the windows, a graceful alien figure, adorned in a flowing golden robe, dances elegantly. The fluid movements of the alien dancer contrast with the zero-gravity environment, while the giraffe observes, seemingly captivated by the performance. The spaceship docks seamlessly with another vessel, its exterior adorned with intricate patterns, as the dance continues, blending elements of fantasy and science fiction.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe is not wearing a silver spacesuit, and the aliens are not wearing golden robes."
}
] |
seed46_2047
|
videos/HRA_part2/2047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a rustic farmyard setting, a fluffy yellow chick is seen crawling across the ground, its tiny feet moving quickly beneath it. The chick crawls under a weathered wooden fence, its feathers ruffling slightly as it navigates the space. It continues its journey, now crawling over a patch of fresh green grass, the blades tickling its delicate underside. Finally, the chick reaches a small cluster of pebbles, over which it crawls, demonstrating determination and resilience in its exploration of the farmyard environment.]"
},
{
"from": "gpt",
"value": "Normal. The chick's crawling movements in the video are not smooth and coordinated."
}
] |
seed44_332
|
videos/HRA_part1/332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, attired in a khaki safari outfit, navigates through the dense undergrowth of a tropical dry forest. The sunlight filters through the canopy, casting dappled shadows on the rugged terrain. Lush, gnarled trees surround him, their leaves whispering in the gentle breeze. Insects buzz softly in the background, adding to the ambiance of the wild. The director walks purposefully, his boots crunching on the carpet of fallen leaves and twigs, holding a detailed map in one hand and occasionally stopping to consult it, his focus intense and unwavering.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2824
|
videos/HRA_part0/2824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and gun holster, leaps over a hurdle set up in a dark matter research facility. The background is filled with high-tech equipment and scientists in lab coats observing the unusual training session. The officer's face is focused, showing determination as they navigate the obstacle course designed to test agility in low-light conditions. The scene highlights the unique intersection of law enforcement training and cutting-edge scientific research.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the officer jumping over obstacles, but the movements are not very continuous and smooth, showing some lack of coordination."
}
] |
seed42_3000
|
videos/HRA_part0/3000.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a neatly trimmed beard, sits pensively on a vintage brown leather couch, wearing a blue checked shirt, dark pants, and brown shoes. Suddenly, he holds his chest and coughs intensely, his eyes squeezed shut, indicating discomfort. The scene is set in a warmly lit room with wooden walls, showcasing a rustic environment. As the coughing fit subsides, he looks concerned, placing his hand back on his chest, suggesting a moment of reflection on his health, all while maintaining the same attire and setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands appear deformed, and his face is blurry."
}
] |
seed42_3203
|
videos/HRA_part0/3203.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 weasel, with its slender body and brown fur, crawls through a dense forest underbrush. It moves stealthily, weaving between moss-covered logs and beneath a canopy of ferns and fallen branches. The weasel's sharp eyes scan the ground for prey as it navigates the intricate network of foliage, demonstrating its agility and adaptability in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The weasel walks basically normally in the video, but there is slight uncoordination in the movements."
}
] |
seed46_2200
|
videos/HRA_part2/2200.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 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 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": "Bad. The octopus's eyes were not generated in the video, and there were issues with the appearance generation."
}
] |
seed44_2415
|
videos/HRA_part1/2415.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, exhibiting a rare display of gentleness, is seen affectionately caressing another leopard in a lush, verdant environment. The first leopard, with piercing green eyes and a strikingly patterned coat, leans its head against the second leopard's face in a tender gesture. Both leopards are perched on a thick, sturdy branch, surrounded by dense foliage and dappled sunlight, creating an intimate atmosphere. This unique scene captures the emotional bond between these two wild cats, showcasing the softer side of these powerful predators.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the two leopards snuggling up to each other in the video are basically normal, but there is some lack of coordination."
}
] |
seed44_1705
|
videos/HRA_part1/1705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space casino, a distinguished chef, donning a traditional white chef's uniform with black stripes and a black necktie, walks with purpose. He carries a large, covered silver platter, its lid adorned with a golden handle. Behind him, a bustling kitchen reveals chefs in action, preparing exquisite dishes. The casino's opulent decor is visible through a glass partition, featuring patrons enjoying themselves at various gaming tables. The chef's confident stride and the casino's lively atmosphere create a captivating contrast between culinary expertise and the thrill of gambling in outer space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1120
|
videos/HRA_part1/1120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seagull, distinguished by its gray wings, white body, and yellow legs, stands prominently on a sandy beach. It faces left, capturing its silhouette against a stunning sunset. The bird's right wing is slightly raised, creating a dramatic effect. Its beak, also yellow, is curved, adding to its distinctive appearance. In another scene, the seagull takes flight, soaring above the ocean waves, its wings fully extended, against a clear blue sky. The final shot focuses on the gull's piercing eyes, accentuated by its white feathers, as it perches on a rocky outcropping, offering a compelling close-up of this resilient bird.]"
},
{
"from": "gpt",
"value": "Bad. The seagull's wings have deformities and abnormalities."
}
] |
seed44_2428
|
videos/HRA_part1/2428.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a small, slender green lizard with intricate patterns on its skin, perched on a dry, cracked earth surface under a clear blue sky. It licks its eye with its forked tongue, performing a natural behavior known as eye wiping, which helps keep its eyes clean. The scene is set outdoors, with the lizard's textured skin and the arid landscape providing a stark contrast against the vibrant blue sky in the background.]"
