video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_216
|
videos/HRA_part2/216.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 professional male lawyer, wearing a dark suit and a white shirt, attentively listens in a courtroom setting, his face expressing concern and focus. Seated at a wooden desk adorned with legal documents, he leans forward intently, his right hand resting on his chin in a gesture of deep consideration. The background features a traditional court setting with wood-paneled walls and a high ceiling, emphasizing the seriousness and formality of the legal proceedings. The judge and other participants are partially visible, adding context to the scene without detracting from the central figure of the engaged lawyer.]"
},
{
"from": "gpt",
"value": "Bad. The male lawyer's hand generation in the video has issues."
}
] |
seed42_175
|
videos/HRA_part0/175.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 medical facility, a man wearing a clean, white lab coat and blue surgical mask diligently wipes down advanced, high-tech equipment with precision and care. The room is illuminated by soft, ambient lighting, highlighting the sterile environment. The man's focused gaze and meticulous movements convey a sense of professionalism and dedication to maintaining the cleanliness of the facility. Around him, the walls are lined with monitors and medical devices, emphasizing the cutting-edge technology used in this extraterrestrial healthcare setting.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, with slight lack of coordination."
}
] |
seed46_1861
|
videos/HRA_part2/1861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 handsome waiter, wearing a crisp white shirt, black vest, and tie, stands in a cozy, warmly-lit room with wooden floors. He gently caresses a fluffy, white cat sitting on a table covered with a red checkered cloth. Beside him, a glass bottle and a wine glass are visible. The cat, adorned with a pink ribbon, looks content as it receives affection from the attentive waiter, whose demeanor suggests a tender, caring personality.]"
},
{
"from": "gpt",
"value": "Bad. The server's hand and the cat's head in the video have generation issues."
}
] |
seed44_1008
|
videos/HRA_part1/1008.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 fearless firefighter, clad in full gear and a protective mask, crawls determinedly across a rugged, volcanic landscape under a smoky orange sky, his actions highlighting bravery and urgency. Beside him, a fellow firefighter also crawls, both navigating the harsh terrain with focused intensity. Their mission is underscored by the dramatic setting of an erupting volcano in the background, emphasizing the high stakes and danger they face. Throughout, the two figures crawl resolutely forward, their forms silhouetted against the fiery, chaotic backdrop, symbolizing human resilience against nature's fury.]"
},
{
"from": "gpt",
"value": "Good. There is no obvious difference in consistency."
}
] |
seed46_1192
|
videos/HRA_part2/1192.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitor, dressed in a gray jacket and blue jeans, is seen crawling on the floor of a large, echoing space, perhaps a warehouse or a vast indoor market filled with various shops. His attention is riveted on an elephant figurine, intricately crafted and positioned nearby. The camera angle shifts to reveal the expansive ceiling and the bustling activity of shoppers in the background, adding a sense of scale and life to the composition. This juxtaposition of the focused janitor, the detailed elephant sculpture, and the lively shopping environment creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers are deformed, and the legs are also deformed and misshapen, with one leg not fully formed."
}
] |
seed46_1405
|
videos/HRA_part2/1405.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, curious ferret clad in a tiny green jacket ambles along a wooden floor, its alert eyes scanning its surroundings. It pauses for a moment, seemingly considering its next move, before continuing its journey. The ferret then stops again, standing on its hind legs with its front paws raised, revealing the white fur beneath the jacket. Its head turns to look directly at the camera, a mischievous glint in its eyes, before it resumes walking, the green jacket swaying with each step. Throughout the video, the ferret's movements are unhurried and deliberate, as it explores its environment with a mix of caution and curiosity.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_286
|
videos/HRA_part2/286.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, wearing a navy uniform with a badge and a black cap, sits at a desk in a sparsely decorated room with a large window in the background, casting a grid-like pattern of light and shadow. He leans forward attentively, reading a document with a serious expression, his right elbow resting on the desk and his left hand holding the page. The room is filled with a sense of calm professionalism, with the window providing a source of natural light that illuminates the officer and the paperwork, highlighting his dedication to duty.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_1182
|
videos/HRA_part0/1182.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large herd of African buffalo, distinguished by their massive curved horns and sturdy builds, gallop across a sunlit savanna, stirring up clouds of dust in their wake. The lead buffalo, a dominant male, charges ahead with determination, followed closely by the rest of the herd. They run through tall grass, which sways in the breeze, creating a dramatic contrast against the clear blue sky. The action is captured in high definition, focusing on the power and grace of these magnificent animals as they thunder across the landscape.]"
},
{
"from": "gpt",
"value": "Bad. The movements are not smooth, and there are sudden changes in the middle frames."
}
] |
seed42_326
|
videos/HRA_part0/326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a navy uniform with a badge and black tactical gear, leaps over a row of lush green vineyards under a bright blue sky, suggesting an urgent pursuit. The officer, equipped with a utility belt and a radio, lands on the other side of the vines, continuing the chase with determination. The scene captures the contrast between the peaceful landscape of the vineyard and the high-stakes action of the law enforcement pursuit.]"
},
{
"from": "gpt",
"value": "Bad. The officer in the video has missing limbs and facial features were not generated, and the radio is blurry."
}
] |
seed42_2584
|
videos/HRA_part0/2584.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a lone jackal stands amidst an otherworldly landscape of active volcanoes, its golden eyes reflecting determination. The creature is seen wiping its face with a paw, a gesture of cleansing, against a backdrop of billowing ash and molten lava flows. Surrounded by the harsh beauty of erupting peaks, the jackal's action conveys resilience and survival in the face of adversity, with the volcanoes' fiery eruptions illuminating the dramatic environment.]"
},
{
"from": "gpt",
"value": "Normal. The jackal's movements in the video are not smooth."
}
] |
seed46_1865
|
videos/HRA_part2/1865.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast, sunlit savanna, two adult buffalo, with shaggy brown fur and impressive horns, engage in a tender moment. One buffalo affectionately caresses the other's face with its muzzle, displaying a rare display of gentleness and connection between these typically rugged creatures. The scene is set against a backdrop of lush grasslands and distant, rolling hills, capturing the essence of their wild habitat while highlighting the intimate bond shared by these majestic animals.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1894
|
videos/HRA_part0/1894.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a navy suit, white shirt, and striped tie, races through a lush green forest, holding a koala in one arm. The koala, clinging tightly, wears a tiny barrister's wig and round spectacles, adding a whimsical touch to the scene. They run past tall trees, ferns, and flowers, with the lawyer's facial expressions alternating between determination and a smile, highlighting the unusual yet playful nature of the chase. The vibrant forest setting, complete with sunlight filtering through the leaves, enhances the dynamic and surreal atmosphere of the scenario.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_3078
|
videos/HRA_part2/3078.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pigeon, with its distinctive gray body and iridescent green neck feathers, perches on a concrete ledge. It has one leg tucked under its body, a common behavior for warmth, and its head is turned to look back over its shoulder. The pigeon's red webbed feet stand out against the gray urban setting, and its eyes, which are set far back in its head, give it a wide field of vision. It sits against a backdrop of a city street, with buildings and pedestrians visible in the distance, capturing a candid moment of this common urban bird.]"
},
{
"from": "gpt",
"value": "Bad. The pigeon's leg is not hidden under its body."
