video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_3090
|
videos/HRA_part2/3090.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-looking man in a gray shirt and blue jeans is crawling on his hands and knees under a wooden deck in a backyard, fixing something. Suddenly, a moose appears in the frame, standing majestically behind the deck, curious about the activity. The worker, unaware of the unexpected visitor, continues his task diligently, his back arched as he focuses on the repair work, while the large, wild animal watches him from a distance, creating an unusual juxtaposition of urban labor and wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_109
|
videos/HRA_part2/109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, futuristic scene, a police officer, clad in a high-tech, silver uniform with a clear, bubble-like helmet, leaps gracefully over a rocky terrain under the Martian sky. An ibex, a type of wild goat, stands majestically nearby, its silhouette outlined against the alien landscape. The officer's powerful jump is captured mid-air, highlighting the reduced gravity of Mars. The constellations and stars above are vivid and numerous, creating a breathtaking backdrop for this extraordinary moment of stargazing from the red planet.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's face was not fully generated, and the fingers were deformed."
}
] |
seed46_2756
|
videos/HRA_part2/2756.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 friendly moose stands in a hospital room, wearing a stethoscope around its neck, implying it plays the role of a doctor. The moose, with a caring expression, wipes the face of a seated patient, a child wearing a yellow shirt, using a soft cloth. The room is filled with natural light, highlighting the gentle interaction between the moose and the child, who looks up at the moose with trust and gratitude. Behind them, medical equipment and a hospital bed are visible, blending the elements of a healthcare setting with the unexpected presence of the animal.]"
},
{
"from": "gpt",
"value": "Bad. The moose's action of wiping the little patient with cloth in the video is not very continuous and there is a lack of coordination."
}
] |
seed44_1660
|
videos/HRA_part1/1660.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 waiter, dressed in a white shirt and black pants, carefully balances a tray of refreshments on his hands, offering it to a friendly mammoth. The mammoth, depicted with brown fur and large tusks, swims leisurely in a serene lake, its body half-submerged in the clear water. The waiter stands at the edge of the lake, extending the tray towards the mammoth, who reaches out with its trunk to gently take a drink. The sky is a vivid orange, suggesting either sunrise or sunset, adding a touch of magic to this extraordinary encounter between two unlikely companions.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's action of using its trunk to take the drink from the server's tray in the video is not smooth and has a sudden change."
}
] |
seed42_2828
|
videos/HRA_part0/2828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, donning a navy blue cap and sunglasses, runs along the sandy shore of a bustling beach resort, where vibrant umbrellas and lively beachgoers fill the background. His attire includes a navy blue shirt with badge, navy blue trousers, and black shoes. The setting is a crowded beach during daytime, with the officer's movement capturing the essence of duty amidst leisure. He sprints past colorful umbrellas and animated vacationers, highlighting the contrast between his purposeful stride and the relaxed atmosphere of the resort.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's facial features in the video are generated blurry, hands and feet are deformed, and the hands and feet of the police officer in the middle frames suddenly disappear or appear. The sunshade umbrellas and vacationers in the background are also generated blurry."
}
] |
seed44_251
|
videos/HRA_part1/251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer wearing a spacesuit decorated with patches and emblems swims effortlessly in zero gravity within a space station habitat. The habitat, illuminated by soft, ambient lighting, features curved walls and large windows offering breathtaking views of the cosmos. A pet lizard, also weightless, floats nearby, its scales reflecting the light in iridescent patterns. The engineer gently propels themselves through the water-filled enclosure, designed to simulate Earth's aquatic environments, while the lizard seems to hover curiously beside them, both adapted to life in the microgravity of the space station.]"
},
{
"from": "gpt",
"value": "Normal. The character's hands are distorted, the lizard's body is twisted, the head is distorted, and the feet are twisted."
}
] |
seed42_2569
|
videos/HRA_part0/2569.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 shot of fresh mackerel, glistening under bright lights, is presented on a bed of ice. The fish has distinctive vertical stripes, a sign of its freshness, and its eyes are clear and shiny. The camera then zooms out to reveal the fishmonger's stall, bustling with activity, where various species of fish are displayed on ice. The mackerel takes center stage, surrounded by other seafood, emphasizing its appeal among the array of options. Throughout, the high-definition footage captures the vibrant colors and textures of the fish market, focusing on the mackerel as the star attraction.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1359
|
videos/HRA_part1/1359.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a gun holster, walks through a vast space library with high ceilings and large windows showing distant stars. The officer, with a serious yet calm demeanor, moves between towering bookshelves filled with ancient books and futuristic data pads. The library is illuminated by soft, ambient lighting, casting a warm glow on the officer's path. As they walk, the officer occasionally glances at the titles, perhaps searching for information or simply appreciating the knowledge stored within this unique cosmic repository.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1537
|
videos/HRA_part1/1537.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene and lush environment, a graceful gazelle is seen gently caressing the face of another smaller gazelle, possibly its offspring, creating a tender and intimate moment between them. The scene is set in a verdant savanna landscape, with tall grass swaying softly in the breeze and trees scattered in the background, providing a peaceful and natural setting for this heartwarming interaction. The larger gazelle, with its delicate features and caring demeanor, conveys a sense of protection and affection toward the younger one, emphasizing the bond between them.]"
},
{
"from": "gpt",
"value": "Normal. The body structures of the antelopes in the video have issues: the large antelope has an extra ear, and the small antelope has two extra legs."
}
] |
seed44_1903
|
videos/HRA_part1/1903.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous woman wearing a thick, brown jacket and dark pants stands on a rocky ledge overlooking a vast, misty valley, preparing to leap from the cliffside. Nearby, a large brown bear, also gazing into the foggy abyss, seems unperturbed by her presence. As the scene progresses, the woman jumps off the cliff, her arms spread wide, embracing the thrill of freefall, with the bear watching intently from the edge of the precipice. Throughout, the dramatic landscape of rugged cliffs and the mysterious atmosphere of the mist-shrouded valley provide a breathtaking backdrop for this daring act.]"
},
{
"from": "gpt",
"value": "Bad. The woman's action of jumping off the cliff with her arms spread wide in the video is not continuous and has a sudden change."
}
] |
seed44_143
|
videos/HRA_part1/143.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A doctor, dressed in a white lab coat over khaki cargo pants and brown leather shoes, runs through a lush, green jungle environment. In his right hand, he holds a clear, plastic container housing a live lizard, which scurries about inside. The doctor navigates through the dense foliage, dodging vines and leaping over fallen logs, his face set with determination as he focuses on his mission. The vibrant greenery of the jungle provides a stark contrast to the doctor's attire, highlighting the unusual nature of this scenario.]"
