video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_2156
|
videos/HRA_part1/2156.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-lit, modern clothing store, a friendly, young female cashier with brown hair tied in a bun assists a male customer. She is shown measuring the hem of a pair of beige slacks, using a measuring tape, while the man stands patiently. The pants are held up by the customer, who wears a casual outfit consisting of a blue shirt and dark pants. The cashier, dressed in a black apron over a white blouse, carefully marks the fabric with a tailor's chalk, indicating where the alteration should be made. The scene is set against the backdrop of the store, with various racks of clothes visible in the background.]"
},
{
"from": "gpt",
"value": "Bad. The woman's hand and arm undergo abnormal mutations when making movements, and the ruler in her hand also becomes deformed. The male customer's hand also becomes deformed."
}
] |
seed44_1604
|
videos/HRA_part1/1604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a gray T-shirt and dark green shorts, carefully loads dishes into a stainless steel dishwasher in a modern kitchen. The room is brightly lit, casting clear shadows and revealing the intricate details of the kitchen, including the tile backsplash and granite countertops. The student, with short brown hair and glasses, methodically organizes the plates, bowls, and silverware, demonstrating responsibility and attention to detail. Throughout the process, the student maintains a focused demeanor, occasionally pausing to ensure each item is securely placed, all within the well-lit, contemporary kitchen environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions of the person organizing the tableware in the video are not continuous, there are sudden jumps."
}
] |
seed46_1382
|
videos/HRA_part2/1382.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 space-themed casino, a large brown bear, standing on two feet, walks with a casual gait, wearing a red shirt, blue jeans, and a gold watch. The bear is surrounded by various elements of the space casino, including a bar with neon lights, slot machines, and a large window displaying a view of the galaxy. As it strides through the casino, the bear passes by a table where alien creatures play cards, their eyes following the unexpected visitor. The atmosphere is filled with a sense of wonder and fun, as the bear continues its stroll, blending seamlessly into the otherworldly environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_268
|
videos/HRA_part2/268.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 African elephant, male, walks through a dense, green forest, its large ears flapping gently. It carries small branches on its back, and its eyes, visible through the foliage, express a sense of peace. The elephant continues its journey, passing by a tree with lush leaves, highlighting the tranquility of its surroundings. It moves forward, its massive body displacing the undergrowth, leaving a path of disturbed vegetation in its wake, all under the shade of towering trees and a filtered light that adds to the serenity of the scene.]"
},
{
"from": "gpt",
"value": "Bad. Failed to generate the small branches on the back of the African bull elephant."
}
] |
seed46_3039
|
videos/HRA_part2/3039.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful cashier, wearing a red apron over a casual outfit, is seen vacuuming a spotless living room with a modern upright vacuum cleaner, showcasing an unusual sight of a retail employee handling household chores. The room is impeccably clean, with hardwood floors and minimal furniture, highlighting the thorough cleaning process. The cashier, with her nametag visible, exhibits a sense of pride in her task, as if applying the same diligence to vacuuming as she would to serving customers. The contrast between her job as a cashier and the domestic activity adds a layer of humor and unexpectedness to the scene.]"
},
{
"from": "gpt",
"value": "Bad. The cashier's actions handling household chores in the video are not smooth."
}
] |
seed42_1094
|
videos/HRA_part0/1094.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A space worker, clad in a high-tech, neon-accented spacesuit, traverses a vast, ethereal galactic nebula, the swirling cosmic clouds of reds and purples forming a breathtaking backdrop. The figure moves with purpose, the lights from their suit casting dramatic shadows against the interstellar gas and dust. A closer shot reveals the worker's faceplate, reflecting the mesmerizing nebula, highlighting their isolated journey among the stars. As they walk, the nebula's colors swirl around them, creating a stunning visual of a human amidst the grandeur of the universe.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2080
|
videos/HRA_part2/2080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two children, a boy and a girl, both dressed in green, are dancing gleefully in a grassy meadow filled with dandelions. They perform a choreographed routine, spinning and leaping with joyful abandon. Suddenly, a vole emerges from the tall grass, peeking curiously at the dancers. Unfazed, the children continue their dance, now incorporating playful gestures towards the small mammal. The vole watches from a safe distance, its presence adding a touch of natural charm to the lively scene. Throughout the dance, the children's outfits, consisting of green shirts and khaki shorts, stand out against the lush greenery of the meadow, creating a vibrant and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Bad. The child's body and limbs undergo sudden mutations and deformities while dancing, and the face also becomes twisted and deformed. The hamster also undergoes deformation and deformities."
}
] |
seed42_1083
|
videos/HRA_part0/1083.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, verdant jungle setting, a group of intrepid explorers clad in khaki safari gear navigate a narrow, foliage-lined path, their expressions a mix of determination and awe. They pause momentarily, observing a majestic silverback gorilla ambling nearby, its powerful form moving gracefully through the underbrush. The gorilla, seemingly undisturbed by the presence of humans, continues its journey, highlighting the peaceful coexistence between wildlife and respectful visitors in this pristine natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2675
|
videos/HRA_part2/2675.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, resembling Chris Hemsworth, waters plants in a lush, green backyard garden filled with various potted plants and trees. He wears a simple white tank top, brown cargo shorts, and brown flip-flops, giving off a casual, laid-back vibe. The scene is set during the day, with bright sunlight illuminating the vibrant greenery and highlighting the actor's chiseled physique. As he tends to the plants, he occasionally pauses to smile at the camera, showcasing his charming personality and the peaceful atmosphere of the garden.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_265
|
videos/HRA_part0/265.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit chaparral landscape, a seasoned farmer wearing a wide-brimmed straw hat, denim overalls, and a plaid shirt is seen joyfully dancing. In the background, a jackal curiously observes from a distance, standing near a weathered wooden fence. The farmer, embodying the spirit of the land, performs lively dance moves, celebrating the beauty of nature around him, with the jackal occasionally mirroring his movements in a playful manner. The chaparral vegetation, characterized by shrubs and small trees, forms a picturesque setting for this unexpected dance performance.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed46_306
|
videos/HRA_part2/306.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 attractive male actor, donning a white tank top, beige shorts, and brown leather sandals, assembles a wooden table in a bright room with large windows and a view of greenery outside. He starts by carefully examining the instructions, his brows furrowed in concentration. Next, he skillfully uses a screwdriver to attach the legs to the tabletop, showcasing his handyman abilities. Then, he wipes his forehead with the back of his hand, a small smile on his lips, indicating satisfaction in his progress. Finally, he stands back to admire the finished product, hands on hips, revealing the completed table in the well-lit space, surrounded by lush vegetation visible through the window.]"
},
{
"from": "gpt",
"value": "Normal. The facial generation of the actor in the video is blurry, and the hands and feet are generated abnormally, with the actor's hand suddenly distorting in the middle frames."