}
] |
seed46_1624
|
videos/HRA_part2/1624.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate, middle-aged nurse with graying hair and a face marked by worry stands in a dimly lit hospital room, her shoulders quivering as she experiences an intense emotional reaction. Dressed in a blue scrub top and black pants, she holds a clipboard against a background cluttered with medical equipment. She is depicted in close-up, her eyes closed in a moment of vulnerability, her body language conveying her internal struggle. The scene captures her in a raw, unguarded moment, her uniform rumpled and her stance unsteady, reflecting the stress and strain of her profession.]"
},
{
"from": "gpt",
"value": "Bad. The nurse's arm is missing in the video, and the fingers were not generated."
}
] |
seed44_2867
|
videos/HRA_part1/2867.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic worker, clad in a high-tech silver spacesuit and helmet, walks across the expansive surface of an enormous solar sail, which glimmers under the vivid light of a distant star. The sail, a vast expanse of shimmering material, stretches out behind the figure, capturing the celestial radiance. The worker, equipped with a portable tool kit attached to the suit, is seen moving purposefully along the sail's surface, conducting maintenance or inspection tasks in the vastness of space. The background is filled with the dark void of space, dotted with distant stars, emphasizing the isolation and grandeur of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1989
|
videos/HRA_part1/1989.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman, adorned in a futuristic, silver metallic suit with a high collar and form-fitting design, rides a majestic, reddish-brown Martian horse across a vast, rocky terrain under a dusky, pinkish-orange sky. The horse gallops gracefully, its hooves kicking up red dust from the planet's surface, as the woman leans forward with determination. Suddenly, she dismounts and begins to dance, her movements fluid and expressive, set against the barren, alien landscape dotted with distant, rugged mountains. As she dances, her silver suit catches the dim light, creating shimmering reflections that contrast with the rough, rusty-red environment of Mars.]"
},
{
"from": "gpt",
"value": "Bad. The female mentioned in the caption getting off the horse and starting to dance does not appear in the video."
}
] |
seed42_1240
|
videos/HRA_part0/1240.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A captivating scene unfolds as a musician, donning a brown leather jacket, dark pants, and a red bandana, explores a subtropical wet forest. He crawls on his hands and knees through the dense undergrowth, his face expressing determination and curiosity. The lush vegetation surrounds him, with tall trees towering overhead and a rich tapestry of ferns and mosses covering the forest floor. The air is thick with the sounds of nature, from the chirping of birds to the rustling of leaves, creating a vivid and immersive environment. As the musician continues his crawl, his passion for discovery and connection with the natural world is palpable, encapsulating the spirit of adventure and the beauty of the subtropical wet forest.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_1558
|
videos/HRA_part1/1558.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, athletic female nurse with short brown hair, wearing a navy scrubs top and gray pants, stretches her body against a white wall. She performs various stretches, including touching her toes and raising her arms overhead, highlighting her flexibility and physical fitness. The room is brightly lit, with a large window and a whiteboard in the background, providing a clinical yet dynamic setting for her routine. Throughout the sequence, she maintains a focused expression, showcasing her dedication to maintaining her physical health in a medical environment.]"
},
{
"from": "gpt",
"value": "Bad. The woman's right arm is partially missing in the video, fingers are not fully generated, eyes are blurry, and part of the clothing is missing."
}
] |
seed44_1785
|
videos/HRA_part1/1785.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, wearing a casual gray shirt, is captured in high definition as he dances alone on a vast, luxurious resort balcony. The setting sun illuminates the horizon, casting a warm glow on the scene. He moves gracefully, his body language expressing pure joy and freedom. In the background, a sprawling, upscale resort with numerous balconies and lush greenery can be seen, highlighting the exotic location. The actor's movements are fluid and expressive, conveying the essence of a carefree spirit embracing the beauty of his surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_159
|
videos/HRA_part0/159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large, male gorilla stands in a lush, green forest, engaging in a series of comical dance moves. He begins by swaying side to side, his massive body moving in time with an unseen rhythm. Suddenly, he breaks into a playful jig, his arms flailing wildly as he hops from foot to foot. The gorilla then attempts a spin, his wide grin revealing a mouthful of sharp teeth. Throughout the performance, the gorilla remains in the same spot, his dance a delightful contrast to the stillness of the surrounding environment. Despite his size and strength, the gorilla's movements are surprisingly graceful, his joyous expression captivating as he continues to dance in the heart of the forest.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1028
|
videos/HRA_part1/1028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 astronaut, clad in a white spacesuit adorned with the American flag, embarks on a spacewalk to repair a satellite. Holding a specialized tool in one hand and a cleaning wipe in the other, they meticulously clean a solar panel against the backdrop of Earth, visible in the distance. The astronaut's gloved hands carefully grip the cleaning wipe as they perform maintenance tasks, ensuring the satellite's functionality. Throughout the spacewalk, the vastness of space surrounds the astronaut, highlighting the isolation and importance of their mission to repair critical equipment orbiting the planet.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's movements in the video are not smooth and uncoordinated."
}
] |
seed44_1340
|
videos/HRA_part1/1340.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished musician, known for his captivating performances, sits in a dimly lit room with wooden floors and walls adorned with musical instruments. He is sewing a button onto his burgundy velvet jacket, his fingers adorned with silver rings. His rugged appearance is highlighted by his scruffy beard and long, wavy hair. Behind him, a large window reveals the silhouette of a tree against a gray sky, adding a touch of melancholy to the scene. Despite the somber atmosphere, his focused gaze and the presence of a vintage microphone stand nearby suggest a sense of determination and passion for his craft.]"
},
{
"from": "gpt",
"value": "Bad. The human hand shows deformities in the fingers."
}
] |
seed42_2870
|
videos/HRA_part0/2870.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director wearing a beige jacket walks through a set resembling a forest, carrying a clapboard marked 'Quantum Leap.' He stops to observe a CGI-generated rhinoceros walking past him, its movements synchronized with the director's pace. The rhinoceros, rendered with high detail, appears to interact naturally with the forest environment, while the director watches intently, his expression conveying a mix of professionalism and wonder.]"
},
{
"from": "gpt",
"value": "Normal. The rhinoceros's legs in the video have generation issues, with slight distortion and deformation in the middle frames."
}
] |
seed46_2707
|
videos/HRA_part2/2707.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, an otter, wearing a red apron and a name tag, stands behind a cash register in a quaint market, its paws adeptly handling coins and bills as it serves a line of patiently waiting customers. The otter, with its brown fur and friendly demeanor, expertly counts change and bags items, occasionally glancing up to greet each customer with a warm smile. Meanwhile, in the background, a group of otters can be seen walking together, their little feet padding across the wooden floor, creating a charming and unexpected sight in this otherwise ordinary store setting.]"
},
{
"from": "gpt",
"value": "Bad. The otter's head and paws behind the cash register and the otter walking behind in the video were generated abnormally, with the facial expressions and paws of the otter behind the cash register distorted in the middle frames."
