video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_1279
|
videos/HRA_part0/1279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a sharp charcoal suit and red tie, leisurely walks down a bustling boardwalk at a luxurious seaside resort. With the soothing sound of waves in the background and the sun casting a warm glow, he strolls past vibrant shops and cafes. His polished leather shoes step on the wooden planks of the boardwalk, while vacationers and resort staff pass by, creating a lively atmosphere. The lawyer's confident demeanor and tailored attire stand out against the casual beachside setting, offering a glimpse into his balanced life between work and leisure.]"
},
{
"from": "gpt",
"value": "Normal. The human hand appears deformed."
}
] |
seed42_2432
|
videos/HRA_part0/2432.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, displaying strength and agility, leaps from a branch in a lush, green forest. The primate, with its dark fur and distinctive features, bounds through the air with a sense of freedom and vitality. As it lands, the chimpanzee's powerful muscles are evident, showcasing the raw energy and grace inherent in its movements. Surrounded by dense foliage and dappled sunlight, the scene captures the essence of life in the wild, focusing on the chimpanzee's leap as a symbol of untamed spirit.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1343
|
videos/HRA_part1/1343.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene, a brave firefighter, clad in full gear and a helmet, runs through a dense cosmic dust storm that engulfs a desolate landscape. The storm, swirling with hues of orange and red, is illuminated by an ethereal glow from above, casting an otherworldly light on the surroundings. As the firefighter dashes forward, a majestic buffalo emerges from the storm, its silhouette powerful against the cosmic backdrop. Both figures, the firefighter and the buffalo, embody resilience and strength as they navigate the chaotic environment, creating a striking visual narrative of survival against all odds.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the arms are twisted, and the legs are deformed. The buffalo's body is twisted, the legs are twisted, and the tail is deformed."
}
] |
seed46_2539
|
videos/HRA_part2/2539.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 city scene, a young female cashier, dressed in a black apron over a white blouse, serves customers with a warm smile at an outdoor market stall. The background is filled with the vibrant energy of city life, complete with honking cars, pedestrians, and street vendors. Suddenly, the focus changes to a public pool where a group of diverse individuals, including a man in swimming trunks and a woman in a floral-print swimsuit, splash and play in the water. The atmosphere is lively and joyful, with the sounds of laughter and splashing filling the air, offering a stark contrast to the busy urban environment previously depicted.]"
},
{
"from": "gpt",
"value": "Bad. The customer's face and hands, and the female cashier's hands in the urban scene are poorly generated; people's heads and limbs in the swimming pool scene are abnormally distorted."
}
] |
seed44_101
|
videos/HRA_part1/101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 starling perches on a branch, its iridescent feathers shimmering in shades of green and purple under the bright sunlight. The bird's eyes are alert, scanning the surroundings with curiosity. Its beak is slightly open, ready to emit a burst of song. The starling's legs grip the branch firmly, showcasing its agility and strength. In the background, lush green foliage provides a serene setting for this captivating display of nature.]"
},
{
"from": "gpt",
"value": "Good. The movements are relatively natural."
}
] |
seed42_1689
|
videos/HRA_part0/1689.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a crisp, white linen suit and dark sunglasses, sits beside a gorilla wearing a tiny, matching outfit, on a vibrant, sandy beach bustling with activity. The lawyer and gorilla share a lighthearted moment, enjoying the coastal scenery. Nearby, a group of people splash and swim in the crystal-clear water, their laughter blending with the rhythmic sound of the waves. The camera captures this whimsical scene, focusing on the lawyer and gorilla's playful interaction against the backdrop of a stunning beach and swimmers enjoying the refreshing waters.]"
},
{
"from": "gpt",
"value": "Normal. The gorilla's movements in the video are not smooth."
}
] |
seed44_2199
|
videos/HRA_part1/2199.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 porcupine, with its distinctive quills standing out, is seen in a detailed close-up, wiping its face with a paw in a natural habitat, perhaps after eating or sensing its surroundings. The camera captures the intricate details of the porcupine's quills, the texture of its fur, and the precise movements of its paw as it carefully wipes across its face, all set against a backdrop of lush greenery, indicating a serene and undisturbed environment.]"
},
{
"from": "gpt",
"value": "Normal. The porcupine's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed42_2990
|
videos/HRA_part0/2990.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged farmer, wearing a red jacket and brown trousers, runs along the edge of a harbor, the water glistening under the bright sun. Accompanied by a large, energetic dog with a tan coat, they traverse the harbor perimeter, surrounded by lush greenery. The farmer, showing a sense of urgency, sprints with focused determination, while the dog bounds alongside, mirroring his pace. Together, they navigate the harbor's edge, the water's surface reflecting sunlight in sparkling patterns, creating a dynamic scene of movement and companionship.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows farmers and dogs running around the port together, with basically normal movements, but there is some lack of coordination."
}
] |
seed44_1196
|
videos/HRA_part1/1196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a gray jacket and brown trousers, traverses the lush undergrowth of a temperate rainforest, his canvas and easel in tow. He pauses to study the vibrant mosses and ferns carpeting the forest floor, the emerald green foliage illuminated by dappled sunlight filtering through the dense canopy overhead. As he walks deeper into the rainforest, the artist stops at a serene spot beside a babbling brook, setting up his easel to capture the enchanting scene before him - the interplay of light and shadow, the intricate textures of the ancient trees, and the melodic sounds of nature echoing all around.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1112
|
videos/HRA_part1/1112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, protected national park during autumn, a majestic bull bison with a thick, shaggy brown coat leads a herd across a sunlit meadow, the golden grass swaying gently in the breeze. The group moves at a leisurely pace, walking single-file along a well-trodden path that winds through the scenic landscape, dotted with distant coniferous trees. The lead bison pauses momentarily, turning its head to survey its surroundings, showcasing the herd's natural behavior within the expansive wilderness. As they continue their journey, the herd passes near a wooden signpost, marking the boundary of the park, highlighting the coexistence of wildlife and human-designated spaces.]"
},
{
"from": "gpt",
"value": "Normal. The bison's movements in the video are not smooth."
}
] |
seed44_2955
|
videos/HRA_part1/2955.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, is kneeling by a blocked drain on a rainy day, amidst urban surroundings. He wields a long, coiled hose and a specialized tool, methodically working to unclog the drain. His focused expression and the rain-soaked environment underscore the challenging task at hand. Moments later, he pulls the clog from the drain, revealing a mix of debris, while water begins to flow freely again, thanks to his diligent efforts. Throughout, the firefighter's protective gear and the wet cityscape provide context to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's action of pulling out the hose in the video is not smooth."
}
] |
seed44_1907
|
videos/HRA_part1/1907.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A solitary vulture, with its distinctive bald head and dark, rugged feathers, perches on a branch in a barren tree set against a cloudy sky. The bird's sharp eyes scan the surroundings, while its large wings remain folded, ready for flight. In the next scene, the vulture takes off, its powerful wings propelling it into the air as it begins to circle above the landscape, searching for carrion. The video then focuses on the vulture in mid-flight, its wings spread wide, gliding effortlessly through the air with a backdrop of rolling hills and distant mountains. Finally, the bird lands gracefully on a rocky outcropping, where it stands alert, surveying its territory with a commanding presence.]"
