video_id
stringlengths 8
11
| video
stringlengths 22
25
| conversations
listlengths 2
2
|
|---|---|---|
seed46_1887
|
videos/HRA_part2/1887.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 charismatic male chef, wearing a classic white chef's jacket and black pants, is filmed in a bustling, modern restaurant kitchen. He begins by seasoning a dish with a sprinkle of herbs, his hands moving with practiced ease. Next, he deftly flips a piece of seared salmon in a sizzling pan, the steam rising around him adding to the atmosphere. Then, he carefully arranges the cooked salmon on a plate, garnishing it with fresh greens and a drizzle of sauce. Lastly, he gives a satisfied nod, presenting the beautifully plated meal to the camera, the vibrant colors of the food contrasting with the stainless steel appliances in the background.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_1803
|
videos/HRA_part2/1803.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising scene set in a subtropical desert landscape, a police officer, clad in a tan uniform and wide-brimmed hat, is gently wiping the face of a curious capybara. The officer, showing unexpected tenderness, kneels beside the large rodent, which is sitting calmly on the sandy terrain, surrounded by sparse vegetation typical of arid environments. The interaction between the law enforcement figure and the capybara underlines an unusual yet touching moment in the vast, sun-baked wilderness.]"
},
{
"from": "gpt",
"value": "Normal. The police officer's movements are uncoordinated."
}
] |
seed42_2508
|
videos/HRA_part0/2508.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, wearing a brown jacket and wide-brimmed hat, walks purposefully across a vast, futuristic farm landscape, with a colossal space elevator looming in the distance, its massive cable stretching into the heavens. The farmer pauses, looking up at the awe-inspiring structure, a blend of hard work and advanced technology coexisting in this extraordinary setting. As he continues walking, the camera captures the juxtaposition of traditional farming life and the futuristic marvel towering over the horizon.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1053
|
videos/HRA_part2/1053.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, with its distinctive short tail and tufted ears, strides purposefully across a dry, rocky terrain under the clear blue sky. Its tawny fur, marked with spots and stripes, blends perfectly with the arid environment. The cat's piercing eyes remain alert, scanning the surroundings for potential prey or threats, as it moves with a confident gait, showcasing its natural agility and strength in the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2725
|
videos/HRA_part2/2725.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit urban alleyway, a middle-aged man wearing a worn-out brown jacket and blue jeans leans against a brick wall. He cradles a small rat in his hands, gently stroking it, while standing next to large, green dumpsters. The rat nestles in his palm, seemingly tamed and cared for, as the man looks down at it with a warm smile. Behind him, the bustling city streets are visible, with passersby and traffic lights, creating a contrast between the tenderness of the moment and the harshness of the urban environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2587
|
videos/HRA_part1/2587.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 and whimsical scene, a Bactrian camel with two humps, typically found in desert environments, is seen swimming in crystal-clear waters. The camel, with its shaggy brown coat and large, curious eyes, moves gracefully through the water, its head held high above the surface. The backdrop features lush greenery and palm trees, contrasting the camel's usual habitat. The setting sun casts a warm glow over the landscape, creating a surreal and captivating moment where desert meets sea.]"
},
{
"from": "gpt",
"value": "Normal. The double peaks were not presented, and it was slightly deformed."
}
] |
seed46_152
|
videos/HRA_part2/152.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 museum dedicated to firefighting history, a lone firefighter, dressed in full gear except for his helmet, meticulously wipes an antique fire engine, showing respect and care for the vintage piece. The museum is filled with various firefighting artifacts, creating a rich historical context. The firefighter, wearing a yellow shirt underneath his uniform, is deeply engaged in cleaning the old fire truck, highlighting the connection between present-day firefighters and their heritage. Surrounded by firefighting memorabilia, he continues to polish the vehicle, emphasizing the importance of preserving the past within the firefighting community.]"
},
{
"from": "gpt",
"value": "Normal. There is an issue with the generation of the firefighter's hand in the video."
}
] |
seed44_2485
|
videos/HRA_part1/2485.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 black cap and a blue flannel shirt, is seen painting an antelope on a large canvas set against a background of lush greenery. The canvas is placed on an easel, and the artist, with a concentrated look, applies vibrant orange paint to depict the animal. The antelope, depicted as running with its head turned back, is captured mid-stride, its movement and grace highlighted by the artist's brushstrokes. The setting sun casts a warm glow over the scene, illuminating the artist's silhouette and the vivid depiction of the antelope in motion.]"
},
{
"from": "gpt",
"value": "Normal. The man's hand is somewhat deformed, and the brush in his hand is bent and distorted."
}
] |
seed46_2554
|
videos/HRA_part2/2554.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, wearing a gray sweater and brown pants, is seen painting en plein air in a lush green forest. Suddenly, a squirrel scurries into the frame, running along the forest floor, its bushy tail bouncing behind it. The artist pauses, observing the squirrel's movements with fascination, capturing the essence of the woodland creature in motion on the canvas. The squirrel, now aware of the artist's presence, stops briefly to look back before continuing its hurried journey, providing a perfect subject for the artist's brushstrokes.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_2837
|
videos/HRA_part0/2837.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic red-tailed hawk soars through a clear blue sky, its powerful wings stretched wide, casting a shadow on the rugged, rocky terrain below. It effortlessly glides over a dense forest, the sunlight glinting off its russet and white plumage, with a backdrop of lush green trees. The hawk then focuses intently, spotting prey from above, its piercing eyes and curved beak displaying its predatory nature. It finishes by perching regally atop a barren tree branch, surveying its domain with a fierce gaze, the wind gently ruffling its feathers.]"
},
{
"from": "gpt",
"value": "Normal. The red-tailed hawk's flying movements in the video are slightly unsmooth."
}
] |
seed42_1018
|
videos/HRA_part0/1018.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 tabby cat with distinct stripes sits calmly in front of a sprawling industrial landscape dominated by oil refineries under a hazy sky. It gently caresses a smooth surface with its paw, its green eyes intently focused on the action. The cat's relaxed posture and deliberate movements contrast sharply with the gritty, mechanical backdrop of pipes and tanks. Throughout the scene, the cat remains the central figure, its fur softly glowing in the muted light, as it continues to tenderly stroke the surface, a curious juxtaposition of tenderness and hardness.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1846
|
videos/HRA_part2/1846.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful musician, wearing a red flannel shirt, blue jeans, and brown boots, runs alongside a spirited golden retriever in a lush green park. Both the musician and the dog display expressions of pure joy and freedom. The musician, equipped with a backpack, is in mid-stride, while the dog bounds ahead, tail wagging. The scene captures the essence of a carefree day in the park, with the musician's attire and the dog's enthusiastic demeanor setting the tone for a playful and energetic outing.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, face, arms, feet, and hands, and the dog's legs and face are also twisted."
}
] |
seed46_2074
|
videos/HRA_part2/2074.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-end restaurant, a well-dressed waiter, wearing a black vest and tie, pulls out a chair for a customer at a candlelit table set with fine china and crystal glasses. The background features other patrons enjoying their meals, adding to the ambiance of a busy, upscale dining experience.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_2944
|
videos/HRA_part0/2944.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A construction worker, wearing a yellow safety vest, blue jeans, and a brown baseball cap, is seen catching a tool thrown by a colleague on a building site, with a large, unfinished structure in the background. The scene captures the moment of action, with the worker's eyes fixed on the incoming tool and his body positioned to make the catch. The atmosphere is tense yet focused, highlighting the trust and coordination between the workers in a high-stakes environment.]"