}
] |
seed46_21
|
videos/HRA_part2/21.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with short brown hair, wearing a khaki safari shirt and matching trousers, stands in a lush, verdant enclosure at a wildlife sanctuary. He gently caresses the wrinkled, gray skin of a large hippopotamus, which towers over him, standing on its hind legs with its front paws on the man's shoulders. The man looks up at the creature with a mixture of awe and tenderness, while the hippo appears relaxed and comfortable with the interaction. The enclosure is filled with tall grasses and scattered trees, providing a natural habitat for the animal, and the man's presence suggests a close bond between human caretaker and wild creature.]"
},
{
"from": "gpt",
"value": "Bad. The hippo in the video did not place its front paws on the man's shoulders."
}
] |
seed46_2375
|
videos/HRA_part2/2375.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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling 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": "Good. Basically correct."
}
] |
seed46_1361
|
videos/HRA_part2/1361.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space opera setting, a cashier, dressed in a metallic green costume with silver accents, is seen crawling across a high-tech stage filled with holographic displays and neon lights. The cashier, wearing a helmet with a transparent visor, moves slowly and deliberately, as if navigating through a complex transaction or performing a ritualistic dance. The background is filled with an audience of alien species, all watching intently as the cashier completes their task, emphasizing the unique blend of everyday life and dramatic performance in this cosmic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3182
|
videos/HRA_part2/3182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional male chef, wearing a clean white chef's jacket with short sleeves, meticulously polishes silverware in a well-lit kitchen. The utensils, which include forks, knives, and spoons, gleam under the bright lights as he works. Behind him, a large window reveals a bustling city skyline during daytime, adding a touch of urban sophistication to the scene. The chef's focused expression and the contrast between the shiny silverware and the white chef's jacket create a visually appealing composition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3217
|
videos/HRA_part2/3217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished chef, donning a classic white chef's uniform and black pants, meticulously dusts antique wooden furniture in a well-lit room. He pauses to check his appearance in a mirror, revealing a pristine outfit complete with a chef's hat. Continuing his task, he dusts a table with care, his attire reflecting his professional role. Lastly, he polishes a wooden chair, his chef's jacket and black trousers standing out against the vintage setting, emphasizing his dual roles as a culinary expert and attentive caretaker of his dining space.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_1157
|
videos/HRA_part2/1157.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station pool, a courageous nurse, wearing a protective spacesuit with a clear helmet, fearlessly swims alongside a non-venomous cobra, which has been specially adapted for space travel. The nurse's spacesuit is adorned with patches representing various medical organizations, highlighting her dedication to healthcare even in the cosmos. The cobra, now a docile companion, glides effortlessly through the water, its scales reflecting the artificial lighting of the space station. This extraordinary scene showcases the integration of healthcare, exotic animals, and space tourism in a serene aquatic environment, encapsulating the essence of adventure and innovation in the final frontier.]"
},
{
"from": "gpt",
"value": "Normal. The cobra's swimming movements in the video are not smooth and continuous."
}
] |
seed44_1099
|
videos/HRA_part1/1099.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a meerkat wearing a green apron and a name tag stands behind a wooden cash register, located on a small island amidst a vast desert. The meerkat, resembling a human cashier, rings up purchases with expertise, surrounded by volcanic landscapes visible in the distance. The sandy terrain is dotted with various items for sale, creating a surreal marketplace. In the next moment, the meerkat walks across the sandy ground, navigating between the cash register and the products, with the volcanoes providing a dramatic backdrop to this unusual shopping experience.]"
},
{
"from": "gpt",
"value": "Bad. The action suddenly changes."
}
] |
seed42_1538
|
videos/HRA_part0/1538.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a dedicated teacher, wearing a vibrant yellow swimsuit and cap, instructs a curious jackal pup, who dons a miniature life jacket, in the art of swimming. They are in a serene, clear blue pool surrounded by lush greenery, creating a harmonious blend of nature and learning. The teacher gently supports the jackal pup, both displaying expressions of concentration and determination as they navigate the water together, embodying an unconventional yet touching teaching moment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1694
|
videos/HRA_part0/1694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic coffee shop filled with warm, golden light and the aroma of freshly brewed coffee, a young female cashier, wearing a green apron over a striped shirt, knits a vibrant red scarf during a lull in business. She sits behind the counter, surrounded by pastries, a cash register, and an espresso machine. Her focused expression and nimble fingers working the knitting needles capture the essence of making something beautiful by hand in a quaint, welcoming environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's fingers in the video are not fully generated, and the yarn is illogical."
}
] |
seed42_1200
|
videos/HRA_part0/1200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vividly contrasting scene, two young boys, one wearing a red life jacket and the other in swimming trunks, are seen engaging with a camel on a sandy shore near shallow water, under a clear blue sky. The camel, adorned with a colorful saddle, dips its head into the turquoise water, while the children look on with delight. One boy, in the red life jacket, reaches out to touch the camel, capturing a moment of unexpected interaction between land and sea creatures. The setting sun illuminates the scene, casting warm hues across the water and highlighting the unique connection between the children and the camel in this coastal environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2080
|
videos/HRA_part0/2080.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, two children, a boy and a girl, both dressed in green, are dancing gleefully in a grassy meadow filled with dandelions. They perform a choreographed routine, spinning and leaping with joyful abandon. Suddenly, a vole emerges from the tall grass, peeking curiously at the dancers. Unfazed, the children continue their dance, now incorporating playful gestures towards the small mammal. The vole watches from a safe distance, its presence adding a touch of natural charm to the lively scene. Throughout the dance, the children's outfits, consisting of green shirts and khaki shorts, stand out against the lush greenery of the meadow, creating a vibrant and engaging visual experience.]"
},
{
"from": "gpt",
"value": "Bad. The children's heads and limbs, as well as the vole's head, are generated abnormally, and the children's limbs suddenly disappear or reappear in the middle frames."