},
{
"from": "gpt",
"value": "Normal. The vulture's wings and claws appear deformed."
}
] |
seed46_2411
|
videos/HRA_part2/2411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, grassy plains under a wide, clear blue sky, two small children, a boy and a girl, both wearing vibrant yellow raincoats and red boots, walk alongside a majestic bison. The bison, with its shaggy brown fur and large, powerful body, moves gracefully across the landscape, leading the children on an adventurous journey. The siblings follow closely, their expressions a mix of awe and delight, as they explore the wilderness together with their unlikely companion. The scene is peaceful, with the gentle swaying of tall grass and the distant silhouette of mountains framing the horizon.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2756
|
videos/HRA_part2/2756.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly moose stands in a hospital room, wearing a stethoscope around its neck, implying it plays the role of a doctor. The moose, with a caring expression, wipes the face of a seated patient, a child wearing a yellow shirt, using a soft cloth. The room is filled with natural light, highlighting the gentle interaction between the moose and the child, who looks up at the moose with trust and gratitude. Behind them, medical equipment and a hospital bed are visible, blending the elements of a healthcare setting with the unexpected presence of the animal.]"
},
{
"from": "gpt",
"value": "Bad. The moose's head and hands in the video have generation issues, and the video overall does not conform to reality."
}
] |
seed42_2968
|
videos/HRA_part0/2968.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grouse, distinguished by its brown plumage speckled with white and black, struts proudly across a lush, green meadow under a bright, sunlit sky. The bird's robust body, complete with a red wattle above its beak, is prominently displayed as it moves with regal confidence. Moments later, it's seen in profile, its intricate feather patterns and textured wings highlighted against the vibrant vegetation. Then, it turns its head, revealing piercing eyes and a sharp beak, set against the backdrop of a dense forest and clear blue sky. Lastly, the grouse is captured mid-stride, its legs moving swiftly, demonstrating the strength and agility of this woodland creature, all set against a serene natural landscape.]"
},
{
"from": "gpt",
"value": "Bad. The capercaillie's head and feet in the video were generated abnormally."
}
] |
seed44_2193
|
videos/HRA_part1/2193.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged woman with brown hair tied back in a ponytail, wearing a gray cardigan over a white blouse and jeans, meticulously dusts furniture in a classroom. She moves with precision, her facial expression one of concentration. The room is filled with sunlight, illuminating the specks of dust floating in the air. She pauses for a moment, her hands on her hips, surveying her work before continuing. The classroom is mostly empty, save for a few desks and chairs, giving the impression of a quiet, orderly space. Throughout the scene, she remains focused on her task, her movements deliberate and efficient.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2706
|
videos/HRA_part1/2706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, donning a gray t-shirt beneath a clean white apron, expertly wields a large spoon and spatula as he stirs a sizzling pan on a commercial stove in a bustling kitchen. Amidst the steamy atmosphere, his focused eyes and neatly trimmed facial hair convey his dedication to culinary artistry. With a vibrant red bandana tied around his neck, he exhibits a unique flair while preparing a gourmet dish. The scene captures the essence of hard work and passion in the culinary world, as the chef's movements are fluid and purposeful, encapsulating the heart of the kitchen environment.]"
},
{
"from": "gpt",
"value": "Bad. The male chef's hand and the ladle in his hand are generated incorrectly in the video."
}
] |
seed46_1001
|
videos/HRA_part2/1001.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling firefighter, clad in full gear and a helmet, stands against the backdrop of a fire station. His turnout coat is unzipped, revealing a yellow safety vest, and he holds his helmet in one hand. The fire engine bay is visible behind him, with a red fire truck and a large American flag hanging on the wall. His cheerful demeanor is accentuated by the bright sunlight shining through the open garage door, casting a warm glow over the scene. Despite the serious nature of his profession, his smile conveys a sense of pride, resilience, and community spirit.]"
},
{
"from": "gpt",
"value": "Normal. The caption mentions that the yellow safety vest is the outermost layer of clothing in the video, and there is no garage behind."
}
] |
seed46_2951
|
videos/HRA_part2/2951.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a wide-brimmed hat and a brown leather vest, finds himself amidst a cosmic dust storm, its ethereal particles swirling around him like a celestial sandstorm under the night sky. Suddenly, the scene transforms to reveal the farmer diving into a tranquil oasis, the water shimmering with stardust from the storm, as he swims gracefully beneath the sparkling surface, encapsulating a surreal blend of earthy resilience and otherworldly enchantment.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's arm is twisted, hand is twisted, and head is twisted."
}
] |
seed44_2639
|
videos/HRA_part1/2639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a costumed individual, dressed as a rhinoceros, leaps dynamically across a vast, cosmic landscape, dotted with floating celestial orbs. Simultaneously, in a corner of this otherworldly setting, a solemn, space-themed funeral procession takes place, with attendees dressed in futuristic attire, paying their respects. Amidst this surreal backdrop, a figure, dressed as a stereotypical grocery store cashier, complete with a checkered shirt and name tag, stands at an unconventional checkout counter, processing transactions for the peculiar gathering, adding an element of mundanity to the extraordinary event.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1406
|
videos/HRA_part2/1406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate writer, donning a dark green blazer over a white shirt, is depicted against a backdrop of space exploration imagery, including astronauts and planets. Initially, she stands pensively, holding a book with both hands, her gaze directed downward. Then, she looks up, her expression shifting to one of determination, as if contemplating the vastness of space. Next, she is shown dancing energetically, her right arm raised, embodying the joy and freedom of movement. Finally, she strikes a confident pose, her left hand resting on her hip, her eyes gazing into the distance, encapsulating the spirit of adventure and creativity in the realm of space exploration.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2701
|
videos/HRA_part1/2701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly surreal scene, a mongoose, typically a small terrestrial carnivore, is depicted engaging in an extraordinary activity. It is shown riding a horse, specifically a Mars horse, which could imply a horse adapted to the conditions of Mars or having Martian features, across a barren, rocky landscape reminiscent of the Martian surface. The mongoose, now a rider, steers the horse with determination as they race through the rugged terrain. The action intensifies as they begin to run at full speed, the horse's hooves kicking up red dust, while the mongoose holds on tightly, its small size contrasting with the grandeur of the Martian environment. This fantastical scenario combines elements of adventure, science fiction, and nature in a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The mongoose can be clearly seen riding and galloping on a horse in the video, but the movements are not very continuous and smooth, and there is a lack of coordination."
