video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed44_1317
|
videos/HRA_part1/1317.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A well-known actor, dressed in a black turtleneck and dark jeans, sits on a lush, green meadow with a large, brown bear. The actor gently caresses the bear's fur, showing a bond between man and beast. The bear, unperturbed by the human presence, leans into the touch, revealing a surprising tenderness. The scene is peaceful, with the verdant landscape and clear blue sky providing a serene backdrop to this unlikely interaction. The actor's calm demeanor and the bear's relaxed stance suggest a mutual trust and understanding in their shared moment of connection.]"
},
{
"from": "gpt",
"value": "Normal. The hand generation of the actor in the video is problematic."
}
] |
seed44_2562
|
videos/HRA_part1/2562.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 octopus with a grayish-brown body and long, flexible arms covered in small suckers rests on a rocky seabed. Its arms curl and extend as it explores its surroundings, demonstrating its intelligence and adaptability. The creature's large, curious eyes are visible as it interacts with the environment, showcasing its awareness and engagement. The octopus then changes color to blend in with the rocks, highlighting its remarkable camouflage abilities, all against the backdrop of an underwater world filled with various marine life and plants.]"
},
{
"from": "gpt",
"value": "Bad. The octopus's tentacles were generated deformed, and there were issues with the head generation."
}
] |
seed44_296
|
videos/HRA_part1/296.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dark suit, white shirt, and blue tie, finds himself inexplicably transported to a different era, reminiscent of the TV show 'Quantum Leap.' Crawling through a dimly lit, gritty tunnel, he struggles to understand his time-bending predicament. The tunnel walls are adorned with graffiti and debris, adding to the disorienting atmosphere. Suddenly, the lawyer emerges into a bustling courtroom from the past, where he must now navigate unfamiliar legal challenges. His bewildered expression and the stark contrast between his modern attire and the vintage courtroom setting underscore the surreal nature of his quantum leap experience.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2748
|
videos/HRA_part0/2748.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 rustic vineyard setting, a young female cashier, dressed in a red apron over a white blouse, diligently wipes down the wooden counter of the quaint tasting room. Sunlight streams in through large windows, highlighting the rich textures of the wood and the lush greenery outside. The atmosphere is peaceful and inviting, with the sound of gentle music playing in the background and the distant hum of vineyard activities. The cashier's focused demeanor and meticulous cleaning convey a sense of pride in her work and the establishment, creating a welcoming environment for visitors.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1723
|
videos/HRA_part1/1723.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man, dressed in a spacesuit with the helmet removed, floats gracefully in zero gravity inside a space station, illuminated by the ethereal glow of Earth in the background. He gently caresses the inner wall of the station, adorned with complex machinery and wires, while looking out at the breathtaking view of our planet through the large circular window, conveying a sense of wonder and intimacy with the cosmos. The setting captures the essence of human achievement in space exploration, with the man's tender gesture toward the space station's interior wall highlighting a unique connection between humanity and its ventures beyond Earth.]"
},
{
"from": "gpt",
"value": "Normal. The video generates an extra helmet, and the man's limbs are abnormally distorted."
}
] |
seed44_3109
|
videos/HRA_part1/3109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A creative writer, adorned in a cozy red sweater and glasses, sits at a wooden table in a rustic cabin, illuminated by the warm glow of a lamp. She holds knitting needles and a half-completed green scarf, with a laptop displaying a novel manuscript nearby. The atmosphere is serene, with the occasional sound of knitting needles clicking and the soft clacking of keys as she types. A cup of tea sits beside her, adding to the peaceful scene. Behind her, a large window frames a view of lush greenery, providing a natural backdrop to her creative space.]"
},
{
"from": "gpt",
"value": "Bad. The woman in the video has uncoordinated movements while knitting."
}
] |
seed46_1289
|
videos/HRA_part2/1289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pristine, high-quality close-up of a fresh cod fillet takes center stage, its surface glistening under bright lights. The fish boasts a clean, white flesh with a hint of natural oils visible, presenting a perfect texture for culinary delights. Set against a simple, dark background, the cod fillet's purity and freshness are accentuated, making it visually appealing for seafood connoisseurs and chefs alike.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1171
|
videos/HRA_part1/1171.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 wildlife sanctuary, a compassionate veterinarian, wearing a khaki shirt and cargo pants, gently wipes the face of a majestic cheetah lying on a checkered cloth, its gaze fixed on the vet. The scene is set outdoors, with lush greenery and wooden fences framing the backdrop, highlighting the unique bond between the medical professional and the wild animal. The vet's careful action, using a soft, white cloth, conveys a sense of tenderness and care, while the cheetah's calm demeanor suggests trust and familiarity.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2768
|
videos/HRA_part2/2768.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling airport terminal filled with travelers and overhead announcements, a young female cashier, dressed in a uniform of a dark blazer, black shirt, and khaki pants, energetically jumps in place behind the counter of a busy snack bar. She pauses to assist customers, her cheerful demeanor evident as she hands over a receipt and change. Moments later, she returns to jumping, her ponytail bouncing, showcasing her lively spirit amidst the routine tasks of her job. The scene captures her vibrant energy in the dynamic environment of an airport, where passengers hurry past in the background.]"
},
{
"from": "gpt",
"value": "Bad. The person's face, hands, and arms are distorted in the video."
}
] |
seed44_3209
|
videos/HRA_part1/3209.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man in a red t-shirt and black shorts is depicted running alongside a kangaroo on a dusty trail surrounded by lush vegetation, both appearing energetic and engaged in the activity. They run together on a dirt path amidst dense greenery, the kangaroo bounding effortlessly beside the man, who maintains a steady pace. The scene captures the unique companionship between the man, dressed casually in a red top and dark shorts, and the kangaroo, as they traverse the natural environment together. The duo continues their run through the vibrant landscape, the kangaroo's powerful legs propelling it forward in sync with the man's strides, highlighting their shared rhythm and connection amidst the verdant scenery.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1994
|
videos/HRA_part1/1994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 compassionate, middle-aged female nurse sits on a wooden chair in a cozy, softly lit room, wearing a light blue scrubs top and black pants. She crochets a vibrant, multicolored blanket with yellow, orange, and red hues, her hands moving skillfully as she focuses on her craft. The room is filled with the warm glow of a standing lamp, casting a gentle light on the scene. Behind her, a large window reveals a lush, green outdoor landscape, providing a serene backdrop for her meditative activity.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1580
|
videos/HRA_part1/1580.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged janitor, wearing a yellow safety vest over a gray shirt, blue jeans, and brown shoes, climbs a tall, metal, industrial ladder in a large warehouse filled with boxes and equipment. He holds a tool in his right hand and reaches up with his left, the afternoon sun shining through the high windows, casting a warm glow over the dusty space. The ladder leans against a tall shelf stacked with supplies, and the man's focus is intense as he ascends, his brows furrowed in determination. Behind him, the vastness of the warehouse stretches out, with rows of shelves disappearing into the distance, emphasizing the scale of his task.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are basically normal, with slight disharmony."
}
] |
seed44_2409
|
videos/HRA_part1/2409.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vibrant coral reef ecosystem, a pair of butterfly fish, characterized by their distinctive black stripes and oval-shaped bodies, gracefully swim among the colorful corals and anemones. One fish displays a striking yellow hue with bold black markings, while the other exhibits a more subdued brown and white pattern. They navigate the intricate underwater landscape, their movements synchronized, as they explore the nooks and crannies of the reef in search of food. The scene is illuminated by the filtered sunlight that penetrates the clear blue water, casting dappled light on the fish and their surroundings.]"
