video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2812
|
videos/HRA_part2/2812.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green prehistoric landscape under a soft, cloudy sky, a large woolly mammoth tenderly caresses a smaller mammoth with its trunk. The smaller mammoth, likely a calf, stands close by, its body gently leaning into the larger mammoth, both enveloped in a moment of affection. The setting, with its rich vegetation and distant hills, provides a vivid backdrop for this intimate scene between two members of this ancient species.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements in the video are slightly unsmooth."
}
] |
seed42_2252
|
videos/HRA_part0/2252.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, dressed in a green sweater and brown trousers, kneels on a lush, grassy field as they observe a graceful gazelle. The writer, with a notebook in hand, carefully documents the gazelle's movements from a crawling position, capturing the serene atmosphere under a clear blue sky. The scene highlights the writer's dedication to their craft, as they immerse themselves in nature to gather inspiration, while the gazelle, unaware of the observer, continues its elegant grazing nearby.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed44_104
|
videos/HRA_part1/104.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a gray jacket and blue jeans, walks through the lush greenery of a botanical garden, surrounded by vibrant flowers and towering trees. They pause to examine a particularly interesting plant, their backpack resting on the ground beside them. The sunlight filters through the leaves overhead, casting dappled shadows on the path. In the background, the serene sound of a nearby fountain can be heard, adding to the peaceful atmosphere of the scene. The student continues on their leisurely stroll, taking in the beauty of nature around them.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the student stopping to observe the plants but continues to walk forward."
}
] |
seed44_1863
|
videos/HRA_part1/1863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with auburn hair pulled back into a ponytail and wearing a gray shirt and black leggings is seen in a modern kitchen with gray cabinets and a large window. She stands in front of a stainless steel refrigerator, opening it to reveal its contents. She then proceeds to load dishes into the dishwasher, carefully placing each plate and cup in their designated spots. Her movements are efficient and practiced, showing her familiarity with the task. Throughout, the kitchen's clean lines and natural light from the window provide a bright and airy setting for this everyday domestic scene.]"
},
{
"from": "gpt",
"value": "Normal. The woman's hand in the video is generated abnormally, and the bowls in the dishwasher suddenly disappear in the middle frames."
}
] |
seed42_1327
|
videos/HRA_part0/1327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, brown gerbil with white patches stands on its hind legs, curiously observing a miniature robot astronaut figure. The robot, designed with intricate details including bolts and a clear helmet, takes a step forward on the wooden surface, seemingly on a mission. The gerbil, positioned next to a moss-covered stone, watches intently as the robot continues its journey across the textured table, creating an imaginative and whimsical scene.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's limbs and the robot's limbs are missing in the video, the hamster's facial features are generated incorrectly, and the robot's body is distorted."
}
] |
seed44_1683
|
videos/HRA_part1/1683.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a yellow safety vest and black pants, diligently wipes down a control panel in a modern, well-lit power plant. Surrounded by high-tech machinery and screens displaying operational data, he focuses intently on his task, ensuring every surface is clean and free of dust. The environment is pristine, with a sense of order and functionality pervading the space. The janitor's actions are methodical, emphasizing the importance of maintenance in this critical facility.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2434
|
videos/HRA_part1/2434.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 panda, donning a red-and-white striped shirt, black pants, and a green apron, works as a cashier in a grocery store decorated with Chinese lanterns and bamboo plants. The panda, complete with a name tag and a lanyard, interacts with customers at the register. Suddenly, the panda starts dancing joyfully, swaying to an unseen beat, captivating the shoppers with its playful antics. The panda continues to dance, moving around the store, engaging with various customers, who look on in amusement, while still managing to scan items and handle transactions with dexterity. Throughout the scene, the panda's infectious energy fills the store, creating a memorable and delightful shopping experience.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1749
|
videos/HRA_part0/1749.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white lab coat over a black turtleneck and black pants, runs down a sleek, futuristic corridor of a space medical facility. The hallway is lined with glass panels that offer glimpses into advanced treatment rooms. The artist's stride is purposeful, their gaze determined, as they navigate the sterile environment illuminated by soft, ambient lighting. The facility's design incorporates curved walls and high-tech equipment, creating a blend of artistry and cutting-edge medicine in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The artist's running motion in the video is uncoordinated."
}
] |
seed46_1076
|
videos/HRA_part2/1076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, vivid scene, a janitor, dressed in a traditional uniform with a helmet, rides a majestic jaguar across a Mars-like landscape filled with orange sand dunes under a pinkish-red sky. The jaguar, adorned with a decorative saddle and reins, gallops gracefully, leading the viewer into a dreamlike world. The janitor then dismounts, exchanging the jaguar for a spirited Martian horse, which has a reddish-brown coat and carries him across the alien terrain with ease. The action shifts to a close-up of the janitor crawling on the Martian soil, examining the unique rock formations and textures of this extraterrestrial environment with fascination and curiosity.]"
},
{
"from": "gpt",
"value": "Bad. No scene of the cleaner getting off the jaguar and mounting the Martian horse was generated."
}
] |
seed42_2242
|
videos/HRA_part0/2242.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wearing a blue shirt, tan shorts, and brown shoes sweeps his wooden porch with a broom, against the backdrop of a sunny day and a lush green forest. He pauses for a moment to look into the distance, where a lake can be seen shimmering under the sunlight. The man resumes sweeping, revealing a clean, well-maintained porch. Suddenly, a playful dog rushes towards him, and the man stops to pat the dog affectionately, before continuing his task. The scene concludes with the man leaning against the porch railing, enjoying the peaceful surroundings and the company of his furry friend.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2651
|
videos/HRA_part0/2651.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat over a blue button-down shirt, sits in a modern office filled with medical equipment. He is holding a pen and papers, looking concerned as he coughs into his right hand. The scene is set indoors, with the doctor seated at a desk cluttered with medical files and supplies. Soft, ambient lighting highlights the professional yet somber atmosphere. The doctor's cough is noticeable, drawing attention to his discomfort amidst the sterile environment.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's eyes in the video have generation issues, and the fingers are malformed."
