video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_2260
|
videos/HRA_part2/2260.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 badger, dressed as a waiter in a crisp white shirt, black vest, and striped bow tie, crawls across a wooden floor. The room is dimly lit, with a large, elegant chandelier hanging above. The badger moves toward a grand dining table set with fine china and silverware, passing by a towering bookshelf filled with leather-bound books. The camera captures the badger's earnest expression and the intricate details of its costume, all set against the backdrop of a lavishly decorated room.]"
},
{
"from": "gpt",
"value": "Normal. The badger's paws in the video have generation issues."
}
] |
seed42_104
|
videos/HRA_part0/104.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 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 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": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1153
|
videos/HRA_part0/1153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, wearing a brown shirt and green shorts, attentively wipes an Asian elephant's face using a small cloth. The elephant, with its trunk slightly raised, stands calmly next to a wooden structure within a spacious enclosure, possibly at a wildlife sanctuary. The man continues to clean the animal's eye area, showing care and familiarity, while the elephant remains still, indicating a trusting relationship between the two. Throughout, the worker focuses on his task, gently tending to the creature's needs in a peaceful outdoor setting.]"
},
{
"from": "gpt",
"value": "Bad. The male staff member wearing a brown top and green shorts did not appear in the video."
}
] |
seed44_2038
|
videos/HRA_part1/2038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 albatross soars gracefully over a vast, shimmering ocean, its expansive wingspan casting a shadow on the water below. The bird's plumage, a stunning blend of white and dark feathers, contrasts beautifully against the blue sky. As it glides through the air, its sharp eyes scan the sea for signs of prey. In the background, the silhouette of an island can be seen, adding depth and scale to the scene. The albatross, a symbol of freedom and endurance, continues its flight, the wind gently ruffling its feathers, embodying the spirit of the open sea.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2451
|
videos/HRA_part2/2451.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 traditional white uniform complete with a tall hat and apron, is depicted in a whimsical scene, engaged in a comical footrace with a brown hare. Both characters are mid-stride, their movements synchronized, as they dash across a lush green meadow dotted with wildflowers. The chef's expression is one of playful determination, while the hare appears equally focused, its ears perked forward. The sunny sky and vibrant landscape provide a cheerful backdrop to this unexpected competition.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2254
|
videos/HRA_part2/2254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, middle-aged with short, neatly trimmed brown hair and a well-groomed beard, pauses in his cleaning duties. Dressed in a dark green uniform with a name badge, he rests a mop against a pristine white wall. His eyes meet the camera, and he gives a slow, deliberate nod, acknowledging an unseen presence. The setting is a spotless, modern school hallway, with large windows casting soft light onto the polished floor, highlighting the cleanliness maintained by the janitor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand shows signs of abnormal mutation, and his arm exhibits deformity and distortion."
}
] |
seed46_1886
|
videos/HRA_part2/1886.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sprightly beaver, clad in rich brown fur, dashes across a lush, verdant forest floor, its bushy tail swaying energetically. The scene is captured in vibrant detail, with the beaver's small ears and alert eyes clearly visible as it navigates the underbrush. Its front paws, equipped with dexterous digits, grip the mossy ground, propelling it forward with a sense of urgency. The background features a dense thicket of trees and foliage, providing a natural habitat for the beaver's lively sprint.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1835
|
videos/HRA_part1/1835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a futuristic space movie set, a life-size animatronic moose, sporting a metallic silver spacesuit, is being wiped down by a crew member in a pristine white lab coat. The set is dominated by a large, circular spaceship door with hexagonal bolts, and features a control panel with green buttons and switches. The moose, with its antlers adorned with blinking red lights, stands against a backdrop of sleek, metallic walls and a floor grid, creating a surreal juxtaposition of nature and sci-fi technology. The crew member meticulously wipes the moose's suit, ensuring it's ready for its intergalactic scene, while the set's high-tech details add to the otherworldly atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. No scene was generated of the staff wiping the mechanical moose; the control panel with green buttons and switches is not installed on the round spaceship door in the video."
}
] |
seed46_1469
|
videos/HRA_part2/1469.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, clad in a yellow high-visibility jacket, blue jeans, and brown work boots, walks purposefully near a yellow Bobcat excavator, which is positioned on a building site filled with sand and dirt. The excavator boasts a wide bucket and sits on the sandy terrain of the lot, while the worker strides with determination, hard hat in hand, past the heavy machinery, embodying the industrious spirit of a bustling worksite.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1636
|
videos/HRA_part1/1636.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 devoted teacher wearing a VR headset and haptic gloves guides students through an immersive virtual reality space training simulation. The teacher demonstrates a caressing gesture, using the VR equipment to teach sensitive and precise movements in zero-gravity conditions. The environment is depicted with advanced graphics, showing the teacher floating among stars and planets, while the students observe from their own VR stations, mimicking the instructor's actions to learn essential space exploration skills.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1789
|
videos/HRA_part2/1789.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 agile antelope leaps majestically across the sun-drenched savanna, its powerful legs propelling it high above the golden grasses. The animal, distinguished by its brown fur and impressive horns, is captured mid-jump, with all four feet off the ground, highlighting its remarkable athleticism. In the background, a vast landscape stretches out under a clear blue sky, dotted with distant trees, emphasizing the vastness of the environment. The scene is one of raw nature, with the antelope's leap frozen in time, showcasing the beauty and grace of these wild creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2041
|
videos/HRA_part1/2041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, flat halibut fish is showcased on a wooden cutting board, its right side facing upward, displaying a clean, unblemished surface. The fish, with a length exceeding two feet, is set against a background of green herbs, lemon wedges, and a chef's knife, evoking a culinary preparation scene. The halibut's left eye is positioned prominently on the top side, indicating the fish's freshness, while its gills are slightly open, revealing the vibrant red color within. The overall setup, with the halibut as the central focus, is meticulously arranged to highlight the quality and size of the fish, perfect for a gourmet seafood dish.]"
},
{
"from": "gpt",
"value": "Bad. The fish's gills are not generated to be slightly open."
}
] |
seed44_273
|
videos/HRA_part1/273.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the heart of Turkey, a vibrant market comes alive with colors and aromas. Rows of stalls adorned with strings of bright red Turkish peppers hang from the ceiling, creating a striking contrast against the blue sky visible through the open roof. Intricately woven rugs in shades of red, green, and yellow cover the walls and floors, while golden lanterns dangle overhead. Amidst the bustling crowd, a vendor passionately promotes his goods, his gestures animated and expressive. Shoppers haggle over prices, their lively exchanges adding to the market's energetic atmosphere. The scene captures the essence of Turkish culture, blending tradition with the dynamic spirit of commerce.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2919
|
videos/HRA_part0/2919.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene, a bobcat is gently caressing a gray cat on a sandy arena floor, both animals seated facing each other. The bobcat, displaying unusual friendliness, reaches out with a paw to touch the cat's face, while the cat responds with a curious gaze. The sandy arena floor provides a textured backdrop, emphasizing the unique interaction between these two feline species. Moments later, the bobcat leans in closer to the gray cat, its paw still extended in a tender gesture, as if sharing a moment of mutual understanding within the sandy enclosure.]"
