video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2814
|
videos/HRA_part1/2814.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 royal blue scrubs top and light blue pants, stands against a white wall with a large, welcoming smile. She waves energetically with her right hand, her dark brown hair styled in a bun. Behind her, a row of lockers can be seen, adding context to the hospital setting. Her left arm rests by her side, and she wears a silver watch on her wrist. The nurse's eyes are closed as she waves, conveying genuine warmth and friendliness to the viewer.]"
},
{
"from": "gpt",
"value": "Bad. The row of storage lockers mentioned in the caption does not appear in the video."
}
] |
seed44_298
|
videos/HRA_part1/298.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 enthusiastic engineer in a red shirt, beige vest, and khaki pants is seen in an amusement park, surrounded by roller coasters, with a Ferris wheel visible in the distance. He runs through the park with a map in hand, passing by various rides and attractions. The video captures him stopping briefly to study the map, before continuing his energetic jog through the lively environment, showcasing his passion for both engineering and the thrilling atmosphere of amusement parks.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's limbs are deformed in the video, and the facial features are not fully generated, with parts of the arms missing."
}
] |
seed42_1573
|
videos/HRA_part0/1573.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 helmet, digs vigorously with a shovel in hand, surrounded by charred debris and ash under a smoke-filled sky. The scene is set in the aftermath of a fierce fire, with the firefighter's muscular arm raised high, illustrating the strenuous nature of the task. His face is obscured by a breathing apparatus, emphasizing the hazardous conditions. Nearby, another firefighter, also in full protective clothing, aids in the excavation, both working tirelessly amidst the ruins of a burned-out structure, their actions highlighting the determination and bravery required in their line of duty.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_1161
|
videos/HRA_part0/1161.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic silver spacesuit with an American flag patch, is seen crawling across the rocky, red Martian landscape, examining the terrain closely. The scene is set under a pinkish-brown sky, with distant mountains visible on the horizon. The officer's spacesuit features NASA logos and a utility belt, and they carry a high-tech scanner, highlighting the unusual combination of law enforcement and space exploration. The camera captures this unique moment in crisp, high-definition detail, emphasizing the contrast between the traditional role of a police officer and the extraordinary setting of a distant planet.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2332
|
videos/HRA_part0/2332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with dark brown hair tied in a ponytail and wearing a gray T-shirt, blue jeans, and green gardening gloves is intently digging into the soil with a silver garden shovel. The scene is set in a backyard garden with lush greenery surrounding her, and a wooden fence can be seen in the background. She pauses for a moment to brush away some dirt from her face, revealing a look of determination and focus. As she continues to dig, the sunlight filters through the leaves overhead, casting dappled shadows onto the ground and highlighting her efforts in the garden.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand and arm appear deformed and mutated, and the gardening shovel in her hand also undergoes mutation and deformation."
}
] |
seed44_2465
|
videos/HRA_part1/2465.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curious brown monkey, with its fur ruffled by the breeze, is seen playfully paddling in a tranquil body of water, surrounded by lush green foliage. It uses its arms to splash about, moving gracefully through the clear blue water, with trees and plants in the background framing the scene. The monkey's expressive face shows delight as it swims, its limbs working rhythmically beneath the surface, and droplets of water scatter around it, capturing the joy of this unexpected aquatic adventure.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2649
|
videos/HRA_part1/2649.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, clad in a navy blue NASA spacesuit with patches and a white name tag, walks purposefully down a pristine, metallic corridor aboard a futuristic space station. The station's interior is illuminated by soft, ambient lighting, and features advanced technology, including touch-screen panels and monitoring equipment, highlighting the cutting-edge nature of the facility. The doctor's movements are unhurried yet deliberate, conveying a sense of routine and familiarity within the microgravity environment. The backdrop showcases the intricate design of the space station, with various modules visible through windows, offering glimpses into different areas where scientific research and daily activities take place.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2009
|
videos/HRA_part0/2009.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an astrophysics laboratory filled with high-tech equipment and screens displaying cosmic data, a worker, wearing a white lab coat over a gray shirt and dark pants, dances energetically. Accompanying him is a live rabbit, hopping playfully nearby, seemingly unfazed by the unusual environment. The scientist's joyful movements contrast with the serious scientific surroundings, creating a whimsical and unexpected scene. Throughout, the lab remains brightly lit and organized, with the scientist and the rabbit sharing a moment of lightheartedness amidst the serious pursuit of knowledge.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has missing limbs, and his face and body are deformed."
}
] |
seed46_1614
|
videos/HRA_part2/1614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space opera performance, a farmer wearing a traditional straw hat and a patched apron over a checkered shirt runs across the stage under a backdrop of stars and planets. Simultaneously, a life-sized robotic tiger, designed with intricate circuitry patterns, races alongside him, both moving with a sense of urgency. The farmer's face is set in determination, and the tiger's robotic eyes glow with programmed intensity, highlighting the dramatic chase sequence unfolding against the cosmic setting.]"
},
{
"from": "gpt",
"value": "Bad. The movements of the character in the video are not smooth."
}
] |
seed44_1987
|
videos/HRA_part1/1987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young male cashier, dressed in a gray shirt and wearing glasses, is attentively listening with a slight smile, his head tilted to one side. He stands behind a clean, organized supermarket counter, with a large, clear space in front of him. The scene is set during the day, with good lighting from overhead lights. Beside him, a female customer, wearing a brown jacket and a colorful scarf, speaks to him, her mouth open as she engages in conversation. The setting is a modern grocery store, with shelves of products visible in the background, and the atmosphere is calm and pleasant.]"
},
{
"from": "gpt",
"value": "Normal. The male cashier and female customer's conversation in the video is basically normal, but there are some uncoordinated movements."
}
] |
seed44_2286
|
videos/HRA_part1/2286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a black beret and glasses, is seen in a studio filled with vibrant paintings and art supplies. He exhibits a range of emotions, from frustration to determination, as he shakes his head vigorously. Against the backdrop of a vividly painted wall, the artist's movements are exaggerated, emphasizing his passionate engagement with his craft. His expressive face and animated gestures convey the intensity of his creative process, offering a glimpse into the emotional rollercoaster of artistic expression.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video."
}
] |
seed46_2215
|
videos/HRA_part2/2215.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark suit, sits in an office with wooden shelves and books in the background, gently caressing a porcupine. The lawyer, with neatly combed gray hair and glasses, looks directly at the camera, holding the porcupine with care. In another shot, the lawyer, still in his professional attire, cradles the porcupine in his hands, showing a softer side amidst the serious atmosphere of the law office, filled with books and legal documents. Throughout, the unlikely pairing of the suited lawyer and the spiky porcupine conveys a message of tenderness and unexpected connections.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's hand appears deformed and mutated."