},
{
"from": "gpt",
"value": "Bad. The actions are not continuous."
}
] |
seed46_223
|
videos/HRA_part2/223.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space station interior resembling a bank, a muscular firefighter, now a space hero, crawls through a narrow air duct lit by blue emergency lights. Dressed in a high-tech firefighting suit with a red helmet, he stealthily moves forward on a mission. He continues crawling, his gear and determination evident, as the dimly lit vent and complex machinery surround him. Suddenly, the focus is on his intense face, showcasing his resolve through the visor of his helmet, as he prepares for action. Lastly, our hero is seen in a crouched position, ready to leap into danger, his advanced firefighting equipment at the ready, within the confined space of the air duct.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_1714
|
videos/HRA_part1/1714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 midst of arid scrublands, a spotted hyena, characterized by its distinctive spots and robust build, is unexpectedly seen swimming across a shallow, sunlit waterhole. Its head held high above the clear water, the hyena propels itself forward with powerful strokes, showcasing its rarely observed aquatic abilities. The serene environment is punctuated by the distant silhouette of a lone tree, highlighting the surprising scene unfolding in this typically dry habitat.]"
},
{
"from": "gpt",
"value": "Normal. The spotted hyena in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed42_1775
|
videos/HRA_part0/1775.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A brown beaver, situated near water, performs a wiping motion with its right paw across its face, specifically from the eyes down to the mouth. The beaver is positioned with its back to the camera, offering a unique perspective. Its tail is submerged in the water, and the wiping action is repeated several times, emphasizing the creature's grooming habits in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed42_3007
|
videos/HRA_part0/3007.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A male spruce grouse, perched on a branch in a dense forest, displays its vibrant plumage featuring shades of brown, gray, and white speckles. Its red eyelids stand out against the dark eye, while its yellow bill adds a striking contrast. The bird's feathers are ruffled, perhaps due to a breeze or during a display, and it is surrounded by lush green foliage, indicating a healthy habitat. The grouse is stationary, offering a clear view of its unique features against the backdrop of a richly textured forest environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed46_1292
|
videos/HRA_part2/1292.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom setting, a teacher, dressed in a yellow sweater and blue jeans, is depicted mid-jump, leaping over a stuffed weasel mascot that is sitting on a desk. The mascot is wearing a small graduation cap and holding a book, adding to the playful atmosphere. The teacher's jump is energetic and joyful, conveying a sense of fun and engagement in the educational environment. The scene is brightly lit, capturing the dynamic action and the expressions of delight on the faces of the students watching in the background.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video has a twisted body, distorted face, twisted arms, and twisted legs."
}
] |
seed46_1310
|
videos/HRA_part2/1310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, distinguished by its brown fur, white underbelly, and tufted ears, stealthily crawls across a sandy surface in a suburban town, near wooden fences and lush greenery. It pauses to sniff the air, displaying its sharp teeth and alert demeanor. The feline then continues its crawl, passing by a stone wall and wooden planks, indicating the proximity to human habitation. Throughout the scene, the bobcat's cautious and curious nature is evident as it explores its surroundings in the town's outskirts.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1883
|
videos/HRA_part2/1883.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged musician, donning a dark jacket and distressed jeans, stealthily walks through the dimly lit corridors of a futuristic space prison. His intense gaze is directed ahead, revealing his determination. The harsh, cold lighting accentuates the high-tech, metallic surfaces of the prison environment. As he moves, the camera captures the tension in his body language, hinting at the imminent danger. Despite the oppressive surroundings, the musician's confident stride and unwavering focus suggest a plan in motion, ready to execute his daring escape.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1736
|
videos/HRA_part1/1736.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 strong woman dressed in black pants, a black sports bra, and protective gear, including shin guards and arm pads, is seen in a well-lit gym. She delivers a powerful roundhouse kick, her body exhibiting grace and power, with boxing gloves on her hands and her hair tied back in a ponytail. Moments later, she throws a fierce punch, her face a mask of determination, showcasing her martial arts skills in a space adorned with punching bags and boxing posters. Finally, she executes a high kick, her form impeccable, against a backdrop of gym equipment and motivational wall art, encapsulating her strength and discipline.]"
},
{
"from": "gpt",
"value": "Bad. The woman's movements in the video are not smooth and lack coordination."
}
] |
seed42_1310
|
videos/HRA_part0/1310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 bobcat, distinguished by its brown fur, white underbelly, and tufted ears, stealthily crawls across a sandy surface in a suburban town, near wooden fences and lush greenery. It pauses to sniff the air, displaying its sharp teeth and alert demeanor. The feline then continues its crawl, passing by a stone wall and wooden planks, indicating the proximity to human habitation. Throughout the scene, the bobcat's cautious and curious nature is evident as it explores its surroundings in the town's outskirts.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2444
|
videos/HRA_part1/2444.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a round face, brown hair styled in a bun, and wearing a gray top is seen sitting alone, her eyes welling up with tears that stream down her cheeks. She looks lost in thought, her gaze distant, as she holds a tissue in her right hand. Moments later, she wipes away her tears with the tissue, her emotions visible in her expressive face. Then, she is captured in a close-up, her eyes closed, a tear rolling down her cheek, her lips slightly parted, as she seems to be taking a deep breath. Lastly, she looks directly at the camera, her eyes filled with unshed tears, her cheeks flushed, conveying a sense of vulnerability and strength in her emotional state.]"
},
{
"from": "gpt",
"value": "Normal. The woman in the video wiping her tears is basically normal, but there is a slight lack of coordination in the movements."
}
] |
seed42_3185
|
videos/HRA_part0/3185.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 scene set within a dense boreal forest, a janitor, dressed in a brown jacket, khaki pants, and a gray cap, diligently wipes a transparent pane that seemingly divides the wilderness. Behind this glass, a majestic leopard prowls within its enclosure, observing the man with curiosity. The forest's lush greenery and tall coniferous trees envelop the surroundings, creating a vivid contrast against the man-made structure. The janitor, focused on his task, occasionally glances at the leopard, acknowledging the unusual juxtaposition of his cleaning duties amidst the wild environment.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's hands, face, and feet are distorted, as well as the leopard's head and legs."
}
] |
seed46_2483
|
videos/HRA_part2/2483.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spotted hyena, mid-jump, leaps across a grassy savanna landscape, its powerful hind legs fully extended beneath it, capturing the essence of its agility and strength. The hyena's spotted coat is vivid against the green vegetation, and its mouth is open, revealing sharp teeth, as it focuses on an unseen target ahead. The scene is set during the golden hour, with warm sunlight casting a glow over the hyena and the surrounding environment, highlighting the texture of the grass and the depth of the landscape.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1750
|
videos/HRA_part1/1750.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A small, energetic ferret clad in a miniature red cape sprints across the frame, set against the backdrop of an otherworldly landscape featuring two active volcanoes, one spewing a spectacular eruption of lava and ash into the twilight sky. The ferret, displaying a sense of urgency and adventure, runs through this dramatic scene, its path illuminated by the orange glow from the volcanic activity, creating a surreal and captivating juxtaposition of elements.]"