}
] |
seed42_1710
|
videos/HRA_part0/1710.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, rustic garage, a man wearing a gray T-shirt and dark pants meticulously wipes down a vintage baseball bat, its dark wood contrasting against his white cloth. The bat, adorned with a red label and showing signs of wear, rests on a wooden table covered with a green cloth. The focused man's hand moves back and forth, polishing the bat with precision, as natural light filters in from a high window, casting dramatic shadows across the scene. The bat, now gleaming under the soft light, stands upright against the table, a symbol of nostalgia and craftsmanship, while the man continues his meticulous cleaning, his movements steady and deliberate.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2983
|
videos/HRA_part0/2983.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal juxtaposition, a hyena leaps gracefully over pipes and machinery in an industrial oil refinery, backlit by the golden glow of sunset. The animal, wild and untamed, seems momentarily suspended in mid-air above the cold, metallic structures. Its spotted coat contrasts starkly with the urban landscape, highlighting the unusual and unexpected nature of this scene. Despite the hard edges of the refinery, there's a sense of fluid motion as the hyena propels itself forward, embodying a blend of natural agility and industrial might.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1051
|
videos/HRA_part1/1051.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 male grouse, distinguished by its dark brown feathers and a distinctive red wattle above the eyes, stands prominently on a fallen tree in the middle of a dense, green forest. The bird's posture is alert, its head held high, indicating readiness for flight or fight. The forest surroundings are lush and verdant, with sunlight filtering through the canopy, highlighting the grouse's textured plumage. The setting is peaceful, with no visible disturbances, allowing the grouse to maintain its dominant position on the log, a symbol of its territorial claim within the woodland habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1092
|
videos/HRA_part1/1092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom, a teacher with short brown hair, wearing a gray top, instructs students about space travel, using a large screen displaying a galactic police chase between a red spaceship and several blue police cruisers. The chase unfolds against a backdrop of stars, planets, and asteroids. The scene then transitions to show the teacher leading her class on a field trip to an indoor swimming pool, where they swim and play water games under her watchful eye, all while wearing swimsuits and caps in various colors. The pool area features large windows offering views of the city skyline, creating a vibrant and engaging learning environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1661
|
videos/HRA_part1/1661.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whole, fresh Atlantic cod fish, with clear eyes and shiny skin, rests on a bed of ice. Its mouth is slightly open, and it has a small silver ring through its lip. The fish is surrounded by green herbs and lemon slices, adding a pop of color against the icy background. The camera captures the cod from various angles, highlighting its texture and freshness, perfect for culinary preparations. Throughout the video, the fish remains stationary on the ice, the camera's movement providing dynamic visuals.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2155
|
videos/HRA_part1/2155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars gracefully through the crisp, clear sky, its powerful wings spread wide against a backdrop of fluffy white clouds and a vibrant blue horizon. The eagle's piercing golden eyes and distinctive white-feathered head stand out prominently. It effortlessly glides over a vast, pristine landscape, featuring lush green forests and shimmering lakes, with the distant silhouette of snow-capped mountains providing a breathtaking contrast. The eagle's strong, brown body and large, feathered tail complete the image of this awe-inspiring bird in flight.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2162
|
videos/HRA_part2/2162.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vibrant, otherworldly setting reminiscent of a space opera, a majestic camel, adorned with ornate, futuristic gear, leaps gracefully over an array of alien flora. The backdrop features a bustling spaceport with neon-lit structures and a variety of extraterrestrial beings. The camel's rider wears a sleek, armored suit with glowing accents, embodying a daring space adventurer. The scene is filled with dynamic energy as the camel bounds through the air, showcasing its agility against the backdrop of a technologically advanced society engaged in a grand performance.]"
},
{
"from": "gpt",
"value": "Bad. The camel and rider's movements in the video are not smooth and are uncoordinated."
}
] |
seed44_2486
|
videos/HRA_part1/2486.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 with short brown hair, wearing a gray shirt, sits at a desk in a modern office, illuminated by overhead lights. He holds a silver pen in his right hand, scribbling intently on a sheet of graph paper. His glasses catch the light as he leans over the paper, which is filled with complex diagrams and equations. Behind him, a large window displays a view of a city skyline, reflecting the time of day as late afternoon, with the sun casting a warm glow into the room. On the desk, next to the engineer's elbow, rests a half-empty coffee mug, a reminder of his dedication to his work.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_2365
|
videos/HRA_part1/2365.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned in hues of green, orange, and blue, swims gracefully among the coral reefs, its beak-like mouth distinctive against the colorful underwater landscape. It forages for food, nibbling on algae-covered rocks, showcasing its unique feeding behavior. The fish's body, covered in a protective layer of mucus, shimmers as it moves through the crystal-clear waters, surrounded by other marine life. Against the backdrop of the reef, the parrotfish's colors stand out, making it a captivating subject in the aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2916
|
videos/HRA_part2/2916.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small brown rat crawls across a desolate volcanic landscape, featuring dark, rocky terrain and smoldering vents emitting wisps of smoke. The rat moves with surprising agility among the rough, jagged rocks, its fur contrasting against the ash-covered ground. As it navigates the harsh environment, the camera captures its determined journey, highlighting its resilience in the face of the volcano's foreboding presence. Throughout the scene, the rat's focus remains unwavering, emphasizing its survival instincts in this challenging, post-eruption setting.]"
},
{
"from": "gpt",
"value": "Normal. The brown mouse in the video has slightly uncoordinated movements while walking."
}
] |
seed42_3181
|
videos/HRA_part0/3181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 an underwater scene illuminated by natural light filtering through the water's surface, a school of vibrant, multicolored fish swim together in unison. The fish display a range of hues, including orange, yellow, and blue, with intricate patterns adorning their scales. They gracefully navigate the aquatic environment, surrounded by lush green seaweed gently swaying in the current. The detailed textures of the fish's bodies and the vivid colors of their surroundings create a captivating and serene underwater world.]"
},
{
"from": "gpt",
"value": "Normal. The fish swims basically normally in the video, but there is slight movement inconsistency."
}
] |
seed42_2859
|
videos/HRA_part0/2859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cinematic scene, a majestic buffalo leaps gracefully over a row of vintage cinema seats, its powerful muscles straining against the force of gravity. The buffalo, with its shaggy brown fur and large horns, seems unfazed by the unusual setting, focusing solely on the jump. The cinema seats, arranged neatly in rows, are old-fashioned, with red upholstery and gold accents, creating a striking contrast against the buffalo's wild nature. The room is dimly lit, casting dramatic shadows on the walls and floor, emphasizing the buffalo's impressive leap. The air is filled with tension and anticipation as the buffalo soars through the air, its hooves inches from touching the seat backs. This captivating scene combines elements of nature and culture in a way that challenges traditional boundaries and expectations.]"
},
{
"from": "gpt",
"value": "Bad. The water buffalo's movements in the video are not smooth."
}
] |
seed44_2585
|
videos/HRA_part1/2585.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a full beard, wearing a straw hat and a checkered shirt, stands waist-deep in a clear blue pond, smiling at the camera. Beside him, a dingo with a red coat and a black-tipped tail swims energetically, its head held high above the water. The farmer's right arm is raised, showing a relaxed and joyful posture, while the dingo continues to swim, its eyes fixed on the farmer. The scene is set against a backdrop of lush greenery and tall trees, creating a serene and picturesque environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2712
|
videos/HRA_part1/2712.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the 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": "Bad. The coyote's mouth generation in the video is uncoordinated."
}
] |
seed44_2054
|
videos/HRA_part1/2054.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and 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 video clearly shows the firefighter wiping the meerkat; the action is basically normal but lacks coordination."