},
{
"from": "gpt",
"value": "Bad. The character's body is twisted, the face is distorted, the arms are twisted, and the legs are contorted."
}
] |
seed42_1740
|
videos/HRA_part0/1740.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a white apron over a black t-shirt and jeans, throws clay on a spinning pottery wheel under the glow of bright studio lights. With intense concentration, they shape the clay into a vase, their hands moving gracefully and purposefully. The camera captures the artist's face, reflecting determination and skill, as they mold the clay. Throughout the process, the artist's attire remains consistent, and the scene is set against a backdrop of a well-lit workshop filled with various pottery tools and finished pieces.]"
},
{
"from": "gpt",
"value": "Normal. The artist's hand in the video has minor issues."
}
] |
seed42_2490
|
videos/HRA_part0/2490.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chimpanzee, covered in dark fur with lighter features around its eyes and mouth, runs across a grassy terrain under a vibrant blue sky. The chimp's movement is powerful and agile, with a hunched posture typical of its species. Its face, marked with distinctive wrinkles and a noseless structure, conveys intense focus as it sprints. In another moment, the chimpanzee is shown from a side view, highlighting its muscular build and the gracefulness of its stride, set against the backdrop of a lush, green environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1338
|
videos/HRA_part0/1338.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diligent window cleaner, equipped with a squeegee and a bucket of soapy water, stands on a ladder propped against a tall, glass-paneled building. Dressed in a yellow high-visibility vest and dark pants, he methodically wipes the glass, leaving a streak-free shine. The bustling cityscape forms the backdrop, with pedestrians passing by and cars moving on the streets below. The sun casts a golden glow on the scene, highlighting the cleaner's hard work as he moves from pane to pane, ensuring crystal clarity for the occupants inside.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1639
|
videos/HRA_part0/1639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 curly brown hair pulled into a bun, wearing a gray T-shirt and jeans, sits on a wooden chair in a spacious studio filled with natural light. She is engrossed in painting a large canvas with vibrant colors using a palette knife, surrounded by various art supplies like brushes, paints, and rags. The room is decorated with other colorful paintings, potted plants, and a large window letting in ample sunlight, creating a warm and inspiring atmosphere. The woman's focused expression and the splashes of paint on her clothes and hands highlight her passion and dedication to her craft.]"
},
{
"from": "gpt",
"value": "Normal. The character's actions of applying color with a palette knife in the video are basically normal, with slight disharmony."
}
] |
seed44_1449
|
videos/HRA_part1/1449.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 crab, displaying a vibrant red and orange carapace, scuttles across a shallow, sunlit tide pool, surrounded by lush green seaweed and other marine life. The crab's claws, one significantly larger than the other, are prominently displayed as it navigates its environment, with the smaller claw delicately handling food. Its intricate shell pattern and the dynamic underwater setting provide a visually engaging scene, all captured in stunning detail against a backdrop of clear, blue water and a sandy ocean floor.]"
},
{
"from": "gpt",
"value": "Normal. The crab's movements are not smooth."
}
] |
seed42_1411
|
videos/HRA_part0/1411.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene set in a vast, starlit cosmos, a renowned actor, dressed in a flowing white robe, participates in an otherworldly religious ceremony. The celestial setting features an enormous, ethereal bear standing on its hind legs, appearing majestic against the backdrop of distant galaxies. The actor, with a determined look, is seen running alongside the cosmic bear, both moving in unison within the sacred space ritual, their journey illuminated by the glow of nebulae and stars.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2721
|
videos/HRA_part2/2721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow firefighting jacket, gently wipes soot off a small, brown hedgehog that's been rescued from a fire. The hedgehog, nestled in the firefighter's protective glove, looks up with curious eyes as it's being cleaned. The scene takes place against the backdrop of a fire-damaged building, with smoke still lingering in the air, emphasizing the tender moment between the rescuer and the rescued animal.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's fingers are deformed in the video, and the hedgehog's face is distorted."
}
] |
seed42_2693
|
videos/HRA_part0/2693.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courageous firefighter, clad in full gear and a helmet, walks alongside a majestic elephant, both navigating through a lush, green environment. The firefighter's equipment includes a heavy-duty jacket, pants, boots, and gloves, signifying readiness for any emergency. The elephant, adorned with intricate patterns on its body, suggests a cultural or ceremonial context. Together, they traverse a dirt path surrounded by dense vegetation, creating an unexpected yet compelling visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The faces of the characters in the video are distorted, hands are twisted, feet are deformed, the elephant's face is distorted, and the legs are twisted."
}
] |
seed42_1696
|
videos/HRA_part0/1696.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 middle-aged doctor, wearing a stethoscope around his neck and a crisp white lab coat over his neatly pressed blue scrubs, finds himself unexpectedly dancing in a vast savanna. As he moves with surprising grace, a curious cheetah, intrigued by the unusual sight, approaches cautiously from the tall grass. The big cat, known for its speed and agility, mirrors the doctor's dance steps, its movements fluid and powerful. The unlikely pair continues their impromptu dance, surrounded by the vast, open landscape, creating a surreal and captivating moment captured in high-definition footage.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2123
|
videos/HRA_part1/2123.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vivid orange kite with intricate black patterns soars majestically against a clear blue sky, its long white tail streaming gracefully behind it. The kite, resembling a dynamic bird in flight, is seen from various angles, showcasing its detailed design and the fluidity of its movements. Against the serene backdrop of fluffy white clouds and the vast horizon, the kite seems to dance with the wind, captivating viewers with its aerial ballet. The interplay of sunlight and shadow enhances the kite's vibrant colors, making it a striking focal point against the peaceful sky.]"
},
{
"from": "gpt",
"value": "Normal. The kite in the video is deformed."
}
] |
seed42_1461
|
videos/HRA_part0/1461.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, green deciduous forest, a local worker wearing a straw hat and khaki clothing kneels near a serene riverbank. Suddenly, a jaguar stealthily emerges from the dense foliage, its golden eyes fixed on the water. The wild cat, exhibiting grace and power, leaps into the river for a refreshing swim, its sleek body cutting through the water effortlessly. The worker watches in awe, a harmonious moment captured between human and nature, all set against the backdrop of the vibrant deciduous forest.]"
},
{
"from": "gpt",
"value": "Bad. The jaguar's movements in the video are not smooth and uncoordinated."
