{"id":20223,"date":"2024-09-19T10:51:44","date_gmt":"2024-09-19T02:51:44","guid":{"rendered":"https:\/\/www.1ai.net\/?p=20223"},"modified":"2024-09-19T10:52:46","modified_gmt":"2024-09-19T02:52:46","slug":"stable-diffusion%e5%85%a5%e9%97%a8%e6%95%99%e7%a8%8b%ef%bc%9a%e5%9c%a8liblibai%e7%94%a8%e5%85%8d%e8%b4%b9%e5%9c%a8%e7%ba%bf%e5%8e%9f%e7%94%9f%e7%95%8c%e9%9d%a2stable-diffusion%e6%9d%a5ai%e7%bb%98","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/20223.html","title":{"rendered":"Getting Started with Stable Diffusion Tutorial: AI Painting with Stable Diffusion at LiblibAI with Free Online Native Interface"},"content":{"rendered":"<p>I realized that there are many other peeps who haven't been exposed to it before<a href=\"https:\/\/www.1ai.net\/en\/tag\/ai%e7%bb%98%e7%94%bb\" title=\"[SEES ARTICLES WITH [AI PAINTING] LABELS]\" target=\"_blank\" >AI Painting<\/a>. In order to help you quickly understand AI painting, as soon as possible to cross the door into the AI painting, start the AI painting journey, I personally feel very necessary to write an article for newbies to start.<\/p>\n<p>Of course it's not just for beginners, there are some peeps who fall into the category of<\/p>\n<ul>\n<li>The configuration of the computer is not enough to set up the SD environment locally.<\/li>\n<li>Do content partners, not too concerned about the tool itself and technical capabilities, focus on creativity and content expression, can generate the effect I want to picture can be.<\/li>\n<\/ul>\n<p>For these types of peeps, I would generally recommend a newbie-friendly AI drawing tool - the LiblibAI website. Just register to use the online<a href=\"https:\/\/www.1ai.net\/en\/tag\/sd%e7%bb%98%e5%9b%be%e5%b7%a5%e5%85%b7\" title=\"[SEE ARTICLES WITH [SD DRAWING TOOL] LABELS]\" target=\"_blank\" >SD Drawing Tools<\/a>The key is that the interface of this online SD drawing tool is almost exactly the same as the SD Web UI, which is very favorable for beginners to start learning SD related skills.<\/p>\n<blockquote>\n<ul>\n<li><strong>LiblibAI Web site<\/strong>:: https:\/\/www.liblib.art\/<\/li>\n<\/ul>\n<\/blockquote>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20228\" title=\"a13430b2j00sk1gzg002id000u000fim\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/a13430b2j00sk1gzg002id000u000fim.jpg\" alt=\"a13430b2j00sk1gzg002id000u000fim\" width=\"1080\" height=\"558\" \/><\/p>\n<p>The site can be used by registering, and currently there are 300 free points available every day, generally generating a picture consumes 2-8 points ranging.<\/p>\n<p>About the LiblibAI website itself is not introduced here, we are mainly for newcomers to get started quickly to be able to produce the first picture-based explanation. Without further ado, directly open the whole.<\/p>\n<p><strong>I. Quick start<\/strong><\/p>\n<p>Enter the Liblibai website address in the browser and click on the \" Online living \" button on the first page\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20224\" title=\"fe8c1089j00sk1gzg001td000u000a6m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/fe8c1089j00sk1gzg001td000u000a6m.jpg\" alt=\"fe8c1089j00sk1gzg001td000u000a6m\" width=\"1080\" height=\"366\" \/><\/p>\n<p>Go to the main screen of LiblibAI drawing.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20226\" title=\"fb78aab2j00sk1gzg000pd000u00084m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/fb78aab2j00sk1gzg000pd000u00084m.jpg\" alt=\"fb78aab2j00sk1gzg000pd000u00084m\" width=\"1080\" height=\"292\" \/><\/p>\n<p>Below you can follow my following interface parameter settings first out of a picture to see the effect. In order to facilitate the demonstration, here I divided into several parts of the parameter settings.<\/p>\n<p><strong>(1) Big models and cue words<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20225\" title=\"a126c11aj00sk1gzg000qd000u0007om\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/a126c11aj00sk1gzg000qd000u0007om.jpg\" alt=\"a126c11aj00sk1gzg000qd000u0007om\" width=\"1080\" height=\"276\" \/><\/p>\n<p>Description of relevant parameter settings:<\/p>\n<ul>\n<li>CHECKPOINT (large model): majicMIX realistic mai orange realistic_v7.safetensors<\/li>\n<li>VAE (VAE model): vae-ft-mse-840000-ema-pruned.safetensors<\/li>\n<li>CLIP Skip Layer Clip Skip: 2 (default value, generally left unchanged)<\/li>\n<li>Cue word (positive cue word): 1 gril, solo.