video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed42_2928
|
videos/HRA_part0/2928.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, typically known for its sturdy build and earthy tones, is depicted in an unexpected scenario, engaging in a joyful dance within its natural habitat. The badger, adorned with a red bow tie and a small top hat, moves energetically to an unseen beat, surrounded by lush greenery and under the shade of towering trees. Its dance is characterized by playful twirls and energetic hops, a stark contrast to its usual demeanor, all captured in a whimsical and vibrant scene that highlights the unexpected delight of a dancing badger in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1196
|
videos/HRA_part2/1196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a gray jacket and brown trousers, traverses the lush undergrowth of a temperate rainforest, his canvas and easel in tow. He pauses to study the vibrant mosses and ferns carpeting the forest floor, the emerald green foliage illuminated by dappled sunlight filtering through the dense canopy overhead. As he walks deeper into the rainforest, the artist stops at a serene spot beside a babbling brook, setting up his easel to capture the enchanting scene before him - the interplay of light and shadow, the intricate textures of the ancient trees, and the melodic sounds of nature echoing all around.]"
},
{
"from": "gpt",
"value": "Bad. The body is uncoordinated, and the canvas and easel are flying away from the hands."
}
] |
seed44_1867
|
videos/HRA_part1/1867.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A worker, wearing a khaki safari outfit complete with a vest, pants, and hat, walks alongside a capybara on a leash. They are strolling on a concrete path that winds through a lush, green landscape filled with trees and shrubs. The capybara, the world's largest rodent, is shown in profile, moving at a relaxed pace beside the human. The setting is a serene, outdoor environment, possibly within a zoo or wildlife sanctuary, where the two amble together in a scene that highlights the unique bond between the caretaker and the animal.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are unsmooth."
}
] |
seed44_293
|
videos/HRA_part1/293.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic lion, defying expectations, swims powerfully through a tranquil body of water, its golden coat glistening as it propels itself forward with muscular strokes. Its piercing gaze is fixed ahead, conveying determination and grace in this unusual aquatic setting. The lion's head remains above the waterline, mane billowing softly, while its body undulates beneath the surface, showcasing an unexpected display of strength and agility in the liquid environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2922
|
videos/HRA_part1/2922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up view of a sea urchin reveals its intricate, spiny exterior, showcasing a variety of colors including green, purple, and brown. The spherical creature sits atop a rocky reef, surrounded by a vibrant marine environment teeming with life. Sunlight filters through the water, casting a warm glow on the sea urchin's textured surface, highlighting its natural beauty and resilience in the underwater world. Against the backdrop of the reef, the sea urchin appears both delicate and formidable, a testament to the diversity of oceanic fauna.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1344
|
videos/HRA_part2/1344.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone gray wolf, drenched in water, swims across a serene lake, its eyes fixed ahead with unwavering determination. The wolf's powerful legs propel it forward through the crystal-clear water, while its sleek fur glistens under the soft, diffused sunlight filtering through the overcast sky. The surrounding lush forest provides a verdant contrast to the tranquil body of water, and in the distance, snow-capped mountains rise majestically, completing the breathtaking natural landscape.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the gray wolf with multiple legs, and the mouth is generated slightly larger."
}
] |
seed44_3095
|
videos/HRA_part1/3095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young woman wearing a yellow top and blue jeans is attentively cleaning a large, rectangular fish tank. She is seen smiling while scrubbing the glass with a sponge, ensuring a clear view of the colorful fish and underwater plants inside. The tank is illuminated by overhead lights, highlighting the woman's focused efforts. Her movements are gentle yet thorough, maintaining the aquatic environment's health and beauty. Throughout the process, the fish swim calmly around her, undisturbed by her presence, as she works diligently to keep their home pristine.]"
},
{
"from": "gpt",
"value": "Normal. The woman's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1110
|
videos/HRA_part0/1110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A waiter, clad in a crisp white shirt and black vest, sprints across a vast, barren lunar landscape, the iconic first steps of Neil Armstrong visible in the distance. Dust from the moon's surface billows behind him as he races, his movements fluid and effortless in the low gravity environment. A lunar module sits in the background, a stark contrast to the elegant attire of the sprinting waiter, who carries a silver serving tray in one hand, merging the worlds of fine dining and space exploration in a surreal scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1554
|
videos/HRA_part0/1554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed man, wearing a navy suit with a light blue shirt and a dark blue tie, stands against a neutral gray background. He points to an unseen object or idea with a confident smile, engaging the viewer with his clear, green eyes. His neatly combed brown hair and clean-shaven face add to his professional appearance. The focus is solely on him, with no additional elements in the frame, as he points with his right index finger, inviting the audience to follow his gesture.]"
},
{
"from": "gpt",
"value": "Normal. The character's fingers are distorted."
}
] |
seed44_2989
|
videos/HRA_part1/2989.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen illuminated by neon lights, a chef wearing a sleek, silver uniform and gravity-defying boots stands aboard an anti-gravity vehicle. The vehicle, resembling a levitating platform with intricate, glowing circuitry, hovers above a metallic countertop cluttered with advanced cooking gadgets. The chef, with a focused gaze, wipes a stainless steel utensil with a microfiber cloth, preparing for culinary innovation amidst the backdrop of a high-tech, floating workstation.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1781
|
videos/HRA_part1/1781.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a spacesuit, floats inside a spacecraft orbiting Earth, holding a chimpanzee wearing a matching miniature spacesuit. Both gaze intently at the stunning planet below through the large viewing window. The actor, with a calm expression, gently strokes the chimp's head as they drift weightlessly. Suddenly, the scene changes to the actor and the chimpanzee swimming together in a clear blue pool, surrounded by lush greenery, with the actor wearing swim trunks and the chimp playfully splashing nearby. They both appear happy and carefree in the water, enjoying each other's company in this idyllic setting.]"
},
{
"from": "gpt",
"value": "Bad. The facial and hand generation of the character and the limbs of the chimpanzee in the space scene have issues; the facial and hand generation of the character in the pool scene have issues, and the chimpanzee is not generated."
}
] |
seed42_2640
|
videos/HRA_part0/2640.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a brown coat, black pants, and a white shirt with a tie, walks through a dense forest, his eyes intently scanning the surroundings. As he strides, a small squirrel scurries across the path in front of him, pausing momentarily to look up at the towering figure before continuing on its way, encapsulating a moment of human interaction with nature's tiny inhabitants in a woodland setting.]"
},
{
"from": "gpt",
"value": "Normal. The video clearly shows the director walking, but the movements are not very smooth and continuous."
}
] |
seed44_217
|
videos/HRA_part1/217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer, clad in a dark blue jacket, black tactical pants, and a peaked cap, leaps over a wooden barrier on a heath, demonstrating agility and readiness. The heath is characterized by lush greenery, tall grass, and scattered trees. The officer's action conveys a sense of urgency and physical prowess, with the natural landscape providing a dynamic setting for the scene.]"
},
{
"from": "gpt",
"value": "Bad. The character's walking in the video is very unsmooth, and the movements are uncoordinated."