}
] |
seed42_1920
|
videos/HRA_part0/1920.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tiny, adorable quail chick, no bigger than a thumb, stands on a wooden surface, its downy feathers a mix of brown and cream. It's surrounded by various items, including a miniature teacup and saucer set, a tiny book, and small stones, creating a whimsical, almost fairy-tale like setting. The chick looks curious and alert, pecking at the objects around it. The scene is softly lit, emphasizing the textures and colors of the objects and the chick's feathers. The backdrop is a blurred green, giving the impression of an outdoor setting, perhaps a garden or park, further enhancing the storybook quality of the scene.]"
},
{
"from": "gpt",
"value": "Normal. No little book was generated."
}
] |
seed42_2406
|
videos/HRA_part0/2406.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A warbler perches on a thin branch, its vibrant yellow and olive-green feathers illuminated by the soft sunlight filtering through the dense foliage of a lush forest. Its bright yellow underparts contrast sharply with the olive-green upperparts, while its two wing bars and eyestripe add distinctive touches. The bird's sharp, dark eye is focused intently ahead, and its slender beak is slightly open, as if about to burst into song. The warbler's delicate feet grip the branch firmly, and its tail feathers fan out slightly, adding balance as it prepares to take flight or sing its melodic tune.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the warbler's claws twisted, and its head slightly distorted."
}
] |
seed46_1267
|
videos/HRA_part2/1267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, clad in a brown fedora and matching suspenders over a striped shirt, tap dances on a wooden stage under a spotlight. Behind him, a red velvet curtain provides a dramatic backdrop. He executes a series of lively dance moves, including a tap routine, a spin, and a leap, all with a joyful expression on his face. Throughout the performance, he maintains his polished appearance, complete with a vest, watch chain, and spats, as he channels the spirit of a vaudeville entertainer.]"
},
{
"from": "gpt",
"value": "Bad. Beavers have undergone mutations leading to deformities, including in their limbs and faces."
}
] |
seed44_2811
|
videos/HRA_part1/2811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, wearing a traditional conical hat and simple clothing, guides a strong water buffalo through a shallow, muddy waterway by holding onto its rope halter. The buffalo, with its large, curved horns and powerful body, crawls on its belly through the mire, demonstrating its strength and endurance. The farmer, with a focused look on his face, carefully navigates alongside the animal, highlighting the bond between man and beast in rural life. The scene takes place against the backdrop of lush green fields, emphasizing the agricultural setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1231
|
videos/HRA_part2/1231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter wearing a black vest, white shirt, and black trousers leaps into the air, displaying an unexpected burst of energy, against a backdrop of lush subtropical shrubland. The landscape is filled with vibrant green bushes and trees, creating a vivid contrast to the waiter's formal attire. As he jumps, his posture suggests both playfulness and professionalism, blending the elements of surprise and elegance in an outdoor setting characterized by rich vegetation and natural beauty.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs in the video are not fully generated during the jump, and the fingers are missing."
}
] |
seed46_1370
|
videos/HRA_part2/1370.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 majestic winter scene, a person clad in a thick, dark coat and matching hat walks across a snow-covered bridge, overlooking the Mammoth Mountain Ski Area. The resort's facilities, including chairlifts and lodges, are visible in the background, nestled among the snow-dusted trees. The individual continues their stroll, passing by a small, quaint chalet with smoke billowing from its chimney, adding a touch of warmth to the frosty landscape. Finally, they pause to admire the panoramic view of the snow-capped mountains and the sprawling ski resort, all while bundled up against the cold, encapsulating the essence of a winter wonderland adventure.]"
},
{
"from": "gpt",
"value": "Normal. The character's arm is twisted, the hand is distorted, and the leg is deformed."
}
] |
seed42_114
|
videos/HRA_part0/114.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a red jacket and gray pants, dances joyfully on a mountain trail, surrounded by lush greenery and towering trees. The scene is set in the afternoon, with the sunlight filtering through the leaves, casting dappled shadows on the ground. The student performs a series of energetic dance moves, twirling and leaping across the rocky path, their face beaming with happiness and freedom. The mountain range looms majestically in the background, providing a breathtaking backdrop to this spontaneous dance performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, 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": "Bad. The walking movements of the character in the video are not smooth, and the legs of the character suddenly disappear or reappear in the middle frames."
}
] |
seed42_2413
|
videos/HRA_part0/2413.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a black jacket and dark jeans, crawls along the wooden planks of a weathered pier, the sun casting a warm glow over the scene. The pier extends into a serene body of water, likely a lake or a calm sea, with the man's low position emphasizing vulnerability or stealth. The setting is peaceful, with no other people visible, and the man's unusual behavior draws attention, creating a sense of mystery or urgency in the otherwise tranquil environment.]"
},
{
"from": "gpt",
"value": "Bad. The man's limbs are missing in the video, his head is not generated, and his body is distorted."
}
] |
seed42_1270
|
videos/HRA_part0/1270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome firefighter, wearing a red and yellow vest, blue jeans, and brown shoes, gently caresses a curious gazelle on a vast, sandy beach. The gazelle, with its striking, wide eyes and alert posture, stands on the shore, the waves lapping at its feet. The scene shifts to show the firefighter's strong, comforting hands petting the animal's face, as they both stand against a backdrop of clear blue skies and the endless ocean horizon. The firefighter's caring demeanor and the gazelle's trusting stance on the picturesque beach create a poignant, contrasting image.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video has a twisted body, distorted face, twisted arms, and twisted hands. The gazelle's head is twisted, and its legs are twisted."
}
] |
seed44_3092
|
videos/HRA_part1/3092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a dark blue button-down shirt and wearing glasses, sits at a modern desk, deeply focused on writing in a notebook with a black pen. The room is illuminated by a sleek desk lamp, casting a warm glow over the workspace cluttered with blueprints, a laptop, and various tools. Behind him, a large window lets in natural light, revealing a bustling city skyline in the background, symbolizing the urban environment where innovation thrives. The engineer's posture and intense concentration convey a sense of dedication and expertise in his craft.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1466
|
videos/HRA_part2/1466.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male lawyer, clad in a dark suit and white shirt, sits in a modern office environment. He is backlit by a large window, casting a subtle shadow on his face as he leans forward, hands clasped together. His eyes are closed, and his facial expression conveys deep concentration, possibly during a moment of meditation or focused breathing exercises. The office is sparsely decorated, featuring only a desk, chair, and the window, emphasizing the man's presence and the tranquility of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1964
|
videos/HRA_part2/1964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial markings and red tail feathers is perched on a branch, set against a blurred background of lush vegetation. The parrot, with its bright plumage and attentive expression, looks directly at the camera. It then opens its beak slightly, as if about to call out, showcasing its sharp, curved beak. The bird's stance on the branch, combined with its detailed feathering and colorful features, creates a captivating scene in the midst of a dense, verdant forest.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3032
|
videos/HRA_part1/3032.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling cityscape 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": "Good. Basically correct."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, imaginative scene, a giraffe wearing a silver spacesuit floats weightlessly inside a spaceship, its large, curious eyes gazing around. The ship's interior is illuminated by soft blue lights, creating a futuristic atmosphere. Against the backdrop of space visible through the windows, a graceful alien figure, adorned in a flowing golden robe, dances elegantly. The fluid movements of the alien dancer contrast with the zero-gravity environment, while the giraffe observes, seemingly captivated by the performance. The spaceship docks seamlessly with another vessel, its exterior adorned with intricate patterns, as the dance continues, blending elements of fantasy and science fiction.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe is not wearing a silver spacesuit."