},
{
"from": "gpt",
"value": "Bad. The head and paws of the mountain cat in the video have generation issues; the head of the gray cat is generated distorted and deformed, and there are problems with the paw generation."
}
] |
seed42_1028
|
videos/HRA_part0/1028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a white spacesuit adorned with the American flag, embarks on a spacewalk to repair a satellite. Holding a specialized tool in one hand and a cleaning wipe in the other, they meticulously clean a solar panel against the backdrop of Earth, visible in the distance. The astronaut's gloved hands carefully grip the cleaning wipe as they perform maintenance tasks, ensuring the satellite's functionality. Throughout the spacewalk, the vastness of space surrounds the astronaut, highlighting the isolation and importance of their mission to repair critical equipment orbiting the planet.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1226
|
videos/HRA_part2/1226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, clad in a yellow high-visibility vest and gray trousers, crawls through a narrow tunnel within a vast, rocky quarry, his flashlight illuminating the rugged terrain. The dusty environment envelops him as he moves with determination, surrounded by towering walls of stone, showcasing the lesser-seen aspects of maintenance work in an expansive quarry setting.]"
},
{
"from": "gpt",
"value": "Bad. The character's crawling motion is not smooth."
}
] |
seed46_2654
|
videos/HRA_part2/2654.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A film director, wearing a black jacket, jeans, and a gray shirt, stands on a bustling movie set under bright lights. Holding a megaphone in one hand and gesturing emphatically with the other, he directs actors and crew members with passion and precision. The set is filled with vintage cars from the 1950s, indicating a period drama, while the director's focused gaze and expressive body language convey his dedication to capturing the perfect shot. Surrounded by a diverse cast and crew, he moves with purpose, demonstrating his leadership and vision in the dynamic environment of a film production.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and the item in their hand are distorted in the video."
}
] |
seed42_301
|
videos/HRA_part0/301.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic marlin breaches the sparkling turquoise ocean, its sleek indigo body glistening in the sunlight. The fish soars through the air, its elongated rostrum pointed skyward, before plunging back into the sea with a splash. Surrounded by the vastness of the ocean, the marlin's powerful leap is captured against a backdrop of rolling waves and a cloud-dappled sky, showcasing the beauty and grace of this magnificent marine creature.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the marlin jumping out of the water and plunging back in with basically normal movements, but there is some lack of coordination."
}
] |
seed46_1635
|
videos/HRA_part2/1635.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a zoological park, a creative director, dressed in a casual yet professional attire, intently observes a small, agile mouse crawling along a weathered wooden fence. The mouse, with its curious eyes and twitching nose, explores its surroundings with cautious determination. The director, holding a clipboard and pen, meticulously studies the creature's movements, occasionally jotting down notes. The scene captures the unique interaction between human observation and the natural behavior of wildlife in the controlled environment of a zoo.]"
},
{
"from": "gpt",
"value": "Normal. The mouse in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2646
|
videos/HRA_part0/2646.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 costumed character resembling a janitor, complete with a green jumpsuit, gray mustache, and brown hair, performs an energetic jump. This quirky figure, embodying both the roles of maintenance worker and woodland creature, is set against a neutral backdrop. The playful scene is enhanced by the addition of an animated beaver, which appears to mimic the janitor's jumping action, creating a comical and engaging visual narrative. Both characters are depicted in vibrant colors, with the beaver sporting realistic features and the janitor maintaining his distinct uniform and facial details.]"
},
{
"from": "gpt",
"value": "Bad. The beaver's head and claws, the cleaner's facial features, fingers, and feet were generated with problems."
}
] |
seed46_294
|
videos/HRA_part2/294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate teacher, donning a red top and black leggings, executes a captivating zero-gravity dance in a spacious, well-lit room. She leaps and twirls effortlessly, mimicking the weightlessness of space, as if defying Earth's gravity. Seamlessly transitioning, she begins running in place, her movements fluid and energetic, demonstrating the illusion of floating while maintaining contact with the ground. Throughout, her expressive face conveys the exhilaration and freedom of movement in a zero-gravity environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher can be clearly seen dancing in the video, but the movements are very discontinuous, and there are sudden changes in the limbs."
}
] |
seed46_1826
|
videos/HRA_part2/1826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 surprising twist, a middle-aged janitor, clad in a yellow vest and holding a mop, finds himself alone in a vast desert landscape at sunset. Surrounded by towering sand dunes and rugged terrain, he spontaneously begins to dance, his movements expressing a mix of joy and freedom. The golden hour light casts long shadows, highlighting his figure against the stark beauty of the desert. As the scene progresses, the janitor's dance becomes more spirited, his face alight with pure happiness, embodying the unexpected delight of finding joy in solitude amidst the desolate wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's limbs and body are not fully generated, the facial features are distorted, the body is deformed, and the fingers are not generated. The mop is also deformed."
}
] |
seed42_1564
|
videos/HRA_part0/1564.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer, dressed in a white shirt and brown trousers, leads a llama on a leash through the verdant pathways of a zoological park, surrounded by lush greenery and exotic plants. The llama, adorned with a decorative blanket and colorful tassels, follows obediently as the farmer guides it past various enclosures housing different species. They walk alongside a water feature, such as a pond or stream, adding to the tranquil atmosphere of the park. The farmer's attire complements the natural surroundings, creating a harmonious scene as they navigate the scenic route together.]"
},
{
"from": "gpt",
"value": "Normal. The farmer and the alpaca walk basically normally in the video, but there is some lack of coordination in their movements."
}
] |
seed42_1093
|
videos/HRA_part0/1093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white lab coat over casual attire, stands pensively on a pier overlooking a serene lake, the sky a blend of sunset orange and twilight blue. Moments later, he is seen in mid-air, having leaped from the pier, his arms spread wide in a joyful gesture. His lab coat flutters dramatically in the wind as he soars above the water, about to plunge into the lake's calm surface, the fading sunlight casting a golden glow over the scene.]"
},
{
"from": "gpt",
"value": "Bad. The jumping action of the character in the video is very unsmooth."
}
] |
seed42_2073
|
videos/HRA_part0/2073.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, a slender gazelle, marked by its distinctive tan coat and white underbelly, is shown crawling on the ground, its posture conveying a sense of caution or rest. The scene is framed by lush green grass and distant acacia trees, creating a tranquil yet alert atmosphere. The gazelle's delicate features and attentive ears are highlighted, capturing the essence of its cautious behavior in the wild. Against this serene backdrop, the animal's careful movements are emphasized, offering a unique perspective on the gazelle's survival instincts in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The generation of the gazelle's ears and horns in the video has issues."