},
{
"from": "gpt",
"value": "Normal. The pectoral fins and tail of the butterfly fish in the video have generation issues, and the white butterfly fish has problems with the mouth generation."
}
] |
seed46_1939
|
videos/HRA_part2/1939.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 smiling student, dressed in a green T-shirt and gray pants, joyfully jumps alongside a kangaroo in a lush, green field under a clear blue sky. The student, wearing brown shoes and a wristwatch, mimics the kangaroo's hopping motion, capturing a moment of playful interaction between human and nature. The kangaroo, with its distinctive features and powerful hind legs, bounds gracefully next to the enthusiastic student, both enjoying the freedom of movement against the serene backdrop of the outdoors.]"
},
{
"from": "gpt",
"value": "Bad. The student's face and limbs, as well as the kangaroo's head and legs in the video, are generated abnormally, with the kangaroo's legs twisting and deforming in the middle frames, and the kangaroo having five legs at the same time."
}
] |
seed42_1113
|
videos/HRA_part0/1113.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone gray wolf, its fur thick and weathered, crawls through a dense forest underbrush, navigating beneath low-hanging branches and over decaying logs. The wolf, exhibiting signs of fatigue or stealth, moves slowly and deliberately, its eyes alert and ears perked, indicating heightened senses. The camera captures this intimate moment from a low angle, emphasizing the wolf's determination and resilience in its natural habitat. The wolf's body language suggests it may be injured or engaged in a cautious hunt, adding to the dramatic tension of the scene.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1460
|
videos/HRA_part2/1460.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A graceful red fox, its fur thick and lustrous, stands at the edge of a steaming hot spring nestled in a lush, green forest. The water bubbles gently, releasing tendrils of mist that swirl around the fox, creating a mystical atmosphere. The fox dips its paw into the warm water, seeming to caress the surface, its eyes closed in apparent bliss. The steam rises from the hot spring, enveloping the fox in a soft, glowing haze, while the dense foliage and tall trees surrounding the clearing provide a serene and secluded setting.]"
},
{
"from": "gpt",
"value": "Bad. The red fox's legs are twisted, paws are deformed, and the face is distorted."
}
] |
seed44_2770
|
videos/HRA_part1/2770.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ibex, distinguished by its curved horns and brown coat, walks steadily across a rocky terrain, with a clear blue sky and distant mountains providing a scenic backdrop. The ibex navigates the rugged landscape with ease, its hooves firmly gripping the stone surface. It pauses momentarily, its head held high, surveying its surroundings before continuing its journey, moving gracefully among the boulders and cliffs. Throughout the scene, the ibex remains the central focus, its presence commanding attention against the stark beauty of the alpine environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2120
|
videos/HRA_part1/2120.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, donning a white painter's smock and denim jeans, meticulously hangs a series of vibrant oil paintings on a gallery wall, the warm glow of spotlights illuminating each frame. The gallery space is vast, with high ceilings and pristine white walls, providing a stark contrast to the rich colors of the artwork. In another shot, the artist, now wearing a beret and glasses, carefully levels a large abstract piece, its bold strokes and dynamic composition capturing the essence of modern art. Finally, standing back, the artist admires the completed arrangement, a harmonious blend of creativity and craftsmanship, the gallery now transformed into a visual narrative of artistic expression.]"
},
{
"from": "gpt",
"value": "Bad. The arms, hands, and face of the person in the video are distorted."
}
] |
seed46_1554
|
videos/HRA_part2/1554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 man, wearing a navy suit with a light blue shirt and a dark blue tie, stands against a neutral gray background. He points to an unseen object or idea with a confident smile, engaging the viewer with his clear, green eyes. His neatly combed brown hair and clean-shaven face add to his professional appearance. The focus is solely on him, with no additional elements in the frame, as he points with his right index finger, inviting the audience to follow his gesture.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1617
|
videos/HRA_part0/1617.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, donning a white lab coat over a gray t-shirt and khaki pants, stands in a futuristic, metallic laboratory. Holding a high-tech device, he demonstrates the concept of time dilation, with visual effects distorting the background and a digital clock appearing to slow down. The scene progresses as he uses a cloth to wipe the perspiration from his forehead, emphasizing the intensity and complexity of his scientific endeavor. Throughout, the lab's modern aesthetic and advanced technology underscore the theme of cutting-edge research and experimentation.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_3030
|
videos/HRA_part2/3030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a human-like jackal, dressed in a red apron and name tag, stands behind a checkout counter. The background features a vibrant, turquoise water surface, suggesting a swimming pool or body of water. The jackal, with its distinctive canine features and upright posture, interacts with customers, handling items scanned over a register. The setting is illuminated by bright, warm lighting, casting a glow on the turquoise water, which stretches out behind the cashier area, merging the indoor and outdoor environments in an unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3030
|
videos/HRA_part0/3030.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surreal scene, a human-like jackal, dressed in a red apron and name tag, stands behind a checkout counter. The background features a vibrant, turquoise water surface, suggesting a swimming pool or body of water. The jackal, with its distinctive canine features and upright posture, interacts with customers, handling items scanned over a register. The setting is illuminated by bright, warm lighting, casting a glow on the turquoise water, which stretches out behind the cashier area, merging the indoor and outdoor environments in an unexpected juxtaposition.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1094
|
videos/HRA_part2/1094.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A space worker, clad in a high-tech, neon-accented spacesuit, traverses a vast, ethereal galactic nebula, the swirling cosmic clouds of reds and purples forming a breathtaking backdrop. The figure moves with purpose, the lights from their suit casting dramatic shadows against the interstellar gas and dust. A closer shot reveals the worker's faceplate, reflecting the mesmerizing nebula, highlighting their isolated journey among the stars. As they walk, the nebula's colors swirl around them, creating a stunning visual of a human amidst the grandeur of the universe.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2049
|
videos/HRA_part1/2049.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 stylish woman in a black-and-white striped dress, reminiscent of a zebra's pattern, walks confidently down a busy city street. She carries a small black purse and wears black sunglasses, adding to her sophisticated appearance. The urban setting is filled with pedestrians and street vendors, providing a dynamic backdrop for her stroll. As she moves, the camera captures her from various angles, highlighting the fluidity of her walk and the attention she garners from passersby. Throughout the scene, she maintains her poise and elegance, embodying the spirit of a modern, independent woman.]"
},
{
"from": "gpt",
"value": "Bad. The hand of the fashionable woman in the video was generated abnormally."
}
] |
seed46_1436
|
videos/HRA_part2/1436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 red starfish with five arms and tiny white spots rests on a bed of pristine white sand, surrounded by shallow turquoise waters that gently lap at its sides. Sunlight filters through the water, casting shimmering light patterns on the starfish and sand. In the background, a vast ocean stretches to the horizon, meeting a clear blue sky dotted with fluffy white clouds. The overall scene exudes tranquility and beauty, capturing the essence of life beneath the sea's surface.]"
},
{
"from": "gpt",
"value": "Normal. The arms of the sea star in the video are generated with different sizes, and the sea sand is generated with the sea star's arms, which does not match the reality."