}
] |
seed42_2614
|
videos/HRA_part0/2614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man with a muscular build, wearing a black tank top and blue jeans, pushes against a large, gray boulder in the middle of a lush forest. His face contorts with effort, highlighting his determination. The scene is set in a dense woodland area, with sunlight filtering through the trees and casting dappled shadows on the ground. The man's strong physique and focused expression convey a sense of strength and perseverance as he exerts himself against the immovable object.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1686
|
videos/HRA_part1/1686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy, baby panda with distinctive black and white fur crawls across a lush, green forest floor, surrounded by vibrant vegetation and bamboo shoots. It moves with a curious, almost playful demeanor, its tiny paws gripping the mossy ground. The scene is filled with natural light filtering through the dense canopy above, casting dappled shadows on the panda as it explores its environment.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the panda in the video are incomplete, and the body proportions are incorrect."
}
] |
seed46_209
|
videos/HRA_part2/209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male musician, donning a white button-down shirt and khaki pants, meticulously dusts a vintage gramophone with a feather duster in a warmly lit, cluttered room filled with musical instruments. His attire includes a brown belt and brown shoes, adding to his polished appearance. The room is decorated with a variety of string instruments hanging from the walls, including violins and cellos, highlighting the musician's passion for music. Throughout the scene, he continues to dust various objects, showcasing his dedication to preserving his cherished belongings, all within the cozy, wood-paneled space.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers and arms are missing in the video, and the facial generation is blurry."
}
] |
seed42_2425
|
videos/HRA_part0/2425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its yellow body and green head, swims gracefully near a coral reef, showcasing its unique features in stunning detail. The fish's eyes, positioned on the left side of its head, are clearly visible, and its beak-like mouth, used for feeding on coral, is prominent. Against a backdrop of colorful corals and underwater plants, the parrotfish's dynamic movements and distinctive appearance stand out, capturing the essence of life beneath the sea. The water around it shimmers with sunlight, adding to the beauty of the scene, as the parrotfish navigates its environment with ease.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1638
|
videos/HRA_part0/1638.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a black vest and bow tie, is seen playfully crawling on his hands and knees across a wooden floor, following a small, adorable hamster. The hamster, enclosed in a clear plastic ball, rolls ahead of him, creating a comical and heartwarming interaction between the two. The setting is a tidy room with a hardwood floor, adding to the charm of this unexpected pairing.]"
},
{
"from": "gpt",
"value": "Bad. The hamster's rolling and the person's crawling movements in the video are very uncoordinated and jerky."
}
] |
seed42_1883
|
videos/HRA_part0/1883.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, donning a dark jacket and distressed jeans, stealthily walks through the dimly lit corridors of a futuristic space prison. His intense gaze is directed ahead, revealing his determination. The harsh, cold lighting accentuates the high-tech, metallic surfaces of the prison environment. As he moves, the camera captures the tension in his body language, hinting at the imminent danger. Despite the oppressive surroundings, the musician's confident stride and unwavering focus suggest a plan in motion, ready to execute his daring escape.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1499
|
videos/HRA_part1/1499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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-themed library, a group of diverse individuals, including a bison cosplayer wearing a full-body brown fur costume, gather for a book club meeting. The cosplayer sits attentively among the members, who are seated on cozy armchairs and couches arranged in a circle. The room features high-tech elements, such as holographic book covers floating above each person, indicating their current reads. The bison cosplayer listens intently, occasionally nodding and gesturing with enthusiasm, while the other members engage in lively discussion about their latest sci-fi novel. In the background, a large window reveals the vastness of outer space, with stars twinkling and galaxies swirling in the distance. Suddenly, the bison cosplayer leaps up and begins to run in place, demonstrating the agility and strength of their chosen animal, much to the amusement of the other book club members.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2749
|
videos/HRA_part0/2749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown pelican with a large, distinctive orange pouch flies low over the surface of a calm bay, its wings spread wide against the vivid blue sky. It gracefully swoops down, diving into the water to catch fish, its body momentarily submerged before it resurfaces, triumphant. The pelican then floats on the water, preening its feathers with a meticulous beak, showcasing its survival skills in the serene coastal environment. Against the backdrop of a clear sky and calm waters, the pelican's flight and feeding habits are highlighted, emphasizing its unique features and behaviors in the wild.]"
},
{
"from": "gpt",
"value": "Bad. The pelican in the video has twisted wings, a twisted body, and a twisted head."
}
] |
seed42_2794
|
videos/HRA_part0/2794.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique and captivating scene, a small brown bat, identified as a Mexican free-tailed bat, swims across a body of water, its wings functioning as paddles. This unexpected sight unfolds against the backdrop of a calm lake, with lush greenery visible in the background. The bat's swimming action is emphasized, showcasing its survival instinct and adaptability in an unfamiliar environment. The video captures this rare moment in high definition, highlighting the bat's struggle and determination as it navigates the water.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_3064
|
videos/HRA_part1/3064.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, middle-aged male doctor stands in a well-lit hospital corridor, wearing a stethoscope around his neck and a white lab coat over a crisp, button-down shirt and slacks. He holds a clipboard in his right hand, reviewing patient records intently. Behind him, the hallway is bustling with medical personnel and equipment, conveying the busy atmosphere of a healthcare facility. The scene captures the essence of a dedicated healthcare professional in the midst of his duties, surrounded by the sights and sounds of a working hospital.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2933
|
videos/HRA_part2/2933.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 legs appear deformed, and both hands are also deformed; the broom in hand suddenly disappears, and the person's face is blurry and distorted. The rabbit also undergoes a sudden mutation and deformity."
}
] |
seed42_1273
|
videos/HRA_part0/1273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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-looking teacher, wearing a gray blazer over a gray shirt, stands against the backdrop of a Martian sunset, characterized by its dusty, pinkish hue. The teacher is wiping the surface of a scientific instrument, possibly a rover component, with a cloth, highlighting the careful preparation for exploration. The setting showcases the unique beauty of a sunset on Mars, with its characteristic colors and textures, providing a captivating contrast to the familiar figure of the teacher engaged in an unfamiliar task on another planet.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2623
|
videos/HRA_part1/2623.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vastness of space, two astronauts clad in advanced EVA suits, adorned with NASA logos, meticulously perform repairs on the International Space Station, crawling along the exterior with focused determination. Sunlight glints off their helmet visors, highlighting their concentration, as they carry out their critical tasks against the backdrop of Earth's horizon, showcasing the isolation and gravity of their mission.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2210
|
videos/HRA_part2/2210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 innovative engineer, adorned in a spacesuit and helmet, stands on the lunar surface, illuminated by the Earth's glow, holding a leash attached to a lion. The lion, also wearing a miniature spacesuit and helmet, jumps playfully in the low gravity environment. Both figures cast long shadows against the moon's dusty terrain, with the Earth shining brightly in the dark, star-studded sky. This surreal scene combines elements of space exploration, wildlife, and human ingenuity in a single captivating frame.]"