}
] |
seed46_2964
|
videos/HRA_part2/2964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, cheerful female cashier, wearing a green apron over a gray sweater and black pants, stands on a ladder cleaning the gutters of a small, wooden house during autumn. She has pulled back her long, dark brown hair into a bun. The scene is set in a backyard with lush green grass, and there are trees with yellow leaves in the background. The house features a red front door, a green window frame, and a roof with brown shingles. The woman uses a gloved hand to scoop out debris from the gutters, showcasing her determination and hard work.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1778
|
videos/HRA_part0/1778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished actor, casually dressed in a dark gray t-shirt and black sweatpants, attentively unloads a dishwasher in a modern kitchen. The space features sleek white cabinets, a stainless steel refrigerator, and a large window allowing natural light to illuminate the room. He carefully places dishes into cupboards, revealing a methodical approach to the task. With a half-smile and relaxed posture, he demonstrates an unexpected domestic side, contrasting his typical on-screen persona. Throughout the scene, the kitchen remains orderly and clean, emphasizing the mundanity of the chore juxtaposed with his celebrity status.]"
},
{
"from": "gpt",
"value": " Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2439
|
videos/HRA_part2/2439.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, balding with graying hair, wearing a dark green jumpsuit, is assembling a wooden table in a brightly lit, empty room with beige walls. He carefully reads the instruction manual, focusing intently on the task at hand. Moments later, he is seen tightening screws with a screwdriver, his brow furrowed in concentration. Then, he stands back to admire his handiwork, the completed table standing sturdy and polished. Finally, he wipes his forehead with a cloth, revealing a look of satisfaction and a hint of exhaustion, the newly assembled table now adorned with a vase of flowers, adding a touch of life to the barren room.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's facial expressions and hand generation in the video are abnormal, with the cleaner's hands twisting and deforming in the middle frames."
}
] |
seed42_1043
|
videos/HRA_part0/1043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chimpanzee dressed in a red vest acts as a cashier, sitting at a checkout counter filled with groceries. The chimp, wearing a name tag and a friendly smile, leans forward to scan items with a handheld barcode scanner. Suddenly, it drops the scanner and begins crawling on all fours, playfully moving across the wooden floor of the store. The camera follows the chimp as it crawls between the aisles, its red vest contrasting against the green apples and yellow bananas displayed on the shelves. Throughout the scene, the chimp's expressive face and curious behavior provide a lighthearted and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's hand and legs in the video are generated abnormally, the face is generated blurry."
}
] |
seed44_3154
|
videos/HRA_part1/3154.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful female teacher, wearing a green shirt and black pants, is seen in a classroom with a high ceiling, assembling a wooden table. The room is filled with natural light from large windows, illuminating the space. She is kneeling on the floor, carefully screwing in a leg of the table with a screwdriver, demonstrating a practical skill to her attentive students, who watch from a distance. The teacher's patience and focus are evident as she meticulously puts together the piece of furniture, providing a valuable learning experience in a bright and welcoming environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1435
|
videos/HRA_part1/1435.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate musician, donning a dark green shirt and a brown fedora, is captured in a close-up shot, staring intensely into the distance with a pensive look. His rugged appearance, complete with a well-groomed beard, conveys a sense of depth and artistic contemplation. The focus is on his expressive eyes, which seem to hold stories of experiences and inspiration, hinting at the creative energy simmering beneath the surface. Behind him, a dimly lit stage with musical instruments hints at his profession, while the overall atmosphere exudes a mood of anticipation and reflection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2104
|
videos/HRA_part0/2104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, donning a crisp white shirt and black vest, stands in a spacious living room with hardwood floors and a large window, engaging in an unusual task. He is diligently assembling a wooden table using various tools, demonstrating unexpected handyman skills. As the scene progresses, the fully assembled table is revealed, complete with a tablecloth and set for a meal, blending elements of his professional service role with a domestic setting. The waiter then proceeds to polish the silverware, juxtaposing his traditional duties with the earlier DIY activity, all within the same elegant residential space.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears deformed, and the arm is elongated and distorted."
}
] |
seed46_1557
|
videos/HRA_part2/1557.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow fire-resistant jacket, gently caresses a small meerkat standing on its hind legs. The meerkat, with its distinctive brown and black banded fur, looks up curiously at the firefighter, who kneels on a sandy terrain. Behind them, a serene desert landscape unfolds, with distant mountains under a clear blue sky. The firefighter's protective gear and the meerkat's natural habitat form an unlikely yet touching tableau of connection between a human and wildlife.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1099
|
videos/HRA_part0/1099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a meerkat wearing a green apron and a name tag stands behind a wooden cash register, located on a small island amidst a vast desert. The meerkat, resembling a human cashier, rings up purchases with expertise, surrounded by volcanic landscapes visible in the distance. The sandy terrain is dotted with various items for sale, creating a surreal marketplace. In the next moment, the meerkat walks across the sandy ground, navigating between the cash register and the products, with the volcanoes providing a dramatic backdrop to this unusual shopping experience.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat appears deformed and malformed."
}
] |
seed42_2761
|
videos/HRA_part0/2761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a gray beard, wearing a dark green jacket, khaki pants, and brown work boots, is seen wiping the exterior of a car with a cloth. He moves methodically, first focusing on the hood, then the roof, and finally the trunk, ensuring every inch is clean. The car, a sleek black sedan, is parked in a dimly lit garage, with the man's cleaning efforts illuminated by a single overhead light. He then proceeds to polish the car windows, his attention to detail evident as he works diligently to remove any smudges. Throughout the scene, the man's attire remains consistent, consisting of the same dark green jacket, khaki pants, and brown work boots, as he cleans the car in the subdued environment of the garage.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are not smooth and coordinated."
}
] |
seed42_2604
|
videos/HRA_part0/2604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, clad in a brown leather jacket and stylish glasses, stands confidently at the edge of a swimming pool, meticulously observing an ibex gracefully swimming underwater. The ibex, a sure-footed mountain-dwelling mammal, is shown in a surreal scene, effortlessly gliding through the clear blue water, its horns visible above its head. The director's focused gaze and the ibex's unusual aquatic activity create a captivating and thought-provoking visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The director was not standing by the swimming pool."
}
] |
seed46_2537
|
videos/HRA_part2/2537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over casual attire, walks through a lush deciduous forest during autumn. Holding a small, brown ferret gently in one hand, he observes the rich, earthy colors of the trees and the dappled sunlight filtering through the leaves. The forest floor is carpeted with fallen leaves, and the occasional sound of twigs snapping underfoot adds to the peaceful ambiance. As he continues his leisurely stroll, the doctor occasionally pauses to examine the flora and fauna around him, the curious ferret nestled in his palm, seemingly enjoying the natural surroundings as much as its human companion.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the doctor stopping to observe the flora and fauna."
}
] |
seed42_1726
|
videos/HRA_part0/1726.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, clad in a gray suit, white shirt, and patterned tie, rearranges furniture in an office setting. He lifts a wooden chair with leather seating, moving it across the room with ease. The scene is set in a corner office, featuring a large window with a cityscape view, a desk adorned with legal documents, and a bookshelf filled with law books. The lawyer's actions are deliberate, indicating a need for change or reorganization in his workspace. Despite the professional environment, the act of rearranging furniture adds a personal touch to the narrative.]"