<\/li>\n<li>Negative cue words: ng_deepnegative_v1_75t,(badhandv4:1.2), EasyNegative,(worst quality:2),<\/li>\n<\/ul>\n<p><strong>(2) Parameter setting<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20227\" title=\"45f4d1f8j00sk1gzg0019d000pm00dlm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/45f4d1f8j00sk1gzg0019d000pm00dlm.jpg\" alt=\"45f4d1f8j00sk1gzg0019d000pm00dlm\" width=\"922\" height=\"489\" \/><\/p>\n<p>Description of relevant parameter settings:<\/p>\n<ul>\n<li>Sample method: Euler a<\/li>\n<li>Sampling Steps: 30<\/li>\n<li>Width: 768<\/li>\n<li>Height: 512<\/li>\n<li>Numer of images: 2<\/li>\n<li>Cue guidance factor (CFG scale): 7 (default)<\/li>\n<li>Random number seed (Seed): -1 (default)<\/li>\n<\/ul>\n<p><strong>(3) ADetailer plugin<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20229\" title=\"1eb614b2j00sk1gzg000yd000p100eum\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/1eb614b2j00sk1gzg000yd000p100eum.jpg\" alt=\"1eb614b2j00sk1gzg000yd000p100eum\" width=\"901\" height=\"534\" \/><\/p>\n<p>Description of relevant parameter settings:<\/p>\n<ul>\n<li>Enable Adetailler: Select, meaning \"Open\"<\/li>\n<li>Model selection: face_yolov8n<\/li>\n<\/ul>\n<p>Well, the basic parameters are all set here, so we can generate pictures. Click the Start Picture button on the page to generate a picture\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20230\" title=\"c799a4b2j00sk1gzg000nd000u0007km\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/c799a4b2j00sk1gzg000nd000u0007km.jpg\" alt=\"c799a4b2j00sk1gzg000nd000u0007km\" width=\"1080\" height=\"272\" \/><\/p>\n<p>Let's take a look at the effect of the generated images. In the parameter above we set the number of images to 2 and the tool will generate 2 images for us.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20231\" title=\"8833f199j00sk1gzg001ld000pk00mem\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/8833f199j00sk1gzg001ld000pk00mem.jpg\" alt=\"8833f199j00sk1gzg001ld000pk00mem\" width=\"920\" height=\"806\" \/><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20232\" title=\"03bd87c7j00sk1gzg001jd000pq00mdm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/03bd87c7j00sk1gzg001jd000pq00mdm.jpg\" alt=\"03bd87c7j00sk1gzg001jd000pq00mdm\" width=\"926\" height=\"805\" \/><\/p>\n<p>Okay, so here's where our first image is generated.<\/p>\n<p><strong>II. Explanation of various parameters<\/strong><\/p>\n<p>Here's a primer on each of the above parameters.<\/p>\n<p><strong>1. Large model (checkpoint)<\/strong><\/p>\n<p>The base model of SD drawing, also called the base model, must be matched with a big model to be used. The big model determines the main style of the generated picture, and different big models will focus on different areas, such as common secondary style, real style, national style, etc. At present, there are two main types of big models based on SD1.5 and SDXL ecology. Currently, there are 2 major types of big models, SD1.5 and SDXL based.<\/p>\n<p>For an in-depth look at big models, see my previous post for more details.<\/p>\n<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/stable-diffusion\" title=\"_Other Organiser\" target=\"_blank\" >Stable Diffusion<\/a>: Models<\/p>\n<p>Stable Diffusion: A Commonly Used Large Model<\/p>\n<p>For beginners, here is a focus on 2 knowledge points<\/p>\n<p>(1) How to add a large model to the CHECKPOINT drop-down list box.<\/p>\n<p>On the home page of the LiblibAI website, you can navigate directly to the detailed interface of the big model by means of search or by links.<\/p>\n<p>Enter \"Male Orange\" in the search box on the first page<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20233\" title=\"996b749cj00sk1gzg000pd000u00058m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/996b749cj00sk1gzg000pd000u00058m.jpg\" alt=\"996b749cj00sk1gzg000pd000u00058m\" width=\"1080\" height=\"188\" \/><\/p>\n<p>Enters into all large model list interfaces associated with the \"Male Orange\" keyword<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20234\" title=\"b56edb9fj00sk1gzg001ld000u0009pm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/b56edb9fj00sk1gzg001ld000u0009pm.jpg\" alt=\"b56edb9fj00sk1gzg001ld000u0009pm\" width=\"1080\" height=\"349\" \/><\/p>\n<p>We select the desired macromodel and click on the image above to enter the macromodel detail screen.