},
{
"from": "gpt",
"value": "Bad. The lion's movements in the video are not smooth."
}
] |
seed46_329
|
videos/HRA_part2/329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fluffy, yellow chick with a small, red beak is seen crawling across a surface covered in hay, its tiny feet moving steadily as it explores its surroundings. The chick pauses momentarily, looking around with bright eyes, before continuing its crawl. The camera captures the chick from various angles, highlighting its downy feathers and the texture of the hay beneath it. Throughout the video, the chick remains the central focus, its curious movements and adorable appearance captivating the viewer's attention.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2230
|
videos/HRA_part1/2230.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green forest setting, a pair of beavers are seen intimately caressing each other, their brown fur glistening with moisture from the nearby river. The male beaver gently touches the female's face with his forepaw, a tender gesture of affection. They are surrounded by tall trees and vegetation, providing a natural and peaceful environment for their interaction. The female beaver responds with a soft look, her whiskers moving slightly as she nuzzles closer to him. This heartwarming scene captures the emotional bond between these two creatures, highlighting the beauty of wildlife relationships.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2348
|
videos/HRA_part1/2348.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in traditional African garb, comprised of a tan shirt, green shorts, and brown sandals, performs an impressive jump over a prone hyena in the middle of a sandy desert. The hyena, positioned on the ground with its head turned toward the man, exhibits a relaxed demeanor. The man's leap is captured mid-air, showcasing his athletic prowess against the stark, arid landscape, with distant mountains providing a scenic backdrop. The scene conveys a sense of adventure and cultural intrigue, highlighting the unique interaction between human and wildlife in a dramatic, yet peaceful, encounter.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2205
|
videos/HRA_part2/2205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a yellow sports bra, black leggings, and white running shoes, runs past a series of modern apartment complexes. She has a focused look on her face, her brown hair tied back in a ponytail, and wears a small backpack. The apartments feature large windows, balconies with plants, and are painted in shades of blue and green. The scene is set in the late afternoon, with the sun casting long shadows and highlighting the architectural details of the buildings. In the distance, lush trees provide a natural contrast to the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs are missing, and her face is deformed."
}
] |
seed46_1063
|
videos/HRA_part2/1063.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a bobcat, recognizable by its short tail and tufted ears, dashes across the frame, passing by an automated checkout machine in a minimally designed convenience store. The animal's panicked sprint is juxtaposed against the sterile environment of the store, where the self-checkout machine stands idle. The bobcat's unexpected intrusion adds an element of chaos to the otherwise mundane setting, creating a surreal moment captured in high definition.]"
},
{
"from": "gpt",
"value": "Normal. The cat in the video is not a short-tailed cat."
}
] |
seed44_2427
|
videos/HRA_part1/2427.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dons a spacesuit and helmet, adorned with vibrant colors and patterns, resembling a solar sail, as they crawl across a barren lunar landscape, backlit by the Earth's glow. The suit, with its reflective, sail-like design, catches the sunlight, creating mesmerizing reflections and shadows. The artist moves slowly, emphasizing the suit's unique texture and the dramatic contrast between the suit and the moon's surface. This artistic portrayal on the moon's surface, with the distant Earth providing a serene backdrop, highlights the intersection of art and space exploration.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2896
|
videos/HRA_part2/2896.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, two people, a male and a female, are shown gently caressing a baby rhinoceros in a natural habitat, surrounded by lush greenery. The couple, both wearing khaki safari gear, including shirts, pants, and hats, interact tenderly with the young rhino, which is standing on sandy soil. The man strokes the rhino's back while the woman looks on, both expressing deep affection and care for the animal. The setting, with its vibrant vegetation and clear blue sky, adds to the peaceful and nurturing atmosphere of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2863
|
videos/HRA_part1/2863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college-aged student, wearing swimming trunks and a snorkel mask, playfully interacts with a gorilla, which is also wearing swimming gear, including swim trunks and goggles, as they splash around in a large outdoor pool. The gorilla, standing upright, reaches its arm out toward the student, who is seen from the waist up, submerged in the water. The scene is set against a backdrop of lush greenery and trees, creating a whimsical and unexpected atmosphere. The student and the gorilla are both engaged in a lighthearted game, enjoying each other's company in the water, with the gorilla's human-like posture adding a touch of surrealism to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The student's head, the gorilla's facial features, and claws were generated with issues in the video."
}
] |
seed42_1452
|
videos/HRA_part0/1452.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant, imaginative scene, a woman with a pixie haircut, dressed in a NASA astronaut suit, interacts playfully with a capuchin monkey wearing a matching miniature spacesuit, both standing inside a futuristic space education center. The room is filled with interactive displays and holographic projections, creating an immersive learning environment. Moments later, they are seen together in an indoor pool, designed to simulate zero-gravity conditions, where the woman and the monkey float effortlessly in their spacesuits, highlighting the unique experience of swimming in a space-themed educational facility.]"
},
{
"from": "gpt",
"value": "Bad. The woman's body is deformed. The arm is malformed. The squirrel monkey is missing a leg."
}
] |
seed42_2323
|
videos/HRA_part0/2323.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by his gray lab coat over a casual button-up shirt and jeans, gently bathes a small, fluffy white dog in an elevated washbasin typically used for washing cars. The scene is set outdoors, with the dog standing on its hind legs, paws on the basin's edge, and the engineer tenderly pouring water over its head from a white jug. The engineer's caring demeanor contrasts with his professional attire, creating a heartwarming image of an unexpected task being performed with love and care.]"
},
{
"from": "gpt",
"value": "Bad. The hands of the person in the video are distorted, the dog's legs are twisted, and the face is slightly distorted."
}
] |
seed42_2190
|
videos/HRA_part0/2190.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a brown beret and glasses, sits in a dimly lit studio filled with art supplies and paintings, engrossed in reading a book about art history. The camera captures the artist's hands turning the pages, revealing colorful illustrations of famous artworks. In another shot, the artist is seen from behind, sitting in front of a large canvas with paintbrushes in hand, contemplating the next stroke while a book on art techniques lies open nearby. Throughout the video, the artist's passion for both creating and studying art is evident in the careful attention given to both the book and the canvas.]"
},
{
"from": "gpt",
"value": "Bad. The artist's hand appears deformed."
}
] |
seed46_2279
|
videos/HRA_part2/2279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, clad in a brown jacket, beige trousers, and a wide-brimmed hat, dances jovially in a mountainous landscape, the distant peaks shrouded in mist. A deer, with a full rack of antlers and a curious gaze, watches him from the edge of a lush forest. The farmer's movements are lively and carefree, his arms raised in the air, as if celebrating the beauty of nature that surrounds him. The deer, sensing no threat, cautiously approaches, its ears perked, adding a touch of whimsy to the scene. The mountains loom majestically in the background, their slopes dotted with trees and patches of greenery, providing a stunning natural backdrop to this unexpected dance.]"
},
{
"from": "gpt",
"value": "Bad. The dance moves are not continuous, there are sudden changes."