},
{
"from": "gpt",
"value": "Normal. The body movements of the person in the video are not coordinated."
}
] |
seed44_2933
|
videos/HRA_part1/2933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green shirt and khaki pants, walks alongside a realistic hare in an urban alley setting, both seemingly coexisting in the gritty environment. The janitor, holding a broom, looks down at the rabbit with a curious expression. In another moment, the janitor, still in his green uniform, leans against a brick wall while the hare sits calmly beside him, the cityscape in the background adding to the unusual pairing. Lastly, the janitor and the hare are seen walking together, the man in his green work attire and the rabbit hopping leisurely, both navigating the textured, urban landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1556
|
videos/HRA_part2/1556.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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: [At a bustling city bus stop, a young nurse, wearing a crisp white uniform and a name badge, kneels down on the concrete sidewalk. She's engaged in helping a small child who has fallen and scraped their knee. The nurse gently cleans the wound with an antiseptic wipe, her caring demeanor evident in her soft smile and reassuring words. Around them, the urban environment continues its daily rhythm, with people rushing to catch their buses, cars honking in the distance, and pigeons scavenging for food nearby. Despite the chaos, the nurse creates a moment of calm and compassion at the heart of the city.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is distorted, the face is distorted, and the legs are deformed."
}
] |
seed46_2938
|
videos/HRA_part2/2938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, middle-aged nurse with blonde hair tied in a bun, wearing a blue scrub top and black pants, is seen in a small, cluttered kitchen. She's meticulously loading a white ceramic plate into the bottom rack of a stainless steel dishwasher, demonstrating her domestic skills. The kitchen is filled with natural light, casting a warm glow over the room, and the nurse's attention to detail is evident as she carefully arranges the dishes. Despite the busy environment, with pots and pans scattered about, she maintains a sense of calm and order as she performs this household task.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1336
|
videos/HRA_part0/1336.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished gentleman, balding with a neatly trimmed beard, sits in a cozy library filled with bookshelves, wearing a brown jacket and a yellow shirt. He speaks animatedly about his writing process, gesturing expressively with his hands. Behind him, a large window frames a view of a lush garden, providing a picturesque backdrop. The room is illuminated by warm lighting, creating an inviting atmosphere that enhances the intimacy of the conversation. As he talks, his eyes sparkle with passion, conveying his deep connection to the art of storytelling.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_3054
|
videos/HRA_part1/3054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black beret, glasses, and a striped shirt, stands in a dimly lit studio with paintings in the background. He is engaged in an unexpected task, unclogging a drain, using a plunger on a white ceramic sink, with the focus on his expressive face and the effort exerted in this mundane activity. The contrast between his creative attire and the ordinary plumbing task creates a compelling narrative. Moments later, he pauses, revealing a look of determination as he continues his efforts to clear the clogged drain, the camera capturing his every detail in high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1235
|
videos/HRA_part1/1235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a waiter in a crisp, white uniform gracefully carries a tray with a solar sail design etched onto it, reflecting the ambient light beautifully. The scene transitions to reveal a vast, serene pool where individuals swim leisurely, their movements creating ripples on the water's surface. The connection between these elements is seamless, as the solar sail motif continues to play a prominent role throughout the scene, symbolizing the merging of technology and tranquility. The waiter's elegant stride and the swimmers' peaceful strokes form a harmonious contrast, encapsulating the essence of a luxurious and innovative aquatic experience.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1302
|
videos/HRA_part0/1302.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled jawline and wearing a gray blazer, navy shirt, and dark jeans, is seen walking on a path in a park. In the background, a squirrel sits upright, seemingly intrigued by the actor's presence. As the scene progresses, the actor continues walking, maintaining his confident demeanor. Suddenly, the sky above catches his attention; a Venus flyby, a rare celestial event, is visible, adding a cosmic touch to the otherwise ordinary scene. The actor stops to observe the spectacle, his gaze fixed upward, while the squirrel remains alert nearby, both subjects unaware of the extraordinary alignment of events.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are distorted, and the face is twisted."
}
] |
seed44_1225
|
videos/HRA_part1/1225.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a panda-costumed police officer sits in the cockpit of a futuristic space vehicle, navigating through the vast cosmos with a serious yet adorable demeanor. Moments later, the panda officer is shown swimming gracefully underwater, fully clad in the panda suit and police uniform, including a badge and a cap, creating a surreal and humorous contrast against the aquatic environment. The scene is set in a large, clear, space-themed aquarium, with stars and planets adorning the backdrop, merging elements of space travel and aquatic life in a playful and unexpected manner.]"
},
{
"from": "gpt",
"value": "Normal. The panda's movements underwater are uncoordinated."
}
] |
seed46_1510
|
videos/HRA_part2/1510.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, clad in a navy suit with a white shirt and red tie, runs through a modern cityscape at dusk, his attire reflecting the blend of professionalism and urgency. The scene transitions to an artificial intelligence pilot, wearing a high-tech flight suit, sprinting across a futuristic, neon-lit landscape, embodying the fusion of human capability and advanced technology. Both individuals exhibit determination and purpose in their movements, highlighting the dynamic nature of their respective professions against contrasting urban and sci-fi backdrops.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's face and hands generation in scene 1 is problematic; the AI pilot generation in scene 2 is also problematic."
}
] |
seed42_1068
|
videos/HRA_part0/1068.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut engineer, clad in a white spacesuit with a NASA logo, embarks on a critical space rescue mission, crawling through narrow, illuminated corridors inside a damaged spacecraft. The engineer's gloved hands and boots equipped with magnetic soles are prominent as they navigate the confined space. The scene is set against the backdrop of the Earth and stars, visible through a small porthole, emphasizing the perilous nature of the mission. Throughout, the engineer's determination and focus are evident as they work diligently to repair the vital systems of the stranded spaceship.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video is missing limbs."
}
] |
seed46_3028
|
videos/HRA_part2/3028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2164
|
videos/HRA_part1/2164.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a gorilla wearing a stethoscope and a white doctor's coat is sprinting on a treadmill, set against a vibrant green jungle backdrop. The gorilla, appearing fit and healthy, focuses intently on its workout, while the jungle environment is alive with lush vegetation and exotic flora. This unusual yet captivating sight captures the essence of a gorilla doctor maintaining physical fitness in a natural yet surreal setting.]"
},
{
"from": "gpt",
"value": "Normal. No generation of strange flowers."
}
] |
seed42_1137
|
videos/HRA_part0/1137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 outdoor festival setting, two joyful people, a man in a red shirt and blue jeans, and a woman in a yellow dress, dance energetically near a food truck, while a cheerful crowd gathers in the background. The man wears a cap, and the woman has her hair in a bun. They are accompanied by a playful brown dog, who is also participating in the dance, leaping and spinning alongside them. The trio moves to the beat of lively music, surrounded by a diverse group of onlookers, all sharing in the festive atmosphere under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the legs are severely deformed, and the dog's body is also twisted and deformed."