}
] |
seed42_3171
|
videos/HRA_part0/3171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman sits serenely in a sunlit room, her eyes closed, focusing deeply on her breath. She wears a simple white blouse, the fabric gently moving with each inhale and exhale, highlighting the tranquility of the moment. Sunbeams filter through sheer curtains, casting a warm glow on her face, emphasizing her peaceful expression. Her hands rest calmly in her lap, fingers slightly curled, embodying a state of deep relaxation and mindfulness. The room is sparsely decorated, with a potted plant in the corner adding a touch of nature to the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2292
|
videos/HRA_part0/2292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 safety vest and hard hat, finds himself in an unexpected scenario as he runs alongside a monkey, both moving rapidly across a cluttered urban environment. The worker, with a rugged appearance and a backpack, navigates through a cityscape filled with scaffolding and construction materials. Meanwhile, the monkey, displaying a mischievous yet determined demeanor, keeps pace, highlighting an unusual companionship between human and primate in a bustling urban setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_168
|
videos/HRA_part2/168.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single, freshly harvested oyster lies open on a bed of crushed ice, its plump, glistening flesh nestled within the rough, grey shell. The oyster's edges are jagged, contrasting with the smooth, pearly interior. A small pool of briny liquor sits at the center, reflecting the overhead lights. Surrounding the oyster are shards of ice, creating a frosty, clean environment that enhances the raw beauty of the seafood delicacy. The overall effect is a close-up, high-definition shot that captures the essence of fresh, oceanic flavors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1332
|
videos/HRA_part0/1332.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dense temperate rainforest, a wet and lush environment with moss-covered trees, a large brown capybara crawls slowly through the undergrowth. It moves deliberately, its round body and small legs barely visible among the ferns and fallen leaves. The air is thick with moisture, and the sounds of dripping water and distant wildlife fill the atmosphere. The capybara's eyes are alert, scanning its surroundings as it navigates the complex terrain of the rainforest floor.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3092
|
videos/HRA_part2/3092.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, dressed in a dark blue button-down shirt and wearing glasses, sits at a modern desk, deeply focused on writing in a notebook with a black pen. The room is illuminated by a sleek desk lamp, casting a warm glow over the workspace cluttered with blueprints, a laptop, and various tools. Behind him, a large window lets in natural light, revealing a bustling city skyline in the background, symbolizing the urban environment where innovation thrives. The engineer's posture and intense concentration convey a sense of dedication and expertise in his craft.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1774
|
videos/HRA_part2/1774.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set within the lush environment of a tropical dry forest, a young, smiling female cashier, wearing a red apron over a white blouse and black pants, energetically jumps over a small log. She lands gracefully, holding a miniature baseball bat, as if ready for an unexpected game amidst the dense vegetation. The vibrant green foliage and dappled sunlight create a vivid contrast against her outfit, capturing the spirit of adventure and playfulness in an unconventional setting.]"
},
{
"from": "gpt",
"value": "Normal. The jumping action of the character in the video is not smooth."
}
] |
seed46_3200
|
videos/HRA_part2/3200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lone jackal leaps through the air, its body stretched in mid-jump, against the backdrop of a desolate volcanic landscape. The creature, with its sandy fur and alert expression, bounds over rugged terrain as steam rises from vents in the ground. The jackal lands and pauses, ears pricked, silhouetted against the smoldering volcano that fills the horizon, its eyes reflecting the fiery glow. Moments later, it springs into action again, bounding away across the rocky, moon-like surface, leaving plumes of dust in its wake.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2596
|
videos/HRA_part2/2596.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a black jacket, blue jeans, and a gray shirt, is seen in close-up, pulling a metal lever on a movie set. The action takes place against a backdrop of a busy production environment, with crew members and equipment visible. The director's intense focus and the gritty details of the lever convey the essence of hands-on filmmaking. Moments later, the director is shown from the side, still engaged in the task, highlighting the physicality and precision required in the role. The scene is captured in high-definition, ensuring every detail of the director's action and the set is vividly portrayed.]"
},
{
"from": "gpt",
"value": "Bad. The director's hand generation in the video has issues."
}
] |
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 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 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 flying movements in the video are uncoordinated."
}
] |
seed42_1067
|
videos/HRA_part0/1067.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman, wearing a vibrant red dress and black high heels, gracefully dances in the center of a bustling restaurant. The place is filled with the warm glow of hanging lights and lively chatter from the patrons seated at their tables. She moves with confidence and joy, her dress swirling around her as she twirls to the rhythm of the live band playing in the corner. The camera captures her expressive face, full of happiness, and the admiring glances of those around her who pause to watch her performance.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2174
|
videos/HRA_part2/2174.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a classic white chef's jacket, black pants, and a black apron, stands on a wooden stool, engaged in the unexpected task of cleaning windows. He uses a squeegee and a bucket of soapy water to methodically clean the glass, revealing the bright, sunny day outside. Despite his professional attire, he tackles the chore with the same dedication he would show in the kitchen, creating an amusing juxtaposition between his culinary expertise and domestic duties. The scene is set against the backdrop of a bustling city street, visible through the window, adding a layer of urban life to the otherwise mundane activity.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2416
|
videos/HRA_part1/2416.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beautifully cooked piece of salmon is presented on a plate, its skin crispy and charred to perfection, the flesh a rich pink hue that contrasts strikingly with the green of the accompanying asparagus spears. The dish is garnished with lemon wedges and fresh dill, enhancing the vibrant colors and textures. The salmon is shown from multiple angles, revealing its succulent interior and the delicate grill marks that add depth and character to the presentation. Set against a rustic wooden table, the scene is completed by a glass of white wine and a simple white bowl containing a side of creamy mashed potatoes, offering a perfect balance of flavors and visual appeal.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_3044
|
videos/HRA_part2/3044.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, donning a clean white uniform and a traditional toque blanche hat, sits at a modern, sleek kitchen table. He is intently typing on a laptop, his fingers deftly moving across the keyboard, with the focus of someone accustomed to multitasking. The background is a bustling commercial kitchen, filled with stainless steel appliances and busy staff working in harmony. Despite the chaos around him, the chef remains composed and focused on his task, exemplifying the blend of professionalism and culinary expertise.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_2592
|
videos/HRA_part2/2592.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 focused young student sits at a wooden desk in a well-lit classroom, diligently sewing a button onto a piece of light blue fabric using a thin needle and white thread. The student, wearing a gray hoodie and blue jeans, attentively works on the sewing project, which is placed atop a larger piece of white fabric. The room is filled with natural light from a nearby window, illuminating the task at hand and highlighting the student's concentration and skill in performing this traditional craft.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2352
|
videos/HRA_part2/2352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, lush green savanna under a bright, sunny sky, a majestic Bengal tiger runs swiftly across the open grassland, its powerful muscles rippling beneath its vibrant orange coat, marked with distinctive black stripes. The tiger's piercing yellow eyes are focused ahead, conveying determination and grace in motion. The scene is framed by distant gallery-like structures, housing various wildlife exhibits, which add a unique architectural element to the natural setting. The tiger's fluid movements and the contrast between the untamed wilderness and the man-made galleries create a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1054
|
videos/HRA_part2/1054.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 softly lit room, two young siblings, a brother and sister, are getting ready for bed. The boy, wearing a blue-striped pajama set, yawns widely, his eyes half-closed, as he sits on the edge of his bed. Moments later, the girl, clad in a pink nightgown, echoes her brother's action with a delicate yawn, her hand covering her mouth, showing manners learned from family. They sit next to each other, displaying the natural bond between them, as they prepare for sleep in their cozy bedroom, the glow of the nightlight casting a warm hue over the scene.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_1796
|
videos/HRA_part0/1796.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a waiter, dressed in a black vest, white shirt, and black trousers, crawls through a network of meerkat tunnels. The tunnels are meticulously crafted from sandy soil, with intricate pathways and chambers. The waiter, displaying a sense of adventure and playfulness, carefully navigates the tight spaces, his movements mimicking those of the meerkats that typically inhabit these underground structures. His attire remains remarkably clean and undisturbed despite the crawling, highlighting the surreal nature of the scenario.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1463
|
videos/HRA_part0/1463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical dry forest, a group of five individuals, three women and two men, engage in a cleaning ritual. The women, dressed in green shirts and beige shorts, wipe leaves from a wooden table under the shade of a large tree. One of the men, wearing a yellow shirt and brown shorts, wipes the surface of a fallen log nearby. The other man, in a white shirt and blue shorts, wipes his brow, likely from the physical exertion of the task. The scene is filled with vibrant green foliage, and a sense of camaraderie and purpose is evident among the group members as they work together in the serene forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes."