}
] |
seed44_2087
|
videos/HRA_part1/2087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space prison, dimly lit by neon blue lights, two figures, a male and female inmate, plot their daring escape. They wear matching orange jumpsuits with black stripes, symbolizing their confined status. Suddenly, they engage in a synchronized dance, using their movement as a clever ruse to distract guards. Their dance, a blend of hip-hop and contemporary styles, captivates the robotic guards, allowing the inmates to stealthily make their way towards freedom. The prison's cold, metallic interior contrasts sharply with the dynamic energy of their dance, highlighting the tension between confinement and liberation. Throughout, the focus remains on the two dancers, their precise movements and the prison's stark, oppressive environment.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, distorted face, twisted arms, and twisted hands."
}
] |
seed44_13
|
videos/HRA_part1/13.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, solitary moose is depicted swimming in a clear, glassy lake surrounded by lush vegetation, with its head and antlers visible above the water's surface. The majestic creature gracefully propels itself forward, its body partially submerged, showcasing its surprisingly strong swimming abilities. In the distance, dramatic cliffs rise from the water's edge, their rugged surfaces covered in dense greenery, providing a stunning contrast against the calm waters. The scene is completed by the inclusion of a second moose, also swimming, creating a captivating visual of these powerful animals in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1800
|
videos/HRA_part1/1800.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red squirrel leaps from branch to branch in a tree that overlooks a vast, industrial landscape of oil refineries. The squirrel's movements are agile and energetic, its bushy tail bouncing as it jumps. The scene is framed by the gnarled branches of the tree, which contrast sharply with the metallic structures of the refineries in the background. Plumes of smoke rise from the refinery stacks, creating a hazy atmosphere that bathes the entire scene in a warm, golden glow. The juxtaposition of nature and industry is striking, with the small, lively squirrel seemingly oblivious to the enormity of the human-made structures around it.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the squirrel in the video are missing, and the body and face are deformed."
}
] |
seed44_2834
|
videos/HRA_part1/2834.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, bearded musician, clad in a black leather jacket and jeans, performs an intense, passionate crawling motion across a vast, icy glacier landscape, his electric guitar amplifying the dramatic scene. The stark, snow-covered mountains and glaciers provide a breathtaking, icy backdrop, contrasting with the musician's raw energy. Throughout the sequence, he continues to crawl, his body language conveying determination and struggle, while the icy wilderness remains a constant, awe-inspiring presence.]"
},
{
"from": "gpt",
"value": "Bad. The musician's face, hands, arms, legs, and the instrument in their hands are distorted in the video."
}
] |
seed44_321
|
videos/HRA_part1/321.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit sits quietly by a serene pond, the first light of sunrise on Mercury casting a pale, ethereal glow over the still waters. The sky is a deep shade of indigo, dotted with fading stars, while the distant horizon glimmers with the soft, alien light of the emerging sun. The rabbit, with its soft fur glistening with dew, prepares to take a unique plunge, as it gently enters the calm waters, creating ripples that expand across the glassy surface, under the enchanting, otherworldly beauty of a Mercury dawn.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2187
|
videos/HRA_part1/2187.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, wearing a blue uniform and a stethoscope around her neck, playfully interacts with a ferret on a clean, white examination table in a well-lit veterinary clinic. The ferret, displaying its natural agility, leaps from the nurse's hands as she gently tosses it upwards. The nurse, with a joyful smile, catches the ferret mid-air, showcasing a tender bond between the caregiver and the small animal in a serene medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The ferret undergoes a mutation and becomes deformed while jumping, and the nurse's hand also appears deformed."
}
] |
seed44_1008
|
videos/HRA_part1/1008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fearless firefighter, clad in full gear and a protective mask, crawls determinedly across a rugged, volcanic landscape under a smoky orange sky, his actions highlighting bravery and urgency. Beside him, a fellow firefighter also crawls, both navigating the harsh terrain with focused intensity. Their mission is underscored by the dramatic setting of an erupting volcano in the background, emphasizing the high stakes and danger they face. Throughout, the two figures crawl resolutely forward, their forms silhouetted against the fiery, chaotic backdrop, symbolizing human resilience against nature's fury.]"
},
{
"from": "gpt",
"value": "Normal. The character's arm is twisted, and the legs are distorted."
}
] |
seed46_2513
|
videos/HRA_part2/2513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a distinguished lawyer, clad in a classic black suit and white shirt, gently caresses the metallic surface of a Mars rover model placed on a wooden table. The room is dimly lit, casting dramatic shadows across the scene. The lawyer's face reflects a mix of fascination and professional poise, while the rover, adorned with intricate details and wheels designed for extraterrestrial terrain, stands as a symbol of human innovation and exploration. This intimate interaction between the legal world and space technology creates a thought-provoking narrative about the convergence of seemingly unrelated fields.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are missing, and the wheels and body of the Mars rover are not properly connected."
}
] |
seed44_1976
|
videos/HRA_part1/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The leopard's legs have undergone a mutation deformity."
}
] |
seed44_1809
|
videos/HRA_part1/1809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 orbiting Earth, a waiter clad in a sleek silver uniform gracefully floats, serving exotic dishes to the guests seated at a long, transparent table. The space station, designed with curved edges and illuminated panels, offers breathtaking views of the planet below. The waiter, equipped with magnetic boots to assist in crawling and maneuvering through zero gravity, carefully balances a tray filled with delicacies. As he crawls from one guest to another, the curvature of the space station's interior is visible, creating a unique dining experience among the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_169
|
videos/HRA_part0/169.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Shanghai, under the glow of neon signs and the hustle of the city streets, a peculiar scene unfolds. A street musician, dressed in a vibrant red jacket and dark jeans, passionately plays a saxophone, its golden finish shimmering under the streetlights. Beside him, a chimpanzee, wearing a tiny blue cap and a checkered shirt, mimics the musician's movements, adding an element of whimsy to the performance. As the music fills the air, a group of runners, clad in various sportswear and illuminated by the urban landscape, passes by, some pausing to watch the unique spectacle, while others continue their journey through the lively Shanghai night.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2933
|
videos/HRA_part0/2933.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a green shirt and khaki pants, walks alongside a realistic hare in an urban alley setting, both seemingly coexisting in the gritty environment. The janitor, holding a broom, looks down at the rabbit with a curious expression. In another moment, the janitor, still in his green uniform, leans against a brick wall while the hare sits calmly beside him, the cityscape in the background adding to the unusual pairing. Lastly, the janitor and the hare are seen walking together, the man in his green work attire and the rabbit hopping leisurely, both navigating the textured, urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face in the video is distorted, the hands and feet are deformed, the rabbit is generated disproportionately, and the broom in the cleaner's hand suddenly disappears in the middle frame."