}
] |
seed44_2087
|
videos/HRA_part1/2087.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prison, dimly lit by neon blue lights, two figures, a male and female inmate, plot their daring escape. They wear matching orange jumpsuits with black stripes, symbolizing their confined status. Suddenly, they engage in a synchronized dance, using their movement as a clever ruse to distract guards. Their dance, a blend of hip-hop and contemporary styles, captivates the robotic guards, allowing the inmates to stealthily make their way towards freedom. The prison's cold, metallic interior contrasts sharply with the dynamic energy of their dance, highlighting the tension between confinement and liberation. Throughout, the focus remains on the two dancers, their precise movements and the prison's stark, oppressive environment.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_3147
|
videos/HRA_part0/3147.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene, a chimpanzee, wearing a small red apron, sits at a cash register typically found in a grocery store. The primate's eyes are closed as it receives a gentle caress from a human hand, which is softly petting its head, evoking a sense of calm and trust between the species. The chimpanzee's relaxed posture and closed eyes indicate a feeling of comfort and safety during this intimate interaction, set against the backdrop of a familiar checkout counter environment.]"
},
{
"from": "gpt",
"value": "Bad. The chimpanzee's eyes are not closed in the video."
}
] |
seed44_3041
|
videos/HRA_part1/3041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, identifiable by her stethoscope and medical attire, navigates a lunar buggy across the moon's desolate surface, which is marked by craters and strewn with rocks. The buggy's wheels kick up fine lunar dust as it traverses the barren landscape. The doctor's face, visible through the helmet of her spacesuit, reflects determination and focus. In a close-up shot, a small, resilient insect-like creature crawls slowly across the moon's rocky terrain, its tiny legs moving deliberately against the stark, gray backdrop. The buggy continues its journey, passing near the crawling creature, emphasizing the contrasting scales of movement and life on the moon.]"
},
{
"from": "gpt",
"value": "Normal. The video does not show the doctor's stethoscope and medical attire."
}
] |
seed46_130
|
videos/HRA_part2/130.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An engineer, wearing a blue plaid shirt, khaki pants, and glasses, sits in a wooden chair in a cozy living room filled with natural light. They hold a crochet hook and yarn, working on a colorful blanket with a complex geometric pattern. The space around them is cluttered with engineering books, blueprints, and tools, blending the worlds of precision and creativity. The camera captures the intricate process, focusing on their hands as they expertly loop the yarn, creating a vivid contrast between the technical skills of engineering and the artistic craft of crocheting.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_170
|
videos/HRA_part0/170.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate writer, donning a black beanie and glasses, sits at a modern desk, engrossed in typing on a sleek laptop. The scene is set in a cozy room with a brick wall and a wooden shelf filled with books, plants, and a clock. Morning sunlight softly illuminates the space, casting a warm glow on the writer's face. A cup of coffee sits nearby, a trusted companion during the creative process. The writer occasionally glances at notes spread across the desk, incorporating ideas into the digital manuscript, capturing the essence of dedication and inspiration in the art of writing.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2962
|
videos/HRA_part1/2962.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 worker, wearing a gray T-shirt with a logo, blue jeans, and a dark cap, assembles furniture in a bright room. He focuses on tightening screws on a wooden dresser using a cordless drill, demonstrating his expertise. The room is filled with natural light, illuminating the task at hand. Moments later, he expertly aligns the dresser drawers, ensuring they fit perfectly. Lastly, he stands back to admire his completed work, a fully assembled dresser standing against a white wall, with the sunlight highlighting the wood grain and the worker's satisfaction in his craftsmanship.]"
},
{
"from": "gpt",
"value": "Normal. The man's hands show deformity, with a third hand appearing. The arm is deformed, and when walking, the man's body and legs show twisting deformities."
}
] |
seed46_2275
|
videos/HRA_part2/2275.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, identifiable by his blue scrubs and stethoscope, walks steadily in zero gravity, orbiting the Earth inside a space station illuminated by the planet's stunning blue and green hues. He maneuvers through the microgravity environment with ease, pushing off surfaces to navigate his path. At one point, he floats near a window displaying the Earth's horizon, backlit by the sun, offering a breathtaking view of our planet from orbit. Throughout the scene, the doctor's calm demeanor and the serene backdrop of Earth's curvature underscore the unique experience of walking in space.]"
},
{
"from": "gpt",
"value": "Bad. The person's head, arms, hands, feet, and legs are distorted in the video."
}
] |
seed46_2694
|
videos/HRA_part2/2694.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 and the item held are twisted, and the arm is distorted."
}
] |
seed42_2761
|
videos/HRA_part0/2761.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged man, balding with a gray beard, wearing a dark green jacket, khaki pants, and brown work boots, is seen wiping the exterior of a car with a cloth. He moves methodically, first focusing on the hood, then the roof, and finally the trunk, ensuring every inch is clean. The car, a sleek black sedan, is parked in a dimly lit garage, with the man's cleaning efforts illuminated by a single overhead light. He then proceeds to polish the car windows, his attention to detail evident as he works diligently to remove any smudges. Throughout the scene, the man's attire remains consistent, consisting of the same dark green jacket, khaki pants, and brown work boots, as he cleans the car in the subdued environment of the garage.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, arms, and the item in their hand are distorted in the video."
}
] |
seed46_2784
|
videos/HRA_part2/2784.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 traditional white uniform with a tall hat, finds himself in an extraordinary situation, crawling on his hands and knees across a lush, green field. Beside him, a friendly hippopotamus ambles along, mirroring the chef's movements in a comical display of camaraderie. The chef's attire, complete with a pristine white apron and polished shoes, contrasts humorously with the unconventional crawling action, while the hippopotamus, with its massive frame and gentle demeanor, adds a surreal element to the scene. Both crawl under a low-hanging branch of a tree, adding a touch of whimsy to the unexpected pairing.]"
},
{
"from": "gpt",
"value": "Bad. The chef's and hippo's crawling movements in the video are not continuous and smooth, there is a lack of coordination."
}
] |
seed44_1797
|
videos/HRA_part1/1797.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vast meadow filled with lush green grass and wildflowers swaying gently in the breeze, a young cashier, wearing a red apron over a white blouse and black pants, is seen running energetically. She has her hair tied back in a ponytail, revealing her focused determination. The cashier takes a moment to pause, hands on hips, catching her breath while admiring the beauty of the surrounding nature. Continuing her run, she passes by a wooden bench, where she stops again, this time leaning forward with her hands on the bench, taking a more prolonged rest. Throughout the video, the meadow remains a constant, picturesque backdrop, providing a serene and inspiring setting for the cashier's outdoor activity.]"
},
{
"from": "gpt",
"value": "Bad. The woman's limbs in the video are incomplete, fingers are not fully generated, the face is blurry, and the limb generation is uncoordinated."
}
] |
seed46_3155
|
videos/HRA_part2/3155.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, clad in a red jacket and black pants, is scaling an indoor climbing wall with intense focus, framed by a large window that bathes the scene in natural light. The gymnasium's high ceiling and climbing wall provide a spacious setting, while motivational posters and equipment add context to the environment. The climber's left hand grips a green hold, their right hand poised to grab a blue hold, and both feet are firmly planted on orange footholds, illustrating their progress up the wall. Their backpack rests on the floor, and a climbing harness and helmet ensure safety during the ascent.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2513
|
videos/HRA_part2/2513.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 juxtaposition, a distinguished lawyer, clad in a classic black suit and white shirt, gently caresses the metallic surface of a Mars rover model placed on a wooden table. The room is dimly lit, casting dramatic shadows across the scene. The lawyer's face reflects a mix of fascination and professional poise, while the rover, adorned with intricate details and wheels designed for extraterrestrial terrain, stands as a symbol of human innovation and exploration. This intimate interaction between the legal world and space technology creates a thought-provoking narrative about the convergence of seemingly unrelated fields.]"