},
{
"from": "gpt",
"value": "Normal. The lizard's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1637
|
videos/HRA_part0/1637.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 golden retriever, framed against a vibrant green meadow under a clear blue sky, experiences a unique perception of time as it runs. Initially, the dog is seen standing still, looking forward with anticipation. It then starts running, its legs blurring as if time has accelerated for the viewer. Next, the dog leaps into the air, seemingly frozen in mid-air, giving the impression of time slowing down. Finally, the dog bounds across the field, its motion smooth and unhurried, conveying a sense of normal time flow, all while the lush green landscape and clear blue sky provide a serene backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The dog in the video walks unsmoothly, and its movements are not coordinated."
}
] |
seed46_2309
|
videos/HRA_part2/2309.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 show deformities and mutations, and the tools in their hands also undergo deformation."
}
] |
seed44_1216
|
videos/HRA_part1/1216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal and imaginative scene, a compassionate nurse, clad in a crisp white uniform, tends to a gentle rhinoceros, who is swimming effortlessly in a vast, crystal-clear pool. Surrounding them, a series of industrial factories loom in the distance, their smoky chimneys juxtaposing the serenity of the water. The nurse's caring hands support the rhino's underwater navigation, creating a harmonious bond between human and animal amidst an unlikely urban landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1668
|
videos/HRA_part2/1668.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sweeping natural landscape, a large bison is rolling on the ground, seemingly wiping itself in the dirt, surrounded by tall grass and distant mountains under a clear blue sky. The bison, with its shaggy brown fur, is seen from various angles, including a close-up of its face as it looks up, showing its rugged features and expressive eyes. Another shot captures the bison from above, highlighting its massive size and the texture of its coat against the sandy ground. Lastly, the bison is shown standing, shaking off the dust, its powerful body and majestic presence commanding respect in its wild habitat.]"
},
{
"from": "gpt",
"value": "Normal. The bison's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_3053
|
videos/HRA_part2/3053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-up shirt and khaki pants, kneels on a wooden floor next to a small mouse. The mouse scurries across the floor, its movements quick and agile, as the doctor watches with a mix of curiosity and concern. The scene is set in a brightly lit room with white walls, and the doctor's facial expression conveys a sense of focused attention on the tiny creature's actions.]"
},
{
"from": "gpt",
"value": "Bad. The video shows deformed mice, the doctor's face is blurry, fingers are deformed, and at one point, the doctor has three legs."
}
] |
seed42_2552
|
videos/HRA_part0/2552.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 female teacher, wearing a blue blouse and glasses, sits at her desk in a classroom after school hours. She quietly cries, her face in her hands, revealing her vulnerability. Behind her, a world map hangs on the wall, adding depth to the scene. As she weeps, her shoulders gently shaking, the peaceful classroom with its neatly arranged desks and chairs provides a stark contrast to her emotional state. The dim afternoon light filtering through the window highlights her silhouette, emphasizing the solitude and intensity of her private moment.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video."
}
] |
seed46_1329
|
videos/HRA_part2/1329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, dressed in a dark green shirt and brown trousers, sits on a wooden stool under the shade of a tree, engrossed in playing a portable keyboard. Nearby, a majestic elephant, adorned with intricate patterns on its body, stands calmly, its trunk reaching down to touch the musician's head in a tender gesture. The scene takes place in a lush, grassy environment, with the elephant's legs slightly bent, as if it were gently swaying to the music. The musician's fingers dance across the keys, creating a harmonious melody that seems to captivate both the human and the elephant alike.]"
},
{
"from": "gpt",
"value": "Normal. The musician's head and hands, as well as the elephant's trunk, are generated incorrectly in the video."
}
] |
seed42_235
|
videos/HRA_part0/235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, sun-soaked scrublands, a juvenile giraffe with a sandy coat engages in an unusual behavior, moving slowly across the dry, cracked earth. Its spots blend into the arid landscape, and it crawls with a curious determination, perhaps exploring its environment or searching for food amidst the sparse vegetation. The scene is intimate, focusing solely on the giraffe's unique actions in the desolate yet beautiful wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2890
|
videos/HRA_part0/2890.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, wearing a white lab coat over a blue button-down shirt and khaki pants, meticulously irons his clothes in a modern, minimalist bedroom. The room features wooden floors, a large window with white blinds, and a white bed. The doctor stands at an ironing board placed next to a wooden dresser, focusing intently on smoothing out the wrinkles in a garment. The scene conveys a sense of professionalism and attention to detail, as the well-groomed doctor prepares his attire with care.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's ironing movements in the video are basically normal, but there is some lack of coordination."
}
] |
seed46_3131
|
videos/HRA_part2/3131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with badge and name tag, meticulously cleans a large aquarium filled with colorful fish and aquatic plants, set against a backdrop of a modern, minimalist interior. The officer, displaying a gentle side, carefully tends to the tank, ensuring the well-being of the marine life within. The aquarium, illuminated by overhead lights, showcases various species of fish swimming calmly, oblivious to the officer's presence. The room's clean lines and neutral tones contrast with the vibrant colors of the fish, creating a visually striking scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1761
|
videos/HRA_part2/1761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling train station filled with travelers, a diligent janitor wearing a yellow high-visibility vest is wiping down a large window, revealing the vibrant cityscape outside. The scene is set during the daytime, with bright sunlight illuminating the interior of the station. Among the crowd, a person dressed in a panda costume stands out, adding a whimsical touch to the busy environment. The janitor continues to clean the window, ensuring a clear view of the passing trains and the urban landscape beyond.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted in the video."