}
] |
seed46_1581
|
videos/HRA_part2/1581.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacious indoor gymnasium illuminated by natural light from large windows, four children wearing colorful clothes engage in various acts of physical exertion. One child, dressed in a red shirt and black shorts, lifts a heavy barbell above their head with a look of intense concentration, demonstrating impressive strength. Another child, wearing a yellow top and blue leggings, performs a handstand against a mirrored wall, showing remarkable balance and poise. A third child, clad in green, does pull-ups on a bar, highlighting their upper body strength. Lastly, a child in a blue outfit leaps over a series of hurdles, capturing the essence of agility and athleticism. The gym's wooden floors and equipment provide a backdrop for these dynamic scenes of youthful energy and determination.]"
},
{
"from": "gpt",
"value": "Normal. A child did not appear in the video."
}
] |
seed44_1821
|
videos/HRA_part1/1821.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mongoose, exhibiting resilience and adaptability, is seen walking through a vast, sunlit landfill. The creature, with its sandy brown fur and alert eyes, navigates the discarded human debris, from plastic bottles to broken electronics. It pauses on a pile of waste, scanning its surroundings with curiosity and survival instinct, highlighting the animal's presence in an unlikely habitat. The mongoose then continues its journey across the landfill, its small figure contrasting against the expansive landscape of garbage under the open sky.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and claws of the mongoose in the video are missing."
}
] |
seed42_1639
|
videos/HRA_part0/1639.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with curly brown hair pulled into a bun, wearing a gray T-shirt and jeans, sits on a wooden chair in a spacious studio filled with natural light. She is engrossed in painting a large canvas with vibrant colors using a palette knife, surrounded by various art supplies like brushes, paints, and rags. The room is decorated with other colorful paintings, potted plants, and a large window letting in ample sunlight, creating a warm and inspiring atmosphere. The woman's focused expression and the splashes of paint on her clothes and hands highlight her passion and dedication to her craft.]"
},
{
"from": "gpt",
"value": "Normal. No towel was generated."
}
] |
seed44_291
|
videos/HRA_part1/291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casually dressed doctor, wearing a white button-down shirt and khaki shorts, leaps into the air on a pristine, sandy beach, with crystal-clear water visible in the background. The doctor, who has brown hair and glasses, is captured mid-jump, displaying a sense of freedom and joy. The scene is set against a stunning backdrop of palm trees and a clear blue sky, creating a perfect blend of professional and leisure elements. The doctor's relaxed attire and the idyllic beach setting convey a sense of balance between work and personal life.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2894
|
videos/HRA_part0/2894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy kitchen with wooden cabinets and cream walls, two young children, a boy and a girl, stand on small stools by the sink, their sleeves rolled up. They are happily washing dishes together, the girl scrubbing a plate with a pink sponge, while the boy rinses a glass under the faucet. The room is filled with natural light from a window above the sink, casting a warm glow on the soap bubbles and wet surfaces. A few clean dishes are stacked neatly on a drying rack nearby, and a colorful dishcloth hangs over the tap, completing the scene of domestic harmony and teamwork.]"
},
{
"from": "gpt",
"value": "Bad. The girl's face in the video is distorted, and the children's hands are deformed."
}
] |
seed42_3138
|
videos/HRA_part0/3138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek black panther walks with measured steps through a dense, shadowy forest, its eyes gleaming with an almost otherworldly green hue. The majestic feline's coat shimmers under the dappled sunlight filtering through the thick canopy above. With each confident stride, the panther's muscles ripple beneath its inky fur, exuding raw power and grace. The underbrush parts gently as the panther moves, revealing the intricate play of light and shadow on the forest floor, punctuated by the occasional flash of vibrant foliage.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
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 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 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_2557
|
videos/HRA_part2/2557.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 station, two figures, a man and a woman, both wearing sophisticated, form-fitting silver spacesuits with intricate blue detailing, walk purposefully down a sleek corridor lit by soft, ambient blue light. They carry themselves with the poise and dignity of diplomats, their movements deliberate and confident. The man sports a neatly trimmed beard and short, dark hair, while the woman wears her long, curly hair in a high bun, adorned with small, sparkling silver clips. Both wear expressions of intense concentration, reflecting the gravity of their mission among the stars. Behind them, the corridor stretches into darkness, hinting at the vastness of space and the unknown adventures awaiting them.]"
},
{
"from": "gpt",
"value": "Good. The video shows a man and a woman walking, with basically normal movements."
}
] |
seed44_2399
|
videos/HRA_part1/2399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, industrial-style hallway, a janitor wearing a yellow vest and holding a mop walks purposefully toward the camera. Behind him, a theoretical spectacle unfolds: a white hole explosion, depicted as an intense burst of light and energy, engulfs the far end of the corridor, creating a dramatic contrast to the mundane setting. The janitor's steady pace and resolute expression suggest an intriguing juxtaposition between the cosmic event and his daily routine.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1087
|
videos/HRA_part1/1087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vibrant underwater scene, an array of colorful anemones sway gently in the ocean current, their tentacles reaching out like delicate fingers. The water around them shimmers with a soft, natural light, illuminating the intricate patterns and textures of these fascinating creatures. Against a backdrop of coral reef, the anemones appear in various shades of purple, red, and orange, creating a stunning contrast against the blue-green hues of the surrounding marine environment. Fish dart playfully among the anemones, adding life and movement to the serene underwater landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1384
|
videos/HRA_part0/1384.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, spiky European hedgehog runs energetically across a lush, green garden, its tiny legs moving swiftly beneath it. The hedgehog, with its distinctive white-tipped spines, navigates through the foliage with determination, its snout pointed forward. In another scene, the hedgehog continues its journey, now scampering across a wooden deck, its movements quick and agile. The video captures the hedgehog's active nature, showcasing its ability to navigate various terrains with ease, all under the cover of night, as indicated by the dimly lit surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2965
|
videos/HRA_part2/2965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand is distorted in the video."
}
] |
seed42_2577
|
videos/HRA_part0/2577.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, wearing a dark blue shirt and gray pants, walks purposefully through a modern art gallery, surrounded by large, abstract paintings and sculptures. He pauses to examine a piece closely, his posture attentive and engaged. Continuing his stroll, he passes by minimalist artworks, each occupying its own space within the spacious, well-lit gallery. Finally, he stops before a particularly striking sculpture, tilting his head to study it from different angles, his attire and demeanor contrasting with the avant-garde surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The hands and legs are slightly deformed."