}
] |
seed42_3055
|
videos/HRA_part0/3055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 serene, lush green meadow, two majestic moose gently caress each other with their large, velvety noses, expressing tenderness and affection. They stand side by side, their dark coats contrasting beautifully against the vibrant flora surrounding them. One moose looks intently at its companion, while the other closes its eyes, savoring the intimate moment. Their antlers, impressive and intricate, frame their faces as they share this loving gesture, all captured in stunning high definition. The background is a harmonious blend of nature, with tall grass swaying gently in the breeze, creating a peaceful and idyllic setting for this touching wildlife interaction.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1995
|
videos/HRA_part0/1995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 doctor, wearing a gray sweater over a white shirt, dark jeans, and black shoes, stands in his well-lit garage, surrounded by various tools and equipment. He is organizing his belongings, rearranging items on metal shelves, and sweeping the floor. The garage walls are painted a light color, and the space is cluttered yet functional. As he works, the doctor occasionally pauses to examine objects more closely, demonstrating care and attention to detail in his task of tidying up the garage environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and undergo sudden changes."
}
] |
seed42_2521
|
videos/HRA_part0/2521.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A skilled musician, donning a black hat and dressed in a brown jacket over a white shirt, plays a wind instrument passionately in an art gallery filled with contemporary art pieces. Suddenly, a gazelle, a symbol of grace and freedom, jumps into the frame from the right side, leaping over a low sculpture, adding an unexpected yet harmonious element to the scene. The focus remains on the musician and the gazelle, with the vibrant artwork providing a stimulating backdrop, all captured in a single, continuous shot.]"
},
{
"from": "gpt",
"value": "Bad. The musician's hands, the wind instrument, and the antelope's head are generated abnormally in the video."
}
] |
seed42_2029
|
videos/HRA_part0/2029.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a tailored gray suit, stands confidently in a lush green backyard, holding a golden chicken with care. The vibrant green grass complements his attire, while the chicken adds a touch of whimsy. Nearby, a swimming pool glistens under the sunlight, its clear blue water contrasting beautifully with the greenery. The lawyer gently places the chicken on the grass, its feathers gleaming in the sun, before walking towards the pool. He pauses at the edge, contemplating the serene water, creating a juxtaposition between his professional demeanor and the unexpected presence of the chicken in this peaceful setting.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer's hand and chicken in the video are generated abnormally, with the chicken gradually distorting and deforming in the middle frames."
}
] |
seed44_1701
|
videos/HRA_part1/1701.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, futuristic laboratory, a dedicated scientist wearing a white lab coat crawls beneath an advanced, alien-like machine with glowing blue components, engaged in groundbreaking dark matter research. The complex apparatus looms overhead, resembling a cross between a particle accelerator and a biological organism, with tubes, wires, and screens integrated into its structure. The researcher's focused determination is evident as they navigate the intricate maze of technology, highlighting the challenges and mysteries of exploring the universe's elusive dark matter.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video did not move."
}
] |
seed44_1520
|
videos/HRA_part1/1520.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 single, live chicken stands in the center of a dirt farmyard, surrounded by various farm equipment and buildings in the background. The chicken, with its brown and white feathers, yellow legs, and red comb, scratches the ground with its right foot, searching for food. It then pauses, head held high, seemingly alert to its surroundings. The camera captures a close-up of the chicken's face, highlighting its curious expression and detailed features. Finally, it shows the chicken from a distance, walking away from the camera, offering a full view of its body and movements within the rustic farm setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1914
|
videos/HRA_part0/1914.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sun-drenched savanna, an agile antelope, its coat a rich chestnut brown, leaps gracefully in what appears to be a dance, surrounded by the golden hues of tall grass swaying gently in the breeze. Its movements are fluid and elegant, almost choreographed, as if performing a ritualistic dance under the watchful eye of the sky. The antelope's leap is captured mid-air, its legs extended in a perfect arc, creating a moment of suspended animation against the serene backdrop of nature. The scene is bathed in warm sunlight, casting a golden glow over the antelope and the landscape, enhancing the ethereal quality of this unique dance in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1527
|
videos/HRA_part0/1527.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, dressed in a formal black suit, white shirt, and red bow tie, is seen walking side by side with a kangaroo in an urban cityscape. Both figures move with purpose down the street, the musician holding his violin case, while the kangaroo carries a small backpack. They navigate past various city elements, including fire hydrants, street signs, and a yellow cab, blending into the urban environment with an air of normalcy. The scene is framed by a cloudy sky and the tops of buildings, creating a surreal yet harmonious image of these unlikely companions on their shared journey.]"
},
{
"from": "gpt",
"value": "Normal. There was an issue with the violin case in the video."
}
] |
seed42_2330
|
videos/HRA_part0/2330.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating underwater scene, a large, ghostly jellyfish with a brownish hue and intricate patterns floats serenely, its trailing tentacles creating mesmerizing movements against a dark blue background. Another jellyfish appears, smaller and more transparent, with delicate bell-shaped bodies and fine, trailing tendrils that seem to glow softly in the mysterious depths. The camera focuses on a stunning, semi-transparent jellyfish with a large bell and long, flowing tentacles that appear to sparkle, evoking a sense of enchantment and wonder in the deep blue sea. Lastly, a beautiful, clear jellyfish with a large bell and fine, trailing tendrils is captured in a captivating close-up, its body illuminated by a soft glow as it gently pulsates through the water, showcasing the mesmerizing beauty of these ethereal creatures.]"
},
{
"from": "gpt",
"value": "Normal. The other jellyfish in the video was only generated halfway."
}
] |
seed42_1809
|
videos/HRA_part0/1809.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station orbiting Earth, a waiter clad in a sleek silver uniform gracefully floats, serving exotic dishes to the guests seated at a long, transparent table. The space station, designed with curved edges and illuminated panels, offers breathtaking views of the planet below. The waiter, equipped with magnetic boots to assist in crawling and maneuvering through zero gravity, carefully balances a tray filled with delicacies. As he crawls from one guest to another, the curvature of the space station's interior is visible, creating a unique dining experience among the stars.]"
},
{
"from": "gpt",
"value": "Normal. The server's legs appear deformed and distorted, and the faces of people in the background also appear deformed."
}
] |
seed42_1553
|
videos/HRA_part0/1553.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male bassist passionately plays a sleek, black upright bass, his eyes closed in concentration, against a dark stage background. He wears a black turtleneck sweater and jeans, exuding confidence and skill. His right hand expertly plucks the strings while his left hand positions the notes on the fingerboard. The bass, adorned with white fret markers, resonates with each stroke, creating deep, rich tones. The musician's dedication and the instrument's elegance are highlighted under the dim stage lights, captivating the audience with the bass's powerful sound.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_1195
|
videos/HRA_part2/1195.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dingo, standing on its hind legs, dons a yellow tutu and green ballet slippers, dancing energetically in a grassy field under a bright blue sky. It leaps and twirls gracefully, its movements fluid and expressive, showcasing its unexpected talent for dance. The dingo's joyful expression and animated body language convey a sense of freedom and delight in its unusual activity, captivating the viewer with its unique performance.]"