},
{
"from": "gpt",
"value": "Normal. The ferret in the video runs basically normally, with slightly uncoordinated movements."
}
] |
seed42_2499
|
videos/HRA_part0/2499.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, known for its brown fur and flat tail, swims underwater in a clear, glassy lake during the daytime. It surfaces, revealing its full body, including the distinctive markings on its face and body. The beaver then proceeds to swim along the bottom of the riverbed, showcasing its webbed hind feet propelling it forward. Throughout the video, the beaver remains submerged, occasionally coming up for air, with the tranquil water and lush green vegetation along the riverbank providing a serene backdrop for this aquatic mammal's natural behavior.]"
},
{
"from": "gpt",
"value": "Normal. The beaver's swimming in the video is basically normal, but there is slight uncoordination in the movements."
}
] |
seed42_3208
|
videos/HRA_part0/3208.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A cheerful male chef, wearing a traditional white chef's uniform with a red neckerchief and a brown apron, stands in a modern kitchen. He holds a large, open recipe book in his hands and writes with a silver pen, his face expressing deep concentration. The kitchen is filled with stainless steel appliances and shelves stocked with various cooking ingredients, creating a professional culinary atmosphere. The chef's sleeves are rolled up, revealing a watch on his wrist, and he occasionally glances up from the book, likely checking the progress of dishes being prepared in the bustling kitchen environment.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_233
|
videos/HRA_part1/233.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged farmer, donning a plaid shirt, denim overalls, and a worn baseball cap, stands in a modern kitchen. He methodically unloads a sleek, stainless steel dishwasher, handling each plate and utensil with unexpected gentleness. The contrast between his calloused hands and the shiny, clean dishes highlights the unusual domestic task for someone more accustomed to farm chores. The kitchen is spacious and well-lit, featuring granite countertops and contemporary appliances, offering a glimpse into the farmer's home life beyond the fields.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed46_2662
|
videos/HRA_part2/2662.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A janitor, wearing a yellow vest over a dark jacket and shirt, pushes a green cart filled with cleaning supplies across a wide, empty corridor. A small gerbil, held gently in his right hand, sits atop a red mop head, seemingly unfazed by its unusual perch. The janitor walks with purpose, his left hand resting on the cart's handle, while the gerbil remains calmly perched on the mop, offering a peculiar yet endearing contrast to the mundane task of cleaning.]"
},
{
"from": "gpt",
"value": "Bad. The facial features and hands of the cleaner, the hamster, and the mop head in the video have generation issues."
}
] |
seed44_2226
|
videos/HRA_part1/2226.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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, wearing a navy uniform with a badge and a peaked cap, kneels in a park surrounded by green grass and trees, gently caressing a small brown hare with soft, comforting strokes. The officer's compassionate expression and careful handling of the hare, which sits calmly in the palm of his hand, convey a sense of tenderness and care. The peaceful setting, with the lush vegetation and clear sky, adds to the tranquil atmosphere of the scene.]"
},
{
"from": "gpt",
"value": "Bad. The police officer's hand and the brown rabbit in the video were generated abnormally, with the brown rabbit's ears distorted and deformed in the middle frames."
}
] |
seed44_2778
|
videos/HRA_part1/2778.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A police officer, clad in a khaki uniform with a badge and a hat, walks alongside a large, majestic rhinoceros. Both traverse a rugged terrain under a bright, sunny sky, creating an unusual yet compelling juxtaposition of authority and wildlife. The officer, equipped with a walkie-talkie on his belt, maintains a calm demeanor, while the rhinoceros, sporting a single horn and thick, wrinkled skin, ambles beside him. The scene unfolds in a spacious, natural environment, far from the urban settings typically associated with law enforcement.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2294
|
videos/HRA_part0/2294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a futuristic space art gallery, illuminated by vibrant neon lights, a magnificent Bengal tiger, detailed with its distinctive orange fur and black stripes, appears to run gracefully through the aisles, its movement captured in stunning detail. The gallery walls are adorned with abstract art pieces, creating a surreal contrast to the powerful, lifelike depiction of the tiger in motion. The tiger's dynamic pose, mid-stride, conveys a sense of freedom and strength within the confined yet imaginative space of the art gallery.]"
},
{
"from": "gpt",
"value": "Bad. The tiger's legs show deformities."
}
] |
seed46_1859
|
videos/HRA_part2/1859.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 uniformed police officer kneels on a grassy park area, attentively watching a squirrel. The squirrel, emboldened, leaps from the ground onto the officer's outstretched arm, seeking a nut held in the officer's other hand. The cop wears a standard police uniform, including a navy blue shirt, black tactical pants, and a badge, while the greenery and trees in the background set a peaceful outdoor scene. The squirrel's acrobatic leap and the officer's gentle interaction create a heartwarming moment in this unexpected encounter.]"
},
{
"from": "gpt",
"value": "Normal. The squirrel's movements in the video are not smooth."
}
] |
seed44_1322
|
videos/HRA_part1/1322.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a neatly trimmed beard, wearing a dark blue chef's jacket, white chef's pants, and a brown apron, is kneeling in a lush, green garden. He is digging with a small, silver shovel, uncovering fresh vegetables and herbs. The chef's focused expression conveys his passion for sourcing ingredients directly from nature, while the vibrant greenery and earthy tones of the soil create a rich, natural backdrop for this culinary endeavor.]"
},
{
"from": "gpt",
"value": "Bad. The man's hand and the shovel in the video have generation issues; the hand distorts and twists in the middle frames, and the shovel suddenly disappears."
}
] |
seed42_2507
|
videos/HRA_part0/2507.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A majestic swordfish, distinguished by its elongated bill resembling a sword, swims gracefully through the clear blue waters of the ocean. Its body, a sleek silver hue with a dark blue back, glides effortlessly as it navigates the aquatic environment. Sunlight filters through the water, casting shimmering highlights on the fish's streamlined form. The surrounding marine life, including schools of smaller fish scattering in its presence, underscores the swordfish's dominance in its habitat. Against the vast, open sea, the swordfish embodies power and agility, its unique appearance and behavior captivating the viewer in this underwater scene.]"
},
{
"from": "gpt",
"value": "Normal. The swordfish's face and fins generation in the video have issues."