}
] |
seed42_1656
|
videos/HRA_part0/1656.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cosmic-themed diner, a cheerful cashier, donning a red polka-dot apron over a black and white striped shirt, energetically dances behind the counter. The backdrop features a vast, detailed image of Jupiter, prominently displaying its iconic Great Red Spot. The cashier's playful movements contrast with the majestic, distant planet, creating a whimsical yet awe-inspiring scene. Patrons enjoy their meals, seemingly unfazed by the extraordinary setting, as the cashier continues to dance, infusing the space with a vibrant, lively atmosphere.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2645
|
videos/HRA_part1/2645.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 diner, a chef with a red bandana, dressed in a white apron over a black shirt, wields a large knife and cooks with intense focus. Suddenly, space police officers, wearing silver armor and wielding high-tech weapons, dash through the neon-lit corridor outside the diner's large windows, chasing an unseen foe. Inside, the chef momentarily pauses, looking concerned, before continuing to expertly chop ingredients. As the police chase intensifies, a group of diverse aliens begins an impromptu dance party in the corner of the diner, moving to an unheard beat, adding a touch of unexpected joy to the tense scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1033
|
videos/HRA_part0/1033.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Asian student, wearing a yellow jacket and khaki pants, walks down a city street with a pet gerbil peeking out of his jacket pocket. The gerbil, visible from the side, has small ears and a round body, adding a touch of whimsy to the scene. The student's attire includes a dark shirt under the yellow jacket, and his pants are neatly tucked into white socks and brown shoes. The urban setting features a crosswalk and pedestrians in the background, providing context to the student's journey.]"
},
{
"from": "gpt",
"value": "Bad. The dark shirt, white socks, and brown shoes of the person in the video did not appear."
}
] |
seed44_2484
|
videos/HRA_part1/2484.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic albatross soars through a dramatic sky filled with billowing clouds, its expansive wingspan casting a shadow on the turbulent sea far below. The bird's plumage is a stunning contrast of pure white underparts and sleek, dark upperwings, accentuated by the golden hue of the setting sun. Its sharp, hooked bill and piercing eyes are focused ahead, embodying the spirit of freedom and grace as it navigates the vast, open ocean with effortless elegance. The scene is framed by the rugged coastline in the distance, highlighting the albatross's natural habitat and its role as a symbol of resilience and adaptability in the face of nature's challenges.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1511
|
videos/HRA_part1/1511.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red fox, standing in a lush green meadow under a vast blue sky, begins by shaking its bushy tail, sending droplets flying in a slow-motion spray. It then proceeds to wipe its face with a paw, leaving water droplets clinging to the fur around its eyes and nose. The fox's alert ears and curious gaze are highlighted as it pauses mid-wipe, showcasing the intimate grooming moment in stunning detail against the serene natural backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The red fox's movements are not smooth."
}
] |
seed42_209
|
videos/HRA_part0/209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male musician, donning a white button-down shirt and khaki pants, meticulously dusts a vintage gramophone with a feather duster in a warmly lit, cluttered room filled with musical instruments. His attire includes a brown belt and brown shoes, adding to his polished appearance. The room is decorated with a variety of string instruments hanging from the walls, including violins and cellos, highlighting the musician's passion for music. Throughout the scene, he continues to dust various objects, showcasing his dedication to preserving his cherished belongings, all within the cozy, wood-paneled space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight awkwardness."
}
] |
seed42_1440
|
videos/HRA_part0/1440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a dark blue cap, aviator sunglasses, and a gray shirt, is captured in high-definition. Initially, he is seen against a backdrop of lush greenery, standing tall with his hands on his hips, exuding confidence. The scene then focuses on his face, highlighting his stylish appearance and a slight smile. Next, Jay is shown from behind, gazing out at a stunning mountainous landscape, conveying a sense of adventure. Finally, he raises his right arm, pointing at something exciting in the distance, his silhouette framed by the natural beauty around him, encapsulating the essence of an outdoor enthusiast.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2109
|
videos/HRA_part2/2109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, young woman, dressed in a red tank top and denim shorts, runs barefoot across a lush, green field under a clear blue sky. She carries a mongoose in her hands, which playfully wraps its tail around her wrist. The woman's hair, tied in a high ponytail, bounces with each stride, and her face is filled with pure joy. The mongoose, alert and curious, looks around with its small, intelligent eyes, seemingly enjoying the exhilarating run alongside the woman. Their motion is fluid and free, embodying the spirit of adventure and the bond between human and nature.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs are missing, her face is blurry, the mongoose's face is not generated, and it lacks limbs."
}
] |
seed46_2345
|
videos/HRA_part2/2345.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a doctor, clad in a crisp white lab coat, stands in a vibrant jungle setting, complete with lush green foliage and exotic flowers. Accompanied by a dingo, the duo begins to dance gracefully, the doctor's stethoscope swinging rhythmically as they move. The dingo, surprisingly elegant, prances alongside, its fur glistening under the golden sunlight filtering through the canopy above. The two continue their dance, the doctor's glasses catching the light and the dingo's tail swishing in time, creating a surreal and joyful spectacle in the heart of the jungle.]"
},
{
"from": "gpt",
"value": "Bad. The person's body is distorted, the face is distorted, the legs are distorted, the feet are distorted, the arms are distorted, the wild dog's body is distorted, the face is distorted, the legs are distorted."
}
] |
seed44_2006
|
videos/HRA_part1/2006.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, reminiscent of Chris Evans, is seen in a minimalist living room with white walls and wooden floors, assembling a piece of furniture. He wears a fitted gray T-shirt, dark jeans, and a watch, his short hair perfectly styled. The room is sparsely decorated, featuring a potted plant and a small painting on the wall. The furniture he's building is a sleek, modern design, and he uses a variety of tools, including a screwdriver and an Allen wrench, demonstrating his handyman skills with ease and confidence.]"
},
{
"from": "gpt",
"value": "Bad. No plants, screwdriver, or hex key were generated."
}
] |
seed46_1129
|
videos/HRA_part2/1129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint village setting, a waiter dressed in a crisp white shirt and black pants is seen sprinting energetically between charming houses with red-tiled roofs. The houses are adorned with lush green vines and windows framed by vibrant flowers. The waiter carries a silver tray aloft, maintaining perfect balance as he navigates the cobblestone streets. Each house has its own unique character, from wooden shutters to ornate door knockers, providing a picturesque backdrop for the waiter's urgent dash. The scene is imbued with a sense of community and lively activity, as the waiter's route weaves through the heart of the village, connecting the homes with his swift, professional service.]"
},
{
"from": "gpt",
"value": "Bad. A server suddenly disappears, and the characters' legs and arms become deformed."