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20235\" title=\"2979bb4aj00sk1gzg001hd000u000g3m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/2979bb4aj00sk1gzg001hd000u000g3m.jpg\" alt=\"2979bb4aj00sk1gzg001hd000u000g3m\" width=\"1080\" height=\"579\" \/><\/p>\n<p>Click Add to Model Library above to add a large model to the Large Model CHECKPOINT drop-down list box on the main drawing screen.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20236\" title=\"d6a28304j00sk1gzg000ad000u00026m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/d6a28304j00sk1gzg000ad000u00026m.jpg\" alt=\"d6a28304j00sk1gzg000ad000u00026m\" width=\"1080\" height=\"78\" \/><\/p>\n<p>MANY TIMES, CLICK ON THE ADD MODEL LIBRARY BUTTON AND DO NOT ADD A LARGE MODEL TO THE CHECKPOINT DROP-DOWN LIST BOX. WE CAN ADD THE NEXT REFRESHING BUTTON, SO WE CAN SEE THAT THE MODEL IS LOADED IN\u3002<\/p>\n<p>(2) Commonly used large models<\/p>\n<p>Based on the SD1.5 Big Model<\/p>\n<ul>\n<li>Universal Large Model: DreamShaper<\/li>\n<li>Realistic large models: DeliberateV2\/ReVAnimated_v122 Mainly a variety of scene realistic<\/li>\n<li>Realistic large models: realisticMIX realistic V7\/realisticVisionV60\/Chilloutmix-Ni-pruned-fp32-fix<\/li>\n<li>Realistic large models: AWPortaint and kimchiMix (optimized for hands)<\/li>\n<\/ul>\n<p>Based on the SDXL Large Model<\/p>\n<ul>\n<li>Universal Model: DreamShaper XL\/juggernautXL_v9 + RDPhoto 2\/RealVisXL V4.0 Lightning\/AlbedoBase XL V2.1\/Dream Tech XL (Tsukuba Industries)<\/li>\n<li>Realistic Class: LEOSAM HelloWorld New World\/wuhaXL V8.2\/wuhaXL_realisticMix<\/li>\n<\/ul>\n<p><strong>2. VAE model<\/strong><\/p>\n<p>The VAE model is understood as the colour filter, which is used primarily to regulate and aestheticize the colour of the picture. The most commonly used VAE model is \"vae-ft-mse-84000-ema-pruned\". Usually, when you use it, you choose the model\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20237\" title=\"4e166274j00sk1gzg000cd000a4008ym\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/4e166274j00sk1gzg000cd000a4008ym.jpg\" alt=\"4e166274j00sk1gzg000cd000a4008ym\" width=\"364\" height=\"322\" \/><\/p>\n<p>Related Note: The LiblibAI tool has restrictions on the use of VAE models, especially when the CHECKPOINT large model is used with the SDXL large model, the VAE model cannot be selected, which greatly reduces the possibility of beginners making mistakes when using VAE models.<\/p>\n<p><strong>3. Prompts<\/strong><\/p>\n<p>Cues are divided into 2 categories<\/p>\n<ul>\n<li>Positive Cue Words: keywords you want the information contained in the generated image to use.<\/li>\n<li>Reverse cue words: keywords used for information you want the generated image to not contain.<\/li>\n<\/ul>\n<p>The cue word is a huge body of content, so I won't expand on this one. Focus on a few points<\/p>\n<ul>\n<li>Prompts need to be described in English, either as a sentence, multiple phrases or words.<\/li>\n<li>Do not know how to write the cue word, you can look at the interface of the LiblibAI big model, which has a large number of enthusiasts posted pictures, many of which contain the cue word, beginners can imitate the writing.<\/li>\n<\/ul>\n<p><strong>4. Sample method and sampling steps<\/strong><\/p>\n<p>These 2 parameters are usually set together.<\/p>\n<p>The so-called sampling method is used to de-noise the image during the process of generating the image.<\/p>\n<p>There are a variety of samplers available today. It is sufficient to focus on a few commonly used samplers.<\/p>\n<ul>\n<li>Euler a<\/li>\n<li>DPM++2M Karras<\/li>\n<li>DPM++SDE Karras<\/li>\n<li>DPM++2M SDE Karras<\/li>\n<\/ul>\n<p>There is a small hint icon next to the liblibAI adoption method.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20238\" title=\"4562ff7ej00sk1gzg0008d000b5002im\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/4562ff7ej00sk1gzg0008d000b5002im.jpg\" alt=\"4562ff7ej00sk1gzg0008d000b5002im\" width=\"401\" height=\"90\" \/><\/p>\n<p>The sampling method is related to the selection of the macromodel, and the sampling method recommended for use with the macromodel is generally available in the macromodel's detail screen.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20239\" title=\"9244e92cj00sk1gzg0027d000u000ncm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/9244e92cj00sk1gzg0027d000u000ncm.jpg\" alt=\"9244e92cj00sk1gzg0027d000u000ncm\" width=\"1080\" height=\"840\" \/><\/p>\n<p>Iteration Steps: is the number of steps needed to generate an image, each sampling step generates a new image based on the image generated in the previous iteration. In general, the number of sampling iteration steps can be set between 20-40.