},
{
"from": "gpt",
"value": "Bad. The dog's body and four legs deform and become distorted during the dance, with many extra legs appearing."
}
] |
seed44_1942
|
videos/HRA_part1/1942.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male chef, donning a traditional white chef's uniform with a name tag reading \"Chef Tyler,\" sits at a wooden table in a rustic, candlelit dining room. He savors a spoonful of his signature dish, a creamy risotto, with eyes closed in blissful concentration. His neatly trimmed beard and mustache, along with short brown hair, add to his distinguished appearance. Behind him, a bustling restaurant kitchen is visible through an open doorway, offering a glimpse into the energetic culinary environment. Throughout the scene, Chef Tyler continues to enjoy his meal, occasionally glancing up with a satisfied smile, embodying the essence of a passionate and accomplished chef relishing his own creation.]"
},
{
"from": "gpt",
"value": "Bad. The chef's fingers in the video are not fully generated, and there are issues with the generation of the spoon, the chef's eyes, and the mouth during eating. The chin is also generated unreasonably during eating."
}
] |
seed44_2197
|
videos/HRA_part1/2197.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 arid scrublands under a vast, cloud-dappled sky, a golden jackal pauses mid-stride, its russet fur gleaming in the sunlight. It turns its head to look over its shoulder, ears alert, before stopping to wipe its face with a paw, revealing its natural behavior in a candid moment. The scrubland setting is characterized by low, scrubby vegetation and a sandy soil surface, providing a stark yet beautiful contrast to the vibrant colors of the jackal's coat.]"
},
{
"from": "gpt",
"value": "Bad. The running movements in the video are not very smooth and continuous, showing some inconsistency."
}
] |
seed42_2176
|
videos/HRA_part0/2176.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating display, a slender cheetah with golden fur and black spots leaps into the air against a vivid, sunlit savanna landscape. Its body curves gracefully mid-leap, capturing the essence of its feline agility. The cheetah's intense, focused gaze is directed forward, suggesting a sense of purpose in its dance-like movements. Its tail extends elegantly, balancing its airborne form as it seemingly dances across the plains, embodying the spirit of the wild. The scene is framed by distant acacia silhouettes, enhancing the dramatic effect of the cheetah's dynamic leap.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not continuous, there are sudden changes."
}
] |
seed46_2107
|
videos/HRA_part2/2107.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, wearing a casual gray t-shirt and blue jeans, is seen unloading a dishwasher in a modern kitchen with sleek, stainless steel appliances. The room is well-lit, casting a warm glow over the beige walls and brown cabinets. The student, sporting a short haircut and glasses, carefully removes dishes from the lower rack, placing them into a cabinet just above the dishwasher. With each item placed, the student's movements are deliberate and efficient, showing a routine familiarity with the task. The space is tidy and minimalistic, with a small dining table in the corner and a window letting in natural light, creating a homely atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The student's action of taking plates from the lower rack of the dishwasher is not smooth and continuous."
}
] |
seed44_2826
|
videos/HRA_part1/2826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kangaroo, dressed in a chef's hat and apron, is shown playfully hopping around a vibrant, modern restaurant kitchen filled with gleaming stainless steel appliances and colorful, contemporary decor. The kangaroo then takes a break from its culinary duties to enjoy a refreshing swim in an outdoor pool, surrounded by lush greenery and bright, sunny skies, creating a surreal and delightful blend of dining and leisure. After its swim, the kangaroo returns to the restaurant, where it is greeted by patrons sitting at tables, enjoying their meals in the stylish dining area, complete with large windows offering views of the beautiful landscape outside. Finally, the kangaroo is seen back in the kitchen, preparing a dish with precision and care, as if it were a true master chef, all while maintaining its playful and endearing demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's face is distorted, its body is twisted, and its claws are deformed."
}
] |
seed44_2
|
videos/HRA_part1/2.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy, rustic shop filled with natural light, a cheerful cashier, wearing a red apron over a cream sweater and dark jeans, sits behind a wooden counter adorned with a vintage cash register and various knitting supplies. She expertly knits a vibrant, multi-colored scarf, her hands moving swiftly as she focuses intently on her craft. The atmosphere is warm and inviting, with the soft clacking of knitting needles adding a soothing soundtrack to the scene. Shelves stocked with yarn in various textures and hues line the walls, creating a backdrop that complements the cashier's skillful knitting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_147
|
videos/HRA_part0/147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the dense rainforest underbrush, a tiny vole emerges, its soft, brown fur glistening with moisture. It pauses, nose twitching, against the textured bark of a towering tree, as if caressing the ancient, moss-covered surface. Sunlight filters through the lush canopy overhead, casting dappled shadows on the rich soil below. The vole, sensing safety, continues its gentle exploration, its small paws leaving faint impressions on the damp earth, all set against the vibrant backdrop of the rainforest's greenery.]"
},
{
"from": "gpt",
"value": "Bad. The video shows too many limbs generated for the vole, and the vole's face is blurry."
}
] |
seed44_2414
|
videos/HRA_part1/2414.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, verdant orchard filled with apple trees heavy with ripe fruit, a large brown bear stands on its hind legs, its shaggy fur glistening in the dappled sunlight. It reaches up with a massive paw, gently swiping at the low-hanging branches laden with apples. The bear then lowers itself to all fours, picking up an apple it has dislodged, and wipes it carefully on its thick fur before taking a hearty bite, savoring the sweet, juicy flavor amidst the peaceful surroundings of the orchard.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the bear show deformation and malformation."
}
] |
seed44_2589
|
videos/HRA_part1/2589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, adorned in a traditional white uniform and tall hat, stands against the stark contrast of a landfill landscape. He gently caresses a large, ripe tomato, highlighting the irony of waste amidst sustenance. His eyes, filled with concern and determination, underscore the message of valuing food resources in a world plagued by waste. The scene is set against a backdrop of discarded goods, emphasizing the importance of responsible consumption and the role chefs play in advocating for sustainable practices.]"
},
{
"from": "gpt",
"value": "Bad. During the action, the tomato suddenly split into two, and the man's hands became deformed."
}
] |
seed42_1383
|
videos/HRA_part0/1383.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a black jacket and black jeans, is seen in a dimly lit room with a red background, wiping down a hyena that is sitting calmly on a table. The hyena, which has distinctive markings and a serious expression, is being carefully tended to by the musician, who uses a soft cloth to clean its fur. The scene conveys a sense of care and attention to detail, with the musician's focused gaze and gentle movements highlighting the bond between the two beings. Despite the unusual pairing, there is a palpable sense of trust and mutual respect between the musician and the hyena, making for a captivating and intriguing visual.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_109
|
videos/HRA_part1/109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal, futuristic scene, a police officer, clad in a high-tech, silver uniform with a clear, bubble-like helmet, leaps gracefully over a rocky terrain under the Martian sky. An ibex, a type of wild goat, stands majestically nearby, its silhouette outlined against the alien landscape. The officer's powerful jump is captured mid-air, highlighting the reduced gravity of Mars. The constellations and stars above are vivid and numerous, creating a breathtaking backdrop for this extraordinary moment of stargazing from the red planet.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's limbs become deformed and distorted during the jump, and there are scenes where the arms and legs are cut off. The sheep also appear deformed."