}
] |
seed42_1290
|
videos/HRA_part0/1290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man wearing a brown leather jacket and a tan hat sits on a large rock in the middle of a vast, grassy plain, writing intently in a small notebook. In the background, a majestic bison is seen grazing peacefully on the lush vegetation. Suddenly, the man lowers his book, revealing a look of awe and inspiration as he watches the bison. He then resumes writing, his posture reflecting deep concentration. The scene shifts to show the bison lying down, seemingly resting, as the man continues to write, now with a sense of urgency, capturing the essence of his experience in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2831
|
videos/HRA_part1/2831.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene unfolds where a costumed musician, dressed in a vibrant green hippopotamus outfit, gracefully crawls across a dimly lit stage. The stage is adorned with a red velvet curtain, adding a touch of drama. The musician's movements are slow and deliberate, almost balletic, as they crawl with an air of performance art. The costume is complete with oversized hippo ears and a large, friendly smile, creating a surreal and captivating visual display.]"
},
{
"from": "gpt",
"value": "Bad. The musicians in the video are generally generated with distortions and deformities."
}
] |
seed46_1447
|
videos/HRA_part2/1447.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ghost shrimp, nearly transparent with a slight gray tint, clings to the side of an aquarium, showcasing its delicate, see-through body and intricate internal structures. It hovers near a piece of driftwood, its multi-segmented legs and antennae visible as it interacts with its environment. The shrimp's eyes, dark and prominent against its translucent body, stand out as it explores its surroundings, highlighting its unique adaptation to freshwater habitats. Against the green backdrop of aquatic plants, the ghost shrimp's ethereal presence is captivating, offering a close-up view of its otherworldly form.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1307
|
videos/HRA_part0/1307.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef wearing a classic white uniform and toque walks alongside a bobcat on a leash in a lush, green park. The chef, holding a large bunch of fresh herbs, interacts casually with the curious bobcat, which wears a matching chef's hat, adding a touch of humor. The two stroll past a row of vibrant red tulips, drawing attention with their unusual companionship. The chef, maintaining a professional demeanor, occasionally glances at the bobcat, ensuring its comfort during their walk. The setting, a well-manicured garden with neatly trimmed hedges, provides a picturesque backdrop for this unlikely duo.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1280
|
videos/HRA_part2/1280.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, dressed in a navy uniform with a badge and a walkie-talkie on his belt, walks through a museum filled with historical artifacts. The museum exhibits a variety of items, including ancient statues, paintings, and glass cases displaying precious jewels. The officer's path takes him past a large statue, a painting of a woman, and a glass case containing a crown, as he ensures the safety and security of the museum's valuable collections. The museum's interior is grand, featuring high ceilings, marble floors, and ornate decorations, providing a fitting backdrop for the treasures it houses.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1055
|
videos/HRA_part1/1055.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 musician, adorned in a casual outfit featuring a gray turtleneck sweater and dark pants, sits on a wooden chair in a cozy, dimly lit room. Surrounded by musical instruments, the artist focuses intently on knitting a vibrant red scarf, demonstrating a surprising talent beyond music. The scene captures the individual's dual passions, highlighting their artistic versatility as they skillfully knit while sitting amongst guitars and sheet music, basking in the warm glow of a single lamp.]"
},
{
"from": "gpt",
"value": "Bad. The character's actions of knitting a scarf in the video are very unsmooth and the movements are quite uncoordinated."
}
] |
seed44_2239
|
videos/HRA_part1/2239.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint, dimly lit restaurant, a neatly dressed waiter, wearing a black apron over a crisp white shirt and black trousers, is seen wiping a table with a white cloth. Unexpectedly, a playful gray cat emerges, rubbing against the waiter's leg. The waiter pauses, gently bending down to pet the friendly feline before resuming his task, the cat now seated beside him, seemingly enjoying the attention in the cozy dining space.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand and arm have undergone deformative mutations, and the kitten has also mutated."
}
] |
seed42_1810
|
videos/HRA_part0/1810.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrial engineer in a gray shirt and khaki pants stands confidently in a modern factory, surrounded by large machinery and pipes, with a swimming pool visible through a window in the background. He then walks purposefully toward the camera, passing by the heavy industrial equipment, with the pool still visible in the distance. Next, he is seen from behind, approaching a large machine with pipes, while the pool can be glimpsed outside through the window. Finally, the engineer takes a break from his work, enjoying a refreshing swim in the outdoor pool, which is now the focal point, set against the backdrop of the industrial facility.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1906
|
videos/HRA_part1/1906.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 skilled musician, garbed in a vibrant red jacket, plays a traditional wooden flute, his eyes closed in concentration, set against a backdrop of rolling hills and lush greenery. In the foreground, an ibex, distinguished by its curved horns, leaps gracefully over a small obstacle, embodying freedom and agility. The harmonious blend of the musician's melodic tunes and the ibex's acrobatic leap creates a captivating scene, where nature and artistry coalesce beautifully under a clear blue sky.]"
},
{
"from": "gpt",
"value": "Bad. The sheep did not generate."
}
] |
seed44_1993
|
videos/HRA_part1/1993.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Caspian tern, the largest species, soars over a coastal landscape, its gray and white plumage gleaming under the sun. It has a bright orange-red bill with a black tip, and its wingspan stretches wide as it glides over the water. Perched on a sandy shore, the bird preens its feathers, revealing its distinctive black crest and elegant posture. In flight again, the tern's powerful wings propel it forward, and it banks sharply, showcasing its agility against a backdrop of rolling clouds and shimmering sea. Finally, diving gracefully into the water, it emerges triumphant with a small fish in its beak, demonstrating its hunting prowess in stunning detail.]"
},
{
"from": "gpt",
"value": "Bad. The tern's wings in the video have generation issues, and the eyes and claws were not generated."
}
] |
seed46_1346
|
videos/HRA_part2/1346.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman with a glowing face, adorned in a dazzling silver spacesuit, performs at a cosmic concert under the celestial dome of twinkling stars. She begins her act crawling across a zero-gravity stage, her movements graceful and fluid in the absence of Earth's pull. The backdrop is a breathtaking galaxy panorama, with nebulae and planets adding a surreal touch to the spectacle. The atmosphere is charged with anticipation and excitement as she interacts with the floating audience, creating an unforgettable experience in the vastness of space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed42_2329
|
videos/HRA_part0/2329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, dressed in a yellow vest and hard hat, stands in awe, experiencing time dilation as he watches a kangaroo jump in slow motion against a backdrop of a bustling city skyline at sunset. The kangaroo, mid-leap, appears weightless and graceful, its powerful hind legs propelling it forward. The worker's expression reflects a mix of surprise and fascination, as if witnessing a surreal moment where the laws of physics seem to bend. The scene is bathed in golden hour light, adding to the dreamlike quality of the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo in the video is severely distorted and deformed."
}
] |
seed44_170
|
videos/HRA_part1/170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate writer, donning a black beanie and glasses, sits at a modern desk, engrossed in typing on a sleek laptop. The scene is set in a cozy room with a brick wall and a wooden shelf filled with books, plants, and a clock. Morning sunlight softly illuminates the space, casting a warm glow on the writer's face. A cup of coffee sits nearby, a trusted companion during the creative process. The writer occasionally glances at notes spread across the desk, incorporating ideas into the digital manuscript, capturing the essence of dedication and inspiration in the art of writing.]"