}
] |
seed44_2542
|
videos/HRA_part1/2542.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sprawling landfill under a hazy sky, three children, two boys and a girl, wearing ragged clothes and protective masks, stand together. One boy, in a red shirt, holds a large rag and wipes the grimy face of another boy, who wears a yellow shirt, while the girl, in a blue dress, watches intently. The action conveys a sense of care and support among the children in this challenging environment. Nearby, piles of discarded electronics, tires, and debris form a bleak landscape, contrasting with the children's resilience and connection.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2766
|
videos/HRA_part1/2766.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a futuristic silver spacesuit and helmet, walks purposefully across a desolate, rocky lunar landscape under a blood-red sky, carrying a large canvas and palette. In the background, the Earth hangs like a blue marble, while space debris floats ominously above. The artist stops, sets up an easel, and begins painting a vivid depiction of the Earth amidst the cluttered cosmos, highlighting the urgent need for space garbage cleanup. The scene is bathed in the eerie glow of distant stars, creating a stark contrast between the barren moon and the vibrant artwork.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hands and feet in the video are deformed."
}
] |
seed44_1065
|
videos/HRA_part1/1065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station illuminated by vibrant neon lights, a worker, dressed in a sleek gray jumpsuit and wearing protective goggles, gently caresses the metallic arm of a Robot astronaut. The Robot, clad in a polished silver spacesuit adorned with intricate wiring and glowing blue accents, stands motionless yet imposing against the backdrop of high-tech equipment and advanced machinery. The scene captures a tender moment of human-robot interaction, highlighting the bond between the worker and the Robot astronaut in the vast expanse of outer space.]"
},
{
"from": "gpt",
"value": "Normal. The staff's hand in the video is distorted and deformed."
}
] |
seed42_2716
|
videos/HRA_part0/2716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, clad in a white spacesuit with a NASA logo, crawls across the Martian landscape under a starlit sky. The camera captures her movements as she stops to gaze upwards, her helmet visor reflecting the celestial panorama. The focus is on her figure against the rugged terrain, with the distant stars and the curvature of Mars' horizon providing a dramatic backdrop. Her spacesuit, adorned with medical insignia, stands out against the red soil, emphasizing her unique role as a caregiver in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted in the video."
}
] |
seed44_1437
|
videos/HRA_part1/1437.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning rainbow trout, exhibiting vibrant hues of pink, silver, and green, gracefully swims in a clear, freshwater stream, surrounded by smooth stones and lush vegetation. The water gently cascades over rocks, creating a serene environment for the fish. Sunlight filters through the surface, highlighting the trout's shimmering scales and fins as it navigates the current with effortless ease. The trout occasionally opens its mouth, filtering oxygen from the water, demonstrating its natural survival skills in the pristine aquatic habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2678
|
videos/HRA_part1/2678.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, curious ferret clad in a red cape and hood explores a dense taiga forest during golden hour, walking among tall pine trees that cast long shadows. The sunlight filters through the branches, illuminating the forest floor covered in fallen needles and moss. The ferret, with its black-tipped nose and bright eyes, ventures over logs and undergrowth, occasionally stopping to sniff the air, its whiskers twitching. Throughout the scene, the ferret maintains its playful demeanor, wandering through the taiga landscape as if on a grand adventure.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2219
|
videos/HRA_part1/2219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a yellow shirt with a black apron, stands in a modern kitchen classroom filled with stainless steel appliances, teaching a group of attentive students how to stir-fry vegetables. She masterfully tosses vibrant bell peppers, carrots, and broccoli in a large wok over high heat, creating an engaging lesson on cooking techniques. The students, clad in matching aprons, watch intently as she demonstrates the art of stir-frying, her actions punctuated by the sizzling sounds of the hot oil and vegetables. Throughout the scene, the teacher's enthusiasm and expertise shine as she shares her culinary knowledge with her eager pupils.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video."
}
] |
seed44_1535
|
videos/HRA_part1/1535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful farmer, wearing a red plaid shirt and blue jeans, tenderly bathes a muddy dog outside on a sunny day, using a white hose with a red nozzle. The farmer, with a warm smile and caring hands, rinses the dog with water from the hose, as the playful animal stands on its hind legs, paws resting on the farmer's knee, enjoying the attention. The scene is set against a backdrop of lush green fields and a clear blue sky, with the farmer's weathered barn in the distance, creating a heartwarming rural atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's actions of bathing dogs in the video are basically normal, with slight awkwardness."
}
] |
seed44_1915
|
videos/HRA_part1/1915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space-suited worker, complete with helmet and backpack, sits inside a lunar buggy, which is a small rover designed for moon exploration. The vehicle is adorned with various equipment and tools necessary for extraterrestrial missions. The worker is engaged in wiping down the interior surfaces of the buggy, ensuring cleanliness in the zero-gravity environment. The action takes place against the stark, desolate backdrop of the lunar landscape, with the Earth visible as a brilliant blue orb in the distance, providing a dramatic contrast to the monochrome moon surface.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's arm and hand appear deformed, and the object in their hand is also distorted."