},
{
"from": "gpt",
"value": "Normal. The man's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed42_1603
|
videos/HRA_part0/1603.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, distinguished by his chiseled jawline and dark, neatly styled hair, stands on a wooden chair in a spacious, modern living room. He wears a casual, fitted black t-shirt and dark jeans, and is engaged in the everyday task of changing a light bulb. The room is furnished with a brown leather sofa and a large flat-screen TV on the wall. The actor's focused gaze and confident posture suggest his ease in handling both dramatic roles and practical household chores. The warm, diffused lighting from other fixtures illuminates the scene, highlighting the actor's profile as he completes the relatable task with a touch of understated elegance.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous, there are sudden changes, and the hands appear deformed."
}
] |
seed44_172
|
videos/HRA_part1/172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, multicolored kite soars majestically against a clear blue sky, its intricate geometric patterns catching the sunlight. Attached to it is a long string held tightly by a child wearing a yellow t-shirt, blue jeans, and a wide-brimmed hat, standing on a lush green hill dotted with wildflowers. The child's face is lifted towards the sky, eyes full of wonder and joy, while the wind gently tousles their hair. Around them, a panoramic view of rolling hills and distant mountains provides a stunning backdrop to this scene of youthful delight and freedom.]"
},
{
"from": "gpt",
"value": "Bad. The child's fingers in the video are not fully generated, the facial features are missing, the kite is distorted, and there are parts of the limbs missing."
}
] |
seed46_3045
|
videos/HRA_part2/3045.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 chimpanzee, exhibiting a gentle demeanor, caresses another smaller chimpanzee with its right hand, both sitting on a brown surface against a green background. The larger chimpanzee, with a caring expression, tenderly strokes the younger one, fostering a sense of intimacy and connection. This heartwarming scene captures the essence of compassion within the primate family, highlighting the nurturing bond between the two creatures in their natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The large gorilla's hand is deformed in the video, and there are issues with the small gorilla's face and hands. In the middle frame, the large gorilla's hand goes straight through the small gorilla's head."
}
] |
seed44_1159
|
videos/HRA_part1/1159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned janitor, clad in a brown jacket and blue jeans, meticulously rakes a pile of autumn leaves into a neat heap on a school campus, his weathered hands gripping the wooden handle of the rake. The scene is set against a backdrop of a large, red-brick school building, with a signpost nearby. He pauses to wipe sweat from his brow, revealing a determined look, before resuming his task with renewed vigor, the golden afternoon sunlight casting long shadows across the leaf-strewn grounds.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1954
|
videos/HRA_part1/1954.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a lifelike jaguar mascot, wearing a brown uniform and a name tag, leaps over a green cash register in slow motion, set against a vibrant yellow backdrop. The mascot, with its mouth playfully open, is captured mid-air, just above the register, which is adorned with colorful bills and coins. The cash register itself is old-fashioned, with a large price display and mechanical keys, adding a nostalgic touch to the dynamic scene.]"
},
{
"from": "gpt",
"value": "Normal. The name tag did not appear in the video."
}
] |
seed44_1917
|
videos/HRA_part1/1917.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 beautifully cooked piece of salmon, expertly seared to achieve a perfect golden crust, sits center stage on a white ceramic plate. The salmon boasts a vibrant orange-pink interior, flaky yet moist, with a hint of dill sprinkled over it. Surrounding the fish are vibrant green asparagus spears, steamed to retain their crisp texture and natural color. Completing the dish is a drizzle of creamy sauce, likely a blend of lemon, butter, and capers, adding a touch of elegance and flavor. The plate is garnished with a sprig of parsley, enhancing the visual appeal of this exquisite salmon dish.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2436
|
videos/HRA_part2/2436.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 meerkat, standing upright on its hind legs, surveys its surroundings in a suburban backyard, with a wooden deck, a lush lawn, and a swimming pool in the background. The meerkat, known for its striped brown fur and alert demeanor, appears curious and engaged with its new environment. It stands on a manicured green lawn, next to a wooden deck with patio furniture, and looks towards a large, clear swimming pool, where the water shimmers under the bright sunlight. The contrast between the wild creature and the domestic setting creates a unique and unexpected visual narrative.]"
},
{
"from": "gpt",
"value": "Normal. The meerkat's movements in the video are slightly uncoordinated."
}
] |
seed44_2131
|
videos/HRA_part1/2131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and safety goggles, carefully crawls across a rugged, volcanic landscape, examining a unique rock formation. Surrounded by steam vents and volcanic rocks, the doctor, complete with a backpack and protective gear, crawls through a narrow crevice, demonstrating determination and focus in the harsh environment. The scene highlights the doctor's adventurous spirit and scientific curiosity, as they navigate the challenging terrain, crawling under low-hanging rock formations, all set against the dramatic backdrop of an active volcano.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1502
|
videos/HRA_part1/1502.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a lush, subtropical woodland setting, a majestic tiger lies on the rich forest floor, its coat blending harmoniously with the dappled sunlight filtering through the dense foliage above. The camera captures the intimate moment as a gentle hand caresses the tiger's head, conveying an unexpected sense of trust and connection between the wild animal and the unseen human presence. The tiger's eyes are closed, its expression one of pure bliss, indicating a rare bond formed within the natural habitat of the subtropical woodlands.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands are distorted, and the tiger's ears are twisted."
}
] |
seed46_1571
|
videos/HRA_part2/1571.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown capybara is seen swimming across a tranquil body of water, its ears and nose poking above the surface as it propels itself forward with powerful kicks from its webbed feet. The scene is set against a lush, green forest backdrop, with sunlight filtering through the trees and casting dappled shadows on the water. Peaceful ripples spread out from the capybara's movements, creating a serene and captivating view of this aquatic rodent in its natural habitat.]"
},
{
"from": "gpt",
"value": "Normal. The capybara's movements in the video are basically normal, with slight coordination issues."
}
] |
seed46_1561
|
videos/HRA_part2/1561.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 astronaut, clad in a sleek silver spacesuit and helmet, leaps into the air against the backdrop of a distant galaxy, stars shimmering in the vast cosmic landscape. The astronaut's pose conveys a sense of weightlessness and freedom as he appears to float in zero gravity, with the vibrant colors of far-off celestial bodies providing a dramatic contrast to his metallic attire. The scene captures the exhilaration and mystery of interstellar exploration, with the astronaut seeming to defy the laws of physics in the boundless expanse of space.]"
},
{
"from": "gpt",
"value": "Bad. The character's hands and feet in the video are generated incorrectly."
}
] |
seed46_2091
|
videos/HRA_part2/2091.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student wearing a gray sweater and black jeans sits in a classroom, wiping the surface of a large, advanced telescope with a cloth, as if preparing it for use. The room is dimly lit, with a projector screen displaying images of deep space in the background. The student's focus is intense, their actions deliberate, as they handle the telescope with care, its size and complexity suggesting it is used for serious astronomical research or communication. The overall scene conveys a sense of dedication and curiosity about the mysteries of the universe.]"
},
{
"from": "gpt",
"value": "Normal. The man's limbs are missing in the video, and his facial features are generated blurry."