}
] |
seed46_2540
|
videos/HRA_part2/2540.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 a bustling metropolis, a police officer, clad in a navy uniform and cap, stands beside a large, friendly dog. The officer gently caresses the animal's head with a smile, forming a contrast against the urban backdrop of towering skyscrapers and busy streets. This tender moment between the law enforcer and the canine companion is captured against the steel and glass skyline, offering a glimpse of compassion amidst the city's concrete jungle.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2822
|
videos/HRA_part2/2822.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor stands in a spacious, modern gymnasium, surrounded by basketball hoops. He wears a gray jacket with a yellow reflective strip and a name tag, paired with khaki pants and black shoes. Holding a large, professional camera, he focuses on capturing images of the facility. The scene is illuminated by bright overhead lights, highlighting the clean, well-maintained space. The janitor's posture and attire convey a sense of pride and responsibility in his role, as he ensures the gym remains in pristine condition.]"
},
{
"from": "gpt",
"value": "Normal. The cleaner's fingers are deformed, the face is distorted, and the camera is deformed."
}
] |
seed42_1760
|
videos/HRA_part0/1760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by soft purple lights and adorned with cosmic artwork, a young, bald writer wearing a black turtleneck and jeans sits pensively at a sleek, metallic desk. He wipes away a smudge on the pristine, reflective surface, revealing a holographic interface beneath. Around him, floating canvases display vibrant, otherworldly landscapes, while the artist himself seems lost in thought, perhaps contemplating his next masterpiece among the stars.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand appears deformed."
}
] |
seed46_2476
|
videos/HRA_part2/2476.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, clad in a brown jacket and worn jeans, kneels in a sprawling wheat field under a cloudy sky, his weathered hands digging into the fertile soil. Suddenly, the focus is on a lone wolf, its gray fur blending with the muted colors of the landscape, crawling stealthily through the tall grass at the edge of the field, its eyes fixed on an unseen prey, creating a tense atmosphere in the rural setting.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's movements in the video are not smooth and coordinated, and the wolf's movements in the grass are not smooth and coordinated."
}
] |
seed42_3184
|
videos/HRA_part0/3184.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green savanna setting, a gentle giraffe is being affectionately caressed by a human, both standing under a vast, open sky. The giraffe, with its distinctive spotted coat and long neck, leans into the touch, expressing comfort and trust. The human, wearing a khaki safari outfit, reaches up to stroke the giraffe's face, creating a tender moment of interspecies connection. The scene is framed by the natural beauty of the savanna, with distant trees and a clear blue sky, emphasizing the harmony between the human and the majestic animal.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1952
|
videos/HRA_part2/1952.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 young female cashier with a name tag, wearing a yellow shirt and black pants, is playfully jumping over a small, live hamster on the floor of a convenience store, capturing a lighthearted moment during her shift. The hamster, seen from above, scurries across the checkered floor, adding to the unexpected and amusing interaction. The cashier, still mid-jump, is framed by shelves of beverages and snacks, creating a surreal yet charming atmosphere in the store aisle. The scene is set under the bright lights of the shop, highlighting the unusual encounter between the employee and the tiny rodent.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video has a twisted body, head, arms, hands, and legs; the hamster's body is also twisted."
}
] |
seed46_1581
|
videos/HRA_part2/1581.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 spacious indoor gymnasium illuminated by natural light from large windows, four children wearing colorful clothes engage in various acts of physical exertion. One child, dressed in a red shirt and black shorts, lifts a heavy barbell above their head with a look of intense concentration, demonstrating impressive strength. Another child, wearing a yellow top and blue leggings, performs a handstand against a mirrored wall, showing remarkable balance and poise. A third child, clad in green, does pull-ups on a bar, highlighting their upper body strength. Lastly, a child in a blue outfit leaps over a series of hurdles, capturing the essence of agility and athleticism. The gym's wooden floors and equipment provide a backdrop for these dynamic scenes of youthful energy and determination.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed42_1316
|
videos/HRA_part0/1316.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a sandy beach, two smiling children, a boy and a girl, gently caress a small green lizard that rests on a patch of dry sand, surrounded by lush vegetation. The boy, wearing a blue t-shirt and blue swimming trunks, and the girl, clad in a pink dress, sit cross-legged as they tenderly pet the lizard. The scene is filled with warmth and sunlight, casting shadows of the children and the lizard onto the sandy ground. Moments later, the lizard scurries away into the foliage, and the children watch it go, their faces a mix of fascination and delight, embodying the innocence and wonder of childhood discovery.]"
},
{
"from": "gpt",
"value": "Normal. The child's hand appears deformed, and the lizard's body is also deformed."