}
] |
seed42_1971
|
videos/HRA_part0/1971.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer with short brown hair, wearing a gray shirt, sits at a modern office desk cluttered with electronics and tools, knitting a red scarf with large needles. The focus is on her hands as they deftly manipulate the yarn and needles, while a laptop with coding screensaver and a blueprint of a circuit board are visible in the background. The office space is filled with tech gadgets, books, and papers, highlighting her professional environment, yet she finds time for a personal hobby, creating a vivid red scarf amidst the technical surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_321
|
videos/HRA_part2/321.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A white rabbit sits quietly by a serene pond, the first light of sunrise on Mercury casting a pale, ethereal glow over the still waters. The sky is a deep shade of indigo, dotted with fading stars, while the distant horizon glimmers with the soft, alien light of the emerging sun. The rabbit, with its soft fur glistening with dew, prepares to take a unique plunge, as it gently enters the calm waters, creating ripples that expand across the glassy surface, under the enchanting, otherworldly beauty of a Mercury dawn.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_3105
|
videos/HRA_part1/3105.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature woman with graying hair, wearing a brown jacket over a peach-colored top, stands against a blurry background, gesturing with her right index finger pointed outward. Moments later, she points emphatically toward the right side of the frame, her face expressing determination. She then points upward with both hands, her eyes following the direction of her gesture, suggesting a moment of revelation or realization. Finally, she points straight ahead with her right index finger, her body language conveying authority and command, all against a softly blurred backdrop.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows the woman making a gesture with her hand, but the movement is not very continuous and smooth, and there is some lack of coordination."
}
] |
seed42_1695
|
videos/HRA_part0/1695.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished, middle-aged musician, wearing a black leather jacket, black jeans, and black boots, checks a smoke detector in a modern, sparsely decorated living room. He stands on a white chair, his guitar hanging from a strap around his neck, as he inspects the device with a focused expression. The room features a large window allowing ample natural light, a white couch, and a white coffee table, creating a contrast against the musician's dark attire. The scene captures a moment of domestic responsibility in the life of an artist.]"
},
{
"from": "gpt",
"value": "Bad. The white coffee table in the video was not revealed."
}
] |
seed46_1702
|
videos/HRA_part2/1702.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, with a thick, shaggy coat, powerful legs, and piercing yellow eyes, swims through a serene, crystal-clear lake surrounded by lush greenery. Its head is raised, showcasing determination, while water droplets glisten on its fur. The wolf's body, well-muscled and agile, propels it forward in the water, highlighting its surprising aquatic prowess. The landscape around the lake is lush and verdant, with tall trees providing a picturesque setting for this unexpected scene of a wolf navigating the water with ease and grace.]"
},
{
"from": "gpt",
"value": "Normal. The limbs of the gray wolf in the video are missing, and the head has not been generated."
}
] |
seed46_3212
|
videos/HRA_part2/3212.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A domestic chicken, speckled brown and white, is seen swimming in a clear mountain lake, surrounded by lush greenery and towering peaks. The bird paddles gracefully, its head held high, as it navigates the pristine waters. The landscape is breathtaking, with dense forests and majestic mountains framing the serene scene. The water shimmers under the sunlight, reflecting the vibrant scenery, while the chicken continues its unusual swim in the idyllic mountain setting.]"
},
{
"from": "gpt",
"value": "Normal. The chicken in the video is mostly shown swimming normally, with slightly uncoordinated movements."
}
] |
seed42_2808
|
videos/HRA_part0/2808.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, wearing a black jacket and blue jeans, is seen caressing a kangaroo at a busy bus stop in the heart of a city. The scene opens with the actor standing next to the marsupial, both seemingly waiting for a bus amidst the urban landscape filled with pedestrians and traffic. As the camera focuses, the actor gently strokes the kangaroo's back, showing a tender connection between them. The kangaroo, unperturbed by the surroundings, leans into the touch, its eyes closed in apparent comfort. Behind them, the bustling city life continues, with cars passing by and people going about their day, creating a contrast to the intimate moment shared between the actor and the kangaroo.]"
},
{
"from": "gpt",
"value": "Normal. The person's hand is distorted in the video, and the kangaroo's face is also distorted."
}
] |
seed46_1685
|
videos/HRA_part2/1685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two individuals, a man and a woman, are engaged in washing a car in a driveway, with lush green grass and a tree visible in the background. The man, wearing a white t-shirt and dark shorts, is seen using a hose to rinse the vehicle, while the woman, clad in a pink tank top and denim shorts, scrubs the car's side with a sponge. Both are focused on their task, with the man holding the hose and the woman applying soap to the car's exterior. They work together harmoniously, the man rinsing and the woman scrubbing, against a backdrop of a sunny day and a neatly kept suburban home.]"
},
{
"from": "gpt",
"value": "Bad. The woman's legs are deformed. Her hands are also deformed. The man's hand is distorted during the wiping process."
}
] |
seed44_1440
|
videos/HRA_part1/1440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic individual named Jay, donning a dark blue cap, aviator sunglasses, and a gray shirt, is captured in high-definition. Initially, he is seen against a backdrop of lush greenery, standing tall with his hands on his hips, exuding confidence. The scene then focuses on his face, highlighting his stylish appearance and a slight smile. Next, Jay is shown from behind, gazing out at a stunning mountainous landscape, conveying a sense of adventure. Finally, he raises his right arm, pointing at something exciting in the distance, his silhouette framed by the natural beauty around him, encapsulating the essence of an outdoor enthusiast.]"
},
{
"from": "gpt",
"value": "Bad. The human hand appears to have undergone a deformity mutation."
}
] |
seed44_198
|
videos/HRA_part1/198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, donning a classic white uniform with a red bandana around his neck, walks through a lush, green forest, his eyes fixed ahead with determination. Accompanied by a small, bushy-tailed squirrel perched on his shoulder, they navigate the woodland together. The chef carries a large basket, presumably filled with foraged ingredients, while the squirrel clutches an acorn in its paws, both on a mission in the vibrant, sun-dappled setting.]"
},
{
"from": "gpt",
"value": "Normal. The chef in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_145
|
videos/HRA_part1/145.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated female teacher, wearing a white shirt and brown overalls, is engaged in an outdoor activity, enthusiastically digging into a sandpit with a small green shovel. Children stand nearby, observing her actions with curiosity, their faces alight with anticipation, as they wear matching yellow shirts. The teacher's energetic movements and the children's attentive expressions convey a sense of learning and discovery in a playful, educational setting.]"
},
{
"from": "gpt",
"value": "Bad. The faces and hands of the female teacher and children, and the small green shovel generation have issues."
}
] |
seed42_2849
|
videos/HRA_part0/2849.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vibrant desert landscape under a warm, golden sun, two people clad in traditional white robes stand beside a camel, which is kneeling obligingly in the sand. Moments later, these individuals mount the camel, which rises to its feet, ready to embark on a journey. Subsequently, the camel starts moving, walking steadily across the sandy dunes with the riders holding on. Finally, gaining momentum, the camel begins to run, carrying the passengers across the undulating desert terrain at an exhilarating pace, their white garments billowing in the wind.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the camel and human in the video are deformed, and the facial features of the human and camel have not been generated."