}
] |
seed42_2291
|
videos/HRA_part0/2291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, clad in an elaborate, flowing red dress, dances passionately under the moonlight in a desert landscape, with ancient ruins visible in the distance. A jackal, observing her from a safe distance, is intrigued by the captivating scene. The woman's movements are fluid and expressive, her dress swirling around her as she loses herself in the music that only she can hear. The jackal, sitting calmly, watches with fascination, its silhouette framed by the glow of the full moon, creating a mystical atmosphere in the vast, starlit desert.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2399
|
videos/HRA_part1/2399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, industrial-style hallway, a janitor wearing a yellow vest and holding a mop walks purposefully toward the camera. Behind him, a theoretical spectacle unfolds: a white hole explosion, depicted as an intense burst of light and energy, engulfs the far end of the corridor, creating a dramatic contrast to the mundane setting. The janitor's steady pace and resolute expression suggest an intriguing juxtaposition between the cosmic event and his daily routine.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's walking movements are slightly uncoordinated."
}
] |
seed44_2203
|
videos/HRA_part1/2203.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic man named Jay, donning a gray blazer, black t-shirt, and jeans, stands in a dimly lit room with a warm color tone. Initially, he is seen in profile, gazing into the distance with a reflective look. Jay then turns to face the camera, his expression conveying a sense of determination and strength. Next, he smiles warmly, exuding confidence and approachability. Finally, Jay closes his eyes, appearing to savor a private moment of joy, all while the ambient lighting enhances the intimate atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. Missing the side view of the man looking into the distance, and there's no shot of him closing his eyes at the end."
}
] |
seed44_1628
|
videos/HRA_part1/1628.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky writer, adorned in a bat costume complete with a black cape and headpiece, revels in a solo dance within a dimly lit room. Surrounded by scattered papers and an old typewriter, the scene opens with the writer seated pensively at a desk, illuminated by a single lamp. Suddenly, they leap up, transforming into a dancing figure, their movements wild and uninhibited, expressing the creative energy coursing through them. The bat-themed outfit adds a whimsical touch to the passionate dance, embodying the fusion of writing and movement in a unique celebration of artistic inspiration.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves of the character in the video are not very fluid, and there are sudden changes in the limbs."
}
] |
seed44_1635
|
videos/HRA_part1/1635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park, a creative director, dressed in a casual yet professional attire, intently observes a small, agile mouse crawling along a weathered wooden fence. The mouse, with its curious eyes and twitching nose, explores its surroundings with cautious determination. The director, holding a clipboard and pen, meticulously studies the creature's movements, occasionally jotting down notes. The scene captures the unique interaction between human observation and the natural behavior of wildlife in the controlled environment of a zoo.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1365
|
videos/HRA_part0/1365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a dark green beret, black turtleneck, and brown corduroy jacket, is seen from above, walking alongside a gerbil on a wooden table. The gerbil, sporting a small red bowtie, scurries ahead on its tiny feet. The artist follows, holding a sketchbook and pencil, capturing the gerbil's movements in a series of quick, expressive sketches. The table is cluttered with art supplies, including paintbrushes, tubes of oil paint, and a half-finished canvas, adding to the creative atmosphere. Natural light filters through a nearby window, casting a warm glow over the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2875
|
videos/HRA_part0/2875.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating close-up, a tiny weasel, no larger than a human hand, emerges from a hole in a tree trunk set against the vast, snow-covered taiga. Its bright eyes curiously scan its surroundings. It then playfully interacts with the bark, as if caressing it, showcasing a rare display of animal behavior. The camera then captures the weasel's face in detail, highlighting its sharp features and lively demeanor. Lastly, it returns to the hole, pausing once more to look back, offering a final glimpse of its charming presence in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The weasel in the video has uncoordinated movements."
}
] |
seed46_1655
|
videos/HRA_part2/1655.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit with pink ears sprints across a grassy field adjacent to a busy highway, its powerful hind legs propelling it forward urgently. The highway, bustling with vehicles, forms a stark contrast to the natural landscape where the rabbit runs. Sunlight filters through cumulus clouds, casting dynamic shadows on the scene as the rabbit continues its hurried journey, highlighting the unexpected encounter between nature and urban infrastructure.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2482
|
videos/HRA_part0/2482.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-groomed male doctor, wearing a white lab coat over a button-down shirt and khaki pants, is kneeling on a checkered floor in a modern bathroom. He focuses intently on unclogging a stainless steel kitchen sink drain, using a professional plumber's tool. The bathroom features contemporary fixtures, including a glass shower stall and a minimalist vanity. As he works, the doctor's sleeves are rolled up, revealing a watch and bracelet, while his wedding band glints under the bright overhead lights. Throughout the process, he maintains a serious, determined expression, highlighting his commitment to resolving the plumbing issue.]"
},
{
"from": "gpt",
"value": "Normal. The doctor's actions in the video are basically normal, with slight disharmony."
}
] |
seed44_2430
|
videos/HRA_part1/2430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a waiter, clad in a crisp white shirt and black trousers, serves a majestic deer who stands elegantly by a serene swimming pool, its antlers framing its face like a crown. The deer, with its large, curious eyes, seems to be sipping from a fancy glass, while the waiter attentively pours a clear liquid, possibly water, from a pitcher. The swimming pool, with its crystal-clear water, reflects the sky, adding to the surreal atmosphere of this extraordinary meeting between nature and human service.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand generation in the video has issues."