}
] |
seed44_1494
|
videos/HRA_part1/1494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A thoughtful young student, dressed in casual attire, gently caresses a chimpanzee seated beside her, both looking straight ahead. The scene is set against the backdrop of a busy industrial area, with large oil refineries visible in the background, emitting plumes of smoke into the hazy sky. Despite the industrial setting, the focus remains on the tender interaction between the student and the chimpanzee, conveying a sense of connection and empathy amidst the urban landscape.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2319
|
videos/HRA_part0/2319.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic, space-themed setting, a large, friendly capybara wearing a golden astronaut helmet embarks on a diplomatic mission. The capybara, donning a silver spacesuit and a golden astronaut helmet, crawls purposefully across a metallic space station floor, surrounded by high-tech equipment and screens displaying cosmic visuals. Its determined gaze and deliberate movements convey the importance of its interstellar diplomatic task. Nearby, alien delegates watch curiously, their various forms and colors contrasting with the capybara's brown fur and the sterile environment. The scene conveys a sense of unity and cooperation among different species in the vastness of space.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2673
|
videos/HRA_part2/2673.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in casual attire, leaps into the air against the backdrop of a vibrant village scene. The village is set amidst lush greenery, with colorful houses lining the cobblestone streets. The student, wearing a yellow t-shirt and denim shorts, is captured mid-jump, their arms spread wide in exhilaration. The scene is filled with natural beauty, from the verdant foliage to the clear blue sky above. As the student jumps, they seem to embody the spirit of youth and adventure, their face alight with joy and energy. Behind them, the village bustles with life, with locals going about their daily routines and children playing nearby. The overall effect is one of vitality and happiness, capturing a fleeting moment of pure delight in a picturesque village setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2075
|
videos/HRA_part2/2075.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 prehistoric mammoth, covered in shaggy brown fur, walks through a barren, icy landscape with a heavy, deliberate gait. Its large tusks curve upward, and its trunk dangles loosely as it moves, its massive body leaving deep footprints in the snow. The scene is set against a bleak, overcast sky, emphasizing the creature's isolation and the harshness of its environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2412
|
videos/HRA_part0/2412.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray hoodie, black pants, and black shoes, jumps dynamically in front of a large-scale painting that depicts a swirling, cosmic-like antimatter containment facility. The artwork showcases vibrant colors and intricate details, capturing the essence of a high-energy, science fiction-inspired scene. The artist's pose, mid-air with arms extended, adds a sense of movement and creativity to the composition. The room is illuminated by a soft, ambient light, highlighting the artist's silhouette and the captivating artwork behind them.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has his limbs, body, and head generated in a twisted and missing manner."
}
] |
seed46_2514
|
videos/HRA_part2/2514.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 habitat designed to mimic Earth's savanna, a majestic rhinoceros, fitted with a specialized spacesuit, calmly walks on artificial grass under a simulated sky. Tourists, dressed in sleek, white spacesuits, observe from a safe distance behind transparent barriers, their expressions a mix of awe and curiosity. The rhino moves gracefully, its every step monitored by advanced technology to ensure its well-being in the zero-gravity environment. This unique scene captures the harmony between wildlife conservation and the boundless possibilities of space exploration, offering viewers a glimpse into a world where nature and technology coexist in the vastness of space.]"
},
{
"from": "gpt",
"value": "Bad. The rhinoceros in the video is not wearing a spacesuit, and the tourists are not behind a transparent barrier."
}
] |
seed44_2680
|
videos/HRA_part1/2680.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cozy kitchen with wooden cabinets and a checkered floor, two young children, a boy and a girl, both wearing playful animal-shaped hats, work together to load a modern, stainless steel dishwasher. The boy, donning a blue striped shirt, carefully places a large plate into the rack, while the girl, clad in a pink dress, adds smaller dishes beside it. The room is filled with natural light from a nearby window, casting warm, golden tones over the scene. As they continue their task, the siblings share a giggle, highlighting the joy in their shared responsibility.]"
},
{
"from": "gpt",
"value": "Bad. The boy's actions of setting the tableware in the video are not continuous, with sudden changes."
}
] |
seed44_1630
|
videos/HRA_part1/1630.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young, passionate writer in a vibrant red dress is captured in a series of captivating moments, all set within the lush, golden ambiance of an orchard during autumn. She begins by standing pensively, holding a vintage typewriter, embodying creativity and inspiration. Next, she's shown mid-dance, arms elegantly extended, her movements expressive and free, the typewriter now resting on the ground, symbolizing her liberation from constraints. In another scene, she leans back, laughing joyously, her feet slightly off the ground, the typewriter still visible, highlighting her uninhibited spirit. Lastly, she strikes a confident pose, hands on hips, with a serene smile, the typewriter by her side, signifying her connection to both art and nature. Throughout, the orchard's warm colors and abundant fruit provide a rich, textured setting for her expressive journey.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has missing limbs, facial and body deformities, and her fingers are not generated."
}
] |
seed42_2093
|
videos/HRA_part0/2093.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."
}
] |
seed44_276
|
videos/HRA_part1/276.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, two people clad in sportswear run side by side down a vibrant street, passing by towering skyscrapers that glisten under the bright sunlight. The runners, a man in a red shirt and black shorts, and a woman in a purple tank top and gray leggings, navigate through the urban landscape with ease. Pedestrians, some in business attire and others casually dressed, walk alongside them, creating a dynamic atmosphere. The towering buildings, adorned with reflective glass, cast long shadows across the street, adding depth and contrast to the urban setting. Throughout the video, the runners maintain their pace, their determination evident as they weave through the crowd and continue their journey among the impressive cityscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2699
|
videos/HRA_part1/2699.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, distinguished by its all-white plumage, stands tall and elegant in a shallow pond, surrounded by lush greenery and trees. Its long, slender legs, yellow-orange bill, and sharp eyesight are highlighted as it searches for prey among the reeds and water plants. The egret gracefully extends its neck, demonstrating its hunting prowess in the serene wetland environment. Moments later, it takes flight, showcasing its expansive wingspan against the clear blue sky, before landing nearby to continue its foraging activities, all within the peaceful setting of the pond and its verdant surroundings.]"
},
{
"from": "gpt",
"value": "Bad. The egret's eyes in the video have problems, the water on the river surface is generated unreasonably, and the wings are not generated on the body."
}
] |
seed46_1987
|
videos/HRA_part2/1987.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young male cashier, dressed in a gray shirt and wearing glasses, is attentively listening with a slight smile, his head tilted to one side. He stands behind a clean, organized supermarket counter, with a large, clear space in front of him. The scene is set during the day, with good lighting from overhead lights. Beside him, a female customer, wearing a brown jacket and a colorful scarf, speaks to him, her mouth open as she engages in conversation. The setting is a modern grocery store, with shelves of products visible in the background, and the atmosphere is calm and pleasant.]"
},
{
"from": "gpt",
"value": "Normal. The facial generation of the male cashier in the video has issues."
}
] |
seed44_1694
|
videos/HRA_part1/1694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, rustic coffee shop filled with warm, golden light and the aroma of freshly brewed coffee, a young female cashier, wearing a green apron over a striped shirt, knits a vibrant red scarf during a lull in business. She sits behind the counter, surrounded by pastries, a cash register, and an espresso machine. Her focused expression and nimble fingers working the knitting needles capture the essence of making something beautiful by hand in a quaint, welcoming environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1815
|
videos/HRA_part0/1815.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 whimsical scene opens with a koala, typically terrestrial, surprisingly adept in water, swimming in a serene, clear blue pool. Its brown fur glistens as it paddles with determination, showcasing an unexpected talent. The koala, wearing a small yellow swim cap, navigates the water with surprising grace, its limbs moving rhythmically. Moments later, it emerges from the pool, shaking off droplets, revealing a cozy green towel wrapped around its body. The koala then sits on the edge of the pool, seemingly pleased with its aquatic adventure, the sunlight sparkling on the water behind it.]"
},
{
"from": "gpt",
"value": "Normal. No yellow swim cap was generated."