}
] |
seed46_1611
|
videos/HRA_part2/1611.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus, showcasing its remarkable camouflage abilities, rests on a sandy seabed, its body appearing as a collection of scattered stones and sand patches. It then changes color and texture, mimicking a cluster of sponges and corals, demonstrating its incredible mimicry skills. Next, it displays a pattern resembling seaweed and plant life, swaying gently as if caught in an underwater current. Finally, the octopus morphs into an imitation of a rocky outcrop, complete with algae and barnacles, further highlighting its extraordinary ability to blend into various marine environments.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1889
|
videos/HRA_part0/1889.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric artist, donning a vibrant red beret and a multicolored, patterned jacket, is depicted in a studio filled with artistic clutter, including paintings, brushes, and easels. The artist is engaging in a lively dance, accompanied by a curious monkey wearing a tiny blue hat, which mirrors the artist's movements, creating a whimsical scene of creativity and playfulness set against a backdrop of artistic chaos.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2747
|
videos/HRA_part0/2747.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, dressed in a formal black suit and tie, stands solemnly at a unique space-themed memorial service. He gently caresses the sleek, metallic casket adorned with constellations, reflecting a deep sense of loss and respect. The service takes place in a futuristic, well-lit room with large windows showcasing the vastness of space, complete with stars and galaxies. The engineer's emotional connection to the deceased is evident in his closed eyes and bowed head, while mourners in the background also dressed in black, pay their respects in a setting that combines elements of space exploration and human emotion.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1399
|
videos/HRA_part2/1399.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 captivating fusion of elements, a majestic black panther, its body outlined in vibrant neon green, is depicted leaping across a cosmic landscape. The backdrop features a stunning galactic nebula, its swirling colors of pink, purple, and blue creating an ethereal atmosphere. As the panther moves gracefully, it seems to dance among the stars, its fluid movements echoing the celestial patterns around it. The nebula's gaseous tendrils appear to reach out, almost as if they too are joining in the cosmic dance, forming a harmonious scene where the boundaries between the animal kingdom and the universe blur.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_254
|
videos/HRA_part0/254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large construction crane dominates the skyline, its yellow and black body towering over a bustling cityscape at dusk. The crane's long arm stretches across the frame, adorned with industrial machinery and cables, as it stands on a partially constructed building amidst other tall structures. Workers in safety gear can be seen moving about the site, dwarfed by the massive crane, which looms against the orange and purple hues of the setting sun, casting long shadows over the urban landscape.]"
},
{
"from": "gpt",
"value": "Bad. The workers mentioned in the caption do not appear in the video."
}
] |
seed44_288
|
videos/HRA_part1/288.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful nurse with short, brown hair and glasses, wearing a patterned, blue medical scrub top and black pants, hangs framed pictures on the walls of a brightly lit hospital room. She stands on a small, yellow stool to reach the wall above a patient's bed, where a colorful, abstract artwork is already hung. The nurse carefully aligns a new frame next to it, creating a comforting environment for patients. She uses a level to ensure each piece is straight, revealing her attention to detail in the cozy, well-decorated space. Throughout, she maintains a warm smile, demonstrating her caring nature as she enhances the room's aesthetic with more framed prints.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, arms are deformed, and the object in hand is also distorted."
}
] |
seed46_2940
|
videos/HRA_part2/2940.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic bald eagle soars through a clear blue sky, its wings outstretched, revealing a span of at least six feet. It glides effortlessly over a rugged mountainous landscape, the peaks dusted with snow against the vibrant backdrop of a pine forest. The eagle's piercing yellow eyes remain fixed ahead, while its sharp, curved beak points skyward. Its powerful talons are visible beneath its body, ready to snatch prey from the ground or water below. The sunlight reflects off its brown and white plumage, highlighting the intricate feather patterns as it navigates the thermals with regal poise.]"
},
{
"from": "gpt",
"value": "Normal. The bald eagle's claws are deformed, the wings are problematic, and the tail is unreasonable."
}
] |
seed42_2868
|
videos/HRA_part0/2868.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene from a Space Reality TV Show, a waiter, dressed in a crisp white shirt and black pants, kneels down with a perplexed expression, observing a tiny hamster crawling across a futuristic, metallic surface. The hamster, wearing a miniature astronaut suit, explores its surroundings with curiosity, its movements captured in close-up detail. The waiter, now sitting cross-legged, watches the hamster with growing amusement, as the tiny astronaut continues its journey across the space station's gleaming floor, the vastness of space visible through large windows in the background.]"
},
{
"from": "gpt",
"value": "Bad. The facial generation of the server in the video is unclear, the fingers are deformed, the hamster's head is blurry, and the limbs are abnormally generated."
}
] |
seed44_1217
|
videos/HRA_part1/1217.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, embodying a rugged yet sensitive character, is depicted in a subtropical desert landscape, where sparse vegetation clings to life among sand dunes and rocky outcrops. The scene opens with a close-up of the actor's hand gently caressing the weathered bark of a mesquite tree, conveying a sense of connection with nature. Moments later, he is shown standing still, eyes closed, face uplifted, feeling the warm desert breeze on his skin, wearing a simple linen shirt and trousers that blend with the earthy tones of the surroundings. The camera then captures him walking barefoot across the sandy terrain, leaving faint footprints that quickly disappear under the shifting sands, highlighting the transient beauty of the desert. Finally, he sits cross-legged, hands resting on his knees, in a meditative pose, his face reflecting inner peace, as the sun begins to set, casting long shadows and painting the sky in hues of orange and pink.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2027
|
videos/HRA_part0/2027.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green swamp environment teeming with life, two young children, a boy and a girl, are seen energetically running and exploring. The boy wears a red t-shirt and khaki shorts, while the girl dons a yellow dress, both dressed appropriately for the outdoors. They splash through shallow water, their faces lit up with joy and wonder, surrounded by tall cattails and lily pads. A wooden bridge can be glimpsed in the background, adding to the sense of adventure in this vibrant natural setting.]"
},
{
"from": "gpt",
"value": "Bad. The video clearly shows children running and exploring, but there is a lack of coordination."
}
] |
seed46_2706
|
videos/HRA_part2/2706.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male chef, donning a gray t-shirt beneath a clean white apron, expertly wields a large spoon and spatula as he stirs a sizzling pan on a commercial stove in a bustling kitchen. Amidst the steamy atmosphere, his focused eyes and neatly trimmed facial hair convey his dedication to culinary artistry. With a vibrant red bandana tied around his neck, he exhibits a unique flair while preparing a gourmet dish. The scene captures the essence of hard work and passion in the culinary world, as the chef's movements are fluid and purposeful, encapsulating the heart of the kitchen environment.]"
},
{
"from": "gpt",
"value": "Bad. The person's hand is distorted, the face is distorted, and the object in the hand is distorted."
}
] |
seed42_1828
|
videos/HRA_part0/1828.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature woman with graying hair, wearing a white blouse and glasses, meticulously irons clothes in a well-lit room. She starts by carefully smoothing out a white shirt with a hot iron, steam rising gently. Then, she moves on to press a pair of khaki pants, folding them neatly over the ironing board. Throughout, she maintains a focused demeanor, her glasses catching the light as she works diligently, the steam from the iron creating a serene, domestic atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_3028
|
videos/HRA_part2/3028.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a brown beret, a beige button-down shirt, and glasses, sits at a wooden desk illuminated by a brass table lamp. He leans back in a brown chair, holding a book with an intense look of concentration. The room is adorned with his own artwork, including a large painting on an easel behind him and smaller framed pieces on the walls. Sunlight filters into the room from a window to the right, casting a warm glow on the artist and his surroundings as he reads. The artist's hands, which hold the book, are decorated with rings, adding a personal touch to the scene.]"
