Datasets:

ShuoShuoShuo

/

PromptsLabels

like 0

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Zoe Kravitz poses as a Gothic Vampire Queen.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 fractal Torii gate made of liquid metal stands in a minimal Japanese temple.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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,landscape" } ]

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

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

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

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

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A monastery church hidden within an underground sewerage network filled with green glowing slime.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A female cyber police officer stands on a futuristic Tokyo 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,landscape,fashion" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Soldiers engage in fierce combat within World War I trenches.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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, people, landscape, vehicles" } ]

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

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

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

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

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

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

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A teenage boy sits peacefully in a misty 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,portrait,landscape,plants" } ]

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An old druid prepares a potion surrounded by fungal enchanters, murlocs, and infernal 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, plants, animals" } ]

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

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A sprawling underwater city teems with seahorses.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [Cyberpunk wildlife engage in fierce battles on the sun-kissed African plains.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [Girls in swimsuits relax on a tropical beach with 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": "people,landscape,fashion" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Rick and Morty fused with Lovecraftian horror, wearing a Vader helmet and Predator tentacles.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 berber tiefling woman with red skin and devil horns.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 futuristic cyberpunk coder man with advanced headset.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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,fashion" } ]

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

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Eldrad, a 1940s sci-fi pilot, stands in a full-length portrait.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, otherwise return selected labels from the second task. OOutput only the selected labels, without any additional text or explanation.\nSelected labels:" }, { "from": "gpt", "value": "portrait, people" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A wizard sits at his computer in a cluttered lan party 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 cyber girl wears a bandana mask in a neon 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,fashion,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A handsome black detective holds a blaster pistol near a dark wood bar in a night futuristic city.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 \n\n(Note: The image contains a weapon, but in a fictional and futuristic context, so it's not considered harmful content.)" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A goddess of fractal coral reefs stands within an elaborate cyberpunk mycelium cathedral.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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,art,plants,landscape" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A Ford-designed off-road SUV drives through a Madagascar landscape with towering baobab 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, vehicles, plants" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [An angry eagle berserker wearing fur armor and claws is in an attack pose.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [A futuristic robot holds a vintage game controller, with a classic game on screen.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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,portrait,vehicles" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A Martian woman with flowing hair sits on a Martian 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, portrait, landscape" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A lighthouse inside a glass jar, surrounded by an owl and pink bonsai tree, is buried in sand.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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, plants, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A demon borzoi floats above the city, gazing downward.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 sewer punk lady student with freckles and a beanie cap stands in front of a graffiti wall.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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,art" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A male rogue with gray-green eyes and blonde hair holds a sword.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 futuristic car speeds through a rainy, neon-lit cityscape 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, vehicles" } ]

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A dark-robed, symmetrical-faced magic cult psychic woman with a third eye gazes 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" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A portrait set against a stormy sky with a black hole.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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,landscape" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [The Templar from Path of Exile looks directly at you.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 psychedelic animal composed of orchid blooms rests on a pond of waterlilies.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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, animals, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A hunter from Bloodborne sits 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": "people,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A creepy ominous religious figure wears a crown in this haunting 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" } ]

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

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

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A man with long hair is portrayed in a detailed, realistic face rendering.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [Donald Trump, transformed into the Hulk, stands amidst a Gears of War battlefield.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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, people, landscape, vehicles" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A futuristic English woman warrior with pink sequin 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,fashion,portrait" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Cyborg torso plugged into a quantum computer with cables.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 haunting dreamscape from a science fiction anime film.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [Ashley Liao, the cyberpunk goddess of lasers and sparks, is depicted as an anglerfish.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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" } ]

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [Christina Hendricks rests on a high rock amidst ancient ruins.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [Sun Wukong flies with a racket as Nike Goddess.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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" } ]

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A steampunk girl space knight poses with laser tachi in outer space.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 pilgrim sits in a ruined gas station with staff.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 beautiful android woman with PCB skin stands amidst PC towers.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [Anime woman with purple hair and horn wears purple 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": "people,portrait,fashion" } ]

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

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

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [A massive stone marble sculpture monument with big pods and people walking nearby.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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, landscape" } ]

[ { "from": "human", "value": "Given the following image prompt and list of labels, \nImage prompt: [James McAvoy as a satyr in bard armor from The Witcher.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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: [This is a waist-up portrait of Mei-Ling Zhou, a chubby Disney Pixar version of Mei from Overwatch.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 queen with bright blue hair stands in front of a golden cathedral at dawn.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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 male sci-fi character in a beige and black jumpsuit.] \nAvailable labels: ['animals', 'art', 'fashion', 'food', 'indoor', 'landscape', 'logo', 'people', 'portrait', 'plants', 'vehicles'] \nYour tasks are as follows:\n1. Determine whether the image contains harmful content or is not safe for work (NSFW). Harmful content includes, but is not limited to, harmful logo, extremist organization or religion, violence, crime, pornography, nudity, weapons, etc. If the image is NSFW, return the label \"NSFW\" (Not Safe for Work).\n2. Identify and select the most relevant labels that describe the key elements of the image the prompt might produce. Provide only the selected labels, separated by commas.\nIf the answer for first task is Yes, return NFSW as the selected labels, 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" } ]