}
] |
seed46_2973
|
videos/HRA_part2/2973.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quiet suburban neighborhood, two young boys stand side by side, wearing casual clothes; one in a gray t-shirt and denim shorts, the other in a red shirt and khaki shorts. They are positioned against a backdrop of a white-painted wooden fence, with lush green bushes visible beyond. The boy in gray has his left foot raised, while the other boy leans forward, both engaged in a playful interaction. Their stance and attire are typical of summertime leisure, capturing a candid moment of childhood camaraderie against a backdrop of a sunny day.]"
},
{
"from": "gpt",
"value": "Bad. The little boy's movements in the video are not smooth."
}
] |
seed42_2950
|
videos/HRA_part0/2950.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A tiny warbler perches on a thin branch, its vibrant yellow-green plumage contrasting beautifully against the lush green foliage of the forest. The bird, no bigger than a sparrow, displays its distinctive black facial markings and streaks, enhancing its charm. It tilts its head curiously, revealing its sharp, pointed beak, perfectly adapted for probing into bark crevices and catching insects. The warbler then flutters its wings, preparing to leap onto another branch, showcasing its agility and grace in the dappled sunlight filtering through the leaves above.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer 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": "Good. Basically correct."
}
] |
seed42_2641
|
videos/HRA_part0/2641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a waiter wearing a black apron over a white shirt is diligently wiping tables outdoors, where various shops with colorful awnings line the street. A friendly-looking golden retriever dog, possibly the waiter's pet, sits attentively nearby, watching him work. The atmosphere is lively, with passersby and the sounds of city life in the background, creating a dynamic and engaging environment. The waiter's focused expression and the dog's patient demeanor add a touch of warmth to the urban setting.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2054
|
videos/HRA_part0/2054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 holding a fire hose, is seen wiping the nose of a meerkat standing on its hind legs, both against a backdrop of a controlled fire burning in a contained area. The firefighter wears a yellow fire-resistant suit, a black helmet, and gloves, while kneeling to gently wipe the meerkat's face with a cloth. The meerkat, curious and seemingly unbothered by the flames in the background, stands upright as the firefighter tends to it, creating an unusual yet touching interaction between the two.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's hand, meerkat's head, and paws were generated incorrectly in the video."
}
] |
seed42_2885
|
videos/HRA_part0/2885.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged lawyer, dressed in a gray suit, white shirt, and blue tie, walks purposefully across a futuristic asteroid mining facility. The setting is a large, circular room with a high ceiling and industrial equipment, bathed in a warm orange glow. He carries a brown leather briefcase in his right hand, displaying a confident and focused demeanor. Behind him, the dimly lit interior of the asteroid can be seen, with mining machinery and workers in protective gear visible in the distance. The lawyer's strides are firm and decisive, highlighting his determination and professionalism in this unique and challenging environment.]"
},
{
"from": "gpt",
"value": "Normal. The lawyer's eyes in the video are generated inconsistently, and the hands and feet are deformed."
}
] |
seed42_106
|
videos/HRA_part0/106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and stethoscope, stands in a lush green forest. A small mongoose, known for its agility, leaps playfully from the doctor's right shoulder to a branch above, capturing the essence of unexpected interactions in nature. The doctor looks on with a mix of surprise and delight, highlighting the unique connection between humans and wildlife. The vibrant green foliage and dappled sunlight create a serene atmosphere, emphasizing the peaceful coexistence between the medical professional and the nimble creature.]"
},
{
"from": "gpt",
"value": "Bad. No generation of the doctor's surprised and delighted expression, and the mongoose's jumping from the doctor's right shoulder to the branch above."
}
] |
seed44_175
|
videos/HRA_part1/175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 medical facility, a man wearing a clean, white lab coat and blue surgical mask diligently wipes down advanced, high-tech equipment with precision and care. The room is illuminated by soft, ambient lighting, highlighting the sterile environment. The man's focused gaze and meticulous movements convey a sense of professionalism and dedication to maintaining the cleanliness of the facility. Around him, the walls are lined with monitors and medical devices, emphasizing the cutting-edge technology used in this extraterrestrial healthcare setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's eye generation in the video is problematic."
}
] |
seed42_186
|
videos/HRA_part0/186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of cheerful children, ranging from toddlers to preteens, are engaged in the task of cleaning windows on a bright, sunny day. They wear casual clothes, including t-shirts, shorts, and sneakers, and sport various hairstyles, from pigtails to afros. The kids use squeegees and rags to wipe down the glass, leaving streaks of water and soap behind. They work together, laughing and chatting, as they tackle the large window panes of a suburban home, with lush greenery visible through the transparent surfaces. The atmosphere is one of teamwork and fun, with the youngsters taking pride in their chores under the warm glow of the sun.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1214
|
videos/HRA_part2/1214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a hedgehog, adorned with miniature headphones and a tiny guitar strapped to its back, embarks on an adventurous journey across a lush, green backyard. It navigates through grassy terrains, darting between vibrant flowers and undergrowth with a sense of purpose. The hedgehog's spines glisten under the golden sunlight, adding a touch of magic to the scene. As it runs, the camera captures the hedgehog from various angles, highlighting its determination and the enchanting world it inhabits. The setting is reminiscent of a fairy tale garden, complete with a wooden fence in the background, framing the hedgehog's spirited escapade.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed46_1091
|
videos/HRA_part2/1091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space-themed wedding set against a cosmic backdrop filled with stars and galaxies, a charming hedgehog, adorned with a tiny top hat and bow tie, serves as the ring bearer. The ceremony takes place on a floating platform amidst a zero-gravity environment. During the reception, the hedgehog enjoys a unique swimming experience in a clear, spherical water tank, effortlessly paddling with its limbs while maintaining its adorable appearance, all while the celebration continues around it.]"
},
{
"from": "gpt",
"value": "Bad. The hedgehog's swimming movements in the video are not smooth, and the limb proportions are not well-coordinated."
}
] |
seed42_1410
|
videos/HRA_part0/1410.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student wearing a green jacket and khaki pants explores a lush rainforest, observing a koala as it clings to a eucalyptus branch. Moments later, the student leaps over a small stream, demonstrating agility and enthusiasm for nature. Then, the koala is seen jumping from branch to branch, its plush fur glistening with dew, highlighting the playful nature of these marsupials in their natural habitat. Finally, the student sits on a mossy log, watching the koala munch on eucalyptus leaves, capturing the serene beauty of the rainforest and the peaceful coexistence between humans and wildlife.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1787
|
videos/HRA_part0/1787.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, donning a brown vest and khaki trousers, races through lush, green vineyards, his expression one of determination. He is followed closely by a prehistoric mammoth, its massive body and shaggy fur moving surprisingly swiftly through the rows of grapevines. The sun, low in the sky, casts long shadows across the fertile landscape, highlighting the unusual pair as they navigate the terraced fields. In the background, a rustic barn and rolling hills provide a classic countryside setting, contrasting with the extraordinary sight of the farmer and the mammoth in motion.]"
},
{
"from": "gpt",
"value": "Normal. The face and hands of the character in the video have generation issues."