},
{
"from": "gpt",
"value": "Normal. Only the camera moves while the character remains stationary."
}
] |
seed42_1326
|
videos/HRA_part0/1326.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a dark, rugged outfit, crawls across a desolate landscape marked by the aftermath of a white hole explosion, which illuminates the scene with an eerie glow. The actor's face is partially obscured by shadows, adding to the suspense. As he moves, the ruins of a futuristic city can be seen in the background, hinting at a catastrophic event. The actor's intense gaze and strained posture convey a sense of urgency and survival in this post-apocalyptic setting. The scene is framed by the remnants of advanced technology and the haunting beauty of the white hole's light, creating a dramatic contrast between destruction and awe.]"
},
{
"from": "gpt",
"value": "Normal. The character's hand in the video has issues, disappearing suddenly in the middle frames."
}
] |
seed44_3116
|
videos/HRA_part1/3116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate musician, donning a black cap, black jacket, and khaki pants, pushes a large, vintage amp through a crowded, dimly lit backstage area at a music venue. The scene is filled with the energy of an upcoming performance, as the musician maneuvers the amp with determination, highlighting the physical effort and dedication required behind the scenes. The musician's attire and the bustling environment capture the spirit of live music culture.]"
},
{
"from": "gpt",
"value": "Bad. The musician can be seen pushing a vintage speaker through the backstage area, with movements that are not continuous and smooth, showing some coordination issues."
}
] |
seed44_2494
|
videos/HRA_part1/2494.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 white hare, its fur gleaming under the moonlight, crawls through a dense thicket of green foliage, navigating the intricate maze of branches and leaves with cautious precision. Its ears, erect and alert, swivel at the slightest sound, while its eyes, large and luminous, remain fixed on the path ahead. The hare's hind legs, powerful and agile, propel it forward in a series of controlled movements, each paw carefully placed to ensure silent progression through the undergrowth. The scene is set against the backdrop of a tranquil night, with the stars twinkling overhead and the distant hoots of owls punctuating the serene atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The rabbit's movements in the video are not smooth."
}
] |
seed44_2686
|
videos/HRA_part1/2686.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged female teacher, wearing a dark blue blazer over a white blouse and carrying a black handbag, walks purposefully down a wide hallway with high ceilings, resembling the interior of a university building. The walls are adorned with educational posters, and the floors are covered with brown carpeting. As she strides forward, the scene subtly transitions to reveal a large window behind her, displaying a breathtaking view of Neptune's turbulent atmosphere, filled with vivid blue and green clouds swirling majestically. This unique setting, combining the familiar environment of a school with the awe-inspiring backdrop of a distant planet, creates a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The character in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed44_2391
|
videos/HRA_part1/2391.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 well-dressed lawyer, wearing a dark suit, white shirt, and red tie, is shown in slow motion kicking a ball on a grassy field under a clear blue sky, embodying a moment of leisure. The lawyer, with short brown hair and a serious demeanor, kicks the soccer ball with his right foot, his left leg slightly bent, and his arms outstretched for balance. In another angle, he is captured mid-kick, the ball frozen in the air, highlighting his form and the vibrant green field. The final shot shows the ball soaring through the air, the lawyer watching intently, encapsulating the essence of unexpected playfulness in a professional setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2694
|
videos/HRA_part1/2694.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a standard uniform with a badge and utility belt, is seen meticulously dusting antique furniture inside a spacious, well-lit room. The officer, sporting a neatly trimmed beard and wearing a hat, focuses intently on the task, highlighting a surprising yet diligent approach to detail. The room features a wooden floor, walls adorned with framed pictures, and a large window allowing ample natural light to illuminate the space. The officer's actions convey a sense of thoroughness and care, emphasizing the unexpected scenario of law enforcement engaging in domestic chores.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, and the object in hand is distorted."
}
] |
seed46_2082
|
videos/HRA_part2/2082.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chef, wearing a traditional white uniform and a tall hat, finds himself in an unexpected encounter with a bobcat. They stand on a dirt path winding through a dense forest, the sunlight filtering through the trees casting dappled shadows on the ground. The chef, holding a basket presumably filled with fresh ingredients, looks surprised yet calm as he meets the gaze of the wild feline. The bobcat, equally intrigued, pauses in its walking, standing tall on the path, its ears perked and tail swishing gently, as if acknowledging the chef's presence in its natural habitat. The two share a moment of mutual respect and curiosity before continuing on their respective paths, the chef moving forward with purpose and the bobcat melting back into the underbrush, both figures disappearing into the lush greenery of the forest.]"
},
{
"from": "gpt",
"value": "Bad. The person's face in the video is distorted, the lynx's body is twisted, the claws are distorted, the face is distorted, and the legs are twisted."
}
] |
seed46_249
|
videos/HRA_part2/249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal and imaginative scene, two children, a boy and a girl, are dancing in a whimsical, cartoon-like environment. The girl, with curly red hair, wears a pink dress, while the boy, sporting brown hair, dons a blue shirt. They are accompanied by a friendly, animated coyote who mirrors their dance moves. The backdrop is a scientific laboratory filled with high-tech equipment, where researchers in lab coats are studying dark matter. This unusual juxtaposition of elements creates a captivating and unique visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The boy's body and limbs show deformed mutations, the girl's hands and arms have deformities, and the faces of the characters in the background are distorted and blurry."
}
] |
seed42_17
|
videos/HRA_part0/17.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dedicated teacher, wearing a vibrant yellow raincoat and matching boots, stands in the shallow waters of a lush wetland, surrounded by cattails and water lilies. She holds a large, transparent jar filled with water and aquatic insects, engagingly teaching a group of students who sit cross-legged nearby, dressed in waterproof jackets and pants. The students attentively listen, some with binoculars around their necks, as they learn about the wetland ecosystem. The teacher then leads the students in a safe, supervised activity where they wade into the water, using nets to catch and examine small fish and plants, all while standing in the calm, knee-deep water of the wetland.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate transparent jars filled with water and aquatic insects, and students with binoculars around their necks."
}
] |
seed44_1850
|
videos/HRA_part1/1850.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 green apron over a casual outfit, stands in a pet store, carefully washing a small brown dog in a white tub. The dog, on a leash, looks relaxed and happy, sitting in soapy water while the cashier, sporting a stylish bun hairstyle, uses a handheld showerhead to rinse the suds away. The scene is set against a backdrop of pet supplies and products, creating a vibrant and welcoming environment. The cashier's warm smile and gentle touch convey a sense of care and affection for the animal, making it a heartwarming moment captured on video.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2508
|
videos/HRA_part1/2508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, wearing a brown jacket and wide-brimmed hat, walks purposefully across a vast, futuristic farm landscape, with a colossal space elevator looming in the distance, its massive cable stretching into the heavens. The farmer pauses, looking up at the awe-inspiring structure, a blend of hard work and advanced technology coexisting in this extraordinary setting. As he continues walking, the camera captures the juxtaposition of traditional farming life and the futuristic marvel towering over the horizon.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's hand generation in the video has issues."