},
{
"from": "gpt",
"value": "Normal. The man's fingers in the video are not fully generated and are missing parts, and his eyes are too small."
}
] |
seed44_3153
|
videos/HRA_part1/3153.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, clad in a brown jacket and blue jeans, walks along a wooden path near a lake, holding a green notebook. An otter swims in the foreground, its head occasionally popping up from the water, mirroring the writer's pace. The writer stops, looking thoughtful, then continues walking, passing a wooden post and a tree with orange leaves, suggesting an autumn day. The otter follows suit, diving under the water and reappearing alongside the writer, who now looks down at the playful creature, sharing a moment of connection in nature.]"
},
{
"from": "gpt",
"value": "Bad. The man's legs are slightly deformed, and the otter in the water also undergoes morphological mutations while swimming. The man's hands also exhibit morphological mutations."
}
] |
seed44_1518
|
videos/HRA_part1/1518.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, elegant restaurant, a human-like weasel dressed in a formal waiter's uniform, complete with a crisp white shirt, black vest, and bow tie, is shown caressing a wine glass with intricate patterns, displaying its refined touch and attention to detail. The weasel's anthropomorphic features are enhanced by its upright posture and expressive face, which conveys sophistication and professionalism. The scene is set against a backdrop of luxurious dining, with the weasel's gentle handling of the glass highlighting its dexterity and grace.]"
},
{
"from": "gpt",
"value": "Normal. The sommelier's gesture of lightly touching the wine glass in the video is not smooth and coordinated."
}
] |
seed46_152
|
videos/HRA_part2/152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 dedicated to firefighting history, a lone firefighter, dressed in full gear except for his helmet, meticulously wipes an antique fire engine, showing respect and care for the vintage piece. The museum is filled with various firefighting artifacts, creating a rich historical context. The firefighter, wearing a yellow shirt underneath his uniform, is deeply engaged in cleaning the old fire truck, highlighting the connection between present-day firefighters and their heritage. Surrounded by firefighting memorabilia, he continues to polish the vehicle, emphasizing the importance of preserving the past within the firefighting community.]"
},
{
"from": "gpt",
"value": "Normal. No yellow shirt was generated."
}
] |
seed46_2226
|
videos/HRA_part2/2226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a peaked cap, kneels in a park surrounded by green grass and trees, gently caressing a small brown hare with soft, comforting strokes. The officer's compassionate expression and careful handling of the hare, which sits calmly in the palm of his hand, convey a sense of tenderness and care. The peaceful setting, with the lush vegetation and clear sky, adds to the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2815
|
videos/HRA_part2/2815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male cashier with short brown hair and glasses, wearing a gray T-shirt and black pants, is seen lifting a large box of soda cans with both hands from a shopping cart onto a checkout counter. The store is busy with customers and products, adding to the bustling atmosphere. Moments later, he lifts another box of similar size with ease, demonstrating his strength and efficiency. The action takes place under bright fluorescent lights, highlighting the cashier's focused expression and determination as he manages the physical demands of his job.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed46_2830
|
videos/HRA_part2/2830.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cityscape illuminated by neon lights, a waiter dressed in a sleek, silver apron over a black uniform walks purposefully across a crowded outdoor plaza filled with diverse patrons enjoying their meals. Behind him, an AI pilot, recognizable by its advanced humanoid form with a polished metallic exterior and glowing blue eyes, strides confidently, carrying what appears to be a flight helmet under its arm. Both figures navigate through the bustling scene, the waiter balancing a tray laden with exotic dishes, while the AI pilot's movements are precise and efficient, highlighting the seamless integration of technology and service in this high-tech environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_2563
|
videos/HRA_part1/2563.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, clad in a crisp blue uniform and black shoes, stands in a spotless hallway illuminated by overhead lights, holding a large, black trash bag. Moments later, he walks down the hall, passing neatly arranged lockers, as he heads towards a propped-open exit door. Upon reaching the door, he pauses under the EXIT sign, preparing to step outside. Finally, he exits into the well-lit outdoors, walking towards a dumpster, his figure silhouetted against the bright sky, embodying the essence of hard work and cleanliness.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's hands and feet in the video have generation issues."
}
] |
seed44_1440
|
videos/HRA_part1/1440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a dark blue cap, aviator sunglasses, and a gray shirt, is captured in high-definition. Initially, he is seen against a backdrop of lush greenery, standing tall with his hands on his hips, exuding confidence. The scene then focuses on his face, highlighting his stylish appearance and a slight smile. Next, Jay is shown from behind, gazing out at a stunning mountainous landscape, conveying a sense of adventure. Finally, he raises his right arm, pointing at something exciting in the distance, his silhouette framed by the natural beauty around him, encapsulating the essence of an outdoor enthusiast.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not smooth."
}
] |
seed46_1196
|
videos/HRA_part2/1196.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, clad in a gray jacket and brown trousers, traverses the lush undergrowth of a temperate rainforest, his canvas and easel in tow. He pauses to study the vibrant mosses and ferns carpeting the forest floor, the emerald green foliage illuminated by dappled sunlight filtering through the dense canopy overhead. As he walks deeper into the rainforest, the artist stops at a serene spot beside a babbling brook, setting up his easel to capture the enchanting scene before him - the interplay of light and shadow, the intricate textures of the ancient trees, and the melodic sounds of nature echoing all around.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1917
|
videos/HRA_part2/1917.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."
}
] |
seed44_2062
|
videos/HRA_part1/2062.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A sparrowhawk soars majestically across a clear blue sky, its sharp eyes scanning the terrain below for any signs of movement. Its streamlined body, covered in a mottled brown and gray plumage, cuts through the air with effortless grace. The bird's hooked beak and powerful talons are on full display as it dives suddenly, plummeting towards the earth in pursuit of prey. In a burst of speed, it snatches a small rodent from the tall grass, its sharp claws closing around the struggling creature. The sparrowhawk then rises again into the heavens, carrying its prize back to its nest, a picture of strength and agility against the vastness of the sky.]"
},
{
"from": "gpt",
"value": "Bad. The rodents did not appear in the video."
}
] |
seed46_1801
|
videos/HRA_part2/1801.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teenage boy, wearing a gray jacket over a blue collared shirt, sits in a classroom with a concerned look on his face. He coughs into his elbow, drawing the attention of his peers. The room is filled with natural light, highlighting the concerned expressions of his classmates who are seated at their desks. A teacher, dressed in a dark blazer and light-colored shirt, stands nearby, watching the situation with a look of care and readiness to assist. The classroom is decorated with posters and artwork, giving it a homely and educational atmosphere.]"
},
{
"from": "gpt",
"value": "Bad. The boy's hand appears deformed."