}
] |
seed46_2086
|
videos/HRA_part2/2086.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 eccentric engineer, clad in a green jumpsuit and safety helmet, finds himself in an unexpected scenario amidst the industrial backdrop of a power plant. Surrounded by towering turbines and complex machinery, he encounters a curious lizard, its vibrant scales contrasting starkly with the metallic environment. Inspired by this unusual meeting, the engineer begins to dance, his movements fluid and joyful, as if the rhythms of the machinery have become his own. The lizard watches, almost as if entranced, as the engineer twirls and leaps, creating a surreal scene where the boundaries between human, nature, and industry blur harmoniously.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed44_2992
|
videos/HRA_part1/2992.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A woman in a khaki safari outfit walks alongside a kangaroo in an Australian outback setting, both appearing relaxed and accustomed to each other's company. The kangaroo, with its distinctive marsupial pouch, hops gently beside her, while the woman, wearing a wide-brimmed hat and sunglasses, carries a walking stick and a backpack. They traverse a landscape dotted with eucalyptus trees and scrub, under a clear blue sky. The woman occasionally looks down at the kangaroo with a smile, highlighting the unusual yet harmonious companionship between human and wildlife in the vast, open wilderness.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed42_2491
|
videos/HRA_part0/2491.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A middle-aged male chef, wearing a traditional white chef's uniform with a tall hat, stands in a modern, well-lit kitchen. He is staring intently at a plate of food he has just prepared, which features a vibrant, colorful dish garnished with fresh herbs. The kitchen is spotless, with stainless steel appliances and countertops, and the chef's focus on the plate highlights his dedication to culinary perfection.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_2289
|
videos/HRA_part2/2289.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 farmer, donning a straw hat, a plaid shirt, and denim overalls, is shown exerting effort as he pulls on a rope tied to a stubborn old tractor stuck in a muddy farm field. The farmer's weathered hands grip the rope tightly, his face contorted with determination, while the lush greenery and distant rolling hills provide a picturesque rural setting. The scene highlights the farmer's resilience and hard work against the backdrop of nature's beauty.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed46_2229
|
videos/HRA_part2/2229.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 majestic brown horse gallops gracefully across the foreground, its muscular form silhouetted against a backdrop of sprawling factories with billowing smokestacks. Amidst this industrial landscape, a group of diverse individuals dressed in vibrant, eclectic clothing forms a stark contrast as they engage in expressive dance moves, their joyous expressions and dynamic movements standing out against the grey, mechanical setting. This unlikely fusion of nature, industry, and human spirit creates a compelling narrative of resilience and vitality.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are uncoordinated, and the horse's movements are not smooth."
}
] |
seed46_1026
|
videos/HRA_part2/1026.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beige jacket, black t-shirt, and khaki pants, stands thoughtfully at a hot springs site, contemplating a unique shot. Suddenly, a rhinoceros emerges from the mist, leaping gracefully over a small pond within the springs. The director watches intently, camera in hand, ready to capture the extraordinary moment as the sun sets behind, casting a golden hue over the scene. The rhinoceros, now the central figure, jumps with surprising agility amidst the steamy waters, creating an unforgettable juxtaposition of nature and wildlife against the backdrop of the director's vision.]"
},
{
"from": "gpt",
"value": "Normal. The rhino's movements in the video are not smooth."
}
] |
seed44_2310
|
videos/HRA_part1/2310.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature man, possibly a writer, wearing a brown jacket, blue shirt, and khaki pants, stands pensively on a rocky cliff overlooking a vast, stormy sea. He wipes his face with his right hand, perhaps reflecting a moment of emotional intensity or physical exertion, as he contemplates the dramatic landscape before him. The rugged terrain and turbulent waters provide a striking contrast to his thoughtful demeanor, emphasizing the solitude and grandeur of his surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_1908
|
videos/HRA_part0/1908.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek black panther crawls across a dry, cracked earth surface under a dense jungle canopy, its muscles rippling beneath glossy fur. The panther's piercing yellow eyes remain fixed on a distant target, conveying intense focus and determination. It moves slowly and deliberately, each paw carefully placed to ensure silent progression, embodying the essence of stealth and power in the heart of the wild.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2676
|
videos/HRA_part1/2676.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 dapper musician, clad in a black suit and red tie, strolls down a gravel path in the midst of a lush forest, accompanied by a friendly moose. The pair walk side by side, the musician holding his violin case, while the moose ambles along, its large antlers brushing against the tree branches. Sunlight filters through the dense canopy overhead, casting dappled shadows on the path as the duo continues their peaceful journey together.]"
},
{
"from": "gpt",
"value": "Bad. The moose's head, the musician's head, and the hands and feet in the video have generation issues."
}
] |
seed42_1760
|
videos/HRA_part0/1760.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the 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 art gallery, illuminated by soft purple lights and adorned with cosmic artwork, a young, bald writer wearing a black turtleneck and jeans sits pensively at a sleek, metallic desk. He wipes away a smudge on the pristine, reflective surface, revealing a holographic interface beneath. Around him, floating canvases display vibrant, otherworldly landscapes, while the artist himself seems lost in thought, perhaps contemplating his next masterpiece among the stars.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed44_1262
|
videos/HRA_part1/1262.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a vividly lush subtropical wet forest, an enthusiastic teacher, wearing a green shirt and khaki shorts, energetically dances among tall trees, their leaves forming a dense canopy overhead. The educator gracefully leaps and twirls, engaging with the natural surroundings, while a curious hare watches from the undergrowth, its ears perked up in interest. Sunlight filters through the foliage, casting dappled shadows on the forest floor, enhancing the magical atmosphere as the teacher continues to dance, celebrating the beauty of the environment with joyful movements.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements are not smooth."
}
] |
seed44_2657
|
videos/HRA_part1/2657.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 with a muscular build, wearing a blue shirt and dark pants, carefully hangs pictures on a living room wall. He uses a level tool to ensure perfect alignment, focusing intently on his task. Moments later, he steps back to admire the arrangement of frames, which include a variety of sizes and styles, creating a visually appealing gallery wall. The room is brightly lit, showcasing the art pieces against a neutral backdrop, with the man's satisfied expression indicating his pride in the finished display.]"
},
{
"from": "gpt",
"value": "Bad. No tool used to check the level, no satisfied expression."
}
] |
seed46_2721
|
videos/HRA_part2/2721.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A firefighter, clad in full gear and a yellow firefighting jacket, gently wipes soot off a small, brown hedgehog that's been rescued from a fire. The hedgehog, nestled in the firefighter's protective glove, looks up with curious eyes as it's being cleaned. The scene takes place against the backdrop of a fire-damaged building, with smoke still lingering in the air, emphasizing the tender moment between the rescuer and the rescued animal.]"
},
{
"from": "gpt",
"value": "Normal. The firefighter's movements in the video are basically normal, with slight awkwardness."
}
] |
seed44_117
|
videos/HRA_part1/117.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 lark soars gracefully across a vast, cloud-dappled sky, its brown, speckled wings outstretched against a backdrop of vibrant blue. It dives down toward a sunlit, rolling meadow filled with lush grasses and wildflowers, then ascends again, singing its melodious song. Perched atop a swaying stalk of golden wheat, the bird's chestnut head tilts curiously, its bright eyes alert and alive with the spirit of dawn. Against the horizon, the silhouette of distant hills cradles the scene, completing the picturesque vision of nature's tranquility.]"
},
{
"from": "gpt",
"value": "Bad. The flying motion is not continuous, there are sudden changes, and the wings detach from the body."
}
] |
seed42_3038
|
videos/HRA_part0/3038.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, high-tech laboratory filled with complex machinery and computer screens displaying intricate data, a lone scientist in a white lab coat meticulously examines a vial containing a mysterious, shimmering liquid, believed to be a sample of dark matter. Meanwhile, in a contrasting scene, a majestic gray wolf, its fur glistening under the moonlight, leaps gracefully from a rock into a serene, moonlit lake, creating ripples that spread across the water's surface. The juxtaposition of these two scenes highlights the intriguing connection between the enigmatic world of dark matter research and the primal, untamed beauty of nature.]"
},
{
"from": "gpt",
"value": "Bad. The gray wolf generation in the video has issues."