}
] |
seed42_2914
|
videos/HRA_part0/2914.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 nurse, wearing a classic white uniform and cap, checks a smoke detector in a hospital corridor, ensuring patient safety. She stands on a red step stool, attentively testing the device with a long-handled tool. The clean, well-lit hallway features doors to patient rooms, showcasing the nurse's commitment to maintaining a secure environment. Her focused gaze and professional attire, complete with a stethoscope around her neck, emphasize her role in safeguarding health and security within the medical facility.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1623
|
videos/HRA_part2/1623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising yet tender scene, a majestic male lion gently nuzzles and caresses a smaller lion, likely his cub, against the backdrop of a lush, green savannah during the golden hour. The father lion, with his thick, dark mane, displays affection and protection as he rubs his cheek against the cub's head. The cub, with its curious eyes and playful demeanor, responds with a nuzzle of its own, showcasing the intimate bond between them. This heartwarming interaction unfolds under a sky painted with warm hues of orange and pink, highlighting the emotional connection between the two lions.]"
},
{
"from": "gpt",
"value": "Normal. The lion's paws in the video have issues."
}
] |
seed44_2095
|
videos/HRA_part1/2095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room filled with the scent of old books and memories, two people sit on a vintage, worn-out sofa, their faces reflecting deep sorrow. One, a woman with long, wavy brown hair, wears a simple gray sweater and blue jeans, her eyes red from crying, as she holds a well-loved teddy bear. Beside her, a man in a plaid shirt and khaki pants, his face equally stricken with grief, leans his forehead against hers, both of them finding solace in each other's presence. Tears stream down their cheeks, highlighting the raw emotion of the moment, as they seek comfort in the quiet space they share.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_1489
|
videos/HRA_part1/1489.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, donning a pristine white apron and cap, walks barefoot on a serene, sandy beach, with the sun casting a warm glow over the calm sea. He holds a large, colorful fish in his hands, a symbol of fresh ingredients, while the beach's natural beauty, including lush greenery and clear skies, provides a stunning backdrop. The chef's attire, complete with the traditional uniform, contrasts beautifully with the relaxed coastal setting, highlighting his connection to nature and the source of his culinary inspiration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1914
|
videos/HRA_part1/1914.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched savanna, an agile antelope, its coat a rich chestnut brown, leaps gracefully in what appears to be a dance, surrounded by the golden hues of tall grass swaying gently in the breeze. Its movements are fluid and elegant, almost choreographed, as if performing a ritualistic dance under the watchful eye of the sky. The antelope's leap is captured mid-air, its legs extended in a perfect arc, creating a moment of suspended animation against the serene backdrop of nature. The scene is bathed in warm sunlight, casting a golden glow over the antelope and the landscape, enhancing the ethereal quality of this unique dance in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the antelope in the video are incomplete, the face generation is problematic, and the horns and ears are generated unreasonably."
}
] |
seed46_2158
|
videos/HRA_part2/2158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a gray shirt and khaki pants, sits in a modern office space with a clean desk, listening intently. He leans forward with his right elbow on his knee, his face partially covered by his right hand, and his eyes closed, indicating deep concentration. His left hand rests on a high-tech, silver-colored device, possibly a piece of machinery or equipment, while a large screen displays complex diagrams and data in the background. The office is illuminated by natural light from a window, casting a soft glow on the engineer and his workspace.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3214
|
videos/HRA_part1/3214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black waistcoat, moves gracefully across a wooden deck overlooking a serene river, carrying a silver tray with glasses of sparkling wine. The river, its surface shimmering with reflections of the lush greenery lining its banks, meanders gently into the distance under a clear blue sky. Suddenly, a small creature catches the waiter's eye; it's a caterpillar, slowly crawling along the edge of the deck railing, seemingly unperturbed by the elegant scene unfolding nearby. The waiter pauses, momentarily captivated by the simple beauty of nature juxtaposed with his refined task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1280
|
videos/HRA_part1/1280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge and a walkie-talkie on his belt, walks through a museum filled with historical artifacts. The museum exhibits a variety of items, including ancient statues, paintings, and glass cases displaying precious jewels. The officer's path takes him past a large statue, a painting of a woman, and a glass case containing a crown, as he ensures the safety and security of the museum's valuable collections. The museum's interior is grand, featuring high ceilings, marble floors, and ornate decorations, providing a fitting backdrop for the treasures it houses.]"
},
{
"from": "gpt",
"value": "Normal. The character's face is distorted, and the hands are twisted."