}
] |
seed42_3097
|
videos/HRA_part0/3097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 unique setting, a male worker in a red uniform tends to an art gallery space that doubles as a swimming pool, with water visible through a glass wall. He walks along the edge of the pool, which is surrounded by artworks, including a sculpture and framed pieces on the walls. The man, wearing red swim trunks, a red polo shirt, and a black cap, interacts with the space, showcasing the blend of aquatic and artistic elements. He is seen both working and swimming, highlighting the versatility of the environment, with the water's surface shimmering under the gallery lights.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_2207
|
videos/HRA_part0/2207.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 skillful musician, clad in a black beret, black jacket, and blue jeans, sits on a wooden bench amidst lush vineyards, playing a vintage guitar with focused intensity. Nearby, a curious squirrel crawls along a vineyard post, its bushy tail swaying as it observes the musical performance from a safe distance. The rolling hills and rows of grapevines provide a picturesque backdrop, with the musician's passionate playing and the squirrel's attentive stance creating a harmonious scene in nature.]"
},
{
"from": "gpt",
"value": "Bad. The musician's arms are generated multiple times, fingers are incomplete, and the squirrel is deformed."
}
] |
seed42_1279
|
videos/HRA_part0/1279.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished lawyer, dressed in a sharp charcoal suit and red tie, leisurely walks down a bustling boardwalk at a luxurious seaside resort. With the soothing sound of waves in the background and the sun casting a warm glow, he strolls past vibrant shops and cafes. His polished leather shoes step on the wooden planks of the boardwalk, while vacationers and resort staff pass by, creating a lively atmosphere. The lawyer's confident demeanor and tailored attire stand out against the casual beachside setting, offering a glimpse into his balanced life between work and leisure.]"
},
{
"from": "gpt",
"value": "Normal. The man's walking in the video is basically normal, with slightly uncoordinated movements."
}
] |
seed44_2258
|
videos/HRA_part1/2258.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged man, reminiscent of Jason Statham, with short, dark hair and a chiseled jawline, wearing a torn gray tank top, tattered khaki pants, and combat boots, stealthily walks through a dimly lit space station corridor. The setting is a gritty, futuristic prison, with cold steel walls, flickering neon lights, and a tense atmosphere. The man moves with purpose and determination, his eyes scanning the surroundings for any sign of danger. In one shot, he pauses, listening intently, before continuing his escape mission. Throughout the sequence, the tension builds as he navigates the confined spaces of the prison, evoking a sense of suspense and urgency.]"
},
{
"from": "gpt",
"value": "Normal. The man's walking movements in the video are basically normal, with slight disharmony."
}
] |
seed44_3086
|
videos/HRA_part1/3086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a brown jacket and blue jeans walks steadily down a country road, a picturesque landscape of rolling hills and green fields stretching out behind him. Suddenly, the scene zooms in to reveal a tiny mouse scampering across the weathered wooden planks of a barn floor, its small size contrasting sharply with the vastness of the barn. The farmer continues his journey, passing by old farm equipment and haystacks, his figure growing smaller in the distance. The mouse, now outside, scurries across the ground, navigating through the cracks and crevices of the ancient barn, before disappearing into a small hole, completing the loop of rural life.]"
},
{
"from": "gpt",
"value": "Bad. The mouse generation in the video is abnormal."
}
] |
seed42_1738
|
videos/HRA_part0/1738.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green forest clearing illuminated by dappled sunlight, a man with short brown hair, wearing a blue shirt, khaki shorts, and brown shoes, stands facing a deer. The deer, with its head lowered, is a majestic eight-point stag. The man gently wipes something from the deer's face using a soft cloth, revealing a tender moment of human-animal interaction. The scene is peaceful, with the man's caring gesture toward the wild creature highlighting the connection between humans and nature.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand undergoes deformation and mutation."
}
] |
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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising 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 movements in the video are very unsmooth and uncoordinated."
}
] |
seed44_3201
|
videos/HRA_part1/3201.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, attired in a red jacket and black leggings, runs across a barren desert landscape, with a lone coyote mirroring her movements at a distance. The woman's clothes flap in the wind as she sprints, her eyes fixed ahead, determined. Meanwhile, the coyote, its sandy fur blending with the surroundings, lopes alongside, its gaze following the woman's every stride. The two continue their parallel race, the woman's red jacket and the coyote's silhouette stark against the vast, sandy terrain, under a wide, cloud-dotted sky.]"
},
{
"from": "gpt",
"value": "Bad. The woman's legs deform and mutate when she runs, as do her arms and hands, and the jackal's legs also deform and mutate when it runs."
}
] |
seed42_2014
|
videos/HRA_part0/2014.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 vivid close-up of a sea urchin reveals its intricate, symmetrical structure as it clings to a rocky surface underwater. Sunlight filters through the clear, blue water, casting a soft glow on the urchin's spines, which are a striking contrast to the dark rocks. The camera captures the water gently swaying the urchin, emphasizing its resilience in the marine environment. The scene is framed by the rocky crevices of the seabed, highlighting the creature's natural habitat, while the muted colors of the rocks and sand provide a serene backdrop for the brightly colored sea urchin.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1715
|
videos/HRA_part2/1715.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 graceful woman stands tall, embracing the sunlight that cascades upon her, highlighting her radiant smile and the vibrant colors of her floral maxi dress. She is positioned on a wooden deck, overlooking a serene lake surrounded by lush greenery, with the distant silhouette of majestic mountains providing a breathtaking backdrop. Her curly brown hair, adorned with a delicate headband, gently sways in the breeze, while her closed eyes suggest a moment of peaceful contemplation. She holds a small bunch of wildflowers in her right hand, adding a touch of nature's beauty to the scene. The warm glow of the sun, combined with the natural splendor of her surroundings, creates a harmonious atmosphere that encapsulates the essence of tranquility and connection with the outdoors.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2300
|
videos/HRA_part2/2300.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic, space-themed setting, a costumed performer dressed as a monkey is seen dancing against a backdrop of asteroid mining operations. The monkey wears a spacesuit with a helmet, moving energetically in zero gravity. Behind it, robots with mechanical arms mine valuable minerals from large asteroids, while spaceships shuttle between them. The scene combines elements of science fiction, entertainment, and industrial activity, all set against the backdrop of outer space. The monkey's playful antics contrast with the serious business of asteroid mining, creating a visually engaging and unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Bad. The actor playing the monkey in the video has unsmooth movements."
}
] |
seed46_3210
|
videos/HRA_part2/3210.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space setting, a renowned actor portrays a courageous character who masterminds a daring bank robbery on a distant planet. Dressed in a high-tech suit, the actor stealthily maneuvers through the alien bank, filled with luminescent crystals and advanced security systems. In a surprising twist, the actor gently caresses a small, friendly porcupine-like creature, which assists in the heist by using its quills to disable the security mechanisms. The scene combines elements of action, suspense, and unexpected tenderness in the vastness of outer space.]"