}
] |
seed42_3022
|
videos/HRA_part0/3022.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A young student, wearing swimming trunks and a cap, playfully interacts with a live rabbit at a backyard pool party. Surrounded by friends, he gently holds the rabbit, which remains calm, near the water's edge. The scene transitions to show the student swimming in the pool, while the rabbit sits safely on a towel nearby, being petted by another person. Throughout, the atmosphere is one of carefree enjoyment, with the student and his friends laughing and splashing in the water, and the rabbit seeming content in its temporary role as a poolside companion.]"
},
{
"from": "gpt",
"value": "Bad. In the video, the student's action of petting the rabbit is not smooth."
}
] |
seed46_1269
|
videos/HRA_part2/1269.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 slowly crawls through a lush, green meadow dotted with small shrubs and trees, its round ears and alert eyes scanning the environment. It moves deliberately, showcasing its unique gait, as it navigates the vibrant grassland under a bright, sunny sky. The rodent's textured fur glistens in the sunlight, highlighting its wet, semi-aquatic nature, as it continues its unhurried crawl across the picturesque landscape.]"
},
{
"from": "gpt",
"value": "Normal. The capybara in the video walks basically normally, with slightly uncoordinated movements."
}
] |
seed46_2291
|
videos/HRA_part2/2291.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 woman, clad in an elaborate, flowing red dress, dances passionately under the moonlight in a desert landscape, with ancient ruins visible in the distance. A jackal, observing her from a safe distance, is intrigued by the captivating scene. The woman's movements are fluid and expressive, her dress swirling around her as she loses herself in the music that only she can hear. The jackal, sitting calmly, watches with fascination, its silhouette framed by the glow of the full moon, creating a mystical atmosphere in the vast, starlit desert.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1118
|
videos/HRA_part1/1118.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 writer, donning a brown jacket, beige slacks, and brown boots, takes a break from his typewriter to rake a large pile of colorful autumn leaves in his backyard, capturing the essence of seasonal change. He pauses, tool in hand, casting a thoughtful gaze at the vintage typewriter sitting on a wooden desk, which is placed under a large, leafy tree. The scene transitions to show him raking leaves with vigor, his attire unchanged, as the leaves form a vibrant heap, evoking a sense of tranquility and the beauty of fall. Finally, he pauses again, this time with a satisfied smile, surveying his neatly raked yard, the pile of leaves a testament to his labor, while the typewriter remains in the background, hinting at his dual passions for writing and nature.]"
},
{
"from": "gpt",
"value": "Bad. The person's fingers were not fully generated, the hoe in their hand underwent a mutation, and the face also became deformed."
}
] |
seed42_1549
|
videos/HRA_part0/1549.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 man named Jay, wearing a black t-shirt, blue jeans, and a silver wristwatch, stands against a plain gray backdrop. Initially, he looks intently at the camera, then breaks into a warm smile. Moments later, he playfully winks, showcasing his friendly demeanor. Finally, Jay is seen laughing wholeheartedly, his joyous spirit captured in high definition, all the while maintaining the simple outfit of a black top, blue denim, and a gleaming watch against the unadorned setting.]"
},
{
"from": "gpt",
"value": "Bad. The man in the video moves awkwardly and his actions are not coordinated."
}
] |
seed42_1893
|
videos/HRA_part0/1893.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a dimly lit, spacious room filled with smoke and vibrant lights, two individuals, a man in a dark green shirt and a woman in a black top, are dancing enthusiastically. Suddenly, they stop, looking startled as a beam of green light illuminates them. An alien creature, with large, expressive eyes and a smooth, gray skin tone, descends from above, capturing their attention. The extraterrestrial being, adorned with a metallic, futuristic outfit, lands gracefully beside them, prompting the humans to react with a mix of fear and curiosity. Despite the initial shock, the trio begins to move in unison, engaging in an otherworldly dance, creating a surreal and captivating scene.]"
},
{
"from": "gpt",
"value": "Bad. The woman's face, the man's face and hands, and the alien's hands and feet are generated abnormally, with the man's hand experiencing a mutation in the middle frame."
}
] |
seed42_251
|
videos/HRA_part0/251.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 spacesuit decorated with patches and emblems swims effortlessly in zero gravity within a space station habitat. The habitat, illuminated by soft, ambient lighting, features curved walls and large windows offering breathtaking views of the cosmos. A pet lizard, also weightless, floats nearby, its scales reflecting the light in iridescent patterns. The engineer gently propels themselves through the water-filled enclosure, designed to simulate Earth's aquatic environments, while the lizard seems to hover curiously beside them, both adapted to life in the microgravity of the space station.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
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 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 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": "Bad. The walking movements of the ibex in the video are uncoordinated."
}
] |
seed44_1066
|
videos/HRA_part1/1066.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A single pigeon, predominantly gray with distinctive black markings, is perched on a concrete ledge. It has a full, round body and is situated in an urban environment, as indicated by the presence of a streetlight and a partial view of a building's facade with windows. The bird faces right, its head turned slightly toward the viewer, revealing one bright, alert eye. Its beak is open, perhaps mid-call, and its feet grasp the edge of the ledge firmly. The scene is set against a backdrop of a clear, blue sky, offering a simple yet effective contrast to the textured details of the pigeon.]"
},
{
"from": "gpt",
"value": "Good. Basically no problem."
}
] |
seed42_3200
|
videos/HRA_part0/3200.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone jackal leaps through the air, its body stretched in mid-jump, against the backdrop of a desolate volcanic landscape. The creature, with its sandy fur and alert expression, bounds over rugged terrain as steam rises from vents in the ground. The jackal lands and pauses, ears pricked, silhouetted against the smoldering volcano that fills the horizon, its eyes reflecting the fiery glow. Moments later, it springs into action again, bounding away across the rocky, moon-like surface, leaving plumes of dust in its wake.]"
},
{
"from": "gpt",
"value": "Bad. The hyena's jumping action in the video is not smooth."
}
] |
seed44_2994
|
videos/HRA_part1/2994.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a captivating scene, two children, a boy and a girl, both dressed in khaki safari outfits, walk alongside a gentle rhinoceros in a lush, grassy savannah setting. The children, appearing fearless and joyful, interact closely with the rhino, which is adorned with natural vegetation, indicating its habitat. The trio moves harmoniously together, with the children occasionally touching the rhino, highlighting a unique bond between humans and wildlife. The scene is set against a backdrop of distant trees and clear skies, emphasizing the beauty and tranquility of their shared environment.]"
},
{
"from": "gpt",
"value": "Bad. The child's face, hands, arms, legs, and rhino head are distorted in the video."
}
] |
seed42_2847
|
videos/HRA_part0/2847.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising blend of elements, a vibrant scene unfolds where a skilled musician, clad in a red suit, passionately plays a saxophone, standing on a floating platform in the middle of a crystalline pool. Behind him, a majestic ibex watches from the edge of the water, its presence adding a touch of wilderness to the urban setting. Towering office buildings loom in the background, their glass facades reflecting the bright sky and the musician's captivating performance, creating a surreal juxtaposition of nature, music, and city life.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed46_2732
|
videos/HRA_part2/2732.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom filled with natural light, a cheerful teacher, wearing a blue shirt, gray pants, and brown shoes, energetically wipes the chalkboard clean using a green eraser, while an otter puppet sits on her shoulder, seemingly assisting her. The teacher's movements are lively and animated, conveying a sense of fun and engagement in the educational process. The otter puppet, with its playful demeanor, adds a whimsical touch to the scene, as it seems to mimic the teacher's actions, creating a captivating visual narrative.]"