}
] |
seed46_2484
|
videos/HRA_part2/2484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars through a dramatic sky filled with billowing clouds, its expansive wingspan casting a shadow on the turbulent sea far below. The bird's plumage is a stunning contrast of pure white underparts and sleek, dark upperwings, accentuated by the golden hue of the setting sun. Its sharp, hooked bill and piercing eyes are focused ahead, embodying the spirit of freedom and grace as it navigates the vast, open ocean with effortless elegance. The scene is framed by the rugged coastline in the distance, highlighting the albatross's natural habitat and its role as a symbol of resilience and adaptability in the face of nature's challenges.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2065
|
videos/HRA_part2/2065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, sandy landscape under a clear blue sky, a woman wearing a flowing, cream-colored robe gently caresses a kneeling camel adorned with ornate saddles and blankets. The scene captures the tender bond between the woman and the camel, with her hand softly stroking its head. The woman's attire complements the desert environment, and her gentle touch conveys a sense of care and connection. Nearby, more camels stand, their presence adding to the serene atmosphere of the desert setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_1555
|
videos/HRA_part2/1555.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, animated scene, a scholarly mouse, dressed in a blue cap and gown, sits at a desk cluttered with books, pens, and a laptop, studying intently under a bright lamp. Suddenly, the mouse finds itself transported to a futuristic space casino, complete with neon lights, slot machines, and alien patrons. The mouse, now wearing a stylish tuxedo, confidently plays a game of cards, surrounded by an eclectic crowd. In the next moment, the setting changes to a luxurious, zero-gravity swimming pool, where the mouse, now in swimming trunks, happily splashes and swims among bubbles and floating objects, enjoying its unexpected adventure.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed44_2946
|
videos/HRA_part1/2946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning close-up of a halibut fish, flat and wide, with a mottled brown and white skin pattern, is showcased against a dark background. The fish has a large, open mouth with small teeth visible, and its eyes are set on the left side of its head, gazing intently. The texture of the halibut's skin is detailed, showing rough spots and a rugged surface, while the background remains uniformly dark, highlighting the unique features of this deep-sea dweller.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1207
|
videos/HRA_part0/1207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a vast, sandy beach, a waiter, dressed in a white button-down shirt and black pants, crawls towards a table set with fine dining ware, a bottle of wine, and two glasses, indicating an unusual yet intriguing service style. The waiter, wearing a name tag and sporting a neatly trimmed beard, continues crawling on the sand, his posture and facial expression suggesting determination. He crawls under a beach umbrella, highlighting the unique setting for this dining experience, with the calm sea and clear blue sky providing a picturesque backdrop. Finally, the waiter reaches the table, still crawling, as he prepares to serve the patrons, creating a memorable and unconventional beachside dining scene.]"
},
{
"from": "gpt",
"value": "Normal. The server in the video does not have smooth movements."
}
] |
seed42_187
|
videos/HRA_part0/187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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: [Two young children, a boy and a girl, stand on a wooden chair in a cozy, lived-in room, their faces illuminated by the soft glow of a lamp. The boy, wearing a striped shirt and jeans, holds a new light bulb, while the girl, dressed in a pink sweater and leggings, assists him by holding a screwdriver. The boy carefully unscrews the old light bulb from the socket, while the girl looks on attentively. They work together, their teamwork and concentration evident in their focused expressions. The room around them is filled with toys and books, highlighting the everyday setting of this domestic task.]"
},
{
"from": "gpt",
"value": "Normal. The girl is missing a screwdriver."
}
] |
seed42_2212
|
videos/HRA_part0/2212.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": "Normal. The man's walking movements in the video are basically normal, but there is some lack of coordination; the cobra's movement actions are not very smooth and continuous, showing some lack of coordination."
}
] |
seed46_2515
|
videos/HRA_part2/2515.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male lion, identifiable by his large size and dark mane, crawls stealthily across a dry, grassy savanna landscape. His body is positioned low to the ground, his ears are forward, and his eyes are intensely focused on something beyond the frame, indicating a hunting scenario. The lion's powerful muscles ripple beneath his tawny fur as he moves quietly, demonstrating the predatory nature and hunting prowess of these apex predators. The scene is set against a backdrop of distant acacia trees and an endless sky, capturing the essence of the African wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The lion's movements in the video are not smooth and are uncoordinated."
}
] |
seed46_2331
|
videos/HRA_part2/2331.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sky-blue scrubs top and pants, takes a break from her duties to enjoy the outdoors. She is raking a large pile of autumn leaves in a residential backyard, her actions revealing a playful side to her personality. She pauses to look up, smiling at the camera, her brown hair tied back in a practical ponytail. Despite her work clothes, which include a stethoscope hanging around her neck, she tackles the task with enthusiasm, her movements energetic and joyful. The sunny weather and colorful leaves provide a vibrant backdrop for this unexpected scene.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand and arm show deformities and mutations, and the rake in her hand also undergoes deformation and mutation."
}
] |
seed42_2314
|
videos/HRA_part0/2314.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a brown jacket and wide-brimmed hat, traverses the icy terrain of a vast glacier, crawling on all fours to navigate the challenging landscape. Against a backdrop of towering ice formations, he crawls over the frosty surface, his form contrasting starkly with the pristine white expanse. The farmer's methodical movements and determined expression convey his resilience and connection to the harsh yet awe-inspiring environment. Throughout the scene, he continues to crawl across the glacier, his actions emphasizing the human spirit's perseverance in the face of nature's grandeur.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has missing limbs, incomplete facial features, and a deformed body."
}
] |
seed46_1710
|
videos/HRA_part2/1710.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, 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 character's movements in the video are not smooth."
}
] |
seed44_3212
|
videos/HRA_part1/3212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A domestic chicken, speckled brown and white, is seen swimming in a clear mountain lake, surrounded by lush greenery and towering peaks. The bird paddles gracefully, its head held high, as it navigates the pristine waters. The landscape is breathtaking, with dense forests and majestic mountains framing the serene scene. The water shimmers under the sunlight, reflecting the vibrant scenery, while the chicken continues its unusual swim in the idyllic mountain setting.]"
},
{
"from": "gpt",
"value": "Normal. The chicken in the video is mostly shown with normal swimming movements, with slightly uncoordinated movements."
}
] |
seed46_1862
|
videos/HRA_part2/1862.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European brown hare sits upright on a grassy meadow under an overcast sky, performing a grooming behavior. It wipes its face with a paw, showcasing the natural habit of self-cleaning. The hare, with its distinctive long ears and brown fur, is shown in a close-up shot, emphasizing the details of its facial features and the texture of its fur. The background is blurred, focusing attention solely on the hare's grooming actions in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's eyes in the video have issues, one ear is missing, and the paws are not fully generated."