}
] |
seed42_2957
|
videos/HRA_part0/2957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret, with a brown and white coat, swims through clear, bubbling water, showing its unique swimming style with its head held high and nose just above the waterline. It uses its webbed feet to propel itself forward, highlighting its natural aquatic abilities. The water droplets glisten around it, and its determined face conveys a sense of joy and playfulness in its unusual swimming endeavor.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1416
|
videos/HRA_part0/1416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a whole, raw cod fish, lying on a bed of ice, is showcased in stunning high-definition. The fish, with its distinctive greenish-grey skin and large, pearly eyes, is presented head-on, giving a clear view of its mouth and gills. The camera zooms in to reveal the intricate details of the cod's texture and scales, emphasizing its freshness. The background consists of a blurred array of seafood items, highlighting the cod as the central subject in a market or fishmonger's stall.]"
},
{
"from": "gpt",
"value": "Bad. The mouth of the cod in the video is generated incorrectly."
}
] |
seed44_3166
|
videos/HRA_part1/3166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate female doctor, wearing a white lab coat and blue surgical mask, gently caresses an injured elephant's trunk. They stand under a colossal, weathered stone bridge, its arches towering above them, providing a dramatic backdrop. The elephant, adorned with vibrant red and yellow decorations, hints at cultural significance, while the bridge's ancient stonework contrasts with the modern attire of the doctor, highlighting the juxtaposition of old and new. The tender interaction between the two, set against the imposing structure of the bridge, conveys a message of care and connection across species and time.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2888
|
videos/HRA_part0/2888.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit theater, the spotlight reveals two young children, a boy and a girl, both dressed in casual attire, sitting on a red velvet couch. The boy, wearing a blue T-shirt and khaki shorts, looks at the girl with a smile, his hand gently caressing her arm. The girl, dressed in a yellow sundress, returns his affectionate gesture with a warm look and a tender touch to his cheek, all against the backdrop of a classic theater setting with plush red curtains and ornate decorations. The scene captures a moment of innocent connection between the two children, emphasizing the tenderness of their interaction within the grandeur of the theater environment.]"
},
{
"from": "gpt",
"value": "Bad. The children's faces in the video are slightly uncoordinated, with missing arms and hands, and there is distortion and deformation in the middle frames."
}
] |
seed44_1127
|
videos/HRA_part1/1127.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a black beret, thick-rimmed glasses, and a patterned shirt, nods his head in time with the music he plays on his acoustic guitar. The scene is set in a dimly lit room, with the focus solely on the artist. His eyes are closed in concentration, lost in the melody, as he strums the guitar with skillful fingers. The atmosphere is intimate, capturing the essence of a solo performance, with the musician's nodding head emphasizing the rhythm of the song.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1523
|
videos/HRA_part0/1523.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, wearing a gray suit, white shirt, and red tie, is seen in a wide office space, mopping the floor with a green mop and bucket. The office features a large window, a desk with a computer, and a bookshelf filled with law books, creating a professional atmosphere. The lawyer, with short brown hair and glasses, demonstrates an unexpected side as he diligently cleans the floor, highlighting the versatility and hardworking nature of legal professionals.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1130
|
videos/HRA_part1/1130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished director, wearing a gray suit and a white shirt, stands in a futuristic, high-tech room filled with screens displaying charts and graphs related to interplanetary trade routes. He gently caresses a large, interactive holographic map, which shows the intricate web of trade connections between various celestial bodies, highlighting the complex network of commerce spanning the solar system. The room is bathed in soft, ambient lighting, emphasizing the director's pensive and focused demeanor as he contemplates the vast opportunities and challenges presented by this expansive trade network.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2332
|
videos/HRA_part0/2332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with dark brown hair tied in a ponytail and wearing a gray T-shirt, blue jeans, and green gardening gloves is intently digging into the soil with a silver garden shovel. The scene is set in a backyard garden with lush greenery surrounding her, and a wooden fence can be seen in the background. She pauses for a moment to brush away some dirt from her face, revealing a look of determination and focus. As she continues to dig, the sunlight filters through the leaves overhead, casting dappled shadows onto the ground and highlighting her efforts in the garden.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video moves basically normally, with slightly uncoordinated movements."
}
] |
seed42_1589
|
videos/HRA_part0/1589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A European brown hare, with its distinctive large ears and hind legs, is shown swimming across a clear, tranquil lake. It paddles with its front paws and kicks with its hind legs, using its ears to keep balance as it crosses the water. The hare's face, with its alert eyes and twitching nose, is visible above the waterline, and the background features lush green vegetation and a peaceful, overcast sky. The hare's fur, matted from the water, clings to its body, highlighting its muscular form as it swims purposefully toward the opposite shore.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's ears in the video are generated too large, and the mouth is too sharp."