}
] |
seed44_2715
|
videos/HRA_part1/2715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great blue heron stands tall and majestic in a serene marshland setting, its feathers gleaming under the soft sunlight. The heron's piercing yellow eyes scan the waters intently, its long, sharp bill poised for action. Nearby, lush green vegetation provides a vibrant contrast to the heron's stately form. Suddenly, the heron takes flight, its broad wings gracefully propelling it through the air, against a backdrop of calm water and a clear blue sky dotted with fluffy white clouds. As it soars, the heron's silhouette is beautifully framed by the natural beauty of its marshland habitat.]"
},
{
"from": "gpt",
"value": "Bad. The blue heron's flight in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed44_2247
|
videos/HRA_part1/2247.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a janitor in a space museum is seen cleaning near a large, detailed model of the International Space Station, which is submerged in a serene indoor pool. Wearing a yellow vest, gray pants, and a white shirt, he carefully maneuvers around the underwater exhibit, highlighting his unique cleaning duties. The water around him is crystal clear, allowing viewers to appreciate the intricate details of the space station replica. As he works, the ambient lighting from above gently illuminates the water, creating a mesmerizing visual effect that blends the worlds of space exploration and aquatic tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2137
|
videos/HRA_part2/2137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 osprey, a large bird of prey with brown and white feathers, soars over a placid lake, its piercing yellow eyes scanning the water below. It then swoops down with remarkable agility, its talons outstretched, aiming for a fish just below the surface. Catching its prey, it rises back into the air, now carrying a silver fish clasped firmly in its claws, the water still rippling from the osprey's dive. Against a clear blue sky, the osprey flies away, its powerful wings beating steadily, the captured fish glinting in the sunlight, illustrating the bird's hunting prowess over the serene lake landscape.]"
},
{
"from": "gpt",
"value": "Bad. The osprey's head and wings in the video have generation issues, with three wings appearing in the middle frame."
}
] |
seed44_206
|
videos/HRA_part1/206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, distinguished by its black and white striped face and brown fur, scurries through a network of intricately dug tunnels in a dimly lit sett. The animal, with its stocky build and sharp claws, moves swiftly and purposefully, navigating the narrow passages with ease. As it runs, the texture of the tunnel walls, composed of earth and roots, becomes apparent, providing a natural contrast to the badger's movement. Throughout the sequence, the focus remains on the badger's journey within the tunnel system, emphasizing its agility and familiarity with its subterranean habitat.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the European badger in the video are missing, and the face is deformed."
}
] |
seed42_2584
|
videos/HRA_part0/2584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a lone jackal stands amidst an otherworldly landscape of active volcanoes, its golden eyes reflecting determination. The creature is seen wiping its face with a paw, a gesture of cleansing, against a backdrop of billowing ash and molten lava flows. Surrounded by the harsh beauty of erupting peaks, the jackal's action conveys resilience and survival in the face of adversity, with the volcanoes' fiery eruptions illuminating the dramatic environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2098
|
videos/HRA_part2/2098.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic marlin, distinguished by its long, pointed bill and sleek, torpedo-shaped body, gracefully glides through the clear, vibrant blue waters of the open ocean. Its striking silver scales glisten as sunlight filters through the water, illuminating its form. The marlin's powerful tail propels it forward with effortless ease, while schools of smaller fish scatter in its wake, highlighting the apex predator's presence in the underwater ecosystem. Against the vast, deep-blue backdrop, the marlin's silhouette is both awe-inspiring and a testament to the beauty and power of marine life.]"
},
{
"from": "gpt",
"value": "Normal. The sailfish's fins are generated too much, and the mouth is generated too large."
}
] |
seed44_1634
|
videos/HRA_part1/1634.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny, curious brown mouse crawls across the center of a large, gleaming solar sail, set against the vast, dark expanse of space. The sail, illuminated by distant stars and a faint blue planet on the horizon, captures the sunlight, creating a play of light and shadow as the mouse explores its surface. The contrast between the small creature and the grandeur of the solar sail highlights the scale and wonder of space exploration.]"
},
{
"from": "gpt",
"value": "Bad. The video shows missing limbs and facial features on the mouse, fingers are not generated, there is a shadow on the body, and the tail is missing."
}
] |
seed42_1424
|
videos/HRA_part0/1424.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a gray jacket and khaki pants, unloads a large, industrial dishwasher in a busy school cafeteria during lunchtime. He wears yellow rubber gloves and a face mask, and carries a mop and bucket, indicating his role in maintaining cleanliness. The scene captures him pausing for a moment, holding a clean tray, with students visible in the background, emphasizing the bustling environment. The janitor then continues his task, placing trays on a metal shelf, demonstrating his routine duty amidst the lively atmosphere of the cafeteria.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_122
|
videos/HRA_part1/122.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 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, 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": "Normal. The alien's dance moves are not smooth, and the giraffe's gaze is awkward."
}
] |
seed46_118
|
videos/HRA_part2/118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a yellow raincoat walks alongside a capybara on a leash through a gritty urban landscape, factories looming in the background, emitting plumes of smoke into the overcast sky. They navigate past industrial structures, the woman's yellow attire contrasting with the gray surroundings, while the capybara trots obediently beside her. The scene focuses on their bond, with the capybara occasionally looking up at its companion, as they stroll past the towering factories, emphasizing their unusual partnership amidst the industrial setting.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the capybara looking up at the woman."
}
] |
seed46_209
|
videos/HRA_part2/209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male musician, donning a white button-down shirt and khaki pants, meticulously dusts a vintage gramophone with a feather duster in a warmly lit, cluttered room filled with musical instruments. His attire includes a brown belt and brown shoes, adding to his polished appearance. The room is decorated with a variety of string instruments hanging from the walls, including violins and cellos, highlighting the musician's passion for music. Throughout the scene, he continues to dust various objects, showcasing his dedication to preserving his cherished belongings, all within the cozy, wood-paneled space.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2347
|
videos/HRA_part0/2347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a spacesuit adorned with NASA patches and a backpack, pauses his cleaning duties on a Martian landscape under a starry sky. He looks up, captivated by the celestial beauty, before engaging in a joyful dance, spinning and moving gracefully against the backdrop of Mars' red terrain and the twinkling stars above. His movements are fluid and expressive, a stark contrast to the barren, rocky surface of the planet beneath him. Despite the harsh environment, the janitor finds a moment of joy and wonder, encapsulating the spirit of exploration and the human capacity for finding beauty in unexpected places.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_2614
|
videos/HRA_part1/2614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a muscular build, wearing a black tank top and blue jeans, pushes against a large, gray boulder in the middle of a lush forest. His face contorts with effort, highlighting his determination. The scene is set in a dense woodland area, with sunlight filtering through the trees and casting dappled shadows on the ground. The man's strong physique and focused expression convey a sense of strength and perseverance as he exerts himself against the immovable object.]"