}
] |
seed46_1159
|
videos/HRA_part2/1159.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 seasoned janitor, clad in a brown jacket and blue jeans, meticulously rakes a pile of autumn leaves into a neat heap on a school campus, his weathered hands gripping the wooden handle of the rake. The scene is set against a backdrop of a large, red-brick school building, with a signpost nearby. He pauses to wipe sweat from his brow, revealing a determined look, before resuming his task with renewed vigor, the golden afternoon sunlight casting long shadows across the leaf-strewn grounds.]"
},
{
"from": "gpt",
"value": "Bad. The character's arm is twisted, the hand is twisted, the face is distorted, the legs are twisted, and the hoe in the hand is twisted."
}
] |
seed42_2658
|
videos/HRA_part0/2658.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A distinguished film director, donning a dark green shirt, beige shorts, and a brown belt, is seen meticulously dusting vintage furniture within a grand room filled with antique artifacts. He pauses to adjust his glasses, revealing a look of deep concentration. His gaze then shifts to a large painting hanging on the wall, as if contemplating its significance. The director continues his task, now focusing on a wooden cabinet, his movements deliberate and precise, demonstrating his attention to detail. Lastly, he inspects a polished table, his reflection visible in its gleaming surface, as he ensures every inch is free from dust, all the while remaining in the same room with its collection of cherished items.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_3066
|
videos/HRA_part1/3066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, vibrant scene, a group of people wearing colorful swimsuits swim in a large, clear pool, with a majestic giraffe standing nearby, observing the swimmers with curiosity. Overhead, a futuristic Photon sail floats gracefully in the sky, reflecting sunlight and casting dynamic shadows onto the water below. The people interact with the giraffe gently, feeding it leaves, while the sail continues its serene journey across the sky, creating a harmonious blend of nature and advanced technology.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, arms are distorted, and the giraffe's face is distorted."
}
] |
seed42_250
|
videos/HRA_part0/250.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room filled with bookshelves, two young boys, one wearing a gray shirt and the other in a navy blue sweater, are diligently organizing books on a lower shelf. The atmosphere is calm and focused, with the boys working attentively side by side. One child carefully selects a book from a pile, examining it before placing it on the shelf, while the other arranges the books alphabetically, ensuring each title is correctly positioned. The room is warm and welcoming, with sunlight streaming in through a nearby window, casting a soft glow over the children as they engage in this educational activity together.]"
},
{
"from": "gpt",
"value": "Bad. The little boy's face and hands are distorted in the video."
}
] |
seed46_2385
|
videos/HRA_part2/2385.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A man dressed in a yellow shirt, green vest, and brown shorts leaps into the air with his arms extended above his head, against a backdrop of dense subtropical forest. The lush green foliage, including palm fronds and ferns, provides a vibrant setting. In another frame, he jumps again, this time with his arms wide open, wearing a white cap, dark sunglasses, and a smile, against a similar background of rich, verdant trees. Throughout the sequence, the man's joyful expressions and dynamic poses capture the essence of his energetic exploration within the vibrant subtropical woodland environment.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video has missing limbs, a deformed body, and facial generation issues."
}
] |
seed44_1116
|
videos/HRA_part1/1116.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a heartwarming scene, a uniformed police officer kneels on lush green grass, gently caressing a tiny vole with utmost care and tenderness. The officer, wearing a classic navy blue police uniform with a badge and a cap placed nearby, ensures the small creature feels safe and secure. The vole, with its delicate features and curious eyes, seems at ease in the presence of the compassionate law enforcement figure. The background is a serene park setting, with trees and a clear blue sky, highlighting the unexpected yet touching connection between the officer and the vole.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1315
|
videos/HRA_part2/1315.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 student, dressed in a yellow t-shirt and blue jeans, is playfully chasing a juvenile rhinoceros across a vast, grassy savannah under a bright blue sky. The action is captured from multiple angles, first showing the student's enthusiastic pursuit, followed by a shot of the rhino's surprised reaction as it turns its head back. Next, the scene focuses on the student's determined facial expression, highlighting the joy and energy of the chase. Finally, a side view captures the dynamic duo running in unison, the student's arms waving wildly and the rhinoceros' ears flapping, both enjoying the spontaneous adventure in the expansive landscape.]"
},
{
"from": "gpt",
"value": "Bad. The character's head, arms, and legs are distorted in the video, as well as the rhino's body, arms, claws, face, and legs."
}
] |
seed46_1555
|
videos/HRA_part2/1555.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, animated scene, a scholarly mouse, dressed in a blue cap and gown, sits at a desk cluttered with books, pens, and a laptop, studying intently under a bright lamp. Suddenly, the mouse finds itself transported to a futuristic space casino, complete with neon lights, slot machines, and alien patrons. The mouse, now wearing a stylish tuxedo, confidently plays a game of cards, surrounded by an eclectic crowd. In the next moment, the setting changes to a luxurious, zero-gravity swimming pool, where the mouse, now in swimming trunks, happily splashes and swims among bubbles and floating objects, enjoying its unexpected adventure.]"
},
{
"from": "gpt",
"value": "Bad. The rat's hand appears deformed, and its face also becomes deformed when the scene changes."
}
] |
seed42_1506
|
videos/HRA_part0/1506.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magnificent tiger, mid-leap, propels itself from a large rock into a lush, green forest, its body stretched out in a powerful arc. The tiger, with its distinctive orange coat patterned with black stripes, exhibits raw strength and grace as it jumps, surrounded by dense foliage and towering trees that provide a natural habitat. The action is captured in stunning detail, focusing on the tiger's muscular form, intense concentration, and the dynamic motion of its leap, encapsulating the essence of wild freedom.]"
},
{
"from": "gpt",
"value": "Bad. The tiger in the video has two tails, and its claws are distorted."
}
] |
seed44_2440
|
videos/HRA_part1/2440.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 domestic chicken, featuring brown and white feathers, is shown swimming in a small, clear body of water, surrounded by green grass and foliage. It paddles energetically with its feet, creating ripples on the water's surface, while its head remains dry above the waterline. The chicken's unique activity is captured in a series of shots that showcase its unexpected aquatic adventure in a natural, backyard setting.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2430
|
videos/HRA_part0/2430.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical and unexpected scene, a waiter, clad in a crisp white shirt and black trousers, serves a majestic deer who stands elegantly by a serene swimming pool, its antlers framing its face like a crown. The deer, with its large, curious eyes, seems to be sipping from a fancy glass, while the waiter attentively pours a clear liquid, possibly water, from a pitcher. The swimming pool, with its crystal-clear water, reflects the sky, adding to the surreal atmosphere of this extraordinary meeting between nature and human service.]"
},
{
"from": "gpt",
"value": "Normal. The deer's action of sipping the liquid from the glass is basically normal, but the waiter's pouring action is uncoordinated."
}
] |
seed44_3134
|
videos/HRA_part1/3134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lawyer, dressed in a casual yet stylish ensemble of a gray turtleneck sweater and black pants, stands in a modern kitchen with sleek, stainless steel appliances. The individual focuses intently on preparing a gourmet meal, chopping ingredients on a wooden cutting board placed atop a granite countertop. The kitchen is illuminated by recessed ceiling lights, casting a warm glow over the scene. Behind the chef, a large window allows a view of a city skyline at twilight, adding a touch of urban sophistication to the domestic setting. The lawyer's movements are confident and practiced, indicating a comfort in both the courtroom and the culinary arts.]"