}
] |
seed42_2924
|
videos/HRA_part0/2924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a meerkat in his facial features and movements, walks through a temperate deciduous forest, wearing a casual outfit consisting of a brown jacket, gray shirt, and khaki pants. He moves through the lush greenery, surrounded by tall trees with leaves varying from deep green to shades of yellow and orange, indicative of the changing seasons. The forest floor is covered in a carpet of fallen leaves, creating a picturesque autumn scene. As he walks, the sunlight filters through the canopy, casting dappled light on the ground, highlighting the natural beauty of the environment.]"
},
{
"from": "gpt",
"value": "Normal. The actor's walking in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed44_2096
|
videos/HRA_part1/2096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green valley, two children, a boy and a girl, both wearing vibrant red raincoats and boots, playfully crawl on their hands and knees, exploring the rich foliage. Suddenly, they pause in awe as a majestic moose, adorned with a full rack of antlers, emerges from the mist, standing tall and still. The scene captures the magical moment when the children and the moose share a silent connection, surrounded by the beauty of nature. The children's wide-eyed wonder and the moose's calm presence create a captivating contrast, all set against the backdrop of the verdant valley.]"
},
{
"from": "gpt",
"value": "Bad. The faces and limbs of the characters in the video are distorted, including the face and legs of the moose."
}
] |
seed44_1730
|
videos/HRA_part1/1730.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, wearing a brown shirt and glasses, is seen in a unique scenario, engaging with a hyena at a public swimming pool. The director, standing at the edge of the pool, interacts with the wild animal, which is swimming in the water, creating an extraordinary juxtaposition of human and beast in an unexpected urban setting. The director's attire, complete with brown shirt and glasses, contrasts with the untamed presence of the swimming hyena, capturing a surreal and captivating moment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1915
|
videos/HRA_part0/1915.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A space-suited worker, complete with helmet and backpack, sits inside a lunar buggy, which is a small rover designed for moon exploration. The vehicle is adorned with various equipment and tools necessary for extraterrestrial missions. The worker is engaged in wiping down the interior surfaces of the buggy, ensuring cleanliness in the zero-gravity environment. The action takes place against the stark, desolate backdrop of the lunar landscape, with the Earth visible as a brilliant blue orb in the distance, providing a dramatic contrast to the monochrome moon surface.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's arm and hand appear deformed."
}
] |
seed46_3201
|
videos/HRA_part2/3201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, attired in a red jacket and black leggings, runs across a barren desert landscape, with a lone coyote mirroring her movements at a distance. The woman's clothes flap in the wind as she sprints, her eyes fixed ahead, determined. Meanwhile, the coyote, its sandy fur blending with the surroundings, lopes alongside, its gaze following the woman's every stride. The two continue their parallel race, the woman's red jacket and the coyote's silhouette stark against the vast, sandy terrain, under a wide, cloud-dotted sky.]"
},
{
"from": "gpt",
"value": "Bad. Actions are not continuous, there are sudden changes."
}
] |
seed44_2269
|
videos/HRA_part1/2269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, smiling cashier, wearing a brown apron over a gray shirt and black pants, meticulously dusts antique wooden furniture inside a vintage shop, highlighted by warm, golden sunlight streaming through the windows. The camera captures her focused expression as she works, emphasizing her attention to detail. Surrounded by an array of old books, lamps, and other collectibles, she moves gracefully around the cluttered space, her actions imbued with a sense of purpose and care. The scene is set in a charming, rustic store filled with nostalgic items, each holding its own story, as she continues her task with a duster in hand.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed46_2679
|
videos/HRA_part2/2679.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a man wearing a spacesuit and holding a large cosmic cloth wipes across the icy, rocky surface of Saturn's rings, set against the vastness of space with stars twinkling in the distance. The man, with a determined expression, is shown from different angles as he meticulously cleans the ring material, creating a stark contrast between the mundane act of cleaning and the extraordinary setting of space. Throughout the sequence, the majestic planet Saturn looms large in the background, its distinct rings partially obscured by the man's cleaning efforts, adding a touch of whimsy to the otherwise serious task.]"
},
{
"from": "gpt",
"value": "Bad. The man's action of wiping the rock with a cloth in the video is discontinuous and has sudden changes."
}
] |
seed46_2474
|
videos/HRA_part2/2474.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, clad in a black outfit with a leather jacket, walks down a dimly lit street at night, a guitar case in hand, as a lizard scurries across the cobblestones beside him. The scene is set under the glow of a single streetlamp, casting long shadows and highlighting the textured walls of the surrounding buildings. The musician, with tousled dark hair and a determined look, strides purposefully forward, while the agile lizard, with its distinctive green and brown scales, moves swiftly alongside, both seemingly on a mysterious journey through the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate the musician with leather jackets and guitar cases, and did not generate long shadows."
}
] |
seed44_3120
|
videos/HRA_part1/3120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, donning a brown bear costume, complete with furry details and a snout, finds himself on a vast, cosmic stage set against the majestic backdrop of Saturn and its intricate ring system, clearly visible in the distance. Under the celestial lights, he begins to dance gracefully, his movements animated and lively, creating a surreal and whimsical scene that juxtaposes the grandeur of space with the playful nature of his attire. The detailed rings of Saturn, comprised of countless ice particles, shimmer in the background, providing a stunning contrast to the earthy tones of the bear suit. Throughout the dance, the man's expressive body language conveys a sense of joy and freedom, inviting the viewer to join in this otherworldly celebration.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1363
|
videos/HRA_part0/1363.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling hospital corridor, a seasoned doctor wearing a white coat and stethoscope around his neck deftly catches a medical file tossed to him by a passing colleague. The walls are painted a calming blue, and the floor is a clean, shiny tile. The doctor, with a confident smile, acknowledges the gesture before continuing on his way, underscoring the seamless teamwork and expertise in a high-stakes environment. The scene captures the essence of medical professionals working together efficiently amidst the challenges of a healthcare setting.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hands and medical documents are distorted."