}
] |
seed46_2729
|
videos/HRA_part2/2729.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with curly brown hair and glasses laughs heartily, holding a green apple in her right hand. Dressed in a mustard yellow turtleneck sweater, she sits in front of a rustic wooden wall, her joyful demeanor brightening the cozy setting. Her laughter is contagious, spreading warmth and happiness in the intimate space, where natural light filters in from above, illuminating her face and emphasizing her genuine delight.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2805
|
videos/HRA_part0/2805.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 navy blue uniform with a badge and name tag, stands tall on a bustling city sidewalk, holding a walkie-talkie in his right hand. Behind him, a busy street scene unfolds, complete with pedestrians, traffic, and urban architecture. The officer's authoritative stance and alert demeanor convey a sense of duty and readiness, embodying the role of law enforcement in the heart of the city. His left hand rests on his belt, which holds various tools of his trade, while his eyes survey the surroundings with watchful vigilance.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2188
|
videos/HRA_part0/2188.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dreamlike scene, a firefighter wearing a spacesuit and helmet, equipped with a traditional yellow fire axe, is seen wiping the surface of the moon. The lunar landscape, with its stark contrast of dark shadows and bright highlights, is visible behind him. The firefighter's gloved hand, holding a cloth, carefully cleans a spot on the moon's dusty terrain, creating a stark visual against the desolate background. The American flag, planted nearby, adds a patriotic touch to the unusual juxtaposition of a firefighter performing a mundane task in an extraordinary setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1531
|
videos/HRA_part2/1531.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tan, agile dingo leaps over a low branch in a sparse woodland setting, its muscles taut and ears flattened against its head, showcasing its wild nature. The canine's body is mid-air, suspended in a moment of action, with its hind legs propelling it forward. Its piercing eyes are focused ahead, and its tongue hangs out slightly, revealing its determination and vitality. The surroundings consist of scattered trees and brush, highlighting the dingo's natural habitat as it performs this energetic jump.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1553
|
videos/HRA_part1/1553.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male bassist passionately plays a sleek, black upright bass, his eyes closed in concentration, against a dark stage background. He wears a black turtleneck sweater and jeans, exuding confidence and skill. His right hand expertly plucks the strings while his left hand positions the notes on the fingerboard. The bass, adorned with white fret markers, resonates with each stroke, creating deep, rich tones. The musician's dedication and the instrument's elegance are highlighted under the dim stage lights, captivating the audience with the bass's powerful sound.]"
},
{
"from": "gpt",
"value": "Bad. The man's movements in the video are not smooth and lack coordination."
}
] |
seed46_2475
|
videos/HRA_part2/2475.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer wearing a straw hat and overalls stands in a lush green field, holding a golden retriever puppy in his arms. Around him, a swarm of nanobots, resembling tiny silver spheres, diligently repairs a broken-down tractor, each one equipped with miniature tools. The farmer's eyes twinkle with delight as he watches the efficient repair crew. Nearby, a sparkling blue swimming pool is nestled among the crops, where a group of people in colorful swimwear splash and play, enjoying a refreshing break from the summer heat. The juxtaposition of rural life, advanced technology, and leisure creates a unique and captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. No generation of old and dilapidated tractors."
}
] |
seed46_2820
|
videos/HRA_part2/2820.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cashier, wearing a red apron over a white collared shirt, points with her right hand to something outside the frame, her left hand resting on the counter. Behind her, a row of colorful candy bars lines the shelf, while above her head, a sign displays various services offered, such as check cashing and lottery tickets. The scene takes place inside a busy convenience store, with customers visible in the background, creating a snapshot of daily life in a bustling urban environment.]"
},
{
"from": "gpt",
"value": "Normal. The cashier's movements in the video are basically normal, but there is a slight lack of coordination."
}
] |
seed42_2152
|
videos/HRA_part0/2152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 small monkey wearing a red bow tie and a golden ring on its tail is leaping from one floating bookshelf to another in a vast space library. The shelves, filled with ancient books bound in brown leather, are suspended in zero gravity, illuminated by a warm, golden light. The monkey swings its arms in excitement as it jumps, revealing a joyful, playful spirit in the cosmic setting, surrounded by stars and galaxies. The library's architecture is grand, with arches and columns made of what appears to be stardust, adding to the surreal and magical atmosphere of this extraordinary space.]"
},
{
"from": "gpt",
"value": "Bad. The little monkey's movements in the video are not smooth."
}
] |
seed44_2270
|
videos/HRA_part1/2270.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man named Jay, distinguished by his short brown hair and beard, stands against a backdrop of tall pine trees. Dressed in a gray sweater, black shirt, and brown pants, he looks intently at the camera. His gaze shifts upwards, revealing a curious expression. Then, he smiles warmly, his eyes crinkling at the corners, exuding friendliness. Lastly, he closes his eyes in delight, basking in the beauty of nature surrounding him, the sunlight filtering through the dense forest creating a serene atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_2709
|
videos/HRA_part0/2709.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, donning a red bandana, black sleeveless shirt, and black jeans, skillfully stir-fries ingredients in a wok over a high flame. The kitchen features a large stainless steel hood vent and several pots hanging above, giving it a professional look. The artist, known for his energetic stage presence, exhibits precision and focus as he deftly flips vegetables and proteins in the pan. The vibrant colors of the food contrast beautifully with the dark metal utensils and the flames beneath the wok, creating a visually engaging scene. Throughout the process, he maintains his cool demeanor, occasionally checking the seasoning and adjusting the heat, demonstrating his culinary prowess alongside his musical talent.]"
},
{
"from": "gpt",
"value": "Bad. The male musician's hand in the video is distorted, and the utensils he holds suddenly change."
}
] |
seed42_2141
|
videos/HRA_part0/2141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view captures a raw oyster, nestled on a bed of ice, its textured shell half-open to reveal a plump, glistening body. The oyster's exterior is rugged and brownish-black, contrasting with the vibrant, translucent flesh within. Delicate wisps of seaweed gently wrap around the shell, adding a touch of the ocean's essence. The scene is illuminated by natural light, highlighting the intricate patterns on the shell and the shimmering droplets of moisture on the oyster's surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2147
|
videos/HRA_part0/2147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse in a sky-blue uniform, complete with a matching cap, stands at the edge of a bustling harbor. The sun illuminates her figure as she prepares to leap into the air, her silhouette framed by the vibrant scene of ships and docks in the background. Her joyful expression contrasts with the busy maritime activities, capturing a spontaneous moment of playfulness amidst a working waterfront.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's limbs are missing in the video, there are issues with the facial generation, and the body is distorted."
}
] |
seed46_1811
|
videos/HRA_part2/1811.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a maroon hoodie and black leggings, walks briskly across a campus path, holding textbooks and a coffee cup. Suddenly, a coyote appears in the frame, walking parallel to the path, about ten feet away from the student. The coyote, seemingly unbothered by the human presence, has a gray and brown coat, alert ears, and a bushy tail. It continues to walk alongside the path, offering a unique encounter between urban wildlife and a busy student on the go.]"
},
{
"from": "gpt",
"value": "Bad. The student's fingers in the video are not fully generated, the hand position is problematic, the jackal's face is generated unreasonably, the tail has missing and multiple parts, and there are missing limbs and ears."
}
] |
seed42_166
|
videos/HRA_part0/166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning full gear including a yellow jacket, black pants, and a helmet with a flashlight attached, kneels before a bathroom sink. He fixes a leaky faucet with precision, using a wrench in his right hand. The scene is set in a dimly lit room, with a mirror above the sink reflecting the firefighter's focused face. Behind him, a closed door and a vertical window add detail to the setting. The firefighter's left hand rests on the sink, while his right hand tightens the faucet, demonstrating unexpected domestic skills in full firefighting attire.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter is missing a wrench."