},
{
"from": "gpt",
"value": "Bad. The actor's movements while petting the animal in the video are not smooth."
}
] |
seed46_1740
|
videos/HRA_part2/1740.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, dressed in a white apron over a black t-shirt and jeans, throws clay on a spinning pottery wheel under the glow of bright studio lights. With intense concentration, they shape the clay into a vase, their hands moving gracefully and purposefully. The camera captures the artist's face, reflecting determination and skill, as they mold the clay. Throughout the process, the artist's attire remains consistent, and the scene is set against a backdrop of a well-lit workshop filled with various pottery tools and finished pieces.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1804
|
videos/HRA_part1/1804.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, donning a red jacket and black clothing, runs through the interior of a historic theater, illuminated by warm lights, with plush red seats and intricate ceiling details in view. He sprints past rows of empty seats, his movement contrasting with the static elegance of the venue. The camera captures his dynamic figure as he dashes across the stage, the ornate architecture of the theater framing him, evoking a sense of urgency within the grand setting. Throughout, the red of his jacket pops against the rich, dark tones of the theater's interior, highlighting his energetic run.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_223
|
videos/HRA_part1/223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station interior resembling a bank, a muscular firefighter, now a space hero, crawls through a narrow air duct lit by blue emergency lights. Dressed in a high-tech firefighting suit with a red helmet, he stealthily moves forward on a mission. He continues crawling, his gear and determination evident, as the dimly lit vent and complex machinery surround him. Suddenly, the focus is on his intense face, showcasing his resolve through the visor of his helmet, as he prepares for action. Lastly, our hero is seen in a crouched position, ready to leap into danger, his advanced firefighting equipment at the ready, within the confined space of the air duct.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1953
|
videos/HRA_part2/1953.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 koala, characterized by its small size and adorable appearance, ambles through a lush, green forest with geysers erupting majestically in the distance, creating a misty, dreamlike atmosphere. The koala, wearing a tiny backpack, explores its surroundings with curiosity, passing by ferns and moss-covered rocks. It occasionally pauses to look at the camera, as if sharing its adventure. The geysers, shooting water high into the air against a backdrop of rolling hills, add a dramatic element to the serene forest setting, all captured in stunning detail.]"
},
{
"from": "gpt",
"value": "Normal. The limbs and ears of the koala in the video have generation issues."
}
] |
seed44_1826
|
videos/HRA_part1/1826.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, and the body is deformed, with fingers not generated."
}
] |
seed44_2669
|
videos/HRA_part1/2669.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A farmer wearing a traditional conical hat and a checkered shirt walks through a lush, green landscape, holding a walking stick in his right hand. Accompanying him is a small monkey perched on his left shoulder, playfully interacting with the farmer as they stroll together. The scene is set in a tropical environment, with vibrant vegetation surrounding them and the warm sunlight filtering through the leaves, casting dappled shadows on the ground. The farmer and the monkey continue their leisurely walk, enjoying each other's company amidst the serene beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2138
|
videos/HRA_part1/2138.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a navy uniform with a badge and gun holster, is kneeling in a park, intently digging with a small shovel into a patch of dirt surrounded by green grass and shrubs. The scene is set under a clear blue sky, with the officer's focus and determination evident as they meticulously excavate the soil. Moments later, the officer, still in their navy uniform and gear, carefully sifts through the dirt with gloved hands, searching for evidence with a serious expression. The location remains the same, a serene park with lush greenery and a cloudless sky overhead.]"
},
{
"from": "gpt",
"value": "Bad. The person in the video does not have a shovel in their hand."
}
] |
seed44_1767
|
videos/HRA_part1/1767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 solitary buzzard perches majestically on a barren branch, its piercing eyes scanning the vast, sunlit savannah below for any signs of movement. The bird, with its distinct brown and white plumage, contrasts starkly against the muted tones of the landscape. Suddenly, it spreads its impressive wingspan and takes flight, gliding effortlessly over the terrain. Its sharp talons are clearly visible as it descends with laser-like precision towards a potential meal, showcasing the raw power and agility of this apex predator. The scene is set against a backdrop of rolling hills and scattered trees, bathed in the warm glow of the afternoon sun.]"
},
{
"from": "gpt",
"value": "Bad. The eagle's wings and claws are distorted in the video."
}
] |
seed42_1468
|
videos/HRA_part0/1468.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful, smiling teacher stands in a classroom filled with sunlight, wearing a stylish outfit consisting of a striped top, dark jeans, and brown boots. Her warm smile radiates positivity as she looks down at a small child, who is sitting on a chair and wearing a gray jacket and gray pants. The child returns her smile, creating a heartwarming scene of connection and joy in the educational setting. The teacher's attire, the classroom environment, and the presence of the child all contribute to a sense of happiness and engagement in learning.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1604
|
videos/HRA_part1/1604.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, dressed in a gray T-shirt and dark green shorts, carefully loads dishes into a stainless steel dishwasher in a modern kitchen. The room is brightly lit, casting clear shadows and revealing the intricate details of the kitchen, including the tile backsplash and granite countertops. The student, with short brown hair and glasses, methodically organizes the plates, bowls, and silverware, demonstrating responsibility and attention to detail. Throughout the process, the student maintains a focused demeanor, occasionally pausing to ensure each item is securely placed, all within the well-lit, contemporary kitchen environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2048
|
videos/HRA_part0/2048.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, with a brown body and lighter underbelly, playfully wipes its face with a paw, sitting upright against a backdrop of lush greenery. Nearby, a highway stretches into the horizon, lined with guardrails and dotted with cars moving in the distance, offering a contrast between nature and urban development. The otter, seemingly unperturbed by the nearby traffic, continues its grooming ritual, highlighting the coexistence of wildlife and human infrastructure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1141
|
videos/HRA_part1/1141.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a middle-aged teacher, wearing a blue shirt and khaki pants, stands in the center of a large, old theater, animatedly teaching a lesson about running. The stage is set with props from various plays, adding a touch of theatricality. Suddenly, a dingo, a wild dog native to Australia, runs onto the stage, interrupting the class. The teacher, unperturbed, incorporates the unexpected guest into the lesson, demonstrating running techniques while the dingo playfully bounds around, all under the grand chandelier of the theater.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3035
|
videos/HRA_part0/3035.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 cityscape filled with diverse restaurants, a police officer, clad in a crisp uniform with a badge and cap, stands attentively near a cozy eatery. The scene shifts subtly to focus on the officer gently caressing the head of a loyal K9 partner, who sits attentively beside him, highlighting a tender moment of connection amidst the urban environment. The pair stands out against the backdrop of restaurant signs, patrons enjoying meals, and the vibrant life of the city, capturing a blend of duty and compassion.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, arms are distorted, and the police dog's head is distorted."