},
{
"from": "gpt",
"value": "Bad. The character's face is distorted, hands are distorted, the object in hand is distorted, arms are distorted, and the sea otter puppet behind is also distorted."
}
] |
seed46_1663
|
videos/HRA_part2/1663.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, clad in full gear and a yellow safety vest, kneels beside an urban street drain, diligently unclogging it with a specialized tool. His focused gaze and steady hands reveal his determination. In another scene, he stands with legs apart, continuing the task with a long, metal drain snake, his yellow fire department jacket and sturdy black boots standing out against the gray cityscape. His efforts are highlighted by the contrast between his vibrant attire and the dull surroundings, emphasizing his commitment to public service beyond firefighting. Throughout, the firefighter's steadfast posture and unwavering concentration underscore his dedication to maintaining community safety, even in mundane tasks.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed46_2266
|
videos/HRA_part2/2266.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 medical facility, an engineer, wearing a gray shirt with a NASA logo, gently caresses a high-tech medical device, displaying tenderness and care. The room is illuminated by the soft glow of screens and equipment, highlighting the advanced technology surrounding him. Against the backdrop of sleek, metallic surfaces and complex machinery, the engineer's tender gesture toward the device, which resembles a combination of a robotic arm and diagnostic tool, conveys a sense of emotional connection and the importance of human touch even in a highly technical environment.]"
},
{
"from": "gpt",
"value": "Normal. The engineer's arms and fingers are missing in the video, and there are issues with the generation of the eyes."
}
] |
seed42_278
|
videos/HRA_part0/278.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 clear, close-up underwater shot, a tiny ghost shrimp, nearly transparent with faint grayish-blue hues, scuttles along the sandy bottom of a freshwater environment. Its delicate, see-through body reveals its intricate internal structure, while its antennae and legs move rapidly as it navigates its habitat. Surrounded by small stones and plant roots, the shrimp pauses momentarily before continuing its journey, showcasing its unique ability to blend into the aquatic surroundings.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_2965
|
videos/HRA_part0/2965.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 male writer, dressed in a black turtleneck sweater and khaki pants, walks through a vast grassland with rolling hills under a clear blue sky. He pauses to observe a herd of deer grazing nearby, the animals' presence adding to the tranquility of the landscape. The writer continues his journey, a pen and notebook visible in his pocket, suggesting inspiration drawn from nature. As he moves further into the grassland, the distant silhouette of mountains can be seen, enhancing the sense of adventure and exploration. Throughout the scene, the focus remains on the writer's contemplative walk among the deer, with the vibrant green grass and expansive sky creating a serene and inspiring atmosphere.]"
},
{
"from": "gpt",
"value": "Normal. The character's movements in the video are not smooth."
}
] |
seed44_2478
|
videos/HRA_part1/2478.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An attractive male actor, wearing a black t-shirt, showcases a ferret jumping from his right shoulder onto his left arm. Set against a dark grey background, the scene highlights the ferret's agility and the actor's engagement with the small animal. The actor's facial expression conveys amusement and surprise, emphasizing the playful interaction between man and pet. Throughout the sequence, the ferret performs several jumps, each time landing gracefully on different parts of the actor's body, while he remains fully engaged and attentive, his black t-shirt providing a stark contrast against the neutral backdrop.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed42_231
|
videos/HRA_part0/231.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 room illuminated by the soft glow of a Martian sunset, visible through a large window displaying the red planet's horizon, two young children sit cross-legged on a wooden floor. They gently caress a small, furry gerbil sitting on a colorful blanket, their faces reflecting expressions of pure delight and wonder, as they interact with the pet in the unique, alien environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_186
|
videos/HRA_part1/186.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 group of cheerful children, ranging from toddlers to preteens, are engaged in the task of cleaning windows on a bright, sunny day. They wear casual clothes, including t-shirts, shorts, and sneakers, and sport various hairstyles, from pigtails to afros. The kids use squeegees and rags to wipe down the glass, leaving streaks of water and soap behind. They work together, laughing and chatting, as they tackle the large window panes of a suburban home, with lush greenery visible through the transparent surfaces. The atmosphere is one of teamwork and fun, with the youngsters taking pride in their chores under the warm glow of the sun.]"
},
{
"from": "gpt",
"value": "Bad. The child's arms have become deformed and mutated. The face has become distorted and deformed."
}
] |
seed42_1784
|
videos/HRA_part0/1784.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A charismatic male musician, clad in a black leather jacket, a graphic tee, and dark jeans, walks his energetic, medium-sized brown dog in an urban park. The artist wears a baseball cap and sports a beard, presenting a relaxed and down-to-earth demeanor. The dog, on a leash, enthusiastically explores the grassy area, its tail wagging. In another scene, the musician, now with his acoustic guitar slung over his back, continues his leisurely stroll, his dog trotting alongside him. The pair strolls past a stone building, adding to the laid-back vibe of the day.]"
},
{
"from": "gpt",
"value": "Normal. The musician's walking movements in the video are not very smooth and continuous."
}
] |
seed46_2492
|
videos/HRA_part2/2492.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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: [On a futuristic space movie set, a dedicated nurse in a pristine white uniform tends to a unique patient—a green lizard-like alien with intricate facial features. She gently wipes the creature's face with a soft cloth, her compassionate expression conveying care and concern. The sterile environment is contrasted by the exotic presence of the alien, creating a captivating scene blending human kindness with otherworldly elements.]"
},
{
"from": "gpt",
"value": "Bad. The character's movements in the video are not smooth."
}
] |
seed42_158
|
videos/HRA_part0/158.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a cozy, well-lit room, two young children sit attentively at a wooden table, each engaged in the meticulous task of hemming pants. One child, a boy with short brown hair wearing a blue t-shirt and jeans, carefully measures the fabric with a silver ruler, ensuring precise folds. Beside him, a girl with long pigtails, dressed in a yellow dress, threads a needle with focused determination, her tongue slightly poking out in concentration. Both use matching white sewing machines placed on either side of the table, their small feet reaching down to operate the pedals. The atmosphere is one of diligent learning, with the children's expressions showing a mix of seriousness and occasional smiles, highlighting their engagement in this practical skill.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2463
|
videos/HRA_part0/2463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a weathered wooden fence post, its striking black-and-white plumage gleaming under the natural light. Against a backdrop of lush green foliage, the bird turns its head to gaze curiously at the camera, showcasing its glossy feathers and bright eyes. Moments later, it spreads its wings, revealing intricate patterns as it prepares to take flight, the detailed texture of the wood contrasting with its vivid plumage. Finally, the magpie takes off, flying gracefully against the backdrop of verdant trees, its movements fluid and captivating in high-definition detail.]"
},
{
"from": "gpt",
"value": "Normal. The magpie in the video was generated abnormally, with the head and wings twisting and deforming in the middle frames."
}
] |
seed42_1313
|
videos/HRA_part0/1313.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 quirky scene unfolds on a bustling Shanghai street, where a creative writer, dressed in a brown jacket and khaki pants, kneels on the pavement, engrossed in scribbling notes. Beside them, an unexpected giraffe, adorned with a red bow tie, also kneels, observing the writer with curiosity. The vibrant urban landscape, filled with pedestrians and vehicles, serves as a lively backdrop, contrasting the unusual duo's focused yet peculiar crawling position on the crowded sidewalk.]"