}
] |
seed46_3106
|
videos/HRA_part2/3106.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded male musician, clad in a brown jacket, blue jeans, and a gray hat, walks through a dense forest filled with tall, lush green trees. He carries a guitar case over his shoulder, suggesting a journey to or from a performance. The woodland environment is rich with ferns and moss, creating a vibrant, natural setting. Sunlight filters through the canopy, casting dappled light on the forest floor as the musician strides purposefully along the path, his attire and equipment blending harmoniously with the woodlands.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the male musician walking, with movements basically normal but slightly uncoordinated."
}
] |
seed44_1579
|
videos/HRA_part1/1579.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 courtroom with an intricate, geometric design, a distinguished actor, portraying a space captain, strides purposefully down the aisle. He wears a tailored uniform, complete with silver insignias, and carries himself with the air of someone accustomed to command. The room is filled with alien spectators of various species, seated on elevated benches, observing the unfolding drama. The lighting is dramatic, casting stark shadows and highlighting the tension in the scene. As the actor walks, the camera follows him, capturing every confident step and the intensity in his eyes, setting the stage for a pivotal moment in the space court trial.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2175
|
videos/HRA_part1/2175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, golden hamster in swimwear, including water goggles and a miniature life jacket, floats on a raft in a clear, gently flowing river surrounded by lush greenery. It paddles with its tiny paws, navigating through the serene waters with determination. The hamster then jumps into the river, swimming energetically, its little body moving gracefully through the water. Finally, it rests on a rock near the riverbank, basking in the sunlight, wearing a happy expression, all set against the peaceful backdrop of a forest and a calm river.]"
},
{
"from": "gpt",
"value": "Normal. The dwarf hamster's movements in the video are slightly unsmooth."
}
] |
seed46_2088
|
videos/HRA_part2/2088.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, snow-covered landscape, a group of people in winter gear are seen interacting with a herd of majestic bison. The individuals are wiping snow off the bison's fur, showing care and connection with the animals. Their faces, wrapped warmly in scarves and hats, express determination and compassion. The bison, with their powerful statures and shaggy coats, stand calmly, accepting the attention. The scene is framed by the serene beauty of nature, with snowflakes gently falling and the distant silhouette of trees providing a peaceful backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed42_2684
|
videos/HRA_part0/2684.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 heroic firefighter, clad in full gear and a yellow helmet, stands in a lush, green forest near a majestic waterfall, holding a gerbil gently in his hands. He carefully wipes water from the small animal's face, ensuring its safety, as the waterfall cascades powerfully in the background, creating a dramatic contrast between the tender moment and the raw force of nature.]"
},
{
"from": "gpt",
"value": "Normal. The hamster's movements in the video are quite uncoordinated, and the firefighter's movements are slightly uncoordinated."
}
] |
seed46_1926
|
videos/HRA_part2/1926.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, remarkably preserved and glowing with bioluminescence, orbits the Earth in a dreamlike sequence, passing over a city skyline with bright lights twinkling below. The scene transitions to the mammoth swimming gracefully underwater in a vast, clear ocean, its massive body moving effortlessly among schools of colorful fish. The camera then pulls back to reveal the mammoth floating in space once again, the blue planet Earth serving as a majestic backdrop, before returning to the serene underwater environment where it continues to swim peacefully, a surreal juxtaposition of ancient life and cosmic wonder.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth's movements in the video are not smooth."
}
] |
seed46_1632
|
videos/HRA_part2/1632.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with short brown hair, sits in a clean, organized office space filled with natural light. Dressed in a gray shirt, black vest, and jeans, he nods in agreement while conversing with someone off-camera. His demeanor is professional yet relaxed, and he gestures with his right hand during the discussion, emphasizing his points. The office environment is modern and minimalistic, featuring a wooden desk, a green plant, and a laptop, contributing to a focused and productive atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2137
|
videos/HRA_part1/2137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 osprey, a large bird of prey with brown and white feathers, soars over a placid lake, its piercing yellow eyes scanning the water below. It then swoops down with remarkable agility, its talons outstretched, aiming for a fish just below the surface. Catching its prey, it rises back into the air, now carrying a silver fish clasped firmly in its claws, the water still rippling from the osprey's dive. Against a clear blue sky, the osprey flies away, its powerful wings beating steadily, the captured fish glinting in the sunlight, illustrating the bird's hunting prowess over the serene lake landscape.]"
},
{
"from": "gpt",
"value": "Normal. The action of the osprey taking off and flying is not very continuous and smooth, there is a lack of coordination."
}
] |
seed46_1589
|
videos/HRA_part2/1589.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 European brown hare, with its distinctive large ears and hind legs, is shown swimming across a clear, tranquil lake. It paddles with its front paws and kicks with its hind legs, using its ears to keep balance as it crosses the water. The hare's face, with its alert eyes and twitching nose, is visible above the waterline, and the background features lush green vegetation and a peaceful, overcast sky. The hare's fur, matted from the water, clings to its body, highlighting its muscular form as it swims purposefully toward the opposite shore.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's movements in the video are basically normal, with slight coordination issues."
}
] |
seed44_2389
|
videos/HRA_part1/2389.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 person wearing a brown bear costume and another individual, both standing in a lush green forest, engage in playful interaction. The person in the bear suit wipes their face with a cloth, as if perspiring from the heat inside the costume, while the other person looks on with amusement. The vibrant greenery of the forest and the clear, sunny sky provide a cheerful backdrop for this lighthearted moment between friends, one of whom is dressed as a bear, playfully wiping their face as they enjoy each other's company in the great outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The person in the brown bear costume has a distorted face, twisted hands, and twisted arms, and another character also has twisted hands."
}
] |
seed44_2050
|
videos/HRA_part1/2050.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, donning a futuristic silver jacket and dark pants, races across the barren, rocky terrain of Mars under a stunning night sky filled with stars and two moons. The landscape features red soil and distant Martian mountains, with the Milky Way galaxy prominently visible above. The writer pauses mid-stride, gazing upwards in awe and inspiration, before continuing the run with determination, the dynamic scene capturing the essence of stargazing from the Red Planet.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1013
|
videos/HRA_part1/1013.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 creative writer, dressed in a futuristic silver jumpsuit and helmet, dances joyously on a meticulously designed space movie set, surrounded by intricate control panels and glowing buttons. The set is filled with high-tech equipment and large, detailed screens displaying cosmic visuals. The writer's movements are expressive and free, conveying a sense of liberation and creativity amidst the futuristic environment. As they dance, the lights from the set illuminate their figure, highlighting their passion for storytelling in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1733
|
videos/HRA_part2/1733.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 magnificent cheetah, known for its prowess on land, surprisingly takes to water, swimming in a large, lush, natural pool surrounded by verdant vegetation. The big cat, identifiable by its distinctive spots, demonstrates its adaptability as it navigates the water, its muscular body moving gracefully beneath the surface. The setting sun casts a warm glow over the scene, highlighting the cheetah's wet fur and the droplets of water displaced by its powerful strokes. This rare sight captures the animal's unexpected aquatic abilities in a serene, wild environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2725
|
videos/HRA_part0/2725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 urban alleyway, a middle-aged man wearing a worn-out brown jacket and blue jeans leans against a brick wall. He cradles a small rat in his hands, gently stroking it, while standing next to large, green dumpsters. The rat nestles in his palm, seemingly tamed and cared for, as the man looks down at it with a warm smile. Behind him, the bustling city streets are visible, with passersby and traffic lights, creating a contrast between the tenderness of the moment and the harshness of the urban environment.]"