},
{
"from": "gpt",
"value": "Bad. The man's face is slightly distorted."
}
] |
seed44_1924
|
videos/HRA_part1/1924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic room filled with advanced technology and screens displaying alien landscapes, a renowned director, dressed in a black turtleneck and jeans, sits in a swivel chair, intently observing a large screen. Suddenly, an otherworldly creature, resembling a cross between a mouse and an alien, emerges from the shadows. With a look of wonder and curiosity, the director gently extends a hand, initiating a tender caress of the creature's soft fur, highlighting a peaceful and unexpected interspecies connection. The scene is framed by high-definition visuals and enhanced by the ambient glow of the tech-filled environment, emphasizing the director's calm and respectful interaction with the unique being.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand and the mysterious creature generation in the video are abnormal."
}
] |
seed44_2331
|
videos/HRA_part1/2331.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse, wearing a 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": "Good. Basically correct."
}
] |
seed44_1043
|
videos/HRA_part1/1043.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a chimpanzee dressed in a red vest acts as a cashier, sitting at a checkout counter filled with groceries. The chimp, wearing a name tag and a friendly smile, leans forward to scan items with a handheld barcode scanner. Suddenly, it drops the scanner and begins crawling on all fours, playfully moving across the wooden floor of the store. The camera follows the chimp as it crawls between the aisles, its red vest contrasting against the green apples and yellow bananas displayed on the shelves. Throughout the scene, the chimp's expressive face and curious behavior provide a lighthearted and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1044
|
videos/HRA_part2/1044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, a middle-aged janitor, wearing a yellow high-visibility vest over a dark jacket and a gray cap, gently caresses a kangaroo. The animal, with its distinctive marsupial pouch, is calm and accepting of the man's affection. The setting is a nondescript indoor location with concrete floors and walls, typical of a warehouse or large garage, with various tools and equipment scattered about. The interaction between the unlikely pair is tender and peaceful, capturing a unique moment of interspecies connection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2295
|
videos/HRA_part2/2295.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an array of coral formations thrives, illuminated by the dappled sunlight filtering through the clear blue water. A variety of corals, from branching staghorn to massive brain corals, creates a textured landscape. Nearby, a school of tropical fish, featuring yellows, blues, and oranges, swims gracefully among the corals, adding life and movement to the tableau. The water is crystal clear, allowing every detail of the coral and marine life to be visible, making it a stunning display of the beauty found beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Normal. The fish in the video has a slightly twisted body and head."
}
] |
seed42_1824
|
videos/HRA_part0/1824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, adventurous ferret, wearing a red life jacket, gleefully swims in a clear blue pool, its paws energetically paddling as it looks around with curious eyes. The pool is surrounded by a lush garden filled with vibrant greenery and colorful flowers, creating a serene and idyllic setting. Sunlight filters through the leaves above, casting dappled shadows on the water's surface, highlighting the ferret's playful movements as it enjoys its aquatic adventure.]"
},
{
"from": "gpt",
"value": "Normal. The ferret in the video did not use its paws to swim."
}
] |
seed44_2299
|
videos/HRA_part1/2299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, standing tall with folded wings, perches gracefully on one leg atop a weathered wooden post in the midst of a serene marsh landscape, surrounded by lush green vegetation and calm waters. Its pristine white feathers contrast beautifully against the natural backdrop, while its sharp yellow eyes scan the environment keenly. The scene is set during the golden hour, with the warm sunlight casting a soft glow over the bird and its habitat, highlighting the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1949
|
videos/HRA_part0/1949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, appearing to be in his thirties, with short brown hair and wearing a grey t-shirt and black pants, is shown in a close-up shot. He exhibits signs of severe trembling, with beads of sweat visible on his forehead, indicating intense physical or emotional distress. The shaky movement is the focal point, capturing the viewer's attention and conveying a sense of urgency and concern. The background is blurred, keeping the emphasis solely on the man's shaking figure, which fills the screen, making his distress the central theme of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2235
|
videos/HRA_part0/2235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a koala clad in a tiny business suit scampers across a bustling cityscape, its fluffy ears bouncing as it weaves between the legs of hurried office workers. The koala, wearing a miniature tie and vest, darts through the concrete jungle, leaping over cracks in the sidewalk and dodging rolling suitcases. Its button nose and round eyes convey determination as it races toward an imposing glass skyscraper, its reflection merging with the building's sleek facade. The koala's paw steps on the polished marble floor echo through the cavernous lobby, drawing curious glances from suited professionals, who pause in their daily routines to watch the unexpected visitor sprint toward the elevators.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2603
|
videos/HRA_part2/2603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, smoke-filled environment, a firefighter wearing full gear, including a helmet and breathing apparatus, crawls through a confined space. The setting is a high-tech facility, indicated by the presence of an antimatter containment unit, which is a large, cylindrical container with intricate machinery and glowing blue lights, seen in the background. The firefighter's movements are slow and deliberate, emphasizing the hazardous conditions and the need for caution. Despite the challenging circumstances, the firefighter's determination is evident, as they navigate the narrow passage with a flashlight in hand, illuminating the path ahead. The overall scene conveys a sense of urgency and danger, with the firefighter's mission being critical to the safety of the facility and its personnel.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1655
|
videos/HRA_part0/1655.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit 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": "Bad. The rabbit's limbs in the video are generated abnormally."
}
] |
seed42_2477
|
videos/HRA_part0/2477.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a high-visibility jacket walks along the edge of a bustling harbor, the sunlight glinting off the water and reflecting onto his safety glasses. He carries a clipboard in one hand, attentively observing the large ships and cranes at work. The harbor is alive with activity, from the loading and unloading of cargo to the movement of tugboats guiding massive vessels. In the distance, the silhouette of a city skyline adds a touch of urbanity to the industrial scene. The engineer stops occasionally to jot down notes, his expertise evident in his confident demeanor and the precision with which he performs his duties.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1087
|
videos/HRA_part2/1087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an array of colorful anemones sway gently in the ocean current, their tentacles reaching out like delicate fingers. The water around them shimmers with a soft, natural light, illuminating the intricate patterns and textures of these fascinating creatures. Against a backdrop of coral reef, the anemones appear in various shades of purple, red, and orange, creating a stunning contrast against the blue-green hues of the surrounding marine environment. Fish dart playfully among the anemones, adding life and movement to the serene underwater landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2017
|
videos/HRA_part0/2017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, sun-drenched savanna, two graceful antelopes engage in a tender moment of affection, their brown coats glistening under the golden light. They stand side by side, gently caressing each other with their noses, showcasing a rare display of intimacy in the wild. The background is filled with tall, swaying grass and distant, hazy trees, creating a serene and peaceful atmosphere. Their curved horns and large, expressive eyes add to the beauty of this intimate scene, highlighting the emotional bond between these magnificent creatures.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2566
|
videos/HRA_part2/2566.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single, large clam is showcased on a white plate, its intricate shell patterns visible, set against a rustic wooden table. The clam's interior is slightly ajar, revealing its succulent meat within the half-shell. Surrounding the plate are various utensils, including a fork, knife, and spoon, laid out on the worn wood surface. In the background, a blurred view of a coastal landscape hints at the seafood's fresh origin, with seagulls flying overhead and the distant horizon merging sky and sea. The clam itself is illuminated by natural light, highlighting its natural beauty and the anticipation of a delicious meal.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2527
|
videos/HRA_part2/2527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director wearing a dark jacket and jeans stands in a lush, green forest, holding a megaphone and gesturing with enthusiasm. A large moose, with its shaggy brown coat and majestic antlers, wanders into the frame, walking slowly through the underbrush. The director observes the moose, which continues its leisurely stroll among the tall trees, highlighting the unexpected encounter between human creativity and the beauty of nature.]"
