Datasets:

ShuoShuoShuo

/

PromptsLabels

like 0

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cyberpunk robot building stands in the ruins of Chernobyl.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A colorful portrait of philosopher Terence McKenna in a retrofuturistic setting.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait,people,fashion,art,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A sculpture of the sun sits atop a fountain, surrounded by water.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "art, landscape, water" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A woman wears a hood made of bats in an office.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "indoor, people, animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A man with auburn hair and freckles wears a purple tunic.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A giant ancient tablet stands in a futuristic metropolis.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, architecture" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A golden armor alien zombie horseman rides a crystal bone dragon in a blossoming meadow.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, landscape, art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A man with five heads sits on a chair in a bloody lake.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "NSFW" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Princess Peach poses in a tight push-up bra with a large bust.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "NSFW" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A demonic orcish punk rock biker poses for a professional photo, wearing a leather jacket.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait,fashion,people,vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A futuristic crystal food blender building stands on a grassy field.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, food, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A muscular barbarian with a full black beard holds a grog, adorned with tribal tattoos.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Lilith, mother of all monsters, stands as a disfigured Gorgon amidst raining ash.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A horse-drawn carriage approaches an obsidian cathedral in lava.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, landscape, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Queen Margherita of Italy and Sophia Loren enjoy a Pizza Margherita together.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,food,indoor,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A 3D goddess with ram skull and Japanese crow kitsune mask.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait, art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A dancing futuristic woman is surrounded by chrome leaves.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,fashion,plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A portrait of a sci-fi space fighter pilot in futuristic attire.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait, people, fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Elsa, corrupted by the fel from World of Warcraft, is eerily depicted.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young DND-playing boy stands with his three construction vehicle friends on a sunny street.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, vehicles, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful girl with pink hair wears heart-shaped sunglasses at the beach.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,fashion,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An anthropomorphic raccoon wearing a dress stands in a detailed environment.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, art, fashion, indoor, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A rugged, handsome ranger stands in full body leather attire with a hairy torso.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Shadow Taehyung and Min-Jun attend a graveyard party surrounded by ghosts.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A single surrealist object is on display as an exotic artifact.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "art, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A gigantic girl's head emerges amidst exotic vegetation, trees, and a massive mecha robot.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, people, plants, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A girl with wavy white long hair sits in her bedroom on a rainy night.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "indoor,people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A girl with messy red hair walks on a mountain overlooking a poor medieval town.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Matt Damon as a delirious American World War 2 sergeant writing a letter at night.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A huge dragon stands against a sunset background.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, landscape, art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Two frail, skinny old people sit next to a fireplace in an abandoned hospital room.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "indoor,people,portait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A medieval male guardian sculpture made of marble and fur.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "art, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Two large moons shine over a field of frozen yellow flowers.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A meteor shower illuminates a field of frozen yellow flowers under two giant moons.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cowboy rides a tiny green dinosaur.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young undead mermaid girl with vibrant red hair gazes out.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A neon armored anthropomorphic dog cyborg sits in clouds.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, art, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful anime high school girl with brown hair and green eyes stands in a detailed school background.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A girl with headphones stands in a forest clearing.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A sfam driver wears a glowing visor and sleek headphones.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,fashion,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [The flower queen goddess poses sensually in front of a futuristic Dubai cityscape.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "NSFW" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A futuristic Korean android with dark makeup, wet curly hair, and neon tears.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Winter mountain range with futuristic base above clouds.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A White Lion General stands heroically in the midst of a battlefield, holding a sabre.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, people, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A phoenix-themed Jean Grey wears a green suit amidst roaring flames.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A tall emo girl artist holds portraits and a persimmon on train.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,art,portrait,fashion,food,vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A lavish yacht party celebrates the Day of the Dead with vibrant decorations.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, vehicles, fashion, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cleric, Jenna Fischer, wears a flower tiara in a fantasy garden.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion,plants,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cute undead skeleton girl with red hair dresses as a knight.