Datasets:

ShuoShuoShuo

/

PromptsLabels

like 0

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A woman sits in a chair by a window with mountains.] \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,landscape,people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A caretta caretta wears an armour of jewels and giant golden beetles in ocean coral reef.] \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, landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young gothic girl stands in front of a grand cathedral 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": "people,portrait,landscape,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A hillside desert pavilion in Palm Springs with a glowing pool.] \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, pool, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful black woman wears a cyber necklace with a giant spider.] \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, animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [The head of a handsome man is partially composed of vibrant rainbows.] \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 cute giantess stands in a miniature city wearing school uniform.] \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: [A stunning female South Korean chef wears a hanbok apron, holding a kitchen knife.] \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,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A dwarf man rides on a futuristic robot in a cyberpunk sci-fi fantasy 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": "people, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Emily Ratajkowski poses in pin-up style with long hair.] \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 trendsetter wears a dark brown batik hoodie, symbolizing fashion of the year.] \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 sleeping dinosaur lays on a bed.] \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: [Sonic Hedgehog surfs through cyberspace in a fractal form.] \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 little fat sweet girl is kissing a huge colorful cute fish.] \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 futuristic portrait illustration of an atompunk space pirate legendary warrior.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A close-up portrait of Rainbow Brite, a cute doll with vibrant colors.] \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: [A dozen glowing UFOs appear in the grey sky in 1990.] \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 female drow elf hunter holds a hand crossbow.] \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,weapons" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Brandi Love stands confidently in a business suit with grey hair and red tie.] \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 warrior lifts his large sword as it's struck by lightning in a stormy fog.] \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 futuristic city in hell featuring alien eldritch demonic architecture and machines.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A giant mechanical kinetic sculpture made of various materials.] \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: [Mindy Kaling, an attractive plus-sized woman, wears a vibrant Sari in a full-body 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": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A nosferatu vampire stands in a ruined castle wearing a coat.] \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,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Natalie Portman as a gravure model wears a Mayan bomber jacket in Majora's 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,fashion,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A girl with pink hair camps in a straw hat.] \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: [A female dark sorceress stands beside a tiger, surrounded by roses and diamonds.] \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,plants,animals,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A knight wears a suit of armor made of water, standing in a Norway fjord.] \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: [Johnny Depp's Captain Jack Sparrow appears in Rick and Morty.] \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 demonic goblin witch biker babe poses in a studded 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": "people,fashion,portrait,vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful young woman with long blonde hair enjoys a serene 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": "people, portrait, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young, athletic male with Mexican facial features and alien DNA stands outdoors.] \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 giant abstract sculpture depicts the birth of the universe.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Two happy penguins sit around a campfire near mountains.] \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 young woman sits alone in her studio apartment, gazing out at a futuristic Tokyo 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": "indoor,people,portrait,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful symmetric Medusa wears ornate cyberpunk robes.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Eldrad, a 1980s sci-fi pilot, stands in full length 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": "people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young woman with blue and blonde hair sits on a bench wearing a flower skirt.] \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 young woman with dark ninja clothes is centered in a symmetrical 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,people,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful woman emerges from the water wearing a cheongsam 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,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Techno mystic princess intergalactica wears labradorite armor.] \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: [A big crow with red eyes stands in front of a full moon, surrounded by red roses.] \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, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A matryoshka wearing neon colored suits sits in an airplane, looking exhausted.] \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,vehicles,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cyberpunk praying mantis mech poses for a futuristic 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,art,animals,vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Blonde Victoria Justice dressed as Bat Girl in a fantasy western 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": "people,fashion,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Geometric colorful sculpture of Grand Canyon on a white 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": "art, landscape, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Cassandra Cain smiling in a modern white Victoria's Secret bra.] \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,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A Roman bust of Mark Zuckerberg lies at the ocean floor.] \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, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: ['A solarpunk city landscape with colorful trees and skyscrapers.'] \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 giant kaiju-sized pond dragon, half fish and half salamander, inhabits a serene koi pond.] \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, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A humanoid stands in a junkyard with glowing screens.] \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 purple-haired girl in a black dress and headdress adorned with gems.] \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 borzoi dog possessed by an evil spirit floats 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": "animals, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A red princess stands with two knights on a green horizon.] \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: [This is a portrait of Judge Dredd from D&D RPG.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A massive lightning strike hits a cluttered bed in a pink bedroom.] \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 semiork skeleton stands in a large castle with a pebble.] \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 half-elf ranger travels across the great plains of Alexandria.] \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, animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A fiery phoenix woman rises from flames, spreading her wings.] \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 woman levitates in a foggy 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": "people, landscape, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A man sits in space wearing a golden-tipped black robe.] \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: [Alex Jones disguised as a frog.] \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, animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Sephiroth stands in a detailed, intricate 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,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A blond girl pulls a box from a shelf in a sci-fi school.] \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 Yogsothoth emerges from a twisted nebula fog with evil tentacles and dead eyeballs.] \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, art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young necromancer woman with long white hair and spiky elf ears wears red clothes.] \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: [A large, vibrantly colored exotic fish swims in a river surrounded by bubbles.] \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 beautiful young Mulan poses in a traditional dress surrounded by cherry blossoms.] \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 bearish gentleman receives medical treatment from a cowboy snake doctor and pinup nurse.] \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,animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Armored rabbits gather with giant swords on a plain.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A psychedelic triangular skeleton wears a long black crown in a shapes 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": "art, logo" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A glass egg contains a baby animal surrounded by wires and liquids.] \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 gorgeous Japan woman warrior with white hair stands in a futuristic city 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,fashion,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A woman composed of wires poses with a disdainful expression.] \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 girl and a boy stand near alien plants with their pet.] \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, animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful teen Assamese girl wears a traditional Bihu 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,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful English Renaissance woman poses beside a river 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": "people, portrait, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A robot dragoness stands elegantly on 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": "animals, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [The last enemy, Death, stands amidst a sci-fi fantasy realm.] \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 machine from Horizon Zero Dawn is decorated with twigs and 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": "plants, vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Family stands in front of a crashed spaceship on an alien planet.] \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,vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A baseball field surrounded by ancient monoliths with glowing runes.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A woman, Julia Fox, wears purple sci-fi armor in a close-up 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": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A punk woman with a mohawk stands proudly amidst splashes of neon clouds and rain.] \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,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: ['Elven bride stands with vivid flower crown and intricate veins.'] \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,plants,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A regal brown-skinned queen with long dark curly hair sits stoically.] \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: [In a futuristic robot repair workshop, people fix a robotic humanoid on a marble surface.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A US soldier poses majestically in a helicopter during Vietnam War.] \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,vehicles" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A crowd observes a holographic futuristic city in a museum.] \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,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A little girl with short black hair and a long braid wears a pink 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": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An alien checks her email submerged in translucent goo.] \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 hooded, partially cybernetic entity wields cosmic weaponry in an epic space scene.] \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 girl with symmetrical facial features drives a Ferrari on her simracing simulator.] \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,vehicles,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Walter White, dressed as Gordan Freeman, holds a gravity gun in Half Life Movie.] \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 snow gryphon stands on a winter mountainside 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": "animals, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A futuristic cityscape with Pokémon, spacecraft, and game centers amidst a vast universe.] \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: [AOC reimagined as Harley Quinn from Suicide Squad.] \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 sculpture with eyestalks and orbs.] \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, sculpture" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A thief princess stands in a Brawl Stars movie poster.] \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 female knight with black bob hair and ornamental armor has splattered blood on her face.] \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" } ]