},
{
"from": "gpt",
"value": "Bad. The man's fingers in the video are deformed, the facial features are distorted, and the overall rat is deformed."
}
] |
seed42_137
|
videos/HRA_part0/137.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a panda wearing a spacesuit floats in zero gravity, gently wiping a tear from its eye with a small cloth. Beside it, two astronauts, also in full space gear, share a tender kiss, signifying a unique 'space wedding'. The panda, adorned with a bow tie and holding a bouquet, serves as a heartwarming witness to this celestial union, all taking place against the backdrop of a starlit universe, with Earth visible through the window of the spacecraft.]"
},
{
"from": "gpt",
"value": "Normal. The panda's movements are not smooth."
}
] |
seed44_3105
|
videos/HRA_part1/3105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature woman with graying hair, wearing a brown jacket over a peach-colored top, stands against a blurry background, gesturing with her right index finger pointed outward. Moments later, she points emphatically toward the right side of the frame, her face expressing determination. She then points upward with both hands, her eyes following the direction of her gesture, suggesting a moment of revelation or realization. Finally, she points straight ahead with her right index finger, her body language conveying authority and command, all against a softly blurred backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the woman pointing in all the directions mentioned in the caption, and it does not show the woman's eyes following the direction of the woman's gesture."
}
] |
seed42_2810
|
videos/HRA_part0/2810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a black turtleneck sweater and khaki pants, walks through a sterile, white space medical facility, illuminated by soft, ambient lighting. He carries a notebook in his right hand, occasionally jotting down notes as he observes various medical procedures taking place in the background. The facility is equipped with futuristic medical equipment, including robotic surgical arms and holographic diagnostic displays, which are visible through glass walls. The writer stops at a large window overlooking a distant planet, offering a glimpse into the vastness of space, providing inspiration for his writing. Throughout the video, the focus remains on the writer's journey through the space station, capturing his curiosity and engagement with the advanced medical technology surrounding him.]"
},
{
"from": "gpt",
"value": "Normal. The writer's head and hand generation in the video have issues."
}
] |
seed42_1126
|
videos/HRA_part0/1126.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, wearing a yellow shirt and khaki shorts, is diligently scrubbing a bathroom floor, their back to the camera, with cleaning supplies visible nearby. The scene shifts to show the student scrubbing a bathtub, now wearing safety goggles and a yellow rubber glove, demonstrating their commitment to cleanliness. Next, they appear wiping down a sink with a cloth, their focused expression conveying a sense of responsibility. Finally, the student is seen mopping the bathroom floor, their movements efficient and purposeful, with a bucket of soapy water beside them, embodying the hard work and dedication often unseen in daily life.]"
},
{
"from": "gpt",
"value": "Normal. The character is missing a leg and an arm, and is suspended in the air, which is unrealistic."
}
] |
seed44_2673
|
videos/HRA_part1/2673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire, leaps into the air against the backdrop of a vibrant village scene. The village is set amidst lush greenery, with colorful houses lining the cobblestone streets. The student, wearing a yellow t-shirt and denim shorts, is captured mid-jump, their arms spread wide in exhilaration. The scene is filled with natural beauty, from the verdant foliage to the clear blue sky above. As the student jumps, they seem to embody the spirit of youth and adventure, their face alight with joy and energy. Behind them, the village bustles with life, with locals going about their daily routines and children playing nearby. The overall effect is one of vitality and happiness, capturing a fleeting moment of pure delight in a picturesque village setting.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2341
|
videos/HRA_part0/2341.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white hare, its fur thick and plush, crawls through a dense thicket of snow-laden pine trees, the texture of its coat contrasting starkly with the icy landscape. The hare's movements are cautious and deliberate, its eyes alert, as it navigates the snowy terrain in search of food. The scene is set against a backdrop of a serene winter forest, the hare's crawling motion emphasized by the slow, methodical pace, creating a sense of intimacy with the animal in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1425
|
videos/HRA_part1/1425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint town with brick-paved streets and Victorian-style buildings, a uniformed police officer stands watch over a community swimming pool filled with clear, blue water. The officer, clad in a crisp blue uniform, cap, and sunglasses, leans against a wooden fence, observing the swimmers. Children play joyfully in the shallow end, splashing each other, while adults lounge on deck chairs under colorful umbrellas. The scene is framed by lush greenery and the charming town in the background, creating a peaceful and idyllic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2381
|
videos/HRA_part0/2381.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cormorant, distinguished by its sleek black body, yellow lower mandible, and piercing eyes, is captured mid-flight over a tranquil lake, showcasing its powerful wingspan against the serene waters below. It then perches on a branch, drying its wings, revealing its unique ability to spread its feathers. Next, the bird plunges into the water, its form streamlined as it hunts beneath the surface, demonstrating its aquatic prowess. Finally, it emerges victorious, a small fish clasped in its beak, highlighting its hunting skills in the wild. Throughout, the cormorant's natural habitat, from the calm lake to the surrounding foliage, is depicted in vivid detail.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and undergo sudden changes."
}
] |
seed42_165
|
videos/HRA_part0/165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station adorned with lush greenery, a distinguished doctor, wearing a classic white lab coat over a crisp blue shirt, performs a solemn wedding ceremony. The couple, dressed in elegant spacesuits with transparent helmets, exchange loving glances as they gently caress each other's hands, symbolizing their deep connection. Behind them, a panoramic view of the Earth and stars provides a breathtaking backdrop, while the doctor's compassionate demeanor adds a touch of humanity to this extraordinary union in zero gravity.]"
},
{
"from": "gpt",
"value": "Normal. The hands of the doctor and the groom in the video are generated incorrectly."
}
] |
seed46_2947
|
videos/HRA_part2/2947.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 gray sweatshirt with the sleeves rolled up, dark pants, and black gloves, stands on a ladder propped against a white house, cleaning the rain gutters. The scene is set in the backyard, with lush green grass and shrubs in the foreground. The artist's tools, including a trowel and a bucket, are visible as they scoop out debris from the gutters. The ladder leans against the house, providing support as the artist works diligently, the greenery and peaceful suburban setting creating a serene backdrop for this everyday task.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1181
|
videos/HRA_part2/1181.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A leopard, showcasing its distinctive golden fur patterned with black rosettes, swims through a clear, sun-dappled body of water, its muscular body cutting through the liquid with surprising grace and strength. Its piercing eyes remain focused, and its ears are flattened against its head as it propels itself forward with powerful strokes, defying the typical terrestrial nature of its kind in this aquatic setting.]"
