[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-571718-105":53,"doc-detail-571718-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","stable-diffusion-basics-advanced-prompting-module-5","Stable Diffusion Basics & Advanced Prompting - Module 5","","Guide to Stable Diffusion text-to-image workflows, starting with using WebUI (txt2img) to generate images from prompts. Explains how to write effective simple prompts, how checkpoint models shape diffusion outputs, and contrasts styles such as realistic, anime, CGI, and photoreal. Covers practical WebUI settings: sampling methods, sampling steps for speed vs detail, and recommended image sizes (including 512x512 as the baseline).",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":51,"@type":70,"position":76},"https://docshare.wps.com/template/general/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/stable-diffusion-basics-advanced-prompting-module-5/571718/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/stable-diffusion-basics-advanced-prompting-module-5/571718.png","ImageObject",442,249,{"name":88,"@type":89},"Taylor Morgan","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-21","2026-10-13",true,{"@type":98,"interactionType":99,"userInteractionCount":9},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"How do I start generating images in Stable Diffusion WebUI?","Question",{"text":108,"@type":109},"Use the txt2img tab in WebUI, describe what you want to generate in a prompt, then click GENERATE.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"What are checkpoint models, and why do they matter?",{"text":113,"@type":109},"Checkpoint models are diffusion weights trained on specific styles. Changing the model while keeping the same prompt can produce different looks (e.g., anime vs photoreal).",{"name":115,"@type":106,"acceptedAnswer":116},"How should I choose sampling steps and image size?",{"text":117,"@type":109},"Sampling steps control detail vs speed; use about 20–35 steps as recommended. For image size, 512x512 is the gold standard, while 512x768 (portrait) and 768x512 (landscape) are OK.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},571718,1792567912,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":50,"category_name":51,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":9,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":135,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":140,"read_time":8},1099523885336,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","STABLE DIFFUSION \\#01  \nSD BASICS & ADVANCED PROMPTING  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \nLET’S GO // WebUi  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \n> Stable Diffusion icon on the desktop  \n-Python (console)  \n-WebUi (browser)  \nOSX Windows  \nTEXT TO IMAGE // txt2img  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \nGenerate images from text prompts.  \n> select txt2img tab  \nPROMPT (simple)  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \nDescribe the image you want to generate.  \n> Try a simple prompt first> “A dog playing poker”  \n> Hit GENERATE  \nCHECKPOINT MODELS  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \nDiffusion weights /Models trained on a specific style.  \n> illustrations  \n> paintings> anime> fantasy  \n> landscapes> animals> fashion styles  \n> cgi / realistic paintings  \n> photorealism> (…)  \nMidjourney does NOT have models & you  \nhave to adjust your style/mediaum via prompt!  \nCHECKPOINT MODELS  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \n“A cat on a bench”  \nv1.5-pruned (Base Model)  \nRealisticVision (photoreal)  \nAnything-V3 (Anime)  \nDeliberate-V3 (CGI)  \nCHECKPOINT MODELS  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \nSame prompt with different models … Let’s try it out!  \n-Anything-V3 (Anime)  \n-RealisticVision (photo-real)  \nSETTINGS: Sampling Methods  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \nSampling Methods (model dependent)  \nEuler a: Fast  \nHeun: Detailed for big GPUs  \nDPM++ 2M Karras: Detailed  \nSETTINGS: Sampling Steps  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)  \nSampling Steps  \n(Level of detail / Iterations)  \nLow number: Fast & rough  \nHigh number: Slow & detailed  \nRecommended:  \n20-35 Steps  \nSETTINGS: Image Size  \nSize of output image.  \n512 x 512 = gold standard  \n512 x 768 (portrait) = OK  \n768 x 512 (landscape) = OK  \nBy HPI MAKER UNIVERSE [markus.wutzlhofer@hpi.de](markus.wutzlhofer@hpi.de)","cbCainhOoT1uI4PI","https://ap.wps.com/l/cbCainhOoT1uI4PI","pdf",46930541,31,"English","# WebUI (Let’s Go)\n## Text to Image (txt2img)\n# Prompting Basics\n## Simple prompt examples\n# Checkpoint Models\n## Base and style-specific models\n## Same prompt, different models\n# Settings\n## Sampling Methods\n## Sampling Steps\n## Image Size","[{\"question\":\"How do I start generating images in Stable Diffusion WebUI?\",\"answer\":\"Use the txt2img tab in WebUI, describe what you want to generate in a prompt, then click GENERATE.\"},{\"question\":\"What are checkpoint models, and why do they matter?\",\"answer\":\"Checkpoint models are diffusion weights trained on specific styles. Changing the model while keeping the same prompt can produce different looks (e.g., anime vs photoreal).\"},{\"question\":\"How should I choose sampling steps and image size?\",\"answer\":\"Sampling steps control detail vs speed; use about 20–35 steps as recommended. For image size, 512x512 is the gold standard, while 512x768 (portrait) and 768x512 (landscape) are OK.\"}]","Stable Diffusion Basics & Advanced Prompting - Module 5 | PDF",1791923323]