}
] |
seed42_1743
|
videos/HRA_part0/1743.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant green parrot with yellow facial feathers and red tail feathers perches on a branch, set against a blurred green background. The bird turns its head to look over its shoulder, displaying its detailed plumage. It then faces forward, revealing its sharp beak and curious expression. Next, it preens itself, using its beak to adjust its feathers, highlighting its self-care behavior. Finally, the parrot opens its wings slightly, showing off more of its stunning colors, all against a consistent blurred green backdrop that keeps the focus on the bird.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3184
|
videos/HRA_part2/3184.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, green 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": "Bad. The action of the person petting the giraffe is not smooth."
}
] |
seed46_3081
|
videos/HRA_part2/3081.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 contemporary art gallery with high ceilings and modern architecture, a janitor wearing a dark green vest, khaki pants, and a name tag, meticulously sweeps the floor. In an unexpected scene, he gently caresses a small vole that has wandered into the gallery, showing a tender side amidst the sterile environment filled with abstract paintings and sculptures. The interaction between the janitor and the vole adds a touch of warmth and humanity to the otherwise cold and impersonal space.]"
},
{
"from": "gpt",
"value": "Bad. The field mouse walks very unsmoothly in the video, the cleaner's movements are uncoordinated, and there is no petting of the field mouse."
}
] |
seed46_1254
|
videos/HRA_part2/1254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, red-tinged ibis with a distinctive, curved beak is perched on one leg, its feathers ruffled by a gentle breeze, against a backdrop of lush, green foliage. It stands calmly on a fallen tree log, surrounded by the serene environment of a marshland, where the water gently laps against the reeds. The bird's piercing yellow eyes survey its surroundings, while the sunlight filters through the leaves, casting dappled shadows on the ground. The ibis then takes flight, its wingspan impressive against the clear blue sky, offering a stunning display of nature's beauty.]"
},
{
"from": "gpt",
"value": "Normal. The actions of the ibis in the video are basically normal but slightly uncoordinated."
}
] |
seed46_2559
|
videos/HRA_part2/2559.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, upscale restaurant, a waiter with a mustache and wearing a black vest, white shirt, and black tie attentively wipes a round table with a white cloth. Behind him, a dingo stands on its hind legs, wearing a chef's hat and apron, attempting to mimic the waiter's actions with a smaller, comically proportioned cloth. The scene is set in an elegant dining room with wooden floors, high ceilings, and large windows, creating a surreal juxtaposition of sophistication and whimsy.]"
},
{
"from": "gpt",
"value": "Bad. The male waiter's hand and arm have undergone deformities, and when the Australian wild dog moves, one of its legs becomes elongated and deformed."
}
] |
seed44_2565
|
videos/HRA_part1/2565.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station, a young female cashier, clad in a green jumpsuit with a name tag, works diligently at a market specializing in hydroponic produce. She crawls under the counter, surrounded by vibrant, healthy greens growing vertically against the back wall, illuminated by LED grow lights. The space agriculture setting is evident from the lush plants and the advanced technology used for cultivation. The cashier's actions are focused and purposeful, highlighting the unique challenges and innovations of farming in space, all within the confines of a bustling space station market.]"
},
{
"from": "gpt",
"value": "Bad. The woman's arm generation is incomplete, and there are issues with the face generation."
}
] |
seed46_3214
|
videos/HRA_part2/3214.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, clad in a crisp white shirt and black waistcoat, moves gracefully across a wooden deck overlooking a serene river, carrying a silver tray with glasses of sparkling wine. The river, its surface shimmering with reflections of the lush greenery lining its banks, meanders gently into the distance under a clear blue sky. Suddenly, a small creature catches the waiter's eye; it's a caterpillar, slowly crawling along the edge of the deck railing, seemingly unperturbed by the elegant scene unfolding nearby. The waiter pauses, momentarily captivated by the simple beauty of nature juxtaposed with his refined task.]"
},
{
"from": "gpt",
"value": "Bad. The caterpillar in the video is twisted, and the character's hand is distorted."
}
] |
seed42_1007
|
videos/HRA_part0/1007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit room, a gray domestic shorthair cat with bright green eyes walks along a wooden floor, passing by an old television set. Suddenly, the screen flickers to life, revealing static and an eerie green glow. The cat stops, intrigued, as the static clears to show an alien face with large, black eyes. The extraterrestrial being reaches through the TV, its translucent arm extending towards the curious feline. The cat, undaunted, sniffs the alien's hand as it hovers near the screen, a moment of intergalactic connection captured in this surreal scene.]"
},
{
"from": "gpt",
"value": "Bad. The cat's limbs appear or disappear suddenly, and its walking is very unsmooth, with uncoordinated movements."
}
] |
seed44_2473
|
videos/HRA_part1/2473.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman dressed in a panther costume, complete with a black leotard, detailed spots, and a lifelike mask, crawls on all fours across a dimly lit stage. The setting is enhanced by a spotlight illuminating her figure, emphasizing the fluidity and grace of her movements, akin to a real panther. The background remains shadowy, drawing attention to her performance as she embodies the essence of the wild animal through her crawling motion.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1474
|
videos/HRA_part0/1474.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant forest setting, a mother beaver tenderly caresses her kit with her large, front paw, both sitting cozily within their wooden lodge. The mother, with her brown fur and attentive gaze, gently strokes the smaller beaver, who looks up at her with wide eyes, creating a heartwarming scene of maternal love. The wooden lodge, intricately built from branches and mud, provides a safe and nurturing environment for the family, with green leaves and trees visible in the background, highlighting the beauty of their natural habitat.]"
},
{
"from": "gpt",
"value": "Bad. The mother beaver's movements in the video are not smooth and the actions are uncoordinated."
}
] |
seed46_2788
|
videos/HRA_part2/2788.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, dressed in a flannel shirt, worn jeans, and a wide-brimmed straw hat, meticulously repairs a wooden fence under the golden glow of the setting sun. His hands, strong and capable, are wrapped around a hammer as he replaces a broken slat, embodying a rugged, down-to-earth character. The rural landscape stretches behind him, dotted with tall grass and distant trees, creating a serene backdrop for his focused labor. The fence, now mended, stands as a testament to his efforts, while the actor takes a moment to lean against it, surveying his work with a sense of accomplishment and satisfaction.]"
},
{
"from": "gpt",
"value": "Bad. The caption mentions the actor tightly holding a hammer, which does not appear in the video."
}
] |
seed46_2663
|
videos/HRA_part2/2663.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 desert-dwelling lizard, specifically a Bearded Dragon, is shown swimming underwater in clear, sunlit water. Its body is fully submerged, and it moves gracefully through the water, showcasing its rarely seen aquatic locomotion. The lizard's skin ripples as it propels itself forward, and its claws can be seen extended as it navigates the aquatic environment. The water is crystal clear, allowing for a detailed view of the lizard's texture and movement, contrasting with its typical arid habitat. Sunbeams penetrate the water, illuminating the scene and highlighting the unique sight of a lizard swimming.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1343
|
videos/HRA_part1/1343.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 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 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": "Bad. The character's movements are not smooth, and the bison's movements are not smooth."
}
] |
seed42_1633
|
videos/HRA_part0/1633.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer kneels on a black rubber mat, meticulously repairing a vintage motorcycle in a cluttered garage. Wearing a gray t-shirt, navy blue cap, and tan cargo pants, he focuses intently on his work, surrounded by tools and parts. The garage walls are adorned with posters of classic cars and bikes, adding a nostalgic touch. A large, well-lit workbench is visible nearby, equipped with various tools and mechanical components. The engineer's hands move skillfully as he tightens bolts and adjusts the bike's engine, demonstrating his expertise and passion for restoring old motorcycles.]"