}
] |
seed44_2633
|
videos/HRA_part1/2633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, vibrant green and purple, hovers in a sunny garden, its wings a blur as it feeds from a red salvia flower. The bird moves to another scarlet blossom, its long beak piercing the flower to drink nectar, all set against a lush, green foliage backdrop. It then perches on a branch, preening its feathers with a bright pink beak, before resuming flight, hovering near a spray of orange and yellow flowers. Finally, the hummingbird returns to the red blooms, feeding once more with the sun illuminating its iridescent plumage, showcasing its agility and grace against a garden filled with various colorful flowers.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1181
|
videos/HRA_part1/1181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 leopard, showcasing its distinctive golden fur patterned with black rosettes, swims through a clear, sun-dappled body of water, its muscular body cutting through the liquid with surprising grace and strength. Its piercing eyes remain focused, and its ears are flattened against its head as it propels itself forward with powerful strokes, defying the typical terrestrial nature of its kind in this aquatic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1402
|
videos/HRA_part2/1402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with glasses, wearing a dark green sweater over a button-down shirt, stands on a chair to change a light bulb in a room with wooden floors and a desk filled with books and writing materials. He holds the new light bulb in his right hand while his left hand grasps the existing bulb, which is attached to a simple ceiling fixture. Behind him, a large window reveals a gray, rainy day outside. The room is dimly lit by a small lamp on the desk, illuminating the clutter of papers, notebooks, and a vintage typewriter. The writer's casual attire, including khaki pants and brown shoes, contrasts with the focused determination on his face as he completes this mundane task amidst his literary surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are not very smooth or continuous."
}
] |
seed46_1915
|
videos/HRA_part2/1915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A space-suited worker, complete with helmet and backpack, sits inside a lunar buggy, which is a small rover designed for moon exploration. The vehicle is adorned with various equipment and tools necessary for extraterrestrial missions. The worker is engaged in wiping down the interior surfaces of the buggy, ensuring cleanliness in the zero-gravity environment. The action takes place against the stark, desolate backdrop of the lunar landscape, with the Earth visible as a brilliant blue orb in the distance, providing a dramatic contrast to the monochrome moon surface.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1598
|
videos/HRA_part2/1598.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful male writer, wearing a blue jacket, dark jeans, and brown shoes, walks through dense shrubbery in a thick forest during daytime. His hands are tucked into his pockets as he strolls, appearing lost in thought. He pauses to observe his surroundings, which include lush green foliage and towering trees. Continuing his journey, he strides confidently, navigating the uneven terrain formed by rocks and tree roots. Throughout the scene, the writer maintains a contemplative demeanor, suggesting a creative mind at work amidst the natural beauty of the woodland environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2014
|
videos/HRA_part2/2014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vivid close-up of a sea urchin reveals its intricate, symmetrical structure as it clings to a rocky surface underwater. Sunlight filters through the clear, blue water, casting a soft glow on the urchin's spines, which are a striking contrast to the dark rocks. The camera captures the water gently swaying the urchin, emphasizing its resilience in the marine environment. The scene is framed by the rocky crevices of the seabed, highlighting the creature's natural habitat, while the muted colors of the rocks and sand provide a serene backdrop for the brightly colored sea urchin.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2098
|
videos/HRA_part1/2098.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 and mouth generation in the video have issues."
}
] |
seed42_1398
|
videos/HRA_part0/1398.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with curly brown hair tied back in a ponytail and wearing a red apron over a casual outfit stands in a modern kitchen, illuminated by bright overhead lights. She focuses intently on slicing a red bell pepper on a white cutting board, her silver ring catching the light. Next, she stirs a sizzling pan of vegetables on a stainless steel stove, steam rising from the pan. Then, she adds a pinch of salt and a sprinkle of fresh herbs to the dish, enhancing its aroma. Finally, she smiles as she plates the finished meal, garnishing it with a sprig of parsley, ready to serve a delicious dinner.]"
},
{
"from": "gpt",
"value": "Normal. The lady's fingers and the shovel in the video are not fully generated."
}
] |
seed42_2395
|
videos/HRA_part0/2395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, ancient-looking turtle with a weathered, brown shell and algae growth moves slowly across a lush, green forest floor, surrounded by vibrant foliage and ferns. Its wise, calm eyes peer from beneath heavy, wrinkled eyelids, and its textured skin and claws are well-adapted to its woodland habitat. The scene is peaceful, with dappled sunlight filtering through the dense canopy above, highlighting the intricate patterns on the turtle's shell as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2884
|
videos/HRA_part1/2884.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a red flannel shirt, blue jeans, brown work boots, and a wide-brimmed straw hat, rakes a large pile of autumn leaves in the midst of a vast, open farmland. The scene is set during the golden hour, with the sun casting a warm glow across the landscape. The farmer pauses to wipe sweat from his brow, revealing a face lined with the wisdom of years spent working the land. He continues his task with a sense of purpose and pride, the leaves forming a vibrant mosaic of reds, oranges, and yellows around him. The video captures the essence of hard work and the beauty of seasonal change in the rural countryside.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_1340
|
videos/HRA_part1/1340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, known for his captivating performances, sits in a dimly lit room with wooden floors and walls adorned with musical instruments. He is sewing a button onto his burgundy velvet jacket, his fingers adorned with silver rings. His rugged appearance is highlighted by his scruffy beard and long, wavy hair. Behind him, a large window reveals the silhouette of a tree against a gray sky, adding a touch of melancholy to the scene. Despite the somber atmosphere, his focused gaze and the presence of a vintage microphone stand nearby suggest a sense of determination and passion for his craft.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_3013
|
videos/HRA_part1/3013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged chef, wearing a white apron over a black shirt and gray pants, is seen scrubbing the bathroom floor with a green cleaning brush. The room is illuminated by overhead lights, and the chef's serious expression conveys the importance of cleanliness. In another angle, the chef, still in his chef's uniform, is shown on his knees, focused on scrubbing the bathroom tiles with determination. The video emphasizes the chef's commitment to hygiene, even in non-food-related areas, as he meticulously cleans the bathroom floor with a green cleaning brush under the bright lights.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and arm undergo deformation and distortion."