}
] |
seed42_3165
|
videos/HRA_part0/3165.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative woman, clad in a yellow top and denim jeans, stands before a large canvas in an airy studio filled with natural light. She holds a paintbrush in her right hand, dabbing it into a vivid palette of colors, while her left hand rests on her hip. Her wavy brown hair cascades down her back as she intently focuses on her artwork, surrounded by a scattering of completed paintings and art supplies. The atmosphere is one of tranquility and inspiration, with the unfinished painting on the easel capturing the essence of her artistic process.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers and brush in the video are deformed, her body is distorted, and her face is incomplete."
}
] |
seed46_1743
|
videos/HRA_part2/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Bad. The parrot's wings are distorted and deformed in the middle frames of the video."
}
] |
seed46_2329
|
videos/HRA_part2/2329.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 construction worker, dressed in a yellow vest and hard hat, stands in awe, experiencing time dilation as he watches a kangaroo jump in slow motion against a backdrop of a bustling city skyline at sunset. The kangaroo, mid-leap, appears weightless and graceful, its powerful hind legs propelling it forward. The worker's expression reflects a mix of surprise and fascination, as if witnessing a surreal moment where the laws of physics seem to bend. The scene is bathed in golden hour light, adding to the dreamlike quality of the encounter.]"
},
{
"from": "gpt",
"value": "Bad. The kangaroo's jumping movements in the video are discontinuous and there are abrupt changes."
}
] |
seed44_2780
|
videos/HRA_part1/2780.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, portraying a member of a nanobot repair crew, leaps dramatically across a futuristic, metallic platform. Dressed in a silver jumpsuit, complete with utility belts and pouches, he soars through the air with intense focus. His movements are agile and purposeful, suggesting urgency in his mission. As he lands, ready to tackle the next task, the background features complex machinery and glowing panels, immersing the viewer in a high-tech, sci-fi environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2583
|
videos/HRA_part2/2583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a full uniform complete with a badge, gun, and hat, is tending to a lush garden in a public park. He begins by weeding around vibrant flowers, his actions gentle yet purposeful. Next, he waters the plants with a hose, the mist from the water creating a small rainbow in the sunlight. Then, he plants a new shrub, digging a hole with a small shovel and carefully placing the plant inside. Finally, he prunes a bush into shape, his movements precise as he shapes the greenery, all while maintaining his authoritative yet approachable demeanor.]"
},
{
"from": "gpt",
"value": "Bad. The police's movements in the video are very unsmooth and uncoordinated."
}
] |
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 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 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": "Bad. The person's arm and hand appear deformed."
}
] |
seed46_3081
|
videos/HRA_part2/3081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 contemporary art gallery with high ceilings and modern architecture, a janitor wearing a dark green vest, khaki pants, and a name tag, meticulously sweeps the floor. In an unexpected scene, he gently caresses a small vole that has wandered into the gallery, showing a tender side amidst the sterile environment filled with abstract paintings and sculptures. The interaction between the janitor and the vole adds a touch of warmth and humanity to the otherwise cold and impersonal space.]"
},
{
"from": "gpt",
"value": "Bad. The video does not show the cleaner touching the field mouse."
}
] |
seed42_3110
|
videos/HRA_part0/3110.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A fluffy white rabbit sits upright on a clean, wooden surface, using its paw to wipe its face meticulously, akin to a cat grooming itself. The action is repeated several times, showcasing the rabbit's cleanliness and the texture of its fur against the smooth wood. The rabbit then pauses, sitting still with its paws down and ears perked up, before resuming the wiping motion, its pink nose twitching occasionally. Throughout the sequence, the rabbit's focus remains on its grooming, offering a charming display of its self-care routine.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1911
|
videos/HRA_part0/1911.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bearded man, presumably a writer, sits cross-legged on a lush, grassy surface, wearing a blue denim jacket and dark pants. He gently caresses a small, brown bear, who reciprocates with a loving nuzzle. The bear, adorned with a red bow tie, displays affection towards the man, who smiles warmly. Both are surrounded by a serene, verdant landscape, with the man's writing materials, including a notebook and pen, visible nearby. The scene conveys a tender moment between the writer and the bear, set against a peaceful outdoor backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand, the brown bear's head, and paws in the video have generation issues."
}
] |
seed44_2636
|
videos/HRA_part1/2636.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 thoughtful male writer sits in a cluttered office, adorned with a gray beanie, black jacket, and glasses, typing on a laptop placed on a wooden desk. The room is filled with books, a typewriter, and a calendar, creating a vintage atmosphere. His hands move swiftly across the keyboard as he focuses intensely on his work, surrounded by objects that inspire creativity, such as a globe, a lamp, and a framed picture. The scene conveys a sense of dedication and passion for writing, with the man deeply engrossed in his craft amidst a space that reflects his personality and interests.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the writer's hands moving quickly on the keyboard, the actions are basically normal but there is some lack of coordination."
}
] |
seed44_2093
|
videos/HRA_part1/2093.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman, wearing a red swim cap and goggles, swims in a clear, blue pool, her form cutting through the water with ease. Suddenly, a curious coyote appears at the edge of the pool, observing the woman with interest. The animal is depicted in fine detail, its sandy fur contrasting with the lush greenery surrounding the pool area. The woman continues her laps, seemingly unaware of the coyote's presence, while the creature watches intently from the poolside, creating an unusual yet captivating scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_205
|
videos/HRA_part2/205.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 renowned actor, wearing a brown costume resembling a moose, dances gleefully in a large, empty studio with high ceilings and exposed pipes. The overhead lights cast a warm glow on the wooden floor, highlighting the actor's animated expressions and exaggerated movements. The studio walls are adorned with abstract paintings and vintage movie posters, adding a whimsical touch to the scene. As the actor continues to dance, their enthusiasm is contagious, bringing a sense of joy and playfulness to the space.]"
},
{
"from": "gpt",
"value": "Bad. The actor's limbs are missing in the video, and the face and body generation are distorted."
}
] |
seed42_2395
|
videos/HRA_part0/2395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 large, ancient-looking turtle with a weathered, brown shell and algae growth moves slowly across a lush, green forest floor, surrounded by vibrant foliage and ferns. Its wise, calm eyes peer from beneath heavy, wrinkled eyelids, and its textured skin and claws are well-adapted to its woodland habitat. The scene is peaceful, with dappled sunlight filtering through the dense canopy above, highlighting the intricate patterns on the turtle's shell as it continues its unhurried journey.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2304
|
videos/HRA_part2/2304.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, identifiable by his white uniform and toque, finds himself in an unexpected scenario, sharing a swimming pool with a large, brown bear. The pool, surrounded by lush greenery, offers a surreal setting as the chef, showing no fear, calmly floats on an inflatable raft, while the bear swims nearby, seemingly enjoying the water. Both characters coexist peacefully in this unusual scene, the chef maintaining his composure and the bear displaying a gentle demeanor, all under the clear blue sky.]"
},
{
"from": "gpt",
"value": "Normal. The chef's movements in the video are basically normal, with slight disharmony."