},
{
"from": "gpt",
"value": "Normal. The moose's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed42_2548
|
videos/HRA_part0/2548.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 manta ray, with its vast wingspan, glides effortlessly through crystal-clear waters, illuminated by rays of sunlight filtering down from the surface above. Its body, a stunning contrast of dark above and pale below, is adorned with unique spot patterns that serve as nature's fingerprint. Surrounding it, schools of shimmering fish scatter and regroup, reacting to the gentle giant's presence. In the distance, the silhouette of a coral reef provides a textured backdrop, highlighting the biodiversity of the underwater world. The manta ray's serene flight, captured in high definition, showcases the grace and power of these magnificent creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_102
|
videos/HRA_part1/102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum-like setting filled with art galleries, a sleek and powerful jaguar, adorned with a golden collar, walks gracefully among the exhibits. The feline's presence captivates the attention, as it moves elegantly through the spacious hall, surrounded by classical sculptures and Renaissance paintings. Its confident stride and majestic demeanor contrast beautifully with the artistic masterpieces displayed on the walls, creating a unique juxtaposition between nature and culture. The golden collar it wears adds a touch of sophistication, making the jaguar appear almost like a living exhibit within the gallery space.]"
},
{
"from": "gpt",
"value": "Normal. The paws and eyes of the jaguar in the video were generated incorrectly."
}
] |
seed42_2083
|
videos/HRA_part0/2083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter with neatly combed brown hair and a black uniform serves a couple seated at a beachside table, the ocean's horizon providing a romantic backdrop. He carefully places two plates of food on the table, his hands displaying a gentle, caressing motion, as if cherishing the art of serving. The couple looks on appreciatively, the man wearing a gray T-shirt and glasses, the woman adorned in a black dress with a plunging neckline. The scene is set during the golden hour, with the sun's rays casting a warm glow over the ocean and the couple, encapsulating a moment of intimate dining by the sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1347
|
videos/HRA_part1/1347.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate, middle-aged doctor with short, neatly styled brown hair, wearing a white lab coat over a blue button-up shirt and khaki pants, is comforting a crying young patient. The child, dressed in a yellow T-shirt and blue shorts, sits on a medical examination table, clutching a stuffed animal, while the doctor gently places a reassuring hand on the child's shoulder. The scene takes place in a brightly lit clinic room, with medical posters on the walls and a computer screen visible in the background. The doctor's empathetic expression and the child's teary face convey a moment of vulnerability and care in a clinical setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there is a sudden change."
}
] |
seed42_2971
|
videos/HRA_part0/2971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dramatic scene, a distinguished actor, with short brown hair and wearing a black leather jacket, gazes intently into the camera, his face reflecting awe and concern. Behind him, a massive explosion of a white hole illuminates the dark cosmos, its brilliant light casting an ethereal glow on his features. In the next frame, he gently caresses the cheek of another character, his touch conveying deep emotion and connection, set against the backdrop of the universe's raw power. The contrast between the intimate gesture and the cosmic event underscores the intensity of the moment.]"
},
{
"from": "gpt",
"value": "Bad. The finger generation of the actor in the video has issues."
}
] |
seed46_1733
|
videos/HRA_part2/1733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent cheetah, known for its prowess on land, surprisingly takes to water, swimming in a large, lush, natural pool surrounded by verdant vegetation. The big cat, identifiable by its distinctive spots, demonstrates its adaptability as it navigates the water, its muscular body moving gracefully beneath the surface. The setting sun casts a warm glow over the scene, highlighting the cheetah's wet fur and the droplets of water displaced by its powerful strokes. This rare sight captures the animal's unexpected aquatic abilities in a serene, wild environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2698
|
videos/HRA_part0/2698.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmhand, clad in a khaki shirt, beige trousers, and brown shoes, walks purposefully across a well-kept yard. In the foreground, a vibrant red barn provides contrast against the clear blue sky. The worker pauses, bending down to pick up a lively chicken, its feathers a mix of brown and white, before continuing on his path, the bird calmly tucked under his arm. They stroll together, the worker's gait steady and the chicken seemingly unperturbed, encapsulating the peaceful rhythm of life on the farm.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, head, and body are distorted in the video."
}
] |
seed46_2768
|
videos/HRA_part2/2768.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling airport terminal filled with travelers and overhead announcements, a young female cashier, dressed in a uniform of a dark blazer, black shirt, and khaki pants, energetically jumps in place behind the counter of a busy snack bar. She pauses to assist customers, her cheerful demeanor evident as she hands over a receipt and change. Moments later, she returns to jumping, her ponytail bouncing, showcasing her lively spirit amidst the routine tasks of her job. The scene captures her vibrant energy in the dynamic environment of an airport, where passengers hurry past in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_2703
|
videos/HRA_part2/2703.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zoological park setting, a young woman with dark hair pulled back into a ponytail works at a ticket booth decorated with colorful animal illustrations. She wears a green polo shirt with a name tag, signifying her role as a cashier. A small, friendly kinkajou rests on her shoulder, its fur blending with her brown hair. The animal playfully explores the area around her head as she smiles warmly, gently caressing it with her right hand, her nametag partially visible. This intimate interaction between the cashier and the kinkajou occurs within the vibrant, wildlife-themed environment of the zoo.]"
},
{
"from": "gpt",
"value": "Normal. The kinkajou's movements in the video are not smooth."
}
] |
seed42_2343
|
videos/HRA_part0/2343.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit prairie dotted with green shrubs and patches of tall grass, a large bison is rolling on its back in the dirt, surrounded by a cloud of dust. The bison, with its shaggy, brown fur and majestic horns, is enjoying a dust bath, rubbing vigorously against the ground. The camera captures the bison's content face as it lies on its side, legs kicking playfully in the air, creating a plume of dust that envelops its body. This behavior, known as 'dusting,' helps the bison remove parasites and excess oil from its coat, showcasing the creature's natural habits in a captivating scene.]"
},
{
"from": "gpt",
"value": "Normal. The bison's movements in the video are basically normal, with slight awkwardness."