}
] |
seed42_2205
|
videos/HRA_part0/2205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a yellow sports bra, black leggings, and white running shoes, runs past a series of modern apartment complexes. She has a focused look on her face, her brown hair tied back in a ponytail, and wears a small backpack. The apartments feature large windows, balconies with plants, and are painted in shades of blue and green. The scene is set in the late afternoon, with the sun casting long shadows and highlighting the architectural details of the buildings. In the distance, lush trees provide a natural contrast to the urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_279
|
videos/HRA_part1/279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 human teacher, wearing a casual blue shirt and jeans, is playfully dancing in a classroom filled with natural light, alongside a chimpanzee. The chimpanzee, dressed in a miniature version of the teacher's outfit, mirrors the teacher's dance moves with joyful expressions. Both the teacher and the chimpanzee engage in synchronized steps, creating a harmonious and whimsical scene, as they move across the room with the sun casting gentle shadows behind them. The teacher's face reflects amusement and connection, while the chimpanzee's animated body language conveys a sense of fun and companionship in their shared activity.]"
},
{
"from": "gpt",
"value": "Bad. The video shows a human teacher and a chimpanzee playing and dancing, but the movements are not continuous and smooth, with noticeable abrupt changes."
}
] |
seed44_2759
|
videos/HRA_part1/2759.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, a mustache, and glasses sits against a white wall, intently sewing a button onto a piece of fabric with a red thread. He wears a gray shirt, and the focus is on his hands, which hold the needle and thread with precision. His facial expression is concentrated, and he occasionally looks up, offering a slight smile. Throughout, he continues his task diligently, the red thread weaving in and out of the button holes, securing it firmly to the fabric. The simplicity of the setting allows the viewer to fully appreciate the man's skill and attention to detail in this everyday task.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2719
|
videos/HRA_part1/2719.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lavish decorations for an extravagant wedding, a neatly-dressed cashier, wearing a classic black vest and bow tie, diligently wipes the immaculate glass counter with a small cloth. The backdrop features elegant table settings, floral arrangements, and a large, illuminated dance floor, all indicative of an upscale celebration. The cashier's meticulous attention to detail ensures the space station's cash register area remains spotless amidst the grand festivities.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2409
|
videos/HRA_part2/2409.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vibrant coral reef ecosystem, a pair of butterfly fish, characterized by their distinctive black stripes and oval-shaped bodies, gracefully swim among the colorful corals and anemones. One fish displays a striking yellow hue with bold black markings, while the other exhibits a more subdued brown and white pattern. They navigate the intricate underwater landscape, their movements synchronized, as they explore the nooks and crannies of the reef in search of food. The scene is illuminated by the filtered sunlight that penetrates the clear blue water, casting dappled light on the fish and their surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The butterflyfish swims basically normally, but there is slight disharmony in the movements."
}
] |
seed46_152
|
videos/HRA_part2/152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 museum dedicated to firefighting history, a lone firefighter, dressed in full gear except for his helmet, meticulously wipes an antique fire engine, showing respect and care for the vintage piece. The museum is filled with various firefighting artifacts, creating a rich historical context. The firefighter, wearing a yellow shirt underneath his uniform, is deeply engaged in cleaning the old fire truck, highlighting the connection between present-day firefighters and their heritage. Surrounded by firefighting memorabilia, he continues to polish the vehicle, emphasizing the importance of preserving the past within the firefighting community.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter wiping the antique fire truck is basically normal, but there are slightly uncoordinated movements."
}
] |
seed46_2147
|
videos/HRA_part2/2147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse in a sky-blue uniform, complete with a matching cap, stands at the edge of a bustling harbor. The sun illuminates her figure as she prepares to leap into the air, her silhouette framed by the vibrant scene of ships and docks in the background. Her joyful expression contrasts with the busy maritime activities, capturing a spontaneous moment of playfulness amidst a working waterfront.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_3214
|
videos/HRA_part2/3214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black waistcoat, moves gracefully across a wooden deck overlooking a serene river, carrying a silver tray with glasses of sparkling wine. The river, its surface shimmering with reflections of the lush greenery lining its banks, meanders gently into the distance under a clear blue sky. Suddenly, a small creature catches the waiter's eye; it's a caterpillar, slowly crawling along the edge of the deck railing, seemingly unperturbed by the elegant scene unfolding nearby. The waiter pauses, momentarily captivated by the simple beauty of nature juxtaposed with his refined task.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_285
|
videos/HRA_part2/285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a gray long-sleeved shirt and khaki pants, is seen wiping down a hippopotamus with a large cloth. The scene takes place in a spacious, well-lit room with concrete walls and floor, resembling a zoo enclosure or animal care facility. The engineer, wearing safety glasses and a name badge, approaches the docile hippopotamus with a bucket of soapy water and a sponge, carefully cleaning its skin. The hippo, appearing calm and cooperative, stands in the middle of the room, surrounded by various tools and equipment typically found in an engineering workshop, creating an unusual yet intriguing juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2896
|
videos/HRA_part1/2896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heartwarming scene, two people, a male and a female, are shown gently caressing a baby rhinoceros in a natural habitat, surrounded by lush greenery. The couple, both wearing khaki safari gear, including shirts, pants, and hats, interact tenderly with the young rhino, which is standing on sandy soil. The man strokes the rhino's back while the woman looks on, both expressing deep affection and care for the animal. The setting, with its vibrant vegetation and clear blue sky, adds to the peaceful and nurturing atmosphere of the moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1906
|
videos/HRA_part0/1906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skilled musician, garbed in a vibrant red jacket, plays a traditional wooden flute, his eyes closed in concentration, set against a backdrop of rolling hills and lush greenery. In the foreground, an ibex, distinguished by its curved horns, leaps gracefully over a small obstacle, embodying freedom and agility. The harmonious blend of the musician's melodic tunes and the ibex's acrobatic leap creates a captivating scene, where nature and artistry coalesce beautifully under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Normal. The jumping motion of the goat in the video is not smooth and coordinated."
}
] |
seed44_1068
|
videos/HRA_part1/1068.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 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 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": "Bad. The character's movements in the video are discontinuous and not smooth."
}
] |
seed42_2097
|
videos/HRA_part0/2097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 leaps across the golden savanna, its body stretched in mid-air with power and grace. The sun illuminates the cheetah's spotted coat, highlighting the taut muscles beneath as it propels itself forward. In the background, acacia trees stand silhouetted against the horizon, their branches reaching towards the clear blue sky. The cheetah's eyes are fixed on its target, a burst of speed and agility encapsulated in this single, awe-inspiring moment.]"
},
{
"from": "gpt",
"value": "Bad. The cheetah's running in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_2285
|
videos/HRA_part0/2285.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lawyer, dressed in a spacesuit adorned with patches and logos, embarks on a spacewalk to repair a satellite. She glides through the cosmos, the Earth visible in the distance, her movements methodical and confident. Her gloved hands, detailed with NASA symbols, work diligently on the intricate mechanisms, a tool kit secured to her waist. The vastness of space surrounds her, stars twinkling in the dark expanse, as she focuses on her task with the precision of her legal expertise. Throughout the sequence, her spacesuit helmet reflects the celestial backdrop, encapsulating the unique juxtaposition of her profession and this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video does not move."