},
{
"from": "gpt",
"value": "Normal. The leopard's head disappears, the body twists, and the legs twist."
}
] |
seed46_1728
|
videos/HRA_part2/1728.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young female barista, wearing a gray apron over a black shirt, completes a transaction with a customer at a contemporary coffee shop. The cafe features wooden floors, a glass cooler, and a large digital menu display. After the sale, she turns to prepare a coffee beverage, carefully measuring ingredients into a French press. With practiced movements, she adds hot water from a stainless steel kettle and stirs the mixture. The barista then pours the freshly brewed coffee into a white ceramic cup, adding a touch of foam art on top before presenting it to the customer with a warm smile. Throughout the process, the cafe's modern decor, including high-top tables and minimalist chairs, provides a backdrop to the barista's efficient and skilled routine.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, and water cup in the video are distorted."
}
] |
seed46_32
|
videos/HRA_part2/32.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-dressed lawyer, complete with a tailored suit, tie, and leather briefcase, finds himself in an unexpected scenario: cleaning windows. With a microfiber cloth in hand, he meticulously wipes a large, clear window pane, revealing a cityscape beyond. The scene is set in a spacious office with modern decor, where natural light illuminates the room, highlighting the lawyer's dedication to detail in an unconventional task. Despite his professional attire, he approaches the chore with the same seriousness and precision as his legal work.]"
},
{
"from": "gpt",
"value": "Bad. The lawyer can be clearly seen wiping the transparent window glass in the video, with discontinuous and uncoordinated movements."
}
] |
seed44_1392
|
videos/HRA_part1/1392.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor dressed in a white lab coat and stethoscope hangs around his neck, kneels on the floor, examining a jaguar cub. The cub, with its distinctive golden fur and black spots, is crawling on the checkered tile floor, exploring its surroundings with curiosity. The room is filled with medical equipment, indicating it's likely an animal clinic. The jaguar cub's small size and playful behavior contrast sharply with the doctor's professional demeanor, creating a unique and touching scene.]"
},
{
"from": "gpt",
"value": "Bad. The doctor's hand undergoes a mutation, and an extra leg appears on the jaguar as it crawls, with its tail floating in the air."
}
] |
seed42_1309
|
videos/HRA_part0/1309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_102
|
videos/HRA_part2/102.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 museum-like setting filled with art galleries, a sleek and powerful jaguar, adorned with a golden collar, walks gracefully among the exhibits. The feline's presence captivates the attention, as it moves elegantly through the spacious hall, surrounded by classical sculptures and Renaissance paintings. Its confident stride and majestic demeanor contrast beautifully with the artistic masterpieces displayed on the walls, creating a unique juxtaposition between nature and culture. The golden collar it wears adds a touch of sophistication, making the jaguar appear almost like a living exhibit within the gallery space.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1995
|
videos/HRA_part1/1995.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 doctor, wearing a gray sweater over a white shirt, dark jeans, and black shoes, stands in his well-lit garage, surrounded by various tools and equipment. He is organizing his belongings, rearranging items on metal shelves, and sweeping the floor. The garage walls are painted a light color, and the space is cluttered yet functional. As he works, the doctor occasionally pauses to examine objects more closely, demonstrating care and attention to detail in his task of tidying up the garage environment.]"
},
{
"from": "gpt",
"value": "Normal. The man's arms and legs deform and become distorted when he moves. The object in his hand also deforms."
}
] |
seed46_1309
|
videos/HRA_part2/1309.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A courageous firefighter, clad in full gear and a yellow fire-resistant jacket, leads a calm brown horse into a shallow, clear lake during a sunny day. The firefighter gently guides the horse, which is adorned with a red blanket, into the water. Both the firefighter and the horse are knee-deep in the refreshing lake, surrounded by lush greenery and a peaceful environment, creating a heartwarming and unexpected scene of tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The horse's legs are deformed, and the firefighter's hands and face are not fully generated."
}
] |
seed44_2280
|
videos/HRA_part1/2280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a gray sweater over a white collared shirt and khaki pants, sits at a desk in a classroom after hours. The room is illuminated by natural light from a large window, casting a warm glow over the scene. The student is focused on replacing batteries in a scientific calculator, an essential tool for their studies. They carefully remove the old batteries, showing a methodical approach to the task, before inserting new ones, ensuring the device is fully functional for upcoming exams. The calculator is placed beside a stack of textbooks and notebooks, highlighting the academic environment.]"
},
{
"from": "gpt",
"value": "Bad. The student's movements in the video are not smooth."
}
] |
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 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 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. The actions are not continuous, there are sudden changes."
}
] |
seed44_2250
|
videos/HRA_part1/2250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmhand, clad in a white shirt and brown apron, gently caresses a small, fluffy yellow chick with a tender smile on his face, showcasing a moment of care and connection in a rural setting. The scene is set against a backdrop of wooden crates and greenery, highlighting the peaceful atmosphere of the farm. His hands, rough from labor yet gentle in touch, cradle the delicate creature, emphasizing the bond between man and nature.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's fingers and the chick's beak are generated incorrectly in the video."
}
] |
seed44_2425
|
videos/HRA_part1/2425.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."
}
] |
seed46_1056
|
videos/HRA_part2/1056.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature silverback gorilla sits in a lush, green environment, gently caressing a smaller gorilla with his large, expressive hands, showing tenderness and care. The silverback, with his powerful build and wise eyes, tenderly strokes the younger gorilla's back, creating a heartwarming scene of connection and affection within the primate family. This intimate moment is framed by the verdant foliage of their natural habitat, highlighting the emotional bond between these two creatures.]"
},
{
"from": "gpt",
"value": "Normal. The larger silverback gorilla's arm is not in the correct position to stroke."
}
] |
seed46_1245
|
videos/HRA_part2/1245.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful 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": "Good. Basically correct."
}
] |
seed42_2326
|
videos/HRA_part0/2326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 kitchen laboratory, a distinguished chef wearing a pristine white chef's jacket and black trousers walks purposefully toward a high-tech, glass-enclosed antimatter containment unit, which emits a soft, eerie glow. The chef's attire is impeccably clean, contrasting with the advanced technology surrounding him. He carries a small, sleek device in his right hand, possibly a tool for interacting with the antimatter. The room is filled with stainless steel counters and equipment, giving it a modern, industrial feel. The chef approaches the containment unit with determination, ready to harness the unique properties of antimatter for an extraordinary culinary creation.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers are missing in the video, and there are issues with the hat generation."