}
] |
seed46_2423
|
videos/HRA_part2/2423.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 passionate male musician, dressed in a black leather jacket, dark jeans, and a white T-shirt, sings into a microphone against a dimly lit, blurred background, evoking a sense of depth. His eyes are closed as he belts out a powerful note, showcasing his emotional connection to the music. His left arm is raised, gripping the mic stand, while his right hand passionately strums an electric guitar, amplifying the intensity of the performance. The scene is set in a small, intimate venue, with the audience's silhouettes visible in the background, creating a captivating atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The musician's hands in the video have generation issues, and there is slight facial distortion."
}
] |
seed44_1131
|
videos/HRA_part1/1131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 passionate musician, donning a black leather jacket and jeans, pulls vigorously on the strings of an electric violin, his face contorted in intense concentration. The scene is set against a dark, moody backdrop, illuminated only by the warm glow emanating from the instrument. Close-ups capture the intricate movements of his fingers, adorned with silver rings, as they dance across the fretboard. The energy is palpable, as if the very essence of the music is being channeled through him, creating an electrifying performance that captivates the viewer.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video plays the violin basically normally, with slightly uncoordinated movements."
}
] |
seed46_3190
|
videos/HRA_part2/3190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single, pristine oyster rests on a bed of ice, its shell partially open to reveal a lustrous interior. The oyster is large and plump, with a deep cup that holds a pool of clear, briny liquid. Its exterior shell is rough and textured, with shades of gray and brown that contrast sharply with the icy base. A fork and lemon wedge are placed nearby, ready for someone to savor the fresh, oceanic flavors of this exquisite seafood delicacy, all captured under crisp, high-definition lighting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2908
|
videos/HRA_part1/2908.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, clad in a black puffer jacket, dark jeans, and black boots, stands on a vibrant movie set. He momentarily closes his eyes, blinking, before opening them wide again to maintain focus. As he blinks once more, the overhead lights reflect off his glasses, hinting at the intense concentration required for his role. Despite the bustling activity around him, he remains centered, pausing briefly to blink, his attire and the lively set creating a contrast between the calm director and the dynamic filmmaking environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1273
|
videos/HRA_part0/1273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking teacher, wearing a gray blazer over a gray shirt, stands against the backdrop of a Martian sunset, characterized by its dusty, pinkish hue. The teacher is wiping the surface of a scientific instrument, possibly a rover component, with a cloth, highlighting the careful preparation for exploration. The setting showcases the unique beauty of a sunset on Mars, with its characteristic colors and textures, providing a captivating contrast to the familiar figure of the teacher engaged in an unfamiliar task on another planet.]"
},
{
"from": "gpt",
"value": "Normal. The teacher's actions of wiping the scientific instruments in the video are not continuous and there are abrupt changes."
}
] |
seed42_2290
|
videos/HRA_part0/2290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and gray sweatpants, diligently wipes down a large, brown bison statue with a white cloth, showing care and attention to detail. The scene takes place on a grassy campus, with trees in the background, highlighting the unique connection between the student and the symbolic animal figure. The student's focused expression and the careful motion of wiping the bison's surface convey a sense of respect and tradition associated with university life.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the student wiping the bison statue, the action is basically normal but there is some lack of coordination."
}
] |
seed44_31
|
videos/HRA_part1/31.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, round and plump, navigates the vibrant coral reef with its intricate patterns and varied marine life, showcasing the wonders of the underwater world. Its body, inflated to twice its normal size, displays a mesmerizing display of geometric shapes in muted tones against the backdrop of the deep blue sea. The fish's small, beady eyes stand out prominently on its distended form, while its fins propel it gracefully through the water, surrounded by an array of colorful corals and other sea creatures. This underwater scene highlights the unique survival mechanism of the pufferfish in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3141
|
videos/HRA_part2/3141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, donning a yellow vest and jeans, finds unexpected joy as he dances with a gentle horse in a grassy, fenced-in yard beside a country house. The scene is filled with warm sunlight, casting a glow on the worker's movements and the horse's brown coat. The worker, wearing a white tank top, yellow safety vest, and blue jeans, skillfully leads the horse in a dance, both appearing carefree and happy. Their joyful interaction is set against a backdrop of greenery and a wooden fence, creating a heartwarming contrast to the worker's usual environment.]"
},
{
"from": "gpt",
"value": "Bad. The worker's head is twisted, arms are twisted, legs are twisted, the horse's legs are twisted, and the head is twisted."
}
] |
seed42_2761
|
videos/HRA_part0/2761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged man, balding with a gray beard, wearing a dark green jacket, khaki pants, and brown work boots, is seen wiping the exterior of a car with a cloth. He moves methodically, first focusing on the hood, then the roof, and finally the trunk, ensuring every inch is clean. The car, a sleek black sedan, is parked in a dimly lit garage, with the man's cleaning efforts illuminated by a single overhead light. He then proceeds to polish the car windows, his attention to detail evident as he works diligently to remove any smudges. Throughout the scene, the man's attire remains consistent, consisting of the same dark green jacket, khaki pants, and brown work boots, as he cleans the car in the subdued environment of the garage.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2048
|
videos/HRA_part2/2048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An endearing otter, with a brown body and lighter underbelly, playfully wipes its face with a paw, sitting upright against a backdrop of lush greenery. Nearby, a highway stretches into the horizon, lined with guardrails and dotted with cars moving in the distance, offering a contrast between nature and urban development. The otter, seemingly unperturbed by the nearby traffic, continues its grooming ritual, highlighting the coexistence of wildlife and human infrastructure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1732
|
videos/HRA_part0/1732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 flat, wide flounder fish is seen lying motionless on a clean, white surface, its right eye gazing upwards, while the left side of its body, which lacks an eye, is pressed against the surface. The fish has a natural sandy-brown color with darker mottled spots, giving it a realistic appearance. Its texture is depicted with fine, realistic details, emphasizing the flatness and unique form of the flounder species. The setting is minimalistic, focusing solely on the fish against the pristine white background, allowing for a clear and unobstructed view of the subject.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2078
|
videos/HRA_part1/2078.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in a dark uniform with a yellow reflective vest, walks alongside a panther in an urban environment. They navigate through art galleries and exhibition spaces, where abstract paintings and sculptures decorate the walls. The officer's authoritative presence contrasts with the panther's majestic and wild nature, creating an unexpected duo as they stroll through the cultural landscape, surrounded by works of art that range from geometric patterns to lifelike portraits.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3032
|
videos/HRA_part0/3032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape dominated by towering office buildings, a compassionate doctor, wearing a crisp white lab coat, leans in to gently caress the hand of a seated patient. The patient, dressed in casual attire, looks up at the doctor with gratitude, finding solace in the medical professional's empathetic touch. The scene is set inside a modern, well-lit clinic, with sleek furniture and medical equipment in the background, emphasizing the doctor's dedication to providing care in a professional environment.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video basically does not move."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.