}
] |
seed42_1226
|
videos/HRA_part0/1226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a yellow high-visibility vest and gray trousers, crawls through a narrow tunnel within a vast, rocky quarry, his flashlight illuminating the rugged terrain. The dusty environment envelops him as he moves with determination, surrounded by towering walls of stone, showcasing the lesser-seen aspects of maintenance work in an expansive quarry setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed42_1679
|
videos/HRA_part0/1679.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dim light of a Martian sunset, casting an eerie orange glow, a small, brown mouse sits atop a large fire helmet, placed on the red, rocky surface of Mars. Nearby, a firefighter, dressed in a full suit and helmet, wipes his brow with a gloved hand, appearing weary yet determined. The vast, desolate landscape stretches out behind him, dotted with the remnants of a recently extinguished extraterrestrial fire, as the distant horizon is bathed in the fading embers of the alien sun.]"
},
{
"from": "gpt",
"value": "Bad. The brown rat undergoes deformities and mutations."
}
] |
seed42_2170
|
videos/HRA_part0/2170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded man in his thirties, wearing a gray cap, green jacket, and brown hiking pants, strides powerfully uphill on a rocky trail. Surrounded by lush vegetation and towering trees, he carries a large backpack and hiking poles, showcasing his adventurous spirit. The scene captures his determined face as he looks ahead, highlighting his focus and resolve. Moments later, he pauses to gaze at the stunning landscape, his green jacket and brown trousers blending harmoniously with the natural environment, embodying the essence of a dedicated hiker immersed in the beauty of the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are uncoordinated."
}
] |
seed42_3206
|
videos/HRA_part0/3206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cave, a small brown bat crawls along the rocky surface, using its wings as makeshift limbs for terrestrial navigation. The bat's eyes are closed, relying on echolocation to sense its surroundings, while its furry body brushes against the damp stone. Nearby, water droplets cling to the cave's textured walls, adding to the atmosphere of a subterranean habitat. The bat's movements are deliberate and cautious, emphasizing its adaptation to life in the dark, confined spaces of its underground home.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1502
|
videos/HRA_part2/1502.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lush, subtropical woodland setting, a majestic tiger lies on the rich forest floor, its coat blending harmoniously with the dappled sunlight filtering through the dense foliage above. The camera captures the intimate moment as a gentle hand caresses the tiger's head, conveying an unexpected sense of trust and connection between the wild animal and the unseen human presence. The tiger's eyes are closed, its expression one of pure bliss, indicating a rare bond formed within the natural habitat of the subtropical woodlands.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2949
|
videos/HRA_part1/2949.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, donning full gear and a helmet, takes a break from his usual duties to engage in a surprising hobby: gardening. He carefully plants flowers in a small garden plot, surrounded by a wooden fence, with a bright red firetruck visible in the background. His gloved hands, typically used to handle hoses and axes, now delicately place marigolds into the soil. The juxtaposition of his robust firefighting attire and the delicate act of gardening creates a unique and compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's hand in the video is generated blurry."
}
] |
seed42_1849
|
videos/HRA_part0/1849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary vulture, with its distinctive bald head and dark plumage, perches majestically on a rocky outcropping, overlooking a vast, arid landscape under an overcast sky. Its powerful, hooked beak is slightly open, revealing its pinkish-red interior, while its piercing eyes survey the terrain for potential prey. The bird's textured skin and feather details are highlighted by the natural lighting, emphasizing its rugged survival instincts in the harsh environment. As it prepares to take flight, the vulture's wings spread wide, displaying their impressive span against the muted tones of the rocky surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The vulture's movements in the video are basically normal, with slight lack of coordination."
}
] |
seed42_1794
|
videos/HRA_part0/1794.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a brown beret, red scarf, and green jacket, walks through a quaint, snow-covered village. The scene focuses on shops with wooden signs and red brick facades, reminiscent of a European winter market. Among the crowd, the artist carries a large painting wrapped in brown paper, attracting curious looks from passersby. In the background, a life-sized beaver statue stands outside a shop, adding a whimsical touch to the picturesque setting. The artist continues walking, blending into the festive atmosphere, with the beaver statue remaining a quirky focal point among the bustling shoppers.]"
},
{
"from": "gpt",
"value": "Normal. The artist in the video walks normally with a large painting wrapped in brown paper, though the movements are slightly uncoordinated."
}
] |
seed42_1995
|
videos/HRA_part0/1995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a gray sweater over a white shirt, dark jeans, and black shoes, stands in his well-lit garage, surrounded by various tools and equipment. He is organizing his belongings, rearranging items on metal shelves, and sweeping the floor. The garage walls are painted a light color, and the space is cluttered yet functional. As he works, the doctor occasionally pauses to examine objects more closely, demonstrating care and attention to detail in his task of tidying up the garage environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2787
|
videos/HRA_part2/2787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Against a vast, icy landscape, two children in vividly colored swimwear are seen joyfully interacting with the glacier's edge, where a pool of crystal-clear water has formed. The girl, wearing a pink swimsuit, playfully splashes the water with her hands, her face alight with delight. The boy, in blue swimming trunks, sits on the ice, dipping his feet into the chilly waters, his expression one of cautious excitement. The camera captures the stark contrast between the vibrant colors of their swimwear and the monochromatic scenery of ice and sky, creating a striking visual tableau. Throughout the scene, the children's interactions with the glacial environment showcase their curiosity and wonder, highlighting the unique experience of swimming beside a glacier.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1053
|
videos/HRA_part2/1053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with its distinctive short tail and tufted ears, strides purposefully across a dry, rocky terrain under the clear blue sky. Its tawny fur, marked with spots and stripes, blends perfectly with the arid environment. The cat's piercing eyes remain alert, scanning the surroundings for potential prey or threats, as it moves with a confident gait, showcasing its natural agility and strength in the wild.]"
},
{
"from": "gpt",
"value": "Bad. There are many extra legs."