},
{
"from": "gpt",
"value": "Normal. The giraffe didn't tie a bow tie."
}
] |
seed42_1839
|
videos/HRA_part0/1839.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, prehistoric landscape under an orange sky, a group of Woolly Mammoths walk together in the distance, creating a sense of awe and grandeur. Meanwhile, in the foreground, a female caveman, dressed in furs and bearing a resemblance to a modern-day cashier, stands against a rocky outcropping, holding what appears to be ancient currency in her hand. She looks intently at the mammoths, which are walking away from her across the ancient terrain, conveying a narrative of survival and commerce in prehistoric times.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2924
|
videos/HRA_part0/2924.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the semantic consistency issues in this video, focusing on the alignment between the text and the visual content. Specifically, point out any discrepancies regarding the subject (e.g., person or animal), quantity, color, scene description, style, and other relevant aspects. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An actor, resembling a meerkat in his facial features and movements, walks through a temperate deciduous forest, wearing a casual outfit consisting of a brown jacket, gray shirt, and khaki pants. He moves through the lush greenery, surrounded by tall trees with leaves varying from deep green to shades of yellow and orange, indicative of the changing seasons. The forest floor is covered in a carpet of fallen leaves, creating a picturesque autumn scene. As he walks, the sunlight filters through the canopy, casting dappled light on the ground, highlighting the natural beauty of the environment.]"
},
{
"from": "gpt",
"value": "Good. No obvious issues."
}
] |
seed44_1072
|
videos/HRA_part1/1072.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 director, donning a casual gray shirt and black cap, is shown engaged in an unexpected task: unclogging a drain. In the first scene, he is kneeling on a hardwood floor, attentively examining a drain with a serious look on his face. Next, he is seen plunging the clogged drain with a red plunger, demonstrating his hands-on approach to problem-solving. Following this, the director is depicted using a drain snake to clear the blockage, his expression one of determination. Lastly, he inspects the drain once more, now clean, with a look of satisfaction, his casual attire contrasting with his professional role.]"
},
{
"from": "gpt",
"value": "Normal. The stick left the hand, and the movement was not continuous."
}
] |
seed44_3112
|
videos/HRA_part1/3112.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An industrious engineer, clad in a blue button-down shirt and khaki pants, kneels beside an indoor track designed for mice. The track, illuminated by overhead lights, features a small mouse energetically running within its confines. The engineer observes intently, notebook in hand, ready to record data from the experiment. Behind him, a lab coat hangs on a hook, and a shelf displays various scientific instruments and books, alluding to the academic setting. Throughout the scene, the mouse continues its steady pace on the track, under the watchful eye of the dedicated engineer.]"
},
{
"from": "gpt",
"value": "Bad. The character's face, hands, feet, mouse body, and head are distorted in the video."
}
] |
seed44_2470
|
videos/HRA_part1/2470.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 fantastical scene, a muscular firefighter in full gear, complete with a red helmet, yellow reflective stripes, and a breathing apparatus, sprints across the rugged terrain of Jupiter's Great Red Spot. The vast, swirling storm serves as a dramatic backdrop, its crimson hues contrasting starkly with the firefighter's outfit. The firefighter's intense gaze and determined stride convey a sense of urgency and purpose, even in this otherworldly environment. The unique landscape, characterized by swirling gas clouds and turbulent weather patterns, adds to the dramatic effect, making this an unforgettable depiction of bravery and athleticism in an extraterrestrial setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed42_2861
|
videos/HRA_part0/2861.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A professional-looking male chef, donning a white chef's jacket and black pants, stands in a bustling kitchen environment, pulling a large, fully loaded dish from a high-end, commercial-grade oven. The oven is integrated into a sleek, stainless steel kitchen setup. The chef exhibits a focused expression, displaying his expertise and confidence. The dish, brimming with an exquisite culinary creation, is positioned at the center of the frame, highlighting its appeal against the busy kitchen backdrop.]"
},
{
"from": "gpt",
"value": "Normal. The video shows the chef taking a dish out of the oven, the action is basically normal but slightly uncoordinated."
}
] |
seed42_2287
|
videos/HRA_part0/2287.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A rugged firefighter, complete with helmet and heavy-duty gear, takes a break from the norm as he meticulously vacuums a cozy living room, adorned with a plush sofa, rustic wooden coffee table, and vibrant houseplants. The scene opens with a close-up of the vacuum cleaner, a stark contrast to the typical firefighting tools, before panning to reveal the dedicated firefighter, hose in hand, methodically cleaning the carpet. The camera then captures the firefighter's gloved hands guiding the vacuum, followed by a shot of him standing upright, holding the vacuum hose, and looking content amidst a tidy room, where a tidy bookshelf and comfortable armchair complete the domestic setting.]"
},
{
"from": "gpt",
"value": "Good. Basically correct."
}
] |
seed44_1826
|
videos/HRA_part1/1826.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [In a surprising twist, a middle-aged janitor, clad in a yellow vest and holding a mop, finds himself alone in a vast desert landscape at sunset. Surrounded by towering sand dunes and rugged terrain, he spontaneously begins to dance, his movements expressing a mix of joy and freedom. The golden hour light casts long shadows, highlighting his figure against the stark beauty of the desert. As the scene progresses, the janitor's dance becomes more spirited, his face alight with pure happiness, embodying the unexpected delight of finding joy in solitude amidst the desolate wilderness.]"
},
{
"from": "gpt",
"value": "Bad. The cleaner's movements in the video are very unsmooth and uncoordinated."
}
] |
seed46_1025
|
videos/HRA_part2/1025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A lone seagull perches regally atop a wooden post on a deserted, windswept beach, its pristine white feathers ruffled by the salty breeze. The gull, with its sharp yellow beak and piercing eyes, surveys the vast expanse of sea and sky, seemingly contemplating the horizon. Suddenly, it spreads its wings, launching into flight, the camera capturing the intricate detail of its feathered anatomy as it glides effortlessly over the undulating waves. The seagull then returns to its perch, standing tall against the dramatic backdrop of an overcast sky, embodying the spirit of the coast.]"
},
{
"from": "gpt",
"value": "Bad. The animals in the video flap their wings unsmoothly and their movements are uncoordinated."
}
] |
seed44_2784
|
videos/HRA_part1/2784.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 fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A chef, donning a 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 person's head is distorted, the arms are twisted, the hands are deformed, the hippo's head is distorted, and the legs are twisted."
}
] |
seed44_1608
|
videos/HRA_part1/1608.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A mature, bespectacled teacher, wearing a gray blazer over a button-down shirt, walks down a dimly lit, empty hallway with lockers on either side. Suddenly, a small brown rat scurries across the floor in front of him, causing the teacher to pause and look down with a mix of surprise and curiosity. The rodent continues its journey undeterred, disappearing around a corner as the teacher resumes his walk, now with a slight smile and a shake of his head, as if amused by the unexpected encounter.]"
},
{
"from": "gpt",
"value": "Bad. The character in the video walks very unsmoothly, with uncoordinated movements; the mouse's movement is also uncoordinated, with middle frames suddenly disappearing."