}
] |
seed46_2979
|
videos/HRA_part2/2979.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray suit with a white shirt underneath, stands in an industrial mine setting, gently caressing the rough texture of a mining wall. The scene is lit dramatically, highlighting the contrast between the lawyer's polished appearance and the gritty environment. The lawyer's face expresses a mix of determination and contemplation, while the mine's machinery and tools are visible in the background, emphasizing the unusual context of this legal interaction.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2291
|
videos/HRA_part1/2291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant woman, clad in an elaborate, flowing red dress, dances passionately under the moonlight in a desert landscape, with ancient ruins visible in the distance. A jackal, observing her from a safe distance, is intrigued by the captivating scene. The woman's movements are fluid and expressive, her dress swirling around her as she loses herself in the music that only she can hear. The jackal, sitting calmly, watches with fascination, its silhouette framed by the glow of the full moon, creating a mystical atmosphere in the vast, starlit desert.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a distorted body, head, feet, legs, and arms."
}
] |
seed46_1621
|
videos/HRA_part2/1621.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional lawyer, dressed in a dark gray suit with a light gray shirt and red tie, prepares coffee in a modern kitchen. The lawyer, wearing glasses, carefully measures coffee grounds into a French press, adding hot water from a sleek electric kettle. The scene captures the lawyer's meticulous attention to detail, from pouring the water to stirring the mixture gently. The lawyer then presses down the plunger slowly, ensuring a rich brew, all while surrounded by stainless steel appliances and minimalist design elements, creating a sophisticated atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_1744
|
videos/HRA_part0/1744.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly contrasting scene, a lone hyena stands in the foreground, its silhouette framed against a golden sunset, while in the distance, meticulously aligned rows of lush green vines stretch across the landscape, indicating a vast vineyard. As the camera pans, a luxurious swimming pool comes into view, nestled amidst the vineyard, shimmering under the fading sunlight, offering a surreal juxtaposition of wild and cultivated beauty.]"
},
{
"from": "gpt",
"value": "Bad. The hyena in the video has a twisted body and a distorted face."
}
] |
seed42_1799
|
videos/HRA_part0/1799.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green meadow under a partly cloudy sky, a majestic stag stands tall, its large, expressive eyes gazing into the distance. It shakes its head vigorously, sending droplets of water flying from its fur. The stag, with its impressive antlers and auburn coat, continues to shake itself dry after what seems to have been a refreshing drink from a nearby stream. The rolling hills and scattered trees provide a serene backdrop, emphasizing the beauty and tranquility of nature. As it finishes drying off, the deer looks around, alert and aware, before returning to its peaceful grazing.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1947
|
videos/HRA_part1/1947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two graceful antelopes gently touch noses in a tender caress, surrounded by lush grasses and distant acacia silhouettes. The golden light bathes the scene, highlighting the intricate details of their fur, the tenderness in their eyes, and the delicate interaction, creating a moment of serene connection amid the wild beauty of their habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2844
|
videos/HRA_part2/2844.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, clad in a khaki shirt and beige pants, is seen wiping down an ancient, weathered stone structure at a historical site, with a dingo curiously observing from a distance. The engineer, wearing safety glasses and latex gloves, meticulously cleans the surface using a microfiber cloth, revealing intricate carvings and details. The dingo, standing on the lush grass nearby, watches intently with its ears perked up, adding a touch of wildlife intrigue to the scene. The historical site, featuring crumbling stone walls and archways, is bathed in warm sunlight, casting dramatic shadows and highlighting the textures and history of the location.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, and arms are distorted in the video, as well as the object they are holding. The Australian dingo's head, body, and legs are also distorted."
}
] |
seed44_167
|
videos/HRA_part1/167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, clad in period-specific attire from the late 1800s, including a brown shirt, brown trousers, and brown boots, explores historical sites in a rural setting. He crawls through dense grass to uncover ancient artifacts, revealing a deep interest in history. Against a backdrop of historical ruins, the farmer meticulously examines the site, emphasizing his connection to the land and its past. Throughout, he maintains a focused demeanor, highlighting his dedication to understanding the historical significance of the area.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2938
|
videos/HRA_part1/2938.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, middle-aged nurse with blonde hair tied in a bun, wearing a blue scrub top and black pants, is seen in a small, cluttered kitchen. She's meticulously loading a white ceramic plate into the bottom rack of a stainless steel dishwasher, demonstrating her domestic skills. The kitchen is filled with natural light, casting a warm glow over the room, and the nurse's attention to detail is evident as she carefully arranges the dishes. Despite the busy environment, with pots and pans scattered about, she maintains a sense of calm and order as she performs this household task.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2172
|
videos/HRA_part0/2172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 live clam lying half-open on a bed of damp sand, revealing its intricate interior textures and colors. The clam's exterior is rugged and brownish-black, while the interior showcases a lustrous, pearly surface. The sandy substrate is speckled with small stones and shells, adding to the natural coastal environment. Sunlight filters through the water, casting a soft glow on the scene, highlighting the clam's delicate features and the surrounding grains of sand.]"
},
{
"from": "gpt",
"value": "Normal. The clam's mouth in the video is generated unreasonably, and the body is not generated."
}
] |
seed46_1750
|
videos/HRA_part2/1750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clad in a miniature red cape sprints across the frame, set against the backdrop of an otherworldly landscape featuring two active volcanoes, one spewing a spectacular eruption of lava and ash into the twilight sky. The ferret, displaying a sense of urgency and adventure, runs through this dramatic scene, its path illuminated by the orange glow from the volcanic activity, creating a surreal and captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1740
|
videos/HRA_part1/1740.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a white apron over a black t-shirt and jeans, throws clay on a spinning pottery wheel under the glow of bright studio lights. With intense concentration, they shape the clay into a vase, their hands moving gracefully and purposefully. The camera captures the artist's face, reflecting determination and skill, as they mold the clay. Throughout the process, the artist's attire remains consistent, and the scene is set against a backdrop of a well-lit workshop filled with various pottery tools and finished pieces.]"
},
{
"from": "gpt",
"value": "Bad. No pottery tools were generated."
}
] |
seed46_2824
|
videos/HRA_part2/2824.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and gun holster, leaps over a hurdle set up in a dark matter research facility. The background is filled with high-tech equipment and scientists in lab coats observing the unusual training session. The officer's face is focused, showing determination as they navigate the obstacle course designed to test agility in low-light conditions. The scene highlights the unique intersection of law enforcement training and cutting-edge scientific research.]"
},
{
"from": "gpt",
"value": "Bad. The video shows the officer jumping, with actions that are not continuous and smooth, and there are abrupt changes."