}
] |
seed46_1012
|
videos/HRA_part2/1012.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter dressed in a crisp white shirt and black trousers finds himself in an unexpected dance-off with a mischievous monkey. The two are surrounded by an array of exotic plants and flowers, giving the impression of a lush garden or jungle setting. The waiter, maintaining a professional demeanor despite the oddity of the situation, gracefully moves to an unseen rhythm, while the monkey, dressed in a miniature tuxedo, gleefully mimics his every step. The playful exchange is captured in high definition, with vibrant colors and dynamic movements, creating a surreal yet captivating spectacle.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_124
|
videos/HRA_part2/124.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man with glasses and a neat beard sits at a wooden desk, intensely pushing letters on a vintage typewriter, surrounded by piles of books and papers. The room is dimly lit by a standing lamp, casting shadows that emphasize his focused expression. Wearing a green military-style jacket, he leans forward, completely absorbed in his work, as if battling to translate his thoughts into words. The cluttered environment reflects his creative process, with the typewriter positioned center-stage, highlighting the act of writing as both a physical and mental endeavor.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_2528
|
videos/HRA_part0/2528.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 powerful kangaroo, exhibiting strength and agility, sprints across a vast, arid landscape under a clear blue sky. Its muscular legs propel it forward in a series of bounding leaps, while its long, thick tail acts as a perfect counterbalance. The kangaroo's fur, a rich sandy brown, blends harmoniously with the earthy tones of the terrain, dotted with sparse vegetation. As it runs, its ears perk up, alert and attentive, showcasing the grace and endurance of this iconic marsupial in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_3017
|
videos/HRA_part0/3017.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 high-tech kitchen illuminated by neon lights, a chef dressed in a white apron and cap, wearing a gas mask, carefully handles a container of antimatter, its energy subtly pulsing within a secure, futuristic device. The chef, displaying remarkable courage, begins to run through the sleek, metallic corridors of a vast space station, the antimatter safely secured in a specialized briefcase designed to withstand extreme conditions. With each stride, the urgency of the situation becomes palpable, the chef's determination evident in the focused gaze beneath the mask, as they navigate the complex towards an unknown destination.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the chef's movements when operating the antimatter container are clearly visible, but they are not continuous and smooth, showing some inconsistency."
}
] |
seed42_316
|
videos/HRA_part0/316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black beret, glasses, and a gray beard, is seen mopping the floor of a large, empty room with high ceilings and a wooden floor, while carrying a guitar on his back. The room is illuminated by soft, ambient lighting, casting a warm glow over the space. The musician, with his distinctive hat, glasses, and gray facial hair, exhibits a sense of dedication as he performs the mundane task of cleaning, accompanied by his trusty instrument. Despite the ordinary activity, his attire and the presence of the guitar hint at his artistic identity.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1291
|
videos/HRA_part0/1291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a dark uniform with a badge, is seen swimming in a large, outdoor pool with a rhinoceros nearby. The setting is a spacious enclosure with lush greenery, reminiscent of a wildlife sanctuary. The officer, wearing sunglasses and a cap, is shown diving into the water, while the rhinoceros, sporting a police-themed saddle, looks on from the edge of the pool. In another scene, the officer is playfully splashing water with the rhinoceros, both enjoying a moment of leisure under the clear blue sky. The final shot captures the officer and the rhinoceros exiting the pool together, the officer patting the rhino affectionately, highlighting an unusual yet heartwarming bond between law enforcement and wildlife.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros's head and the police officer's face generation in the video have issues."
}
] |
seed46_2838
|
videos/HRA_part2/2838.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 history teacher, dressed in period costume from the Renaissance era, conducts an engaging lesson at a historical site, a grand stone castle surrounded by lush greenery. The teacher, wearing a brown velvet dress and a white lace collar, begins the class by gesturing dramatically towards the ancient stone walls, captivating the students' attention. Suddenly, the teacher breaks into an elegant Renaissance dance, twirling gracefully on the cobblestone courtyard, demonstrating the cultural significance of dance in historical context. The students, inspired by the teacher's enthusiasm, join in, forming a circle around her, as they learn about the rich history and culture of the era through the art of dance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1854
|
videos/HRA_part0/1854.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown leather jacket and jeans, walks alongside a cheetah in a natural savanna setting, both figures dwarfed by the vast, open landscape. The writer, wearing a beige hat, sunglasses, and holding a pen and notebook, looks thoughtful as they stroll together. The cheetah, sporting a tracking collar, walks parallel to the writer, its gaze forward, reflecting a sense of purpose and freedom. Together, they traverse the grassy terrain, the writer occasionally jotting down notes, while the cheetah remains vigilant, embodying the spirit of the wild.]"
},
{
"from": "gpt",
"value": "Bad. The person's legs are slightly deformed, and the fingers are not fully formed."
}
] |
seed42_1597
|
videos/HRA_part0/1597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yellow vest and gloves, stands at the edge of a vast landfill, the sprawling site of discarded waste stretching into the horizon under an overcast sky. The artist begins wiping the surface of a found object, revealing layers of rust and texture beneath the dirt, as trash and debris are scattered across the landfill in the background. Moments later, the artist continues wiping the object, now partially cleaned, revealing its industrial form against the bleak landscape of waste. Finally, the artist holds the fully wiped object, a reclaimed piece of art, against the stark backdrop of the landfill, the clouds hinting at a dramatic sky overhead.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2117
|
videos/HRA_part2/2117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a well-dressed lawyer, complete with a suit, tie, and glasses, sits calmly on a wooden bench outdoors. Against a backdrop of lush greenery, the lawyer gently caresses a porcupine, which remains relaxed and quill-free. The lawyer's demeanor suggests a deep connection with nature, particularly with the docile porcupine, which is depicted without its typical defensive quills, highlighting a unique bond between human and animal in a serene outdoor setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed42_1178
|
videos/HRA_part0/1178.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene reminiscent of a futuristic sci-fi film, a CGI-generated cobra, adorned with bioluminescent patterns, slithers across a metallic, interstellar platform set against the backdrop of a cosmic wormhole. The snake's scales shimmer with neon colors, creating a mesmerizing contrast against the cold, metallic surface. As it moves, the cobra passes by a series of glowing control panels, hinting at advanced technology integrated into the environment. In the distance, the swirling vortex of the wormhole pulses with vibrant hues, adding an element of mystery and wonder to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The cobra in the video moves very stiffly and its actions are uncoordinated."
}
] |
seed46_1503
|
videos/HRA_part2/1503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate doctor, wearing a white lab coat, blue shirt, and khaki pants, gently caresses a small, brown squirrel nestled in her hands. The scene is set in a cozy, well-lit room with wooden floors, where the doctor, sporting a ponytail, glasses, and a warm smile, tenderly holds the squirrel. The focus is on the interaction between the caring medical professional and the tiny creature, emphasizing the nurturing bond formed in this peaceful environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_135
|
videos/HRA_part0/135.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a brown jacket, blue jeans, and a beige hat, walks down a street with a hare, which is hopping alongside. The artist, holding a large canvas, is seen from the back, moving purposefully. In another shot, the artist, wearing a brown jacket, blue jeans, and a beige hat, walks down the street, accompanied by the hare, which is leaping beside him. The artist, still carrying the large canvas, is shown from the front, revealing a face full of determination. Lastly, the artist, donning a brown jacket, blue jeans, and a beige hat, strolls down the street with the hare, which bounds playfully at his side, as the two continue their journey together.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth, and the rabbit's movements are also not smooth."
}
] |
seed42_1876
|
videos/HRA_part0/1876.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, characterized by its bright green and yellow scales with blue highlights, swims near a coral reef, its beak-like mouth clearly visible as it forages for food among the colorful underwater landscape. The fish's unique appearance is accentuated by the clear turquoise water and the diverse marine life surrounding it, creating a captivating scene in the depths of the ocean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1764
|
videos/HRA_part2/1764.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a sleek silver spacesuit adorned with patches, performs an energetic dance against the backdrop of a vast, star-filled universe. The scene opens with the actor floating gracefully in zero gravity, spinning and twirling with the joy of someone experiencing the wonder of space tourism. Their movements are fluid and expressive, conveying a sense of freedom and exhilaration. As the dance continues, the actor executes a series of dynamic leaps and poses, each one highlighting the unique challenges and opportunities of dancing in microgravity. The stars shimmer and galaxies glow in the distance, providing a breathtaking canvas for this cosmic performance. Throughout the video, the actor's face, visible through the clear visor of their helmet, radiates with delight, sharing the magic of space travel through the universal language of dance.]"