},
{
"from": "gpt",
"value": "Bad. The character's face and hands are distorted in the video."
}
] |
seed44_2327
|
videos/HRA_part1/2327.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 pufferfish, with its distinctive round shape and small size, swims gracefully in a vibrant coral reef environment. Its body, covered in tiny, pebble-like protrusions, is a mix of yellow and white with intricate black patterns. The fish inflates to nearly twice its original size, demonstrating its defense mechanism against potential predators lurking among the colorful corals and marine life surrounding it. The water is crystal clear, allowing every detail of the pufferfish's unique appearance and behavior to be captured in stunning high definition.]"
},
{
"from": "gpt",
"value": "Normal. The pufferfish's mouth and fins generation in the video have problems."
}
] |
seed46_1583
|
videos/HRA_part2/1583.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical, neon-lit diner from another dimension, a badger, dressed in a crisp waiter's outfit complete with a bow tie and apron, is seen energetically tap dancing. The animated badger performs intricate dance steps on a checkered floor, surrounded by surreal, cosmic decor, creating an otherworldly atmosphere. This captivating scene is enhanced by the vibrant, pulsating lights that illuminate the peculiar space, giving it an electrifying, interdimensional vibe. The badger's expressive face and lively movements convey a sense of joy and wonder in this extraordinary setting.]"
},
{
"from": "gpt",
"value": "Bad. The badger in the video walks very unsmoothly, with uncoordinated movements."
}
] |
seed44_172
|
videos/HRA_part1/172.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, multicolored kite soars majestically against a clear blue sky, its intricate geometric patterns catching the sunlight. Attached to it is a long string held tightly by a child wearing a yellow t-shirt, blue jeans, and a wide-brimmed hat, standing on a lush green hill dotted with wildflowers. The child's face is lifted towards the sky, eyes full of wonder and joy, while the wind gently tousles their hair. Around them, a panoramic view of rolling hills and distant mountains provides a stunning backdrop to this scene of youthful delight and freedom.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1480
|
videos/HRA_part1/1480.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising juxtaposition, a large hippopotamus walks along a riverbank, its massive body glistening under the sun, with industrial factories looming in the background. The scene opens with a wide shot of the river, where the hippo emerges from the water, its wet skin reflecting the sunlight. It then proceeds to walk along the riverbank, its powerful legs propelling it forward, as it passes by the factories, which emit plumes of smoke into the sky. The camera focuses on the hippo's movements, capturing its every step as it traverses this unusual landscape, the factories serving as a stark contrast to the natural beauty of the animal.]"
},
{
"from": "gpt",
"value": "Bad. The hippo's head is twisted, and the legs are twisted."
}
] |
seed42_3129
|
videos/HRA_part0/3129.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, adorned in a red apron with a white floral pattern, sits on a wooden chair in a sunlit room filled with art supplies. She gently caresses a chicken, which is perched on her lap, its head adorned with a vibrant red comb. The room is decorated with colorful paintings, a large easel, and a variety of art tools, creating a warm and creative atmosphere. The artist's face, framed by curly brown hair, expresses love and connection as she interacts with the bird, highlighting the unique bond between the two.]"
},
{
"from": "gpt",
"value": "Normal. The artist's eyes in the video have generation issues, the fingers are deformed, the chicken's head is abnormally generated, and the claws are deformed."
}
] |
seed42_2457
|
videos/HRA_part0/2457.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, smiling female musician, wearing a gray sweater, sits against a rustic wooden backdrop. She holds knitting needles and yarn in her hands, crafting a vibrant orange scarf. Her fingers, adorned with rings, skillfully manipulate the needles as she knits. Next, she wears a maroon beret and continues knitting, her eyes focused on her work. Then, she looks up from her knitting, her hazel eyes meeting the camera with a warm smile. Lastly, she proudly holds up the completed scarf, now a beautiful addition to her outfit, against the backdrop of wooden planks, showcasing her dual talents in music and knitting.]"
},
{
"from": "gpt",
"value": "Bad. The musician's hand generation in the video has issues."
}
] |
seed44_2446
|
videos/HRA_part1/2446.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the hazy, ethereal atmosphere of Neptune, a space-suited firefighter, equipped with a specialized breathing apparatus and protective gear, is seen wiping the visor of his helmet. A neon bat, adapted to the planet's unique environment, hangs upside-down from a rocky outcropping nearby, its vibrant wings contrasting against the dimly lit, gaseous landscape. The firefighter's actions are deliberate and methodical, emphasizing the importance of maintaining clear visibility in the challenging conditions of Neptune's alien skies.]"
},
{
"from": "gpt",
"value": "Normal. The action of the firefighter wiping the helmet visor is basically normal, but there is some lack of coordination."
}
] |
seed44_2964
|
videos/HRA_part1/2964.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, cheerful female cashier, wearing a green apron over a gray sweater and black pants, stands on a ladder cleaning the gutters of a small, wooden house during autumn. She has pulled back her long, dark brown hair into a bun. The scene is set in a backyard with lush green grass, and there are trees with yellow leaves in the background. The house features a red front door, a green window frame, and a roof with brown shingles. The woman uses a gloved hand to scoop out debris from the gutters, showcasing her determination and hard work.]"
},
{
"from": "gpt",
"value": "Bad. The female cashier's face, hands, arms, and items in her hands are distorted in the video."
}
] |
seed46_134
|
videos/HRA_part2/134.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, identifiable by their beret and smock, kneels on a lush, alien landscape, sketching a capybara. The capybara, depicted in a relaxed posture, is the focal point, sitting amidst Martian flora. The scene is illuminated by the vibrant hues of a Martian sunset, casting an ethereal glow across the terrain. The artist's concentrated expression and the capybara's calm demeanor create a sense of tranquility, enhanced by the distant, rugged Martian mountains and the unique atmospheric conditions of the planet, which contribute to the vivid sunset colors. The artist's tools, including a palette and brushes, are scattered nearby, adding to the creative atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The actions are discontinuous."
}
] |
seed46_1499
|
videos/HRA_part2/1499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space-themed library, a group of diverse individuals, including a bison cosplayer wearing a full-body brown fur costume, gather for a book club meeting. The cosplayer sits attentively among the members, who are seated on cozy armchairs and couches arranged in a circle. The room features high-tech elements, such as holographic book covers floating above each person, indicating their current reads. The bison cosplayer listens intently, occasionally nodding and gesturing with enthusiasm, while the other members engage in lively discussion about their latest sci-fi novel. In the background, a large window reveals the vastness of outer space, with stars twinkling and galaxies swirling in the distance. Suddenly, the bison cosplayer leaps up and begins to run in place, demonstrating the agility and strength of their chosen animal, much to the amusement of the other book club members.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1395
|
videos/HRA_part1/1395.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, brown capybara sits calmly in a natural setting, surrounded by lush greenery and water in the background. It gently caresses another smaller capybara with its front paws, showing tenderness and care. Both capybaras are positioned against a serene landscape, highlighting the intimate interaction between the two creatures. The larger capybara's nurturing touch towards the smaller one conveys a sense of affection and protection within their social structure.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2503
|
videos/HRA_part0/2503.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 brown mouse leaps through the air in a grassy field, its tiny body arched gracefully as it propels itself forward. The scene is set against a backdrop of lush green foliage and blue skies, with the mouse's agile movement captured mid-jump. Its wiry tail extends behind it, adding to the sense of dynamic motion, while its round ears and beady eyes give it a characteristically cute appearance. The mouse lands softly on a patch of green grass, ready to spring into action again at a moment's notice.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2641
|
videos/HRA_part0/2641.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a bustling city scene, a waiter wearing a black apron over a white shirt is diligently wiping tables outdoors, where various shops with colorful awnings line the street. A friendly-looking golden retriever dog, possibly the waiter's pet, sits attentively nearby, watching him work. The atmosphere is lively, with passersby and the sounds of city life in the background, creating a dynamic and engaging environment. The waiter's focused expression and the dog's patient demeanor add a touch of warmth to the urban setting.]"