}
] |
seed46_1739
|
videos/HRA_part2/1739.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 deer, with its fur glistening under the sunlight, leaps gracefully over a cash register, which is placed in an unexpected outdoor setting. The animal's movements are fluid and effortless as it clears the register, symbolizing a moment of nature intruding upon the human world. The cash register, typically found indoors, is now situated among lush greenery, with the deer's leap adding an element of surprise and magic to the encounter.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1535
|
videos/HRA_part1/1535.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 farmer, wearing a red plaid shirt and blue jeans, tenderly bathes a muddy dog outside on a sunny day, using a white hose with a red nozzle. The farmer, with a warm smile and caring hands, rinses the dog with water from the hose, as the playful animal stands on its hind legs, paws resting on the farmer's knee, enjoying the attention. The scene is set against a backdrop of lush green fields and a clear blue sky, with the farmer's weathered barn in the distance, creating a heartwarming rural atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The farmer's warm smile was not generated."
}
] |
seed42_2871
|
videos/HRA_part0/2871.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 upscale restaurant, a waiter, dressed in a black suit with a white shirt, black tie, and a pocket square, gently caresses a small, live vole on a pristine white tablecloth. The scene is set against a backdrop of expensive cutlery, crystal glasses, and fine china. The waiter's facial expression conveys a sense of care and tenderness, while the vole appears calm and unafraid. The room is softly lit, casting warm shadows on the walls adorned with elegant paintings and tapestries. This unusual interaction unfolds in slow motion, capturing every detail of the waiter's delicate touch and the vole's relaxed demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The waiter's hand is distorted and deformed in the video, the hamster is generated abnormally, and the tableware is also generated abnormally."
}
] |
seed46_207
|
videos/HRA_part2/207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 zero gravity, a whimsical scene unfolds where a small, brown porcupine floats, performing a delightful dance. It gracefully pirouettes against a backdrop of stars and the vast cosmos, its quills gently swaying in the absence of gravity. The porcupine then leaps playfully, executing mid-air flips and twists with an infectious joy, its quills shimmering under celestial lights. Throughout the dance, the porcupine's movements are fluid and weightless, embodying the freedom and fun of dancing in space, all captured in stunning high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The porcupine generation in the video is abnormal."
}
] |
seed46_1512
|
videos/HRA_part2/1512.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dynamic montage begins with a charismatic musician wearing a space-themed outfit, strumming an electric guitar under the glow of neon lights, surrounded by cosmic visuals. The scene shifts to a historic moon landing, featuring a space-suited astronaut planting a flag on the lunar surface, with the Earth visible in the distance. Lastly, we see a determined athlete sprinting across a track, the focus on their powerful legs and the intensity in their eyes, pushing towards the finish line against a backdrop of cheering spectators. Each scene is seamlessly connected through a thematic thread of human achievement and exploration.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_1994
|
videos/HRA_part0/1994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A compassionate, middle-aged female nurse sits on a wooden chair in a cozy, softly lit room, wearing a light blue scrubs top and black pants. She crochets a vibrant, multicolored blanket with yellow, orange, and red hues, her hands moving skillfully as she focuses on her craft. The room is filled with the warm glow of a standing lamp, casting a gentle light on the scene. Behind her, a large window reveals a lush, green outdoor landscape, providing a serene backdrop for her meditative activity.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
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 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 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": "Good. Basically correct."
}
] |
seed46_1378
|
videos/HRA_part2/1378.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged woman with curly brown hair tied in a ponytail engages in gardening activities on a bright, sunny day. She wears a straw hat, a yellow sleeveless top, and green gardening gloves. Her face is turned towards the sun, revealing a joyful smile as she tends to the plants. The garden is lush and colorful, filled with various flowers and greenery. In one scene, she carefully waters the plants using a green watering can, her actions gentle and nurturing. Throughout the video, her expressions convey a sense of peace and satisfaction, encapsulating the therapeutic nature of gardening.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_192
|
videos/HRA_part1/192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, wearing a yellow helmet, a white tank top, blue jeans, and brown work boots, pauses from his labor to stand on a sandy beach, the serene ocean stretching behind him. He takes a moment to enjoy the view before energetically diving into the clear blue water, his clothes still on, embracing the refreshing swim. Underwater, he opens his eyes, revealing his blue goggles, as he swims with purpose, surrounded by the vivid marine life and the bright sunlight filtering through the surface. Afterward, he emerges from the sea, dripping wet, and walks back to his work site, leaving wet footprints on the sand, embodying a break well taken.]"
},
{
"from": "gpt",
"value": "Bad. The face, hands, and feet of the worker in the video have generation issues."
}
] |
seed46_1808
|
videos/HRA_part2/1808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small gerbil, with a brown and white coat, leaps energetically from one wooden platform to another within its cage, demonstrating agility and speed. The rodent lands on a branch, its furry tail swaying, before it jumps again, this time onto a spinning wheel. It pauses for a brief moment, standing upright on the wheel with its front paws raised, before continuing to jump and explore its habitat. Throughout the scene, the gerbil's movements are captured in high detail, highlighting its playful nature and lively spirit.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's paws in the video are generated abnormally, with distorted limbs and paws in the middle frames, sometimes disappearing or appearing suddenly."
}
] |
seed46_1517
|
videos/HRA_part2/1517.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charming hedgehog, adorned with a miniature top hat and a tiny bow tie, pirouettes gracefully on a wooden stage under the glow of a spotlight. The hedgehog's expressive eyes sparkle with joy as it twirls, its quills gently swaying to an unheard melody. The backdrop features a painted night sky, complete with twinkling stars and a crescent moon, adding a whimsical touch to the scene. The hedgehog continues its delightful dance, captivating the audience with its unexpected grace and charm, all set against the enchanting night sky.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's limbs in the video are not fully generated, and the body is generated unreasonably."
}
] |
seed44_1818
|
videos/HRA_part1/1818.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant botanical garden, a middle-aged janitor, wearing a green vest over a blue collared shirt and tan pants, gently caresses a camel. The scene opens with the janitor standing near a wooden fence, holding a leaf blower, before focusing on him tenderly touching the camel's nose. The setting shifts to the janitor embracing the camel's head, conveying a sense of affection and care. Lastly, he is seen feeding the camel from his hand, surrounded by the vibrant greenery of the botanical garden, creating a harmonious and unexpected connection between man and animal in a serene environment.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the cleaner holding a leaf blower."
}
] |
seed46_1816
|
videos/HRA_part2/1816.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist wearing a blue denim jacket and black cap, holding a paintbrush in his right hand, walks alongside a large elephant with intricate, colorful patterns painted on its body. Both the artist and the elephant stroll through a lush, green landscape filled with tall trees and vibrant vegetation. The elephant carries a canvas on its back, and the artist occasionally glances at it as they walk together in harmony. They are surrounded by the natural beauty of the environment, which complements the vivid artwork on the elephant's skin.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_121
|
videos/HRA_part1/121.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene indoor scene opens with a close-up of a calm, gray tabby cat sitting on a wooden floor next to a white wall. The cat, adorned with a blue collar, gazes intently at the camera. Suddenly, a human hand enters the frame from above, gently stroking the cat's head, evoking a relaxed response. The camera then captures the affectionate interaction from various angles, showcasing the cat's contentment and the tender touch of the unseen person, all within the cozy confines of a home environment.]"