}
] |
seed44_1932
|
videos/HRA_part1/1932.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 inventive engineer, wearing safety goggles and a lab coat, has designed a unique, waterproof hamster-sized diving suit. The hamster, now transformed into an aquatic explorer, swims energetically in a clear fish tank, bubbles rising around it. The tank is placed on a wooden table in a cluttered workshop filled with tools and gadgets. The engineer watches intently, clipboard in hand, documenting the hamster's swimming patterns as it propels itself through the water with its tiny limbs, creating a whimsical yet scientific scene.]"
},
{
"from": "gpt",
"value": "Bad. The hamster in the video was generated abnormally."
}
] |
seed44_2375
|
videos/HRA_part1/2375.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling market under the cover of night, a worker, clad in a dark apron and white shirt, stands against the backdrop of a vibrant, neon-lit street scene. He gently caresses a bat, its wings spread open, revealing intricate details. The bat, symbolic of good luck in some cultures, is held with care and respect, highlighting the unique bond between the worker and this often-misunderstood creature. The scene is set in a lively, urban environment, where the contrast between the worker's tender interaction with the bat and the surrounding chaotic marketplace creates a compelling narrative.]"
},
{
"from": "gpt",
"value": "Normal. The bat's claws are distorted, wings are distorted, and head is distorted."
}
] |
seed42_2914
|
videos/HRA_part0/2914.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated nurse, wearing a classic white uniform and cap, checks a smoke detector in a hospital corridor, ensuring patient safety. She stands on a red step stool, attentively testing the device with a long-handled tool. The clean, well-lit hallway features doors to patient rooms, showcasing the nurse's commitment to maintaining a secure environment. Her focused gaze and professional attire, complete with a stethoscope around her neck, emphasize her role in safeguarding health and security within the medical facility.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1865
|
videos/HRA_part2/1865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two adult buffalo, with shaggy brown fur and impressive horns, engage in a tender moment. One buffalo affectionately caresses the other's face with its muzzle, displaying a rare display of gentleness and connection between these typically rugged creatures. The scene is set against a backdrop of lush grasslands and distant, rolling hills, capturing the essence of their wild habitat while highlighting the intimate bond shared by these majestic animals.]"
},
{
"from": "gpt",
"value": "Normal. The horns of the two water buffalo in the video are generated in the wrong position, and there are issues with the nose and eyes of the right water buffalo."
}
] |
seed44_2835
|
videos/HRA_part1/2835.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising yet tender scene, a large brown bear gently caresses a smaller, lighter-brown bear against the backdrop of a vast savanna landscape. The two bears sit on the golden grass, under a clear blue sky dotted with a few white clouds. The big bear has its arm around the smaller one, while the other paw is softly stroking the smaller bear's head. Both bears wear collars, indicating they might be part of a conservation program. This heartwarming interaction unfolds in a protected area of the savanna, where wildlife coexists in harmony.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_198
|
videos/HRA_part2/198.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 correct."
}
] |
seed46_1297
|
videos/HRA_part2/1297.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, dressed in a traditional white uniform and toque, encounters a curious brown bear on a winding forest path. The chef, holding a large basket of freshly picked mushrooms, stops in surprise, maintaining a cautious yet calm demeanor. The bear, intrigued by the chef's presence, stands on its hind legs, sniffing the air with interest. The scene is set in a lush, green forest, with sunlight filtering through the dense canopy, casting dappled shadows on the ground. The chef, with a look of determination, slowly backs away, keeping a steady eye on the bear, who watches intently, its ears perked up, before both continue on their respective paths, the chef returning to the kitchen and the bear disappearing back into the woods.]"
},
{
"from": "gpt",
"value": "Bad. The brown bear in the video is missing legs, and there are issues with the bear's face generation, as well as problems with the chef's face and hand generation."
}
] |
seed46_1985
|
videos/HRA_part2/1985.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, wearing swimming trunks and a smile, playfully interacts with a confident brown cat on the edge of a turquoise pool, its paws dipping into the water. The man gently splashes the cat, who responds with curiosity, showcasing their unique bond. The scene is set against a sunny, clear sky, with lush greenery in the background, highlighting the tranquility of the moment. The cat, comfortable and engaged, demonstrates its unusual fondness for water, while the man enjoys this special connection with his feline companion.]"
},
{
"from": "gpt",
"value": "Bad. The cat's face is distorted, and the paws are twisted."
}
] |
seed44_257
|
videos/HRA_part1/257.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 mesmerizing cuttlefish, displaying a captivating array of color patterns, gracefully hovers in its underwater environment. It exhibits intricate skin textures and hues, from rich purples to vibrant yellows, against a dark blue ocean backdrop. Its large, expressive eyes and eight arms, adorned with suckers, are prominently featured. The cuttlefish then changes its coloration to mimic the sandy seafloor, showcasing its remarkable camouflage abilities, all within the serene, deep-sea habitat.]"
},
{
"from": "gpt",
"value": "Bad. The squid's face in the video is deformed, and the tentacles have not been generated."
}
] |
seed46_2206
|
videos/HRA_part2/2206.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a yellow fire-resistant jacket, methodically mops the floor of a fire station common room, which features a pool table, a large flat-screen TV, and a couch. The mop bucket sits nearby, and the firefighter's focus and precision in cleaning contrast with the typically rugged image associated with firefighting. The scene highlights the everyday tasks and responsibilities of firefighters when they are not actively battling fires, emphasizing the importance of maintaining a clean and orderly living environment within the station.]"
},
{
"from": "gpt",
"value": "Bad. The firefighter's face and hands, as well as the mop, are poorly generated in the video. The mop is bent and deformed in some middle frames, and sometimes it goes straight through the mop bucket on the ground."
}
] |
seed46_2016
|
videos/HRA_part2/2016.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a majestic gorilla, adorned with a vibrant, golden crown and a silver cape, dances gracefully on a floating platform set within Neptune's ethereal atmosphere. The planet's vivid blue and green gaseous clouds swirl dramatically in the background, creating an otherworldly backdrop. The gorilla performs a series of elegant dance moves, its powerful yet gentle demeanor captivating the viewer. The platform, illuminated by a soft, celestial glow, adds to the mystical ambiance of this extraordinary interstellar dance performance.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2036
|
videos/HRA_part2/2036.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 warm, cozy kitchen filled with the golden glow of overhead lights, a waiter, now donning a chef's hat and apron over his uniform, meticulously prepares a cake. He carefully cracks eggs into a large mixing bowl, the shells falling neatly into a small bin nearby. With precision, he adds scoops of flour and sugar to the mix, the powdery ingredients forming clouds in the air. The waiter, now transformed into a baker, expertly folds the ingredients together with a large spatula, the batter smooth and free of lumps. As he preheats the oven, the anticipation of the cake's delightful aroma fills the room, promising a sweet finale to any meal.]"
},
{
"from": "gpt",
"value": "Normal. There are deformities and distortions in the hands, and the shovel in the man's hand is also deformed."