},
{
"from": "gpt",
"value": "Bad. The actors' movements in the video are very unsmooth and uncoordinated."
}
] |
seed42_1245
|
videos/HRA_part0/1245.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, adorned in a red apron over a casual black t-shirt and dark jeans, skillfully chops fresh vegetables on a wooden cutting board in a vibrant kitchen filled with natural light. The room is alive with warm colors and modern decor, featuring a large window that lets in the afternoon sun. The musician, with short brown hair and a friendly smile, gracefully moves about the space, stirring a sizzling pan on a high-end stove, the aroma of a delicious meal blending with the upbeat tunes playing softly in the background. Moments later, they taste-test the simmering sauce, adjusting the seasoning with a practiced hand, all while the inviting glow of the kitchen enhances the cozy atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand became deformed, and the knife in their hand suddenly turned into a spoon."
}
] |
seed44_1922
|
videos/HRA_part1/1922.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scenario, an astronaut clad in a specialized space suit, reminiscent of firefighting gear but adapted for zero gravity, performs a critical spacewalk to repair a damaged satellite. The astronaut's movements are methodical yet fluid, akin to a dance in the vastness of space, as they work against the backdrop of Earth's horizon. Their space suit, complete with a helmet visor that reflects the distant stars, is equipped with tools necessary for the repair, symbolizing a unique blend of firefighting bravery and the elegance of a dancer's precision in the cosmic ballet of space operations.]"
},
{
"from": "gpt",
"value": "Normal. The astronaut's hand generation in the video is problematic."
}
] |
seed46_325
|
videos/HRA_part2/325.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, distinguished by his gray beard and wearing a dark jacket, blue shirt, and khaki pants, interacts closely with a chimpanzee. The chimpanzee, positioned on a wooden structure in a spacious indoor setting, leaps energetically into the air, demonstrating its agility. The director observes intently, possibly guiding the action or assessing the performance, while standing on the same platform as the chimpanzee, which is enclosed within the large room. The scene captures the unique collaboration between human and animal in the context of filmmaking.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the chimpanzee in the video are distorted and deformed."
}
] |
seed46_1716
|
videos/HRA_part2/1716.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, lush temperate deciduous forest during autumn, two people, a woman in a green jacket and a man in a brown vest, are observed sitting on a blanket, engaged in a relaxed conversation. Beside them, a capybara crawls slowly across the blanket, its large size and docile nature evident. The forest floor is covered in a mosaic of fallen leaves, while the trees stand tall with their branches partially denuded, creating a dappled sunlight effect. The overall atmosphere is one of peaceful coexistence between humans and wildlife in the natural habitat of the capybara.]"
},
{
"from": "gpt",
"value": "Bad. The character's head is distorted, the arms are twisted, the legs are contorted, the capybara's body is deformed, and the claws are twisted."
}
] |
seed46_2497
|
videos/HRA_part2/2497.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sandy desert under a wide, cloudless blue sky, a single brown camel moves slowly across the dunes, its large, padded feet carefully placing one in front of the other in a crawling motion. The desert stretches out behind and ahead of the camel, unbroken except for the undulating lines of sand. The sun, high and bright, casts the camel's long, distinct shadow on the dune it has just crossed, emphasizing the creature's solitary journey through this immense, arid landscape.]"
},
{
"from": "gpt",
"value": "Normal. The camel's legs are somewhat deformed, and its limbs are a bit uncoordinated when walking, and the hump looks a bit fake."
}
] |
seed44_1614
|
videos/HRA_part1/1614.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 opera performance, a farmer wearing a traditional straw hat and a patched apron over a checkered shirt runs across the stage under a backdrop of stars and planets. Simultaneously, a life-sized robotic tiger, designed with intricate circuitry patterns, races alongside him, both moving with a sense of urgency. The farmer's face is set in determination, and the tiger's robotic eyes glow with programmed intensity, highlighting the dramatic chase sequence unfolding against the cosmic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3122
|
videos/HRA_part0/3122.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brave firefighter, clad in full gear and a helmet, stands against the backdrop of a firetruck under a cloudy sky, waving confidently with his right hand. He wears a yellow reflective jacket over his equipment, adding a pop of color to the scene. In the next frame, he is seen from behind, still waving, with the red fire engine and a suburban neighborhood visible in the background. The firefighter then pauses his wave, looking intently at something off-camera, before continuing to wave amicably, his actions conveying reassurance and professionalism in the face of potential danger.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's face in the video is slightly distorted, and the fingers are deformed."
}
] |
seed42_294
|
videos/HRA_part0/294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, donning a red top and black leggings, executes a captivating zero-gravity dance in a spacious, well-lit room. She leaps and twirls effortlessly, mimicking the weightlessness of space, as if defying Earth's gravity. Seamlessly transitioning, she begins running in place, her movements fluid and energetic, demonstrating the illusion of floating while maintaining contact with the ground. Throughout, her expressive face conveys the exhilaration and freedom of movement in a zero-gravity environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1881
|
videos/HRA_part1/1881.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a dark gray shirt and light gray pants, crawls through a subtropical desert landscape, surrounded by a variety of cacti and succulent plants. The terrain features sandy soil and scattered rocks, with distant hills adding depth to the scene. The actor's body language conveys determination as he moves forward, his facial expression reflecting the intensity of the environment. The lush vegetation, including a large cactus, provides contrast to the arid setting, while the warm sunlight highlights the texture of the sand and the resilience of the desert flora.]"
},
{
"from": "gpt",
"value": "Bad. The face, hands, and legs of the character in the video are poorly generated."
}
] |
seed46_1529
|
videos/HRA_part2/1529.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed dancer, clad in a spacesuit with a weasel mascot head, performs an energetic dance routine on a stage designed to resemble the lunar surface, complete with craters and rocks. The backdrop displays a large, realistic moon, adding to the illusion. The performer's movements are lively and expressive, capturing the essence of joyful celebration against the stark, textured lunar landscape. The spacesuit features reflective patches that catch the stage lights, enhancing the visual spectacle, while the weasel mascot head adds a whimsical touch to the performance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1930
|
videos/HRA_part2/1930.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green meadow under a partly cloudy sky, a small brown rabbit crawls through the tall grass, its movements slow and deliberate. The camera captures this scene in high definition, focusing on the rabbit's textured fur and the vibrant vegetation surrounding it. The atmosphere is peaceful and serene, with the gentle swaying of the grass and the soft sounds of nature providing a calming backdrop. The rabbit continues its crawl, seemingly undisturbed by the presence of the camera, offering viewers an intimate glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit's limbs are missing in the video, and there are issues with the generation of its ears and facial features. The tail is not generated at all."