},
{
"from": "gpt",
"value": "Normal. The person in the video petting the cat is basically normal, but there are slightly uncoordinated movements."
}
] |
seed44_1025
|
videos/HRA_part1/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Bad. The flying action is deformed; the wings are moving, but the bird's body is not."
}
] |
seed46_2472
|
videos/HRA_part2/2472.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, donning a chef's uniform comprised of a white double-breasted jacket and a black and white checkered apron, is seen rock climbing on a sunny day. He confidently grasps the rocks, displaying strength and determination, while his outfit, complete with a black cap, adds a unique twist to the typical rock climber's attire. The clear blue sky and lush greenery surrounding him provide a striking contrast to his chef's garb, making for an unexpected yet captivating scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1828
|
videos/HRA_part1/1828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature woman with graying hair, wearing a white blouse and glasses, meticulously irons clothes in a well-lit room. She starts by carefully smoothing out a white shirt with a hot iron, steam rising gently. Then, she moves on to press a pair of khaki pants, folding them neatly over the ironing board. Throughout, she maintains a focused demeanor, her glasses catching the light as she works diligently, the steam from the iron creating a serene, domestic atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands in the video are distorted."
}
] |
seed46_1051
|
videos/HRA_part2/1051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male grouse, distinguished by its dark brown feathers and a distinctive red wattle above the eyes, stands prominently on a fallen tree in the middle of a dense, green forest. The bird's posture is alert, its head held high, indicating readiness for flight or fight. The forest surroundings are lush and verdant, with sunlight filtering through the canopy, highlighting the grouse's textured plumage. The setting is peaceful, with no visible disturbances, allowing the grouse to maintain its dominant position on the log, a symbol of its territorial claim within the woodland habitat.]"
},
{
"from": "gpt",
"value": "Bad. The capercaillie in the video has a deformed head and twisted claws."
}
] |
seed46_101
|
videos/HRA_part2/101.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A starling perches on a branch, its iridescent feathers shimmering in shades of green and purple under the bright sunlight. The bird's eyes are alert, scanning the surroundings with curiosity. Its beak is slightly open, ready to emit a burst of song. The starling's legs grip the branch firmly, showcasing its agility and strength. In the background, lush green foliage provides a serene setting for this captivating display of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1356
|
videos/HRA_part1/1356.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 iridescent, hovers in a close-up shot against a blurred background of lush vegetation. Its wings, a blur of motion, propel it as it feeds from a red salvia flower, the curved beak piercing the bloom. The bird's small size, quick movements, and the detailed feathers are highlighted, set against the rich greenery and soft, natural lighting. The scene captures the hummingbird's agility and the delicate interaction between the bird and the flower, encapsulating the beauty of nature in high definition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2541
|
videos/HRA_part1/2541.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, seemingly a teacher, sits at a sewing machine in a homey, cluttered room filled with natural light. She wears a simple white shirt and has short, neatly styled brown hair. The room is decorated with a large painting and a calendar on the wall, adding a personal touch. The teacher deftly operates the sewing machine, carefully hemming a pair of pants, demonstrating her skill and focus on the task at hand.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed42_1127
|
videos/HRA_part0/1127.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate musician, donning a black 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_1617
|
videos/HRA_part0/1617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 engineer, donning a white lab coat over a gray t-shirt and khaki pants, stands in a futuristic, metallic laboratory. Holding a high-tech device, he demonstrates the concept of time dilation, with visual effects distorting the background and a digital clock appearing to slow down. The scene progresses as he uses a cloth to wipe the perspiration from his forehead, emphasizing the intensity and complexity of his scientific endeavor. Throughout, the lab's modern aesthetic and advanced technology underscore the theme of cutting-edge research and experimentation.]"
},
{
"from": "gpt",
"value": "Bad. The digital clock and cloth were not generated; there were issues with the face and hands of the character in the video."
}
] |
seed46_2276
|
videos/HRA_part2/2276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a grey t-shirt, beige shorts, and a cap, is organizing his spacious garage, which features a white ceiling and walls. The garage is filled with various items, including bicycles, a stroller, storage containers, and a large, open shelving unit containing numerous tools and equipment. The doctor methodically arranges these items, creating a neat and orderly space. As he works, he occasionally pauses to examine specific objects, such as a red bicycle, before continuing his task with purpose and precision. Throughout the process, the garage remains well-lit, highlighting the doctor's meticulous efforts to transform the cluttered area into a well-organized and functional space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_120
|
videos/HRA_part2/120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown jacket and khaki pants, stands in a savanna environment, engaged in gently wiping the face of a seated cheetah. The big cat is calm, displaying trust, as it sits on a sandy ground strewn with rocks and twigs. The director's caring action is evident as they tenderly clean the cheetah's face using a soft cloth, all while surrounded by the natural habitat of tall grass and distant trees.]"
},
{
"from": "gpt",
"value": "Normal. The action of the person polishing the leopard in the video is not smooth."
}
] |
seed46_3206
|
videos/HRA_part2/3206.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 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 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": "Normal. The bat's claws are distorted, the face is distorted, the wings are distorted, and the head is distorted."
}
] |
seed42_1556
|
videos/HRA_part0/1556.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [At a bustling city bus stop, a young nurse, wearing a crisp white uniform and a name badge, kneels down on the concrete sidewalk. She's engaged in helping a small child who has fallen and scraped their knee. The nurse gently cleans the wound with an antiseptic wipe, her caring demeanor evident in her soft smile and reassuring words. Around them, the urban environment continues its daily rhythm, with people rushing to catch their buses, cars honking in the distance, and pigeons scavenging for food nearby. Despite the chaos, the nurse creates a moment of calm and compassion at the heart of the city.]"
},
{
"from": "gpt",
"value": "Normal. The nurse's face, the child's hands and legs, and the pigeons are poorly generated in the video."