},
{
"from": "gpt",
"value": "Normal. The character's face, hands, and feet are distorted in the video."
}
] |
seed42_3142
|
videos/HRA_part0/3142.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In an otherworldly ecosystem on an alien planet, a unique creature resembling Earth's beaver crawls through a dense, bioluminescent forest. Its brown fur stands out against the vibrant, glowing flora. The beaver-like being navigates the intricate terrain, its flat tail dragging slightly, as it explores the mysterious landscape filled with towering, luminescent trees and strange, colorful plant life. This extraterrestrial environment, illuminated by an eerie yet beautiful light, provides a surreal setting for the beaver's curious journey.]"
},
{
"from": "gpt",
"value": "Normal. The biological generation in the video is abnormal."
}
] |
seed42_28
|
videos/HRA_part0/28.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a serene, lush forest setting filled with tall, verdant trees and patches of sunlight filtering through the leaves, a mongoose is gently caressing a smaller mongoose, possibly its offspring, with its nose. The larger mongoose, with its sleek brown fur and attentive eyes, exhibits tenderness and care, creating a heartwarming scene of familial affection in the midst of the natural environment.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1290
|
videos/HRA_part0/1290.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged, bearded man wearing a brown leather jacket and a tan hat sits on a large rock in the middle of a vast, grassy plain, writing intently in a small notebook. In the background, a majestic bison is seen grazing peacefully on the lush vegetation. Suddenly, the man lowers his book, revealing a look of awe and inspiration as he watches the bison. He then resumes writing, his posture reflecting deep concentration. The scene shifts to show the bison lying down, seemingly resting, as the man continues to write, now with a sense of urgency, capturing the essence of his experience in the wild.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand proportions in the video are not well coordinated."
}
] |
seed46_1337
|
videos/HRA_part2/1337.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished doctor, donning a navy blue polo shirt, beige shorts, and brown shoes, is organizing a cluttered garage filled with various items. Initially, he stands thoughtfully amidst the chaos, surrounded by a bike, a toolbox, and gardening equipment. He then proceeds to sort through a pile of objects, showcasing his methodical approach. Next, he is depicted lifting a heavy object, demonstrating his physical strength. Finally, he is shown proudly admiring his neatly organized garage, with shelves neatly arranged and tools hanging orderly on the walls, a testament to his hard work and attention to detail.]"
},
{
"from": "gpt",
"value": "Bad. The video did not generate a toolbox, and the gardening equipment is incomplete."
}
] |
seed46_2782
|
videos/HRA_part2/2782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative musician, clad in a black shirt and black jeans, is seen in a studio, wiping down a zebra-striped bass guitar with a cloth. The room is filled with musical instruments and equipment, including a drum set, a keyboard, and various guitars. The musician's focus is intense as they meticulously clean the unique instrument, the zebra-striped bass guitar, ensuring it remains in pristine condition. The scene is intimate, capturing the musician's dedication to their craft amidst a backdrop of musical passion and creativity.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted in the video."
}
] |
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 semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a white apron over a black t-shirt and jeans, throws clay on a spinning pottery wheel under the glow of bright studio lights. With intense concentration, they shape the clay into a vase, their hands moving gracefully and purposefully. The camera captures the artist's face, reflecting determination and skill, as they mold the clay. Throughout the process, the artist's attire remains consistent, and the scene is set against a backdrop of a well-lit workshop filled with various pottery tools and finished pieces.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1097
|
videos/HRA_part1/1097.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic great horned owl perches regally on a rugged branch, its piercing yellow eyes gazing intently into the distance. It's nestled among lush greenery, with sunlight filtering through the leaves, casting a warm glow on the owl's mottled brown and grey feathers. The owl's large, expressive eyes stand out against its feathered face, framed by tufts resembling horns. Its beak, curved and sharp, complements the fierce yet serene demeanor of this nocturnal hunter, set against a backdrop of dense forest vegetation.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_235
|
videos/HRA_part2/235.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 vast, sun-soaked scrublands, a juvenile giraffe with a sandy coat engages in an unusual behavior, moving slowly across the dry, cracked earth. Its spots blend into the arid landscape, and it crawls with a curious determination, perhaps exploring its environment or searching for food amidst the sparse vegetation. The scene is intimate, focusing solely on the giraffe's unique actions in the desolate yet beautiful wilderness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2202
|
videos/HRA_part1/2202.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone giraffe runs across an open savanna, its distinctive patterned coat and long legs propelling it forward in a graceful stride. The scene is captured in vibrant detail, with the grassy plains stretching out behind the majestic creature. The sky is a brilliant blue, dotted with fluffy white clouds, providing a stunning contrast to the earthy tones of the giraffe's coat. As it runs, its spots seem to blur, creating a mesmerizing effect that highlights the beauty and power of this remarkable animal.]"
},
{
"from": "gpt",
"value": "Bad. The giraffe's movement in the video is not smooth, and the actions are uncoordinated."
}
] |
seed42_140
|
videos/HRA_part0/140.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 janitorial worker, clad in a crisp, light blue uniform shirt and black pants, meticulously rearranges furniture in a spacious, modern office during the daytime. He lifts a wooden chair with a green seat cushion, revealing a clean, polished floor beneath. Next, he pushes another chair into place, aligning it perfectly with the desk. Then, he adjusts a sleek, white office table, ensuring it is straight and centered. Finally, he steps back, hands on hips, surveying his work with a sense of pride and accomplishment, the room now neatly organized and ready for use.]"
},
{
"from": "gpt",
"value": "Bad. The hands appear deformed, and the facial features are not fully formed. Two chairs are generated fused together."
}
] |
seed42_198
|
videos/HRA_part0/198.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, donning a classic white uniform with a red bandana around his neck, walks through a lush, green forest, his eyes fixed ahead with determination. Accompanied by a small, bushy-tailed squirrel perched on his shoulder, they navigate the woodland together. The chef carries a large basket, presumably filled with foraged ingredients, while the squirrel clutches an acorn in its paws, both on a mission in the vibrant, sun-dappled setting.]"
},
{
"from": "gpt",
"value": "Normal. The character's face in the video is distorted, the monkey's face is distorted, and the claws are distorted."
}
] |
seed44_2077
|
videos/HRA_part1/2077.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 hummingbird, iridescent green with a crimson throat, hovers in a clear blue sky, its wings a blur of motion. It approaches a red feeder, designed with four feeding stations, each marked with a yellow flower, hanging from a branch in a lush, green forest. The bird lands momentarily on the feeder before resuming its characteristic hovering flight, sipping nectar with its long, slender beak. Against the vibrant backdrop of the forest, the hummingbird's agility and the feeder's design stand out, capturing the beauty of nature in a serene setting.]"
},
{
"from": "gpt",
"value": "Bad. The hummingbird's movements in the video are not smooth and coordinated."