}
] |
seed46_2061
|
videos/HRA_part2/2061.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, dressed in a vibrant red tank top and black leggings, runs across a sandy trail in a lush, green forest. Her brown curly hair bounces as she moves with determination. A small, agile lizard scurries across the path ahead of her, its quick movements catching her attention. The woman momentarily looks down at the lizard, her eyes widening in surprise, before refocusing on her run, her strides strong and purposeful against the backdrop of towering trees and dappled sunlight.]"
},
{
"from": "gpt",
"value": "Bad. The lizard, woman's face, hands, and feet were generated abnormally in the video."
}
] |
seed42_2239
|
videos/HRA_part0/2239.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quaint, dimly lit restaurant, a neatly dressed waiter, wearing a black apron over a crisp white shirt and black trousers, is seen wiping a table with a white cloth. Unexpectedly, a playful gray cat emerges, rubbing against the waiter's leg. The waiter pauses, gently bending down to pet the friendly feline before resuming his task, the cat now seated beside him, seemingly enjoying the attention in the cozy dining space.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_1597
|
videos/HRA_part2/1597.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a yellow vest and gloves, stands at the edge of a vast landfill, the sprawling site of discarded waste stretching into the horizon under an overcast sky. The artist begins wiping the surface of a found object, revealing layers of rust and texture beneath the dirt, as trash and debris are scattered across the landfill in the background. Moments later, the artist continues wiping the object, now partially cleaned, revealing its industrial form against the bleak landscape of waste. Finally, the artist holds the fully wiped object, a reclaimed piece of art, against the stark backdrop of the landfill, the clouds hinting at a dramatic sky overhead.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2932
|
videos/HRA_part0/2932.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown rat is seen leaping through dense heathland, its body mid-air as it propels itself forward over the foliage. The rodent's movement is captured in detail, showcasing its agility and strength as it navigates the underbrush. The surroundings consist of abundant greenery, with the rat's jump highlighting its natural habitat among the heaths. The focus remains on the rat throughout, emphasizing its action-packed leap within the lush environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_3109
|
videos/HRA_part0/3109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned in a cozy red sweater and glasses, sits at a wooden table in a rustic cabin, illuminated by the warm glow of a lamp. She holds knitting needles and a half-completed green scarf, with a laptop displaying a novel manuscript nearby. The atmosphere is serene, with the occasional sound of knitting needles clicking and the soft clacking of keys as she types. A cup of tea sits beside her, adding to the peaceful scene. Behind her, a large window frames a view of lush greenery, providing a natural backdrop to her creative space.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3065
|
videos/HRA_part2/3065.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, casually dressed in a white T-shirt and beige shorts, walks along a stone path on campus, accompanied by a small, green lizard perched on their right shoulder. The student, wearing a backpack and baseball cap, strolls under the shade of lush trees, while the reptile remains calmly positioned, seemingly enjoying the ride. The scene captures the unusual yet harmonious relationship between the student and the lizard, both navigating the campus environment together.]"
},
{
"from": "gpt",
"value": "Bad. The lizard in the video was generated abnormally, and the student's fingers were generated deformed."
}
] |
seed44_248
|
videos/HRA_part1/248.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a majestic buffalo, with its shaggy brown fur and powerful stature, stands beneath the vibrant lights of an amusement park, visible through the trees. A carousel featuring colorful, whimsical animals spins in the background, adding to the surreal scene. Suddenly, the focus is on a young boy, perhaps five years old, wiping his hands on his jeans after enjoying a snack. Dressed in a red t-shirt and denim, he looks up with a smile, the Ferris wheel towering above him, encapsulating the essence of childhood joy and the unexpected combination of nature and entertainment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1404
|
videos/HRA_part0/1404.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating scene unfolds on a moonlit beach, where a diverse group of people, dressed in vibrant, patterned shirts and shorts, gather around a bonfire. The atmosphere is festive, with a bat flying gracefully across the night sky, its silhouette visible against the glowing embers. The crowd dances energetically to lively music, their movements fluid and joyful, while others look on, clapping and cheering. Nearby, the calm sea reflects the firelight, creating a mesmerizing, shimmering effect on the water's surface. The sandy beach, dotted with palm trees, provides a picturesque setting for this nocturnal celebration.]"
},
{
"from": "gpt",
"value": "Bad. The character's body movements are not coordinated."
}
] |
seed44_2440
|
videos/HRA_part1/2440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 domestic chicken, featuring brown and white feathers, is shown swimming in a small, clear body of water, surrounded by green grass and foliage. It paddles energetically with its feet, creating ripples on the water's surface, while its head remains dry above the waterline. The chicken's unique activity is captured in a series of shots that showcase its unexpected aquatic adventure in a natural, backyard setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_1727
|
videos/HRA_part1/1727.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform and a wide-brimmed hat, stands beside a camel at a vibrant, bustling beach, where people are swimming in the azure waters under a bright, sunny sky. The camel, adorned with colorful decorations, looks out at the ocean, while the officer, holding a leash, oversees the scene with a watchful eye. Behind them, a sandy dune leads to a lush green landscape, creating an unusual yet captivating juxtaposition of desert and seaside environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_232
|
videos/HRA_part0/232.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, distinguished by his curly hair, beard, and glasses, is seen shoveling snow in a backyard during daylight. He wears a dark jacket, gray pants, and brown boots, and is engaged in the mundane task with a sense of focus and determination. Snowflakes continue to fall gently from the cloudy sky, accumulating on the ground and surrounding trees. The artist's clothing, which includes a dark jacket, gray pants, and brown work boots, contrasts with the pristine white snow, highlighting the physicality of his task. Despite the cold weather, he remains dedicated to clearing the snow, his breath visible in the crisp air, while a small dog watches him from a distance, adding a touch of companionship to the scene.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are slightly unsmooth."
}
] |
seed44_2551
|
videos/HRA_part1/2551.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A college student, dressed in a flowing white robe with gold trim, stands in a vast, dimly lit space chamber, holding a fluffy rabbit gently against her chest. The chamber is filled with rows of benches, each occupied by similarly dressed figures, all facing an altar adorned with candles and space-themed decorations. The student caresses the rabbit lovingly, her face expressing deep reverence and peace, as the soft light from the candles illuminates the scene, casting a warm glow on everyone present. The rabbit, seemingly aware of its significant role, remains calm and still, adding a sense of serenity to the unique religious ceremony taking place among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, the rabbit's body is distorted, and the head is distorted."
}
] |
seed42_1742
|
videos/HRA_part0/1742.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 aquarium filled with clear, blue water, a translucent ghost shrimp, barely visible, floats motionless near the bottom, its delicate legs folded. It then swims upward slowly, revealing its transparent body and the tiny creature inside, before coming to a stop near the surface. The shrimp hovers there, seemingly weightless, before descending again to the sandy bottom, dotted with small stones and pieces of aquatic plants, offering a glimpse into the elusive life of this ethereal crustacean.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.