}
] |
seed44_2206
|
videos/HRA_part1/2206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, clad in full gear and a yellow fire-resistant jacket, methodically mops the floor of a fire station common room, which features a pool table, a large flat-screen TV, and a couch. The mop bucket sits nearby, and the firefighter's focus and precision in cleaning contrast with the typically rugged image associated with firefighting. The scene highlights the everyday tasks and responsibilities of firefighters when they are not actively battling fires, emphasizing the importance of maintaining a clean and orderly living environment within the station.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed42_2142
|
videos/HRA_part0/2142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with short brown hair, wearing a gray shirt and glasses, sits in a chair in a living room setting, gently caressing a small, fluffy white cat. The room is filled with natural light from a window behind him, illuminating the intimate interaction. The cat, appearing relaxed and content, lies on its back on the man's lap as he strokes its belly. The scene conveys a sense of warmth and affection between the man and the cat, with the soft focus on their faces capturing the tender moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1559
|
videos/HRA_part0/1559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a crisp uniform consisting of a navy blue shirt, matching trousers, and a peaked cap, is engaged in an unusual task inside a busy restaurant district. He is meticulously wiping down a row of outdoor tables, each set with white tablecloths and surrounded by patrons enjoying their meals. The backdrop features a variety of restaurants, ranging from elegant dining establishments to casual eateries, all bustling with activity. The scene captures the unexpected sight of law enforcement taking on a service role, contributing to the cleanliness and ambiance of the dining area.]"
},
{
"from": "gpt",
"value": "Bad. The limbs and fingers of the police officer in the video are missing, the eyes are not generated, and the faces of the background characters are blurry."
}
] |
seed42_1125
|
videos/HRA_part0/1125.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, wearing a dark suit, shirt, and tie, walks through a stunning geothermal field, surrounded by steaming geysers and colorful mineral deposits. The scene begins with the lawyer walking towards a large, erupting geyser, the water shooting high into the air against the dramatic landscape. Next, he pauses to observe another geyser, the steam rising from it creating a mystical atmosphere. Then, he continues walking, passing by a series of smaller geysers, their bubbling waters and vibrant colors contrasting sharply with his formal attire. Lastly, the lawyer is seen walking away from the camera, the vast geothermal field stretching out behind him, the geysers and steam adding an otherworldly touch to the professional setting.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2852
|
videos/HRA_part2/2852.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a white shirt, blue overalls, and a wide-brimmed straw hat, runs across a vast, golden wheat field under a clear blue sky. Suddenly, the scene transforms as if by quantum leap, revealing the farmer now sprinting through a futuristic cityscape filled with neon lights and towering skyscrapers. Despite the change, he maintains his determined expression and rustic attire, creating a stark contrast between the rural and urban environments.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's running in the video is basically normal, with only slightly uncoordinated movements."
}
] |
seed42_2589
|
videos/HRA_part0/2589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, adorned in a traditional white uniform and tall hat, stands against the stark contrast of a landfill landscape. He gently caresses a large, ripe tomato, highlighting the irony of waste amidst sustenance. His eyes, filled with concern and determination, underscore the message of valuing food resources in a world plagued by waste. The scene is set against a backdrop of discarded goods, emphasizing the importance of responsible consumption and the role chefs play in advocating for sustainable practices.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1419
|
videos/HRA_part1/1419.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 firefighter, clad in full gear and a helmet, is sprinting with intense focus through a lush, green park. He's gripping a fire hose as he runs beside a serene lake, where ducks are seen swimming in the background. The scene conveys a sense of urgency and determination, with the firefighter's muscular physique straining against his equipment. The park is filled with vibrant greenery and tall trees, providing a stark contrast to the firefighter's urgent mission. As he races past a wooden bench and a playground, the peaceful setting underscores the potential danger lurking nearby.]"
},
{
"from": "gpt",
"value": "Bad. The hands and legs are deformed."
}
] |
seed44_166
|
videos/HRA_part1/166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, donning full gear including a yellow jacket, black pants, and a helmet with a flashlight attached, kneels before a bathroom sink. He fixes a leaky faucet with precision, using a wrench in his right hand. The scene is set in a dimly lit room, with a mirror above the sink reflecting the firefighter's focused face. Behind him, a closed door and a vertical window add detail to the setting. The firefighter's left hand rests on the sink, while his right hand tightens the faucet, demonstrating unexpected domestic skills in full firefighting attire.]"
},
{
"from": "gpt",
"value": "Bad. The hand appears deformed, and the wrench is also deformed."
}
] |
seed42_166
|
videos/HRA_part0/166.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 firefighter, donning full gear including a yellow jacket, black pants, and a helmet with a flashlight attached, kneels before a bathroom sink. He fixes a leaky faucet with precision, using a wrench in his right hand. The scene is set in a dimly lit room, with a mirror above the sink reflecting the firefighter's focused face. Behind him, a closed door and a vertical window add detail to the setting. The firefighter's left hand rests on the sink, while his right hand tightens the faucet, demonstrating unexpected domestic skills in full firefighting attire.]"
},
{
"from": "gpt",
"value": "Normal. The faucet has become bent and deformed."
}
] |
seed44_2457
|
videos/HRA_part1/2457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling female musician, wearing a gray sweater, sits against a rustic wooden backdrop. She holds knitting needles and yarn in her hands, crafting a vibrant orange scarf. Her fingers, adorned with rings, skillfully manipulate the needles as she knits. Next, she wears a maroon beret and continues knitting, her eyes focused on her work. Then, she looks up from her knitting, her hazel eyes meeting the camera with a warm smile. Lastly, she proudly holds up the completed scarf, now a beautiful addition to her outfit, against the backdrop of wooden planks, showcasing her dual talents in music and knitting.]"
},
{
"from": "gpt",
"value": "Normal. The action of the musician raising the scarf is basically normal."
}
] |
seed44_113
|
videos/HRA_part1/113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker in a power plant environment is seen wiping down a large turbine with a yellow cloth, dressed in a navy blue uniform, complete with a shirt, trousers, and safety shoes. The scene captures the maintenance aspect of power generation, with the worker focused on cleaning the metallic surface of the turbine. The power plant's interior is visible, featuring high ceilings, large machinery, and industrial pipes, all bathed in artificial lighting. The worker's attire, which includes a hard hat and protective gloves, emphasizes safety protocols in the industrial setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2600
|
videos/HRA_part0/2600.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 blend of scenes, a majestic African lion strides powerfully across a vast, barren asteroid, its golden coat contrasting starkly against the monochrome landscape pockmarked with craters. The lion, undeterred by the alien environment, explores the rocky terrain as if it were a savannah, with distant stars and a nebula providing a cosmic backdrop. Nearby, a futuristic mining facility operates diligently, extracting precious resources from the asteroid's surface, emphasizing the juxtaposition of nature and technology in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1371
|
videos/HRA_part0/1371.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic display, a snake charmer clad in a richly colored red robe and matching turban leans forward, engaging intently with a king cobra emerging from a traditional wicker basket. The snake, adorned with intricate patterns, rises dramatically from the basket, its hood spread wide. The charmer's hands, decorated with silver bracelets, gently caress the serpent's body, emphasizing the bond between human and animal. The scene is set against a vibrant, patterned cloth, adding to the exotic atmosphere, with the charmer's face expressing both respect and control as he interacts with the majestic creature.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.