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20240\" title=\"6e46771dj00sk1gzg0008d000b4002jm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/6e46771dj00sk1gzg0008d000b4002jm.jpg\" alt=\"6e46771dj00sk1gzg0008d000b4002jm\" width=\"400\" height=\"91\" \/><\/p>\n<p><strong>5. Image width and height<\/strong><\/p>\n<p>FOR THE SD V1.5 MODEL, THE OPTIMAL WIDTH RATIO: 512 X 512. THE FOLLOWING IS A COMMON WIDTH RATIO:<\/p>\n<ul>\n<li>One: 1 (square): 512 x 512, 768 x 768<\/li>\n<li>3:2 (Landscape): 768 x 512<\/li>\n<li>2:3 (vertical): 512 x 768<\/li>\n<li>4:3 (horizontal): 768 x 576<\/li>\n<li>3:4 (vertical): 576 x 768<\/li>\n<li>16:9 (widescreen): 912 x 512<\/li>\n<li>9:16 (onscreen): 512 x 912<\/li>\n<\/ul>\n<p>Optimal aspect ratio for SDXL model: 1024*1024. below are the commonly used aspect ratios:<\/p>\n<ul>\n<li>1:1 (square): 1024 x 1024, 768 x 768<\/li>\n<li>3:2 (Landscape): 1152 x 768<\/li>\n<li>2:3 (vertical): 768 x 1152<\/li>\n<li>4:3 (Landscape): 1152 x 864<\/li>\n<li>3:4 (vertical): 864 x 1152<\/li>\n<li>16:9 (widescreen): 1360 x 768<\/li>\n<li>9:16 (onscreen): 768 x 1360<\/li>\n<\/ul>\n<p>Note on aspect ratio settings:<\/p>\n<ul>\n<li>The width and height should ideally be divisible by 8.<\/li>\n<li>Common ratios: 1:1, 2:3 (3:2), 3:4 (4:3), 9:16 (16:9)<\/li>\n<li>It's easy to generate all sorts of weird images when the aspect ratio isn't set properly.<\/li>\n<\/ul>\n<p><strong>6. Cue guide factor<\/strong><\/p>\n<p>Determines the image degrees of freedom, the higher the value, the more the generated image will match the cue word. The default value is 7, and is usually set between 5-10. It is also not recommended to set it too large.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20241\" title=\"d4d0e876j00sk1gzg0007d0009u002xm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/d4d0e876j00sk1gzg0007d0009u002xm.jpg\" alt=\"d4d0e876j00sk1gzg0007d0009u002xm\" width=\"354\" height=\"105\" \/><\/p>\n<p><strong>7. Seed of random numbers (Seed)<\/strong><\/p>\n<p>Equivalent to the DNA of the picture, determines the content of the picture, generally set to -1 (default), indicating random generation, SEED the same case, you can generate a more similar picture.<\/p>\n<p>For beginners, it may be confusing why my same parameters generate different images every time, mainly because we set the random number seed to -1, and every time we generate the image is random. So, accept this concept.<\/p>\n<p>With the above basics to lay the groundwork for a basic concept of the basic parameters of the interface, such as their own hands to successfully draw a few pictures, even if the beginner.<\/p>","protected":false},"excerpt":{"rendered":"<p>I found that there are still many of my friends who have not been exposed to AI painting before. In order to help you quickly understand AI painting, as soon as possible to cross the door into the AI painting, start the AI painting journey, I personally feel it is very necessary to write an article for beginners to start. Of course, not only for beginners, there are some partners belong to the computer configuration is not enough to build the local SD environment Do content partners, not too concerned about the tool itself and technical capabilities, focus on creativity and content expression, can generate the effect I want to picture. For these types of partners, I would generally recommend a suitable AI painting tool for novices - LiblibAI website. Only need to register to use the online SD drawing tool, the key is this online SD drawing tool interface and SD We<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[149,144],"tags":[491,4396,197,198],"collection":[262],"class_list":{"0":"post-20223","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-jiaocheng","7":"category-baike","8":"tag-ai","9":"tag-sd","10":"tag-stable-diffusion","12":"collection-stablediffusion"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/20223","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=20223"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/20223\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=20223"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=20223"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=20223"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=20223"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}