}
] |
seed42_1437
|
videos/HRA_part0/1437.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stunning rainbow trout, exhibiting vibrant hues of pink, silver, and green, gracefully swims in a clear, freshwater stream, surrounded by smooth stones and lush vegetation. The water gently cascades over rocks, creating a serene environment for the fish. Sunlight filters through the surface, highlighting the trout's shimmering scales and fins as it navigates the current with effortless ease. The trout occasionally opens its mouth, filtering oxygen from the water, demonstrating its natural survival skills in the pristine aquatic habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1167
|
videos/HRA_part2/1167.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings in the early morning light of the African savanna. Suddenly, it jumps into the air, its body stretched out horizontally, with the vast, grassy plains and distant acacia trees forming a picturesque backdrop. The meerkat lands softly on the ground, its eyes wide and alert, before quickly resuming its watchful stance, ears perked and ready for any sign of danger or activity in the wild landscape that surrounds it.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1069
|
videos/HRA_part1/1069.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife park worker, clad in khaki shorts, a green shirt, and a wide-brimmed hat, interacts closely with a hippopotamus in a large, naturalistic enclosure filled with clear, blue water. The worker confidently swims alongside the hippo, which floats gracefully on its back, showcasing the unique bond between caretaker and animal in a peaceful, sunlit setting. Moments later, the worker is seen playfully engaging with the hippopotamus, which swims submerged in the water, its eyes closed in apparent bliss, highlighting the trust and connection they share in their aquatic environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2046
|
videos/HRA_part2/2046.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a dark green jacket over a gray shirt, tends to laundry in a busy laundromat. Surrounded by rows of washing machines and dryers, he checks the status of a load in a washer, occasionally glancing at the patrons around him. He then moves to a dryer, where he retrieves a bundle of freshly laundered linens, carefully folding them with practiced hands. Amidst the hum of machinery and the scent of detergent, the janitor continues his duties, maintaining order in the bustling environment. Throughout the scene, he remains focused and diligent, his actions highlighting the routine yet essential task of laundry care in a public space.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's face and hands in the video have generation issues, with the cleaner's hand suddenly distorting in the middle frames."
}
] |
seed42_1821
|
videos/HRA_part0/1821.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 mongoose, exhibiting resilience and adaptability, is seen walking through a vast, sunlit landfill. The creature, with its sandy brown fur and alert eyes, navigates the discarded human debris, from plastic bottles to broken electronics. It pauses on a pile of waste, scanning its surroundings with curiosity and survival instinct, highlighting the animal's presence in an unlikely habitat. The mongoose then continues its journey across the landfill, its small figure contrasting against the expansive landscape of garbage under the open sky.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A fluffy 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": "Bad. The rabbit's paws in the video are generated multiple times."
}
] |
seed46_142
|
videos/HRA_part2/142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A close-up shot of a fresh, whole mackerel fish, glistening under bright lights, lies on a bed of ice. The fish features intricate, dark-blue stripes over a silver body, a hallmark of its species. Its eyes are clear and shiny, indicating freshness, while its mouth is slightly open. The tail fin is curled, and the dorsal fins stand erect, showcasing the fish's natural beauty and texture. Surrounding the mackerel are ice crystals, reflecting light and adding to the icy, clean presentation of the seafood.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1343
|
videos/HRA_part0/1343.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dramatic scene, a brave firefighter, clad in full gear and a helmet, runs through a dense cosmic dust storm that engulfs a desolate landscape. The storm, swirling with hues of orange and red, is illuminated by an ethereal glow from above, casting an otherworldly light on the surroundings. As the firefighter dashes forward, a majestic buffalo emerges from the storm, its silhouette powerful against the cosmic backdrop. Both figures, the firefighter and the buffalo, embody resilience and strength as they navigate the chaotic environment, creating a striking visual narrative of survival against all odds.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1235
|
videos/HRA_part0/1235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic setting, a waiter in a crisp, white uniform gracefully carries a tray with a solar sail design etched onto it, reflecting the ambient light beautifully. The scene transitions to reveal a vast, serene pool where individuals swim leisurely, their movements creating ripples on the water's surface. The connection between these elements is seamless, as the solar sail motif continues to play a prominent role throughout the scene, symbolizing the merging of technology and tranquility. The waiter's elegant stride and the swimmers' peaceful strokes form a harmonious contrast, encapsulating the essence of a luxurious and innovative aquatic experience.]"
},
{
"from": "gpt",
"value": "Bad. The server's hand generation in the video is problematic."
}
] |
seed46_1945
|
videos/HRA_part2/1945.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished writer, donning a brown tweed jacket, sits at a wooden desk adorned with books and a typewriter, gently caressing a small, docile cheetah resting its head on the desk. The writer, with a neatly trimmed beard, looks intently at the camera, while the cheetah, with a collar and a bell, remains calm and attentive. The scene captures the unlikely companionship between the intellectual and the wild animal, set against a backdrop of a study filled with bookshelves and framed pictures.]"
},
{
"from": "gpt",
"value": "Normal. The eyes and hands of the writer, and the eyes of the cheetah in the video have issues."
}
] |
seed44_2825
|
videos/HRA_part1/2825.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer wearing a red swimming cap and goggles is seen underwater, swimming in a clear, blue pool. Above the water, a majestic lion stands on the edge of the pool, observing the swimmer. The scene is set against the backdrop of quaint towns in the distance, their rooftops visible above the trees, creating a surreal and unexpected juxtaposition of elements. The engineer's swimming motion is smooth and deliberate, contrasting with the stillness of the lion, which adds to the dreamlike quality of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1463
|
videos/HRA_part0/1463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush subtropical dry forest, a group of five individuals, three women and two men, engage in a cleaning ritual. The women, dressed in green shirts and beige shorts, wipe leaves from a wooden table under the shade of a large tree. One of the men, wearing a yellow shirt and brown shorts, wipes the surface of a fallen log nearby. The other man, in a white shirt and blue shorts, wipes his brow, likely from the physical exertion of the task. The scene is filled with vibrant green foliage, and a sense of camaraderie and purpose is evident among the group members as they work together in the serene forest environment.]"
},
{
"from": "gpt",
"value": "Bad. The number of people mentioned in the caption is incorrect, and there is an extra fallen log."
}
] |
seed46_2241
|
videos/HRA_part2/2241.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful farmer, donning a brown shirt and blue overalls, stands in a lush green field under a clear blue sky, smiling as he observes a rabbit. The rabbit, located near the center of the frame, leaps into the air with excitement, its hind legs propelling it forward in a graceful arc. The farmer's joyful expression and the rabbit's energetic jump create a heartwarming scene, capturing the simple pleasures of rural life. The setting is enhanced by the vibrant green grass and the warm sunlight, which bathes the scene in a golden glow.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.