},
{
"from": "gpt",
"value": "Normal. The server wiped the wrong area, and the server's hand did not touch the table."
}
] |
seed44_2605
|
videos/HRA_part1/2605.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 large, brown capybara runs energetically across a grassy plain, its wet nose and alert eyes highlighting its distinctive features. It bounds forward with determination, showcasing its muscular legs and agile movements. Moments later, the capybara leaps gracefully over an obstacle, demonstrating its impressive jumping ability. Then, it sprints with focused intensity, ears perked, and nostrils flared, against a backdrop of lush vegetation and distant hills. Finally, the capybara continues its swift run, its body language conveying strength and vitality as it navigates the open landscape.]"
},
{
"from": "gpt",
"value": "Bad. The capybara's ears in the video have generation issues, and there are missing limbs."
}
] |
seed42_1041
|
videos/HRA_part0/1041.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [Two young boys, one wearing a yellow shirt and the other in red, energetically scrub the bathroom floor with sponges, creating soapy lather. They are focused on their task, with one boy on his hands and knees, working diligently, and the other standing, intently cleaning the wall tiles. The room is filled with the soft sound of water and the energetic movements of the children, who seem to find joy in the chore, transforming the mundane task into a playful activity. Their faces are expressions of determination and delight, turning the bathroom into a space of unexpected fun and teamwork.]"
},
{
"from": "gpt",
"value": "Normal. The boy in the yellow shirt moves the sponge too fast."
}
] |
seed46_2131
|
videos/HRA_part2/2131.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 doctor, wearing a white lab coat and safety goggles, carefully crawls across a rugged, volcanic landscape, examining a unique rock formation. Surrounded by steam vents and volcanic rocks, the doctor, complete with a backpack and protective gear, crawls through a narrow crevice, demonstrating determination and focus in the harsh environment. The scene highlights the doctor's adventurous spirit and scientific curiosity, as they navigate the challenging terrain, crawling under low-hanging rock formations, all set against the dramatic backdrop of an active volcano.]"
},
{
"from": "gpt",
"value": "Bad. During the process of climbing the mountain, the man's arm undergoes a sudden mutation and deformity, with a third arm appearing, and the hand also becomes deformed."
}
] |
seed46_2402
|
videos/HRA_part2/2402.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a whimsical scene, a costumed firefighter, complete with helmet and yellow firefighting jacket, races through a lush, green forest, closely pursued by an animated beaver wearing a miniature firefighter uniform, also with a helmet and a small red cape. The firefighter leaps over a fallen log, demonstrating agility, while the beaver follows suit, mimicking every action with playful determination. Both characters run with purpose, the firefighter leading the charge and the beaver keeping pace, highlighting a fun, animated adventure set against the vibrant backdrop of a dense woodland.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous and undergo sudden changes."
}
] |
seed46_219
|
videos/HRA_part2/219.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 endearing otter, with its distinct brown fur and charming face, sits on a wooden boardwalk, creating an unusual yet captivating scene. It reaches out with its paw, seemingly caressing the surface of the weathered wood, as if cherishing a familiar touch. The otter's playful demeanor and the texture of the boardwalk combine to form a narrative of unexpected encounters and gentle interactions in a natural yet built environment.]"
},
{
"from": "gpt",
"value": "Normal. The otter's movements in the video are basically normal, but there is slight disharmony."
}
] |
seed44_1767
|
videos/HRA_part1/1767.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 solitary buzzard perches majestically on a barren branch, its piercing eyes scanning the vast, sunlit savannah below for any signs of movement. The bird, with its distinct brown and white plumage, contrasts starkly against the muted tones of the landscape. Suddenly, it spreads its impressive wingspan and takes flight, gliding effortlessly over the terrain. Its sharp talons are clearly visible as it descends with laser-like precision towards a potential meal, showcasing the raw power and agility of this apex predator. The scene is set against a backdrop of rolling hills and scattered trees, bathed in the warm glow of the afternoon sun.]"
},
{
"from": "gpt",
"value": "Normal. The flying motion is unsmooth."
}
] |
seed46_1443
|
videos/HRA_part2/1443.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising and surreal scene, a large, gray rhinoceros leaps into the air, defying expectations, with its powerful legs extended and body arched. This incredible moment is captured against a backdrop of a vast savanna landscape, dotted with trees and stretching to a distant horizon under a bright blue sky. The rhino, known for its heavy, armored skin and imposing horn, is shown mid-jump, creating a unique and unforgettable image that highlights the animal's unexpected agility and strength.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_2473
|
videos/HRA_part0/2473.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 motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman 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": "Normal. The person in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed42_1705
|
videos/HRA_part0/1705.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 casino, a distinguished chef, donning a traditional white chef's uniform with black stripes and a black necktie, walks with purpose. He carries a large, covered silver platter, its lid adorned with a golden handle. Behind him, a bustling kitchen reveals chefs in action, preparing exquisite dishes. The casino's opulent decor is visible through a glass partition, featuring patrons enjoying themselves at various gaming tables. The chef's confident stride and the casino's lively atmosphere create a captivating contrast between culinary expertise and the thrill of gambling in outer space.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_1747
|
videos/HRA_part2/1747.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman wearing a white sleeveless top and blue jeans, her hair tied back in a bun, is energetically scrubbing the bathtub in a spotless white bathroom. The overhead lights reflect off the shiny surfaces, highlighting her vigorous cleaning. She uses a green scrub brush and yellow rubber gloves, her face set with determination as she tackles the task at hand. The bathroom is spacious and well-lit, with a large mirror above the sink and a window letting in natural light, all contributing to a sense of cleanliness and order.]"
},
{
"from": "gpt",
"value": "Normal. The woman's arm in the video is poorly generated, and her fingers are missing."
}
] |
seed44_1464
|
videos/HRA_part1/1464.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In the vast, golden expanse of the temperate grasslands, a lone dingo, its sandy fur blending with the surroundings, stands alert. It shakes off water droplets, its ears pricked forward, before wiping its face with a paw in a natural grooming gesture. The dingo then continues its vigilant stance, scanning the horizon under a clear blue sky, the wind gently swaying the tall grass around it. This intimate moment captures the creature's resilience and adaptability in its native habitat, the rolling plains stretching to the horizon under a wide, cloudless sky.]"
},
{
"from": "gpt",
"value": "Bad. The legs of the stray dog in the video are over-generated."