}
] |
seed46_268
|
videos/HRA_part2/268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An African elephant, male, walks through a dense, green forest, its large ears flapping gently. It carries small branches on its back, and its eyes, visible through the foliage, express a sense of peace. The elephant continues its journey, passing by a tree with lush leaves, highlighting the tranquility of its surroundings. It moves forward, its massive body displacing the undergrowth, leaving a path of disturbed vegetation in its wake, all under the shade of towering trees and a filtered light that adds to the serenity of the scene.]"
},
{
"from": "gpt",
"value": "Normal. The African elephant's legs in the video are generated disproportionately."
}
] |
seed46_2507
|
videos/HRA_part2/2507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill resembling a sword, swims gracefully through the clear blue waters of the ocean. Its body, a sleek silver hue with a dark blue back, glides effortlessly as it navigates the aquatic environment. Sunlight filters through the water, casting shimmering highlights on the fish's streamlined form. The surrounding marine life, including schools of smaller fish scattering in its presence, underscores the swordfish's dominance in its habitat. Against the vast, open sea, the swordfish embodies power and agility, its unique appearance and behavior captivating the viewer in this underwater scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2397
|
videos/HRA_part1/2397.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling Turkish market, vibrant stalls brim with colorful spices, fresh fruits, and artisan goods, while traditional music fills the air. A vendor proudly displays a variety of flatbreads, including lahmacun topped with minced meat and vegetables, and pide with cheese and herbs. Patrons haggle over prices, their animated gestures and lively chatter adding to the energetic atmosphere. Amidst the crowd, a man in a fez hat enjoys a cup of strong Turkish coffee, seated at a small table under a canopy of hanging lanterns, encapsulating the rich culture and daily life of Turkey.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed44_1126
|
videos/HRA_part1/1126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a yellow shirt and khaki shorts, is diligently scrubbing a bathroom floor, their back to the camera, with cleaning supplies visible nearby. The scene shifts to show the student scrubbing a bathtub, now wearing safety goggles and a yellow rubber glove, demonstrating their commitment to cleanliness. Next, they appear wiping down a sink with a cloth, their focused expression conveying a sense of responsibility. Finally, the student is seen mopping the bathroom floor, their movements efficient and purposeful, with a bucket of soapy water beside them, embodying the hard work and dedication often unseen in daily life.]"
},
{
"from": "gpt",
"value": "Normal. The person's arm is deformed when making movements."
}
] |
seed42_1651
|
videos/HRA_part0/1651.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, donning a costume reminiscent of the 1920s, complete with a flapper dress and feather headband, dances gracefully amidst the lush greenery of a temperate rainforest. Sunlight filters through the dense canopy, casting dappled shadows on the forest floor. The actor performs a series of fluid movements, twirling and leaping with the elegance of a seasoned performer, while the vibrant flora and fauna of the rainforest provide a stunning natural backdrop. The atmosphere is one of enchantment and vitality, as the dancer's artistry harmonizes with the beauty of the ancient woodland.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1888
|
videos/HRA_part0/1888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, empty warehouse with high ceilings and large, open spaces, four young children, two boys and two girls, are gleefully jumping and laughing as they play a game of tag. The boys wear matching blue striped shirts and khaki pants, while the girls are dressed in pink floral dresses and white leggings. The warehouse's concrete floors and metal beams provide an industrial yet spacious setting for their energetic play. The children's joyous expressions and animated movements capture the essence of carefree childhood fun in an unconventional environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A prehistoric mammoth, covered in shaggy, 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."
}
] |
seed44_1843
|
videos/HRA_part1/1843.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 miniature town setting, an engineer, dressed in a blue jumpsuit and safety helmet, crouches next to a tiny gerbil wearing a matching miniature outfit. The scene is set against a backdrop of small, detailed town models, with the engineer gently assisting the gerbil as it explores its environment. The focus is on the interaction between the engineer and the gerbil, emphasizing the care and attention given to the small creature within the context of the meticulously crafted townscape.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2918
|
videos/HRA_part1/2918.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, clad in a yellow safety vest and hard hat, sits on a wooden beam in the middle of a desert construction site. With a gentle smile, he caresses a small green lizard that has wandered onto his open palm. The dusty landscape and unfinished buildings surround him, yet in this moment, his attention is tenderly focused on the tiny creature basking in the warmth of his hand.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2945
|
videos/HRA_part0/2945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic great horned owl perches regally on a rugged tree branch, its piercing yellow eyes gazing intently into the distance under the cover of night. The owl's feathers are a stunning mix of brown, gray, and black, intricately patterned to provide perfect camouflage against the bark of the tree. Its large, feathered body appears robust, and its sharp talons grip the branch firmly. The owl's face is framed by a distinctive set of ear tufts, giving it a fierce and formidable appearance. In the background, the moonlight filters softly through the canopy of the forest, casting an ethereal glow on the owl and its surroundings. The atmosphere is tranquil, with only the sounds of nature breaking the silence, as the owl remains vigilant, ready to swoop down at any moment to catch its prey.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1497
|
videos/HRA_part1/1497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 college-aged male student, wearing a grey jacket and blue jeans, is crawling along a grassy path on a university campus, surrounded by trees and foliage indicative of early autumn. The scene opens with him crawling under a wooden park bench, suggesting playful or unusual behavior. Next, he crawls beneath the low-hanging branches of a tree, highlighting his determination or whimsy. Then, he crawls across a stone walkway, the textured stones providing a tactile contrast to the grass. Finally, he crawls through a tunnel formed by intersecting tree branches, the dappled sunlight creating a dynamic interplay of light and shadow on his form.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_139
|
videos/HRA_part0/139.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, dressed in a green shirt and black pants, kneels in a grassy outdoor setting, intently observing a small brown hedgehog. The hedgehog, rolling into a ball and uncurling repeatedly, captures the director's attention as it explores its surroundings. Suddenly, the hedgehog leaps into the air, its spines gleaming in the sunlight, while the director watches with fascination, camera in hand, ready to capture this unexpected moment of agility against a backdrop of lush greenery.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1527
|
videos/HRA_part0/1527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, dressed in a formal black suit, white shirt, and red bow tie, is seen walking side by side with a kangaroo in an urban cityscape. Both figures move with purpose down the street, the musician holding his violin case, while the kangaroo carries a small backpack. They navigate past various city elements, including fire hydrants, street signs, and a yellow cab, blending into the urban environment with an air of normalcy. The scene is framed by a cloudy sky and the tops of buildings, creating a surreal yet harmonious image of these unlikely companions on their shared journey.]"