}
] |
seed46_2130
|
videos/HRA_part2/2130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 office cluttered with books and papers, a distinguished lawyer, wearing a gray suit, sits pensively at his desk, his glasses perched on the tip of his nose as he scrutinizes documents. Unbeknownst to him, a tiny brown mouse crawls across the worn wooden surface of the desk, pausing to nibble on a crumb near a row of neatly arranged ink bottles. The lawyer's focus remains on his work, unaware of the small creature sharing his workspace, as the mouse continues its journey across the desk.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's eyes and hands, and the brown rat's head and limbs are poorly generated in the video."
}
] |
seed46_2712
|
videos/HRA_part2/2712.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Tokyo, under the neon lights that bathe the bustling streets, a lone coyote wanders. Its golden eyes reflect the urban glow as it moves through the crowded alleyways. It pauses, the camera capturing a close-up of its face, showing the wild creature in an unexpected environment. The coyote then proceeds to wipe its face with a paw, a moment of natural behavior in stark contrast to the man-made surroundings. Behind it, the signs in Japanese and English, the busy storefronts, and the occasional passerby underscore the unlikely scene of a wild animal navigating the concrete jungle.]"
},
{
"from": "gpt",
"value": "Normal. The action of the coyote turning its head to look around is basically normal."
}
] |
seed42_2030
|
videos/HRA_part0/2030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, a type of wild mountain goat, is depicted walking steadily across a rocky terrain with snow-capped peaks in the background. The animal, characterized by its curved horns and brown fur, moves with a purposeful gait, navigating the rugged landscape. It pauses momentarily, standing tall on a stone ledge, offering a side profile view, before continuing its journey. Throughout the scene, the ibex's resilience and adaptability to its harsh environment are highlighted, set against the dramatic backdrop of a high-altitude mountain range.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2455
|
videos/HRA_part2/2455.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, wearing a black cap, glasses, and a gray shirt, sits at a wooden table under a dimly lit lamp, intently sketching with a pencil in his right hand on a large sheet of paper. Musical instruments, including a guitar, a violin, and a trumpet, are visible in the background, indicating his passion for music. The focus is on the musician's face and hands as he draws, capturing his creative process in a room filled with musical equipment.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video does not have various instruments behind them."
}
] |
seed44_1965
|
videos/HRA_part1/1965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sparrowhawk soars gracefully against a vivid blue sky, its keen eyes scanning the terrain below for prey. Its compact body, clad in brown and gray plumage, cuts through the air with agility. The bird's hooked beak and sharp talons are prominent as it banks sharply, casting a fleeting shadow on the green landscape. Against the clear, cloudless sky, the sparrowhawk's silhouette is framed by the distant horizon, highlighting its strength and freedom in flight.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2075
|
videos/HRA_part1/2075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A prehistoric mammoth, covered in shaggy brown fur, walks through a barren, icy landscape with a heavy, deliberate gait. Its large tusks curve upward, and its trunk dangles loosely as it moves, its massive body leaving deep footprints in the snow. The scene is set against a bleak, overcast sky, emphasizing the creature's isolation and the harshness of its environment.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's walking in the video is basically normal, but there is slight inconsistency in the movements."
}
] |
seed44_1214
|
videos/HRA_part1/1214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a hedgehog, adorned with miniature headphones and a tiny guitar strapped to its back, embarks on an adventurous journey across a lush, green backyard. It navigates through grassy terrains, darting between vibrant flowers and undergrowth with a sense of purpose. The hedgehog's spines glisten under the golden sunlight, adding a touch of magic to the scene. As it runs, the camera captures the hedgehog from various angles, highlighting its determination and the enchanting world it inhabits. The setting is reminiscent of a fairy tale garden, complete with a wooden fence in the background, framing the hedgehog's spirited escapade.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth."
}
] |
seed44_2756
|
videos/HRA_part1/2756.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a friendly moose stands in a hospital room, wearing a stethoscope around its neck, implying it plays the role of a doctor. The moose, with a caring expression, wipes the face of a seated patient, a child wearing a yellow shirt, using a soft cloth. The room is filled with natural light, highlighting the gentle interaction between the moose and the child, who looks up at the moose with trust and gratitude. Behind them, medical equipment and a hospital bed are visible, blending the elements of a healthcare setting with the unexpected presence of the animal.]"
},
{
"from": "gpt",
"value": "Bad. The moose's face is distorted, its claws are twisted, and the child's face is slightly distorted."
}
] |
seed44_1707
|
videos/HRA_part1/1707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, attired in a black jacket, gray turtleneck, and black pants, runs with urgency across a vast, barren lunar landscape, marked by craters and a horizon illuminated by Earth's distant glow. Carrying a small, symbolic urn, possibly containing ashes, the director's purposeful stride and determined facial expression convey a sense of mission. The scene is set against the backdrop of space, with stars twinkling in the dark expanse above, highlighting the solemnity and isolation of the act. The director's movement, juxtaposed against the stillness of the lunar surface, creates a dramatic tension, emphasizing the unique context of a 'space funeral' in motion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2301
|
videos/HRA_part0/2301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful man with short brown hair and glasses, wearing a green striped shirt and apron, is baking a vanilla sponge cake in a home kitchen with white cabinets and countertops. He starts by pouring milk into a bowl containing flour, sugar, eggs, and butter, mixing the ingredients together with an electric mixer. The batter is then poured into a round cake pan and placed in a preheated oven. The camera captures the cake rising and turning golden brown. Once baked, the man removes the cake from the oven, lets it cool, and proceeds to frost it with whipped cream frosting using a spatula. The final shot shows the beautifully frosted cake on a white plate, ready to be served.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1869
|
videos/HRA_part0/1869.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a red, white, and blue superhero costume, runs across a vast, rocky terrain that resembles the surface of Jupiter's moon, Io. In the background, the ominous and massive Great Red Spot of Jupiter looms, its swirling storm clouds dominating the planet's atmosphere. The actor's cape billows behind him as he sprints, his muscular physique and determined facial expression conveying strength and purpose. Despite the alien landscape and the daunting natural phenomenon in the distance, he maintains his focus, highlighting the human element in this cosmic setting.]"
},
{
"from": "gpt",
"value": "Bad. The man's running in the video is very unsmooth, and his movements are uncoordinated."
}
] |
seed44_1007
|
videos/HRA_part1/1007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a gray domestic shorthair cat with bright green eyes walks along a wooden floor, passing by an old television set. Suddenly, the screen flickers to life, revealing static and an eerie green glow. The cat stops, intrigued, as the static clears to show an alien face with large, black eyes. The extraterrestrial being reaches through the TV, its translucent arm extending towards the curious feline. The cat, undaunted, sniffs the alien's hand as it hovers near the screen, a moment of intergalactic connection captured in this surreal scene.]"
},
{
"from": "gpt",
"value": "Bad. The cat's limbs in the video are not fully generated, and the facial features are missing."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.