}
] |
seed42_3134
|
videos/HRA_part0/3134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional lawyer, dressed in a casual yet stylish ensemble of a gray turtleneck sweater and black pants, stands in a modern kitchen with sleek, stainless steel appliances. The individual focuses intently on preparing a gourmet meal, chopping ingredients on a wooden cutting board placed atop a granite countertop. The kitchen is illuminated by recessed ceiling lights, casting a warm glow over the scene. Behind the chef, a large window allows a view of a city skyline at twilight, adding a touch of urban sophistication to the domestic setting. The lawyer's movements are confident and practiced, indicating a comfort in both the courtroom and the culinary arts.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2745
|
videos/HRA_part0/2745.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male chef, wearing a traditional white chef's uniform with a black necktie and a tall toque blanche hat, stands on a small wooden stool. He is in the process of changing a light bulb in a restaurant kitchen, surrounded by stainless steel appliances and shelves stocked with cooking utensils. The kitchen is brightly lit, except for the area where the burnt-out bulb needs replacement. The chef, with a slight smile, carefully unscrews the old light bulb, demonstrating a lighthearted moment in his daily routine amidst the professional culinary environment.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the chef changing a lightbulb."
}
] |
seed44_1446
|
videos/HRA_part1/1446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bee-eater perches regally on a branch, its vibrant plumage a stunning mix of green, blue, and brown feathers, set against a backdrop of lush foliage and clear blue sky. Its long, curved beak points upward, ready to snatch prey from the air. In the next frame, it takes flight, wings outstretched, revealing the striking contrast of its underbelly and the iridescent sheen of its back feathers. It swoops gracefully, capturing an unsuspecting insect in mid-air, before returning to its perch, triumphant, the captured prey visible in its beak, all set against the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2562
|
videos/HRA_part2/2562.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus with a grayish-brown body and long, flexible arms covered in small suckers rests on a rocky seabed. Its arms curl and extend as it explores its surroundings, demonstrating its intelligence and adaptability. The creature's large, curious eyes are visible as it interacts with the environment, showcasing its awareness and engagement. The octopus then changes color to blend in with the rocks, highlighting its remarkable camouflage abilities, all against the backdrop of an underwater world filled with various marine life and plants.]"
},
{
"from": "gpt",
"value": "Normal. The octopus swims basically normally, but there is slight movement disharmony."
}
] |
seed44_1220
|
videos/HRA_part1/1220.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a black baseball cap, black shirt, khaki pants, and black shoes, is shown repairing a vintage bicycle against a backdrop of lush greenery and sunlight filtering through the trees. He is engaged in fixing the bike's chain, showcasing his mechanical skills. In another shot, he carefully inspects the bicycle's frame, his face expressing concentration and expertise. He then tightens a bolt on the bike's wheel, demonstrating his proficiency in bike maintenance. Lastly, he adjusts the bicycle's seat, ensuring it is perfectly aligned, all while surrounded by the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2380
|
videos/HRA_part2/2380.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red beret and a white apron over her colorful outfit, stands in a vibrant laundry room filled with patterned tiles and graffiti art. She smiles as she sorts clothes into a vintage washing machine, her creative spirit evident in the artistic space around her. The room is illuminated by soft, yellow lights hanging from the ceiling, casting a warm glow over the artist's industrious yet joyful task. Surrounded by various paints and brushes on the walls, she pauses to admire a piece of abstract art hanging nearby, before returning to her domestic chore with a renewed sense of purpose.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video are not fully generated, there is a missing part of the arm, and the face is deformed."
}
] |
seed46_2860
|
videos/HRA_part2/2860.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown mouse, with large ears and a long tail, crawls across a wooden surface, its movements quick and cautious. The mouse pauses momentarily, its nose twitching as it sniffs the air, before continuing on its path. The texture of the wood grain is visible beneath the mouse's tiny feet, which grip the surface as it navigates its environment. The scene is captured in high definition, allowing every detail of the mouse's fur and the wooden surface to be seen clearly. The background is a soft, neutral tone, ensuring the focus remains on the mouse as it crawls.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1902
|
videos/HRA_part0/1902.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic child, donning a vibrant yellow shirt and dark blue jeans, is captured in high definition as they dance with uninhibited joy on a wooden stage. The stage is adorned with a colorful backdrop of balloons in various shades of red, green, and blue, creating a festive atmosphere. The child's face is illuminated by stage lights, highlighting their expressions of pure delight. Their energetic movements fill the frame, conveying the infectious spirit of youthful exuberance against the backdrop of the elaborately decorated stage.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2586
|
videos/HRA_part1/2586.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 uniform with a badge and a walkie-talkie attached to his belt, kneels in a zoological park, intently observing a crawling creature. The lush greenery and trees of the park provide a serene backdrop. The officer's focus is directed at a small animal slowly making its way across the ground, highlighting a unique interaction between law enforcement and wildlife in an urban zoo setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2236
|
videos/HRA_part1/2236.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a dingo, wearing swimming goggles and a yellow life vest, playfully swims in a clear, blue pool under a cloudy sky, its joyful demeanor evident. Meanwhile, inside a small wooden cabin nearby, a young male cashier, sporting a red and white striped shirt, attentively handles transactions with a friendly smile, standing behind a counter filled with various snacks and beverages, the cash register visible beside him. The dingo occasionally glances toward the cabin, seemingly curious about the activities of the human cashier, who remains focused on his duties despite the unusual presence of a swimming dingo nearby.]"
},
{
"from": "gpt",
"value": "Bad. The generation of the wild dog's head and the male cashier's hand in the video has issues."
}
] |
seed42_2507
|
videos/HRA_part0/2507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill resembling a sword, swims gracefully through the clear blue waters of the ocean. Its body, a sleek silver hue with a dark blue back, glides effortlessly as it navigates the aquatic environment. Sunlight filters through the water, casting shimmering highlights on the fish's streamlined form. The surrounding marine life, including schools of smaller fish scattering in its presence, underscores the swordfish's dominance in its habitat. Against the vast, open sea, the swordfish embodies power and agility, its unique appearance and behavior captivating the viewer in this underwater scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1186
|
videos/HRA_part0/1186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A magpie perches on a weathered wooden fence post, its distinctive black-and-white plumage gleaming under the soft sunlight. Against a backdrop of lush green foliage and clear blue skies, the bird's eyes sparkle with curiosity. It tilts its head to the side, seemingly observing its surroundings with interest. The vibrant colors of nature serve as a striking contrast to the magpie's striking feathers, highlighting its unique beauty in the serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1957
|
videos/HRA_part1/1957.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vividly lit classroom, a biology teacher, wearing a green button-down shirt and khaki pants, kneels on the floor with a focused gaze. A live lizard, displaying intricate patterns, crawls across the tabletop in front of him. The teacher's hands are positioned ready to guide the creature gently, ensuring its safety during this educational demonstration. Students observe intently from their desks, their faces a mix of fascination and mild concern, as the small lizard explores its temporary environment under the watchful eye of their knowledgeable instructor.]"
},
{
"from": "gpt",
"value": "Bad. The human hands appear deformed and distorted, and the lizards also show deformities."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.