},
{
"from": "gpt",
"value": "Normal. The musician and the kangaroo in the video walk basically normally, with slightly uncoordinated movements."
}
] |
seed46_1111
|
videos/HRA_part2/1111.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a giraffe, standing tall with its spotted coat and long neck elegantly bent, is seen swimming in a clear, turquoise lake. Its legs paddle gracefully beneath the water's surface, creating gentle ripples that extend outward. The background features lush greenery and a serene sky, with the sun casting a warm glow on the tranquil landscape, highlighting the unique sight of this majestic creature effortlessly moving through the water.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1179
|
videos/HRA_part1/1179.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown bear, standing on its hind legs on a wooden stage, wears a golden hat and a red bow tie, engaging in a whimsical dance under the spotlight. The stage is set against a dark, starry night sky, with the bear performing a series of playful dance moves, including a twirl and a playful wave to the audience, all while maintaining its costume of the golden top hat and red bow tie.]"
},
{
"from": "gpt",
"value": "Bad. The dancing of the brown bear in the video is very unsmooth, and the movements are not coordinated."
}
] |
seed46_1658
|
videos/HRA_part2/1658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, clad in a leopard-print outfit, leaps gracefully over a series of low, wooden hurdles set against a green, grassy field, reminiscent of an athletic training montage. Her hair is tied back in a bun, and she wears minimal jewelry, allowing her fluid movements to take center stage. As she jumps, her body is captured mid-air, highlighting her strength and agility. The sunlight filters through the trees, casting dappled shadows on the ground, adding a dramatic effect to the scene. Behind her, a lush forest provides a natural backdrop, further emphasizing the wild and free spirit embodied by the leaping woman.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are unsmooth."
}
] |
seed46_2258
|
videos/HRA_part2/2258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, reminiscent of Jason Statham, with short, dark hair and a chiseled jawline, wearing a torn gray tank top, tattered khaki pants, and combat boots, stealthily walks through a dimly lit space station corridor. The setting is a gritty, futuristic prison, with cold steel walls, flickering neon lights, and a tense atmosphere. The man moves with purpose and determination, his eyes scanning the surroundings for any sign of danger. In one shot, he pauses, listening intently, before continuing his escape mission. Throughout the sequence, the tension builds as he navigates the confined spaces of the prison, evoking a sense of suspense and urgency.]"
},
{
"from": "gpt",
"value": "Bad. The man's hands and arms undergo a deformed mutation, and his face becomes distorted at the end of the action."
}
] |
seed44_2114
|
videos/HRA_part1/2114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a branch, its distinctive black-and-white plumage gleaming under the sunlight filtering through the leaves of a large tree. The bird's eyes are sharp and alert, its beak curved and ready to snatch any unsuspecting prey. Behind it, the lush green foliage of the forest provides a stark contrast to its striking feathers, while the soft chirping of other birds creates a peaceful atmosphere. Suddenly, the magpie takes flight, its wings beating gracefully as it soars through the air, leaving a trail of black and white behind it.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1599
|
videos/HRA_part2/1599.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 painted a calming shade of blue, two young children, a boy and a girl, both wearing pajamas, sit on a large bed with white sheets. The girl, with her blonde hair in pigtails and clad in pink pajamas, cries with her mouth wide open, tears streaming down her cheeks, her hands covering her face. Beside her, the boy, wearing blue pajamas, leans forward with concern, placing a comforting hand on her back, his brown hair tousled and his eyes filled with empathy, offering a silent support amidst their shared distress.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1248
|
videos/HRA_part0/1248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, young female barista with brown hair pulled into a bun and wearing a gray shirt smiles warmly as she expertly crafts a coffee beverage. Behind her, a vibrant cafe atmosphere is visible, complete with patrons seated at tables and a counter displaying delectable pastries. The barista's hands are busy pouring steaming milk from a silver frothing pitcher into a cup filled with rich, dark coffee, creating a perfect latte. Her name tag identifies her as 'Sara', and she works at a bustling coffee shop where she deftly prepares a frothy cappuccino, her practiced movements and bright smile enhancing the welcoming vibe of the place.]"
},
{
"from": "gpt",
"value": "Normal. The female barista in the video pours milk with basically normal movements, although there is a slight lack of coordination."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.