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait, fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A traveler wanders through mountains, gazing up at the clouds during sunset.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A fallen angel Ana De Armas portrait in a luxurious setting.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait, indoor, people, fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Lord Ganesha idol stands at ancient mystical gate in jungle.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, plants, art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A thin male teacher with long dark hair and silver attire.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A dark cyberpunk Hindu sadhu stands in a futuristic environment.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A Victorian lady stands in a futuristic city, surrounded by towering buildings.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,fashion,landscape,cityscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A junkyard filled with robots and robot parts in disarray.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A convoluted portrait of Numero magazine is editorially presented in a vibrant composition.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait,fashion,art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Morrigan Aensland, a charming succubus, casts magic in a strapless dress.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "NSFW" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Rock girl holds electric guitar, gazing at black fortress.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A portrait sculpture of Adam Sandler with a toothy smile is displayed on a pedestal.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait, people, art, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Pikachu is a playable character in Dead by Daylight game.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "No, NSFW \n\nSelected labels: animals, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cyberpunk neon crayfish with metallic components.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Hatsune Miku wears a comfy blouse, showcasing her personification with unique eyes.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait,fashion,people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A small blue slime observes a sitting black dragon inside a cave.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A 2044 space sport engineer adorned with wires, flowers, and a computer crown.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait, fashion, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A portrait of Vladimir Putin surrounded by a floral Horizon Zero Dawn machine and a robot crafted from marijuana.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait,people,plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A man is held upside down by a giant kraken in Amsterdam.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, animals, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Alien goddess Bella Hadid wears Iris van Herpen dress.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "fashion,people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young Tai warlord stands on a battlefield, his face marked with a red handprint.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Benjamin Netanyahu is an otherworldly iridescent alien overlord.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cottage by a lake with swans and a rowing boat.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, animals, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful young girl sits on a bench in an abandoned castle.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,landscape,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A curvy witch with long gray hair and Asian eyes stands.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Workers play dominoes under a tree in Salvador, Brazil.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, plants, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An anime girl in steel plate armor sits in a classroom.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "indoor,people,fashion,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A detailed painting of a Gundam mobile suit.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "vehicles, art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cat wears a black cape hoodie in a sideview portrait.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, fashion, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Teenager sits on a bench in an abandoned train station.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A deer stands amidst rocky Roman ruins with old signs.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A paperback book cover features a sunburst above a road.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, road, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A Slavic fire goddess stands in a wheat field at sunset.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, people, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Duraid Lahham, a character from Arknights, with symmetrical facial features and short neck.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A neon cat stands in a futuristic Japanese cityscape.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A family wearing 1860s era clothes stands in a park surrounded by alien plants.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,fashion,landscape,plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Daenerys Targaryen stands regally next to a majestic dragon in a fantastic dress.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,fashion,animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A strong barbarian woman wields a sword in the desert.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, landscape, weapons" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A bald warrior male dwarf with a long brown beard stands in a mountainous landscape.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, people, portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A futuristic woman wears a wire-mesh hat and necklace in a Renaissance-inspired portrait.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait,fashion,people,art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A small sailboat navigates through a fire tornado in the open ocean.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A dwarf warrior with a long white hair and fur cape holds beer.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion,food" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A massive fantasy Tree of Life stands in a serene lake.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A wombat Jedi stands ready for battle with its lightsaber.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cyborg vampire with gunmetal grey skin and medical anatomy is depicted in three views.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A person travels through multiple astral planes.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A lake reflects massive oval mirrors amidst antlers and forest.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A white knight rides a horse in front of a castle.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "animals, landscape, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A giant alien tree stands tall in a mystical fantasy landscape.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A computer workstation with multiple monitors and electronics occupies a small studio apartment room.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A single tree stands by a golden river in a cave.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A male android, resembling Liam Hemsworth, poses like a statue.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people, portrait" } ]