Datasets:

ShuoShuoShuo

/

PromptsLabels

like 0

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Franz Schubert, a happy vampire, shows his fangs.] \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 smiling Asian girl with blonde hair wears a bohemian outfit.] \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: [Mother Earth and Alien Technology face off in a skully 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,art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A crying android woman stands in a futuristic Blade Runner-inspired 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 young Lagos urban boy works on his computer in his modern bedroom artstation.] \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 Phyrexian dreadnought-Borg Queen hybrid is possessed by machine spirits.] \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: [Will Smith wears orange paladin armor in a closeup.] \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 smiling happy mask salesman is shown with his eyes closed in a cinematic 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, indoor" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A delicate wolf sculpture made of ornate lollypops is on display.] \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, food, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A woman wears a triangular headwrap in an ornate 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, art" } ]

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Mr. Bean and Peewee Herman engage in an intense wrestling match.] \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 cat silhouette with pulsar emissions on black cotton.] \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, animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A foxy wizard druid holds a staff with an amethyst gemstone.] \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, people, portrait, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An infinite labyrinthine corridor stretches into brutalist concrete architecture.] \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" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A futuristic sneaker with neon illuminated rubber soles and soft orange laces sits on a grey 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": "fashion, indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A 26th century woman with a detailed 26th century hairstyle.] \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 walking wood and metal house with two mechanical legs and one big eye stands amidst pine trees.] \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 man wears a cowl with a chained old book.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "people,portrait,fashion,indoor" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A goddess is surrounded by jellyfish phoenix and giant 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": "people, plants, animals" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful long hairstyle adorned with flowers and beads.] \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,plants" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A beautiful anime catboy with fennec ears and cream-colored hair wears a white sweater.] \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, animals, fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An old man's face emerges from a pizza margherita head.] \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": "food, people, portrait" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Chris Farley hosts SNL amidst a bloody, apocalyptic chaos.] \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: [Scientists work on a giant, gory Mickey Mouse head.] \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 battle-damaged Norse sun god wears a golden tentacle 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: [A black cat holds a teacup in front of a sofa.] \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 cute little boy is sleeping in a beautiful green forest at night.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "landscape, people, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A giant red knight with a beautiful girl on his shoulder battles monstrous creatures.] \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 male robotic silver dragon with a visor screen 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": "animals, art, people" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Jesse Faden stands in a solar temple surrounded by glowing birds.] \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,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Two performers, one with short dreads hair cut, are crowd surfing at a concert.] \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 handsome man with long black curly hair and tan skin wears a cowboy 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,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A majestic alien landscape features giant columns of volcanic rocks.] \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 beautiful, realistic portrait of Emma Watson in a goofy smile.] \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 portrait of a man with a wire mesh skull.] \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 male goose sorcerer wears bright armor with angel 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,art,fashion,portrait,animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A hiphop solarpunk crew enjoys summertime chill with a corgi.] \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, fashion" } ]

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A medieval hooded figure with an owl's face stands alone.] \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, animals" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A decaying undead space marine clad in intricate ornate cybernetic 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,portrait,fashion" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An Asian girl is playing in a river.] \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, river" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A young couple enjoys spaghetti at a drive-in 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": "food, people, vehicles" } ]

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A cyborg woman kisses a robot, their faces intertwined in affection.] \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 skeleton wanders through a dungeon with a torch.] \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 man in white stands watchfully near an old Jeddah alley's magical portal.] \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 medieval town stands by a river in a swamp.] \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 funky gothic girl is depicted in a full-body portrait with a detailed 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": "people,portrait,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A female astronaut with medium blonde hair poses in a library.] \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 man in a yellow hazmat suit faces a massive Cthulhu demon.] \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 portrait of a Japanese Yokai animal, illustrated in stunning detail.] \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, portrait, people" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A girl in a torn dress wields a sledgehammer to fight teddy bears on the 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": "NSFW" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A fuming mushroom lady champion stands in an action pose on the forest 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": "people, plants, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A girl in school uniform with horns and a peace sign.] \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 elderly Japanese woman wears a suit and 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,indoor" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [The Terminator witnesses the Battle of Little Bighorn.] \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 woman with punk outfit sits on a skyscraper rooftop.] \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: [Humanoid plant figures gather for a mystical seance in a bioluminescent 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,plants,landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Petro Poroshenko holds a knife in his 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": "NSFW" } ]

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

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

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Space vikings push ornate swan boat through space galaxies.] \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, vehicles" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Dogs with three eyes howl at alien moons from a cliff.] \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: [The portrait of a stunning black anime goddess crafted from rainbow crystals.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A muscular green Pepe frog jumps towards the starry sky.] \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 grid of cube-shaped eyes with square pupils and irises, featuring lashes.] \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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A vibrant tropical underwater forest jungle flourishes with exotic flora.] \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: [Lightning strikes a pirate vessel sailing through crashing ocean waves.] \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, vehicles" } ]

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

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

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