}
] |
seed44_2053
|
videos/HRA_part1/2053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, futuristic space station, a diligent janitor, clad in a silver reflective suit, pushes a high-tech cleaning cart while walking down a long, sterile corridor illuminated by cool, artificial lights. Suddenly, the walkie-talkie on his belt crackles to life, transmitting a message from mission control regarding an incoming transmission from deep space. The janitor stops, listens intently, and acknowledges the message before continuing his duties, passing by a large window displaying the awe-inspiring view of distant galaxies and star clusters. Throughout the scene, a small Bobcat construction vehicle, equipped with advanced space-grade tools, can be seen in the background, autonomously performing maintenance tasks on the station's outer hull.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2671
|
videos/HRA_part1/2671.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 grey suit, white shirt, and patterned tie, walks purposefully across a grassy field under a twilight sky, carrying a large, transparent bag. In the distance, a comet streaks across the night sky, its tail glowing brightly. The lawyer pauses, turning his head to gaze up at the celestial phenomenon, his expression a mix of awe and determination. Despite the extraordinary sight, he continues his steady walk, the comet's light illuminating his path forward.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2685
|
videos/HRA_part0/2685.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 film director, wearing a brown leather jacket and dark jeans, stands in a rugged chaparral landscape, gesturing emphatically. He watches intently as a porcupine, quills fully displayed, jumps over a small log, showcasing its surprising agility in the wild environment. The director's focused stance and the porcupine's unexpected leap are framed by the chaparral vegetation, highlighting the unique interaction between human creativity and natural wildlife.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2650
|
videos/HRA_part1/2650.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sophisticated office setting, a professional lawyer, dressed in a navy suit, white shirt, and striped tie, sits at a cluttered desk adorned with legal documents and a laptop. He pauses from his work to look up, captivated by a stunning holographic display of an exoplanet orbiting its star, projected from his device. The lawyer then wipes away the hologram with a sweeping hand gesture, returning his attention to the challenging legal briefs spread out before him, highlighting the contrast between his daily duties and the captivating world of astronomical discoveries.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_1328
|
videos/HRA_part0/1328.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 Neptune's ethereal atmosphere, human figures, clad in futuristic, silver, metallic swimsuits and equipped with advanced breathing apparatus, swim gracefully through the gaseous clouds. Their movements are fluid and balletic, almost as if they are performing an underwater dance in the sky. The humans, both male and female, exhibit expressions of wonder and awe as they navigate the alien environment. They perform synchronized swimming routines, moving in perfect harmony with each other and the surrounding gas giant atmosphere. The scene is illuminated by a distant sun, casting a soft, dreamlike glow on the figures as they glide through the thick, swirling clouds of Neptune.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has incomplete and deformed body parts, limbs, and face."
}
] |
seed42_2056
|
videos/HRA_part0/2056.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young male cashier, sporting a clean-shaven face and a neatly tucked-in red shirt, diligently organizes items on a grocery store shelf. The store is devoid of customers, allowing him to focus on restocking with precision. He carefully places a can of beans onto the shelf, surrounded by other neatly arranged cans. His hands, free of gloves, handle each item with care, ensuring they are perfectly aligned. The well-lit supermarket aisle provides a clear view of the organized products, highlighting the cashier's attention to detail in his task.]"
},
{
"from": "gpt",
"value": "Bad. The character's hand is distorted in the video."
}
] |
seed42_1024
|
videos/HRA_part0/1024.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A whimsical scene unfolds as a farmer, clad in a traditional straw hat and plaid shirt, steers a futuristic tractor through a vast cornfield under a twilight sky filled with stars. The tractor, equipped with advanced technology and neon lights, glides smoothly over the soil, creating an otherworldly contrast against the rustic landscape. Suddenly, the farmer breaks into a joyful jig, dancing alongside his vehicle with a wide grin, celebrating the harvest under the celestial canopy. The sequence captures the unique blend of rural charm and space-age innovation, all set against the enchanting backdrop of a starlit night.]"
},
{
"from": "gpt",
"value": "Bad. The farmer's driving movements in the video are not smooth, and the dance moves are uncoordinated."
}
] |
seed44_1380
|
videos/HRA_part1/1380.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 ruggedly handsome actor, sporting a full beard, stands in a rural setting under an overcast sky, gently caressing a brown horse with white markings. He wears a gray shirt, blue jeans, and a brown belt, while the horse stands placidly in a grassy area dotted with small trees. The actor's affectionate interaction with the animal conveys a sense of peace and connection in the pastoral environment. The horse, with its mane and tail blowing slightly in the wind, is clearly comfortable with the actor, who continues to stroke its neck with tenderness and respect.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2946
|
videos/HRA_part1/2946.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A stunning close-up of a halibut fish, flat and wide, with a mottled brown and white skin pattern, is showcased against a dark background. The fish has a large, open mouth with small teeth visible, and its eyes are set on the left side of its head, gazing intently. The texture of the halibut's skin is detailed, showing rough spots and a rugged surface, while the background remains uniformly dark, highlighting the unique features of this deep-sea dweller.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_2855
|
videos/HRA_part1/2855.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clad in a blue shirt and khaki pants is seen walking alongside a chimpanzee wearing a tiny red cap, both navigating through a lush, verdant forest. The engineer, carrying a backpack and holding a machete, looks thoughtful as they traverse the underbrush. The chimp, balancing on two legs with a banana in its hand, occasionally glances up at the engineer with curiosity. They continue their journey together, the engineer leading the way with purpose, while the chimpanzee follows closely, the dense greenery of the forest enveloping them.]"
},
{
"from": "gpt",
"value": "Bad. No machete, banana, or gorilla movement and positioning as described in the text."
}
] |
seed44_2351
|
videos/HRA_part1/2351.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 waiter, dressed in a crisp white shirt and black trousers, serves a coyote who is seated at a wooden table set among the lush greenery of the woodlands. The coyote, looking surprisingly refined with a napkin tucked into its collar, enjoys a meal as if dining at a fine restaurant. Behind them, a natural pool glistens under the sunlight, inviting a sense of tranquility and relaxation, contrasting the unexpected yet harmonious interaction between the waiter and the wild coyote.]"
},
{
"from": "gpt",
"value": "Normal. The scarf of the jackal in the video is missing, the tail and paws are generated unreasonably, the server's fingers are not fully generated, there are issues with the face generation, and the body is not generated."
}
] |
seed44_3076
|
videos/HRA_part1/3076.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing a casual outfit of a gray jacket over a black shirt and dark pants, is seen cleaning a table at a busy train station. The environment is filled with travelers rushing to catch their trains, creating a bustling atmosphere. The student diligently wipes the surface, moving from left to right, ensuring cleanliness in the public space. The scene captures the student's commitment to maintaining hygiene amidst the chaotic surroundings of the train station.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1958
|
videos/HRA_part1/1958.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 habitat, an anthropomorphic chimpanzee, clad in a silver spacesuit and helmet, performs an energetic dance against a backdrop of advanced technology and starlit windows. The chimp's movements are lively and expressive, conveying a sense of joy and freedom in the zero-gravity environment. Accompanied by upbeat music, the chimpanzee's dance includes playful jumps and twirls, highlighting its adaptability and charisma in the unique setting of a space station, where screens display vibrant colors and the vastness of outer space provides a stunning contrast to the lively performance.]"
},
{
"from": "gpt",
"value": "Bad. The limbs of the chimpanzee in the video are missing, and the face is deformed."
}
] |
seed44_1884
|
videos/HRA_part1/1884.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic starship bridge, illuminated by soft blue and green lights, a small, fluffy white hare is crawling across the command deck. The hare moves slowly, its ears perked up, exploring the high-tech environment filled with control panels and large viewing screens displaying cosmic visuals. The bridge is otherwise empty, save for the advanced technology and the occasional blinking lights, creating a surreal contrast between the sci-fi setting and the unexpected presence of the crawling hare.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.