}
] |
seed46_2109
|
videos/HRA_part2/2109.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A vibrant, young woman, dressed in a red tank top and denim shorts, runs barefoot across a lush, green field under a clear blue sky. She carries a mongoose in her hands, which playfully wraps its tail around her wrist. The woman's hair, tied in a high ponytail, bounces with each stride, and her face is filled with pure joy. The mongoose, alert and curious, looks around with its small, intelligent eyes, seemingly enjoying the exhilarating run alongside the woman. Their motion is fluid and free, embodying the spirit of adventure and the bond between human and nature.]"
},
{
"from": "gpt",
"value": "Bad. The woman's running in the video is very unsmooth, and her movements are uncoordinated."
}
] |
seed44_1605
|
videos/HRA_part1/1605.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 prehistoric landscape under an overcast sky, a colossal mammoth, covered in thick, shaggy fur, is seen crawling on its knees, struggling through deep snow. Its large tusks and body are caked with ice and snow, emphasizing its immense size and the harsh conditions it endures. The creature's eyes, filled with determination and resilience, are set against the barren, icy wilderness, capturing the essence of survival in a frozen world.]"
},
{
"from": "gpt",
"value": "Normal. The mammoth in the video walks basically normally, with only slightly uncoordinated movements."
}
] |
seed44_3025
|
videos/HRA_part1/3025.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the motion issues in this video, focusing on the continuity and smoothness of actions, as well as their coherence and adherence to the laws of physics. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [An artist, dressed in a gray turtleneck, paints a large canvas featuring a moose in outer space, depicted in vibrant colors and abstract style. The scene shows the artist wiping paint from their hands while gazing thoughtfully at the artwork, which portrays the moose as a diplomat in a cosmic setting, surrounded by stars and planets. The artist's attire, including black pants and shoes, contrasts with the colorful painting, emphasizing the creative process and the unique concept of a moose on a space diplomatic mission.]"
},
{
"from": "gpt",
"value": "Bad. The artist's movements while painting on the canvas in the video are not smooth."
}
] |
seed46_2714
|
videos/HRA_part2/2714.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 classroom aboard a space station, a compassionate teacher, dressed in a blue jumpsuit with patches and pins adorning her chest, gently caresses the head of a curious alien student. The student, with large, expressive eyes and a small, round body, sits attentively at a desk cluttered with advanced technology and educational tools. The room is filled with natural light from a large window showing a stunning view of Earth and the vast cosmos beyond, emphasizing the peaceful diplomatic mission of education among the stars.]"
},
{
"from": "gpt",
"value": "Normal. The person's hands and face are distorted in the video."
}
] |
seed42_1827
|
videos/HRA_part0/1827.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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, adorned in a stylish yellow dress, gracefully caresses the powdery sand of an idyllic beach resort as the turquoise sea gently laps at the shore. Her eyes closed, she savors the serene moment, feeling the warmth of the sand between her toes. The peaceful atmosphere is punctuated by the rhythmic sounds of the ocean, the soft rustle of palm fronds, and the distant calls of seagulls, all contributing to a scene of blissful tranquility. The vibrant colors of her attire contrast beautifully with the natural hues of the beach, creating a captivating visual harmony.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_1267
|
videos/HRA_part1/1267.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 beaver, clad in a brown fedora and matching suspenders over a striped shirt, tap dances on a wooden stage under a spotlight. Behind him, a red velvet curtain provides a dramatic backdrop. He executes a series of lively dance moves, including a tap routine, a spin, and a leap, all with a joyful expression on his face. Throughout the performance, he maintains his polished appearance, complete with a vest, watch chain, and spats, as he channels the spirit of a vaudeville entertainer.]"
},
{
"from": "gpt",
"value": "Bad. Beaver's paws are twisted, face is distorted, legs are twisted."
}
] |
seed46_3041
|
videos/HRA_part2/3041.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 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 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 insect-like creature in the video has a distorted body."
}
] |
seed46_1238
|
videos/HRA_part2/1238.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 close-up view of a European starling perched on a branch, its vibrant plumage shimmering with hues of green and purple under the sunlight. The bird's beady eye is fixed ahead, and its feathers appear ruffled, as if enjoying a gentle breeze. The starling's curved bill and round body are distinct against the blurred green foliage in the background, creating a contrast that highlights the bird's intricate details. The scene is set in a serene forest environment, where the starling seems unperturbed by the camera, offering a rare glimpse into its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed44_2299
|
videos/HRA_part1/2299.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 great egret, standing tall with folded wings, perches gracefully on one leg atop a weathered wooden post in the midst of a serene marsh landscape, surrounded by lush green vegetation and calm waters. Its pristine white feathers contrast beautifully against the natural backdrop, while its sharp yellow eyes scan the environment keenly. The scene is set during the golden hour, with the warm sunlight casting a soft glow over the bird and its habitat, highlighting the tranquility of the moment.]"
},
{
"from": "gpt",
"value": "Good. No obvious problems."
}
] |
seed46_1976
|
videos/HRA_part2/1976.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 sleek, spotted leopard leaps across a mossy log in a dense, lush forest, its powerful muscles rippling under golden fur flecked with black rosettes. Towering trees with emerald canopies surround the scene, dappled sunlight filtering through the leaves, casting an ethereal glow. The big cat lands gracefully on the forest floor, strewn with ferns and fallen leaves, before bounding away into the undergrowth, demonstrating the apex predator's agility and strength in its natural habitat.]"
},
{
"from": "gpt",
"value": "Good. Basically no issues."
}
] |
seed44_2463
|
videos/HRA_part1/2463.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality 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 magpie perches on a weathered wooden fence post, its striking black-and-white plumage gleaming under the natural light. Against a backdrop of lush green foliage, the bird turns its head to gaze curiously at the camera, showcasing its glossy feathers and bright eyes. Moments later, it spreads its wings, revealing intricate patterns as it prepares to take flight, the detailed texture of the wood contrasting with its vivid plumage. Finally, the magpie takes off, flying gracefully against the backdrop of verdant trees, its movements fluid and captivating in high-definition detail.]"
},
{
"from": "gpt",
"value": "Bad. The magpie in the video generated abnormally, with the head and wings twisting and deforming in the middle frames."
}
] |
seed46_294
|
videos/HRA_part2/294.mp4
|
[
{
"from": "human",
"value": "<video>\nSuppose you are an expert in judging and evaluating the quality of AI-generated videos, please watch the frames of a given video and see the text prompt for generating the video.\nThen identify the fidelity issues in this video, assessing the realism of the content, including people, animals, and other objects. Highlight any problems such as missing limbs, deformed hands or faces, or other unrealistic elements. Provide a rating evaluation: Good, Normal, or Bad, along with a concise explanation supporting your assessment.\nYour task is provided as follows: Text Prompt: [A passionate teacher, donning a red top and black leggings, executes a captivating zero-gravity dance in a spacious, well-lit room. She leaps and twirls effortlessly, mimicking the weightlessness of space, as if defying Earth's gravity. Seamlessly transitioning, she begins running in place, her movements fluid and energetic, demonstrating the illusion of floating while maintaining contact with the ground. Throughout, her expressive face conveys the exhilaration and freedom of movement in a zero-gravity environment.]"
},
{
"from": "gpt",
"value": "Bad. The teacher's facial features in the video are generated blurily, and the limbs are distorted. The teacher's limbs suddenly disappear or reappear in the middle frames."
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.