}
] |
seed44_198
|
videos/HRA_part1/198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, donning a classic white uniform with a red bandana around his neck, walks through a lush, green forest, his eyes fixed ahead with determination. Accompanied by a small, bushy-tailed squirrel perched on his shoulder, they navigate the woodland together. The chef carries a large basket, presumably filled with foraged ingredients, while the squirrel clutches an acorn in its paws, both on a mission in the vibrant, sun-dappled setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1056
|
videos/HRA_part0/1056.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mature silverback gorilla sits in a lush, green environment, gently caressing a smaller gorilla with his large, expressive hands, showing tenderness and care. The silverback, with his powerful build and wise eyes, tenderly strokes the younger gorilla's back, creating a heartwarming scene of connection and affection within the primate family. This intimate moment is framed by the verdant foliage of their natural habitat, highlighting the emotional bond between these two creatures.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1244
|
videos/HRA_part2/1244.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense, misty rainforest, a sleek black panther emerges from the undergrowth, its coat glistening with moisture. It pauses by a moss-covered tree trunk, the camera capturing every detail in high-definition clarity. The panther begins to groom itself, using its rough tongue to meticulously clean its fur, wiping away water droplets and debris, all against the lush, verdant backdrop of the rainforest environment. The focus is on the panther's self-cleaning behavior, highlighting the textures of its fur and the intricate patterns of the surrounding foliage.]"
},
{
"from": "gpt",
"value": "Normal. The black panther's movements in the video are basically normal, with slight inconsistencies."
}
] |
seed46_1837
|
videos/HRA_part2/1837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a casual outfit of a blue jacket and jeans, walks alongside a graceful gazelle through the spacious interior of a futuristic space hotel. The hotel's design features large windows showcasing the vastness of space, with Earth visible in the distance. The student and the gazelle navigate the corridors, passing by otherworldly landscapes displayed on interactive walls. At one point, they pause near a recreational area, where guests can observe cosmic phenomena through a panoramic observatory dome. Throughout their walk, the unique bond between the student and the gazelle is evident, highlighting the extraordinary nature of this extraterrestrial encounter.]"
},
{
"from": "gpt",
"value": "Bad. The student's legs appear to be completely deformed, as well as the gazelle's legs. The student's hands suddenly become longer."
}
] |
seed42_2741
|
videos/HRA_part0/2741.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating male musician, clad in a brown leather jacket, blue shirt, and black pants, gently caresses his acoustic guitar while sitting on a wooden bench. Surrounded by lush, green ferns and towering trees in a dense forest, he looks down at his instrument with a serene smile. The scene is illuminated by the soft glow of sunlight filtering through the foliage, casting dappled shadows on the mossy ground. The musician's tender touch and loving gaze convey a deep connection with his guitar, set against the serene backdrop of nature's splendor.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1262
|
videos/HRA_part2/1262.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical wet forest, an enthusiastic teacher, wearing a green shirt and khaki shorts, energetically dances among tall trees, their leaves forming a dense canopy overhead. The educator gracefully leaps and twirls, engaging with the natural surroundings, while a curious hare watches from the undergrowth, its ears perked up in interest. Sunlight filters through the foliage, casting dappled shadows on the forest floor, enhancing the magical atmosphere as the teacher continues to dance, celebrating the beauty of the environment with joyful movements.]"
},
{
"from": "gpt",
"value": "Bad. The rabbit in the video is not generated."
}
] |
seed46_2921
|
videos/HRA_part2/2921.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 yet harmonious scene, a veterinarian, dressed in a khaki safari outfit, carefully tends to a young rhinoceros in a spacious, fenced enclosure, with lush greenery visible in the background. The compassionate doctor gently examines the rhino, which is lying on a sandy surface, seemingly at ease. The rhinoceros, displaying signs of improvement, attempts to crawl forward on its front legs, indicating a recovery from a recent ailment or procedure, all under the watchful eye of the dedicated wildlife doctor.]"
},
{
"from": "gpt",
"value": "Normal. The veterinarian and the rhinoceros' movements in the video are slightly unsmooth."
}
] |
seed42_1917
|
videos/HRA_part0/1917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully cooked piece of salmon, expertly seared to achieve a perfect golden crust, sits center stage on a white ceramic plate. The salmon boasts a vibrant orange-pink interior, flaky yet moist, with a hint of dill sprinkled over it. Surrounding the fish are vibrant green asparagus spears, steamed to retain their crisp texture and natural color. Completing the dish is a drizzle of creamy sauce, likely a blend of lemon, butter, and capers, adding a touch of elegance and flavor. The plate is garnished with a sprig of parsley, enhancing the visual appeal of this exquisite salmon dish.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1863
|
videos/HRA_part2/1863.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman with auburn hair pulled back into a ponytail and wearing a gray shirt and black leggings is seen in a modern kitchen with gray cabinets and a large window. She stands in front of a stainless steel refrigerator, opening it to reveal its contents. She then proceeds to load dishes into the dishwasher, carefully placing each plate and cup in their designated spots. Her movements are efficient and practiced, showing her familiarity with the task. Throughout, the kitchen's clean lines and natural light from the window provide a bright and airy setting for this everyday domestic scene.]"
},
{
"from": "gpt",
"value": "Bad. The hands undergo deformities and mutations, and the plate also deforms while being held."
}
] |
seed46_2486
|
videos/HRA_part2/2486.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 with short brown hair, wearing a gray shirt, sits at a desk in a modern office, illuminated by overhead lights. He holds a silver pen in his right hand, scribbling intently on a sheet of graph paper. His glasses catch the light as he leans over the paper, which is filled with complex diagrams and equations. Behind him, a large window displays a view of a city skyline, reflecting the time of day as late afternoon, with the sun casting a warm glow into the room. On the desk, next to the engineer's elbow, rests a half-empty coffee mug, a reminder of his dedication to his work.]"
},
{
"from": "gpt",
"value": "Bad. The engineer's face and hands in the video have generation issues, and the coffee cup next to the engineer's elbow suddenly disappears in the middle frames."
}
] |
seed44_2390
|
videos/HRA_part1/2390.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a waiter wearing a traditional French uniform, complete with a black vest, white shirt, black bow tie, and black pants, is shown running alongside a full-grown rhinoceros. Both are moving at a steady pace across a lush, green grassland, under a bright blue sky dotted with white clouds. The waiter maintains a focused expression, while the rhinoceros runs with its head held high, creating a surreal and comical juxtaposition of elegance and wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and legs are distorted, as well as the rhinoceros's face and legs."
}
] |
seed46_2095
|
videos/HRA_part2/2095.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room filled with the scent of old books and memories, two people sit on a vintage, worn-out sofa, their faces reflecting deep sorrow. One, a woman with long, wavy brown hair, wears a simple gray sweater and blue jeans, her eyes red from crying, as she holds a well-loved teddy bear. Beside her, a man in a plaid shirt and khaki pants, his face equally stricken with grief, leans his forehead against hers, both of them finding solace in each other's presence. Tears stream down their cheeks, highlighting the raw emotion of the moment, as they seek comfort in the quiet space they share.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.