}
] |
seed46_2425
|
videos/HRA_part2/2425.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant parrotfish, distinguished by its yellow body and green head, swims gracefully near a coral reef, showcasing its unique features in stunning detail. The fish's eyes, positioned on the left side of its head, are clearly visible, and its beak-like mouth, used for feeding on coral, is prominent. Against a backdrop of colorful corals and underwater plants, the parrotfish's dynamic movements and distinctive appearance stand out, capturing the essence of life beneath the sea. The water around it shimmers with sunlight, adding to the beauty of the scene, as the parrotfish navigates its environment with ease.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_1096
|
videos/HRA_part2/1096.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 reality TV set, an antelope, wearing a small golden bell around its neck, stands calmly against a backdrop of stars and galaxies. The animal is gently caressed by a human figure dressed in a spacesuit, conveying a sense of comfort and companionship in the vastness of space. The astronaut's gloved hand softly touches the antelope's face, while the creature looks on serenely, the golden bell shining under the starlight, creating a surreal and touching moment in an extraterrestrial environment.]"
},
{
"from": "gpt",
"value": "Normal. Finger deformity, not fully generated."
}
] |
seed44_2782
|
videos/HRA_part1/2782.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative musician, clad in a black shirt and black jeans, is seen in a studio, wiping down a zebra-striped bass guitar with a cloth. The room is filled with musical instruments and equipment, including a drum set, a keyboard, and various guitars. The musician's focus is intense as they meticulously clean the unique instrument, the zebra-striped bass guitar, ensuring it remains in pristine condition. The scene is intimate, capturing the musician's dedication to their craft amidst a backdrop of musical passion and creativity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_249
|
videos/HRA_part1/249.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal and imaginative scene, two children, a boy and a girl, are dancing in a whimsical, cartoon-like environment. The girl, with curly red hair, wears a pink dress, while the boy, sporting brown hair, dons a blue shirt. They are accompanied by a friendly, animated coyote who mirrors their dance moves. The backdrop is a scientific laboratory filled with high-tech equipment, where researchers in lab coats are studying dark matter. This unusual juxtaposition of elements creates a captivating and unique visual narrative.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1679
|
videos/HRA_part1/1679.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dim light of a Martian sunset, casting an eerie orange glow, a small, brown mouse sits atop a large fire helmet, placed on the red, rocky surface of Mars. Nearby, a firefighter, dressed in a full suit and helmet, wipes his brow with a gloved hand, appearing weary yet determined. The vast, desolate landscape stretches out behind him, dotted with the remnants of a recently extinguished extraterrestrial fire, as the distant horizon is bathed in the fading embers of the alien sun.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_1352
|
videos/HRA_part0/1352.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 actor, resembling a young Russell Crowe, sits in a dimly lit room, deeply engrossed in sketching. He wears a white shirt with rolled-up sleeves, revealing a watch on his right wrist, and a black blazer draped casually over his shoulders. The room is adorned with various artworks, adding to the creative atmosphere. The actor's intense focus is evident as he draws, his face reflecting deep concentration. The camera captures his every move in stunning detail, from the way his fingers grip the pencil to the intensity in his eyes, all set against the backdrop of an art-filled room.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2047
|
videos/HRA_part0/2047.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic farmyard setting, a fluffy yellow chick is seen crawling across the ground, its tiny feet moving quickly beneath it. The chick crawls under a weathered wooden fence, its feathers ruffling slightly as it navigates the space. It continues its journey, now crawling over a patch of fresh green grass, the blades tickling its delicate underside. Finally, the chick reaches a small cluster of pebbles, over which it crawls, demonstrating determination and resilience in its exploration of the farmyard environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions of chicks walking on the grass and pebbles in the video are not very continuous and smooth, showing some inconsistency."
}
] |
seed42_1997
|
videos/HRA_part0/1997.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, clad in a tan vest, dark pants, and brown gloves, interacts with a realistic monkey puppet, crawling on all fours across a lush green landscape. The detailed puppet, featuring lifelike fur and expressive eyes, follows the worker's movements closely. The worker, with a serious yet focused demeanor, guides the monkey puppet through various natural terrains, including dense foliage and rocky terrain, highlighting the puppet's agility and realism. Throughout the scene, the worker's connection with the monkey puppet conveys a sense of companionship and shared purpose in their outdoor adventure.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_254
|
videos/HRA_part2/254.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A large construction crane dominates the skyline, its yellow and black body towering over a bustling cityscape at dusk. The crane's long arm stretches across the frame, adorned with industrial machinery and cables, as it stands on a partially constructed building amidst other tall structures. Workers in safety gear can be seen moving about the site, dwarfed by the massive crane, which looms against the orange and purple hues of the setting sun, casting long shadows over the urban landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_3112
|
videos/HRA_part2/3112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious engineer, clad in a blue button-down shirt and khaki pants, kneels beside an indoor track designed for mice. The track, illuminated by overhead lights, features a small mouse energetically running within its confines. The engineer observes intently, notebook in hand, ready to record data from the experiment. Behind him, a lab coat hangs on a hook, and a shelf displays various scientific instruments and books, alluding to the academic setting. Throughout the scene, the mouse continues its steady pace on the track, under the watchful eye of the dedicated engineer.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1851
|
videos/HRA_part1/1851.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 futuristic engineer, clad in a high-tech silver suit, is depicted running across a vast Galactic nebula, with swirling cosmic clouds and distant stars providing a dramatic backdrop. The engineer, wearing a sleek helmet that reflects the nebula's vibrant colors, is shown in various dynamic poses, conveying a sense of speed and determination. The scene is set against a massive, ethereal nebula, its colorful gas formations creating a stunning visual contrast with the engineer's metallic attire, emphasizing the thrilling combination of human endeavor and the awe-inspiring scale of the universe.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_3071
|
videos/HRA_part2/3071.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a spacesuit adorned with patches and equipped with a jetpack, orbits the Earth while holding a moose, its antlers visible. Below, on a pristine planet, a worker in a blue uniform tends to a pool, where a moose swims leisurely, its large frame gliding through the crystal-clear water. The worker, wearing a blue cap, looks up at the space-suited figure and the orbiting moose, a sense of wonder in their eyes. This juxtaposition of scenes captures the surreal and unexpected elements of life in space and on Earth.]"
},
{
"from": "gpt",
"value": "Bad. The astronaut's hand is deformed, and the elk in the pond is also deformed."
}
] |
seed44_1550
|
videos/HRA_part1/1550.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 teacher, wearing a gray crew neck shirt, khaki pants, and black shoes, is seen from above, loading a stainless steel dishwasher in a well-lit kitchen. The kitchen features white cabinets, a white refrigerator, and a gray countertop. The teacher, with short brown hair and glasses, carefully places dishes into the lower rack of the dishwasher. In another angle, the teacher, now wearing a gray shirt and dark pants, continues loading the dishwasher, placing a cup in the upper rack. The room is brightly lit, with white walls and ceiling, and the teacher's focused expression conveys a sense of routine and responsibility.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are twisted, and arms are deformed."
}
] |
seed42_1516
|
videos/HRA_part0/1516.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 industrious male engineer, wearing a blue button-down shirt and glasses, meticulously irons his clothes in a modestly furnished room with a wooden floor and cream walls. He stands at an ironing board covered with a white cloth, carefully smoothing out wrinkles in a garment. The room is illuminated by natural light from a window behind him, casting a warm glow over the scene. On the wall to his right, a large painting in shades of green adds a splash of color to the otherwise simple space. Beside the window, a desk with a laptop and engineering blueprints hints at his professional life, while a shelf filled with books and a houseplant brings a personal touch to the environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.