{"id":20203,"date":"2024-09-19T10:44:31","date_gmt":"2024-09-19T02:44:31","guid":{"rendered":"https:\/\/www.1ai.net\/?p=20203"},"modified":"2024-09-19T10:52:23","modified_gmt":"2024-09-19T02:52:23","slug":"%e5%8f%af%e4%bb%a5%e5%9c%a8%e7%ba%bf%e4%bd%93%e9%aa%8cflux%e7%9a%84%e7%bd%91%e7%ab%99%ef%bc%8c%e4%bd%bf%e7%94%a8liblibai%e5%bf%ab%e9%80%9f%e5%bc%80%e5%90%afai%e7%bb%98%e7%94%bb%e4%b9%8b%e6%97%85","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/20203.html","title":{"rendered":"You can experience Flux's website online and quickly start your AI painting journey with LiblibAI!"},"content":{"rendered":"<p>Given that many people who are just getting started<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>The guys want to play Flux, but the lack of computer configuration on the one hand, and the unfamiliarity of the workflow on the other hand, discourages many of them. Today, I would like to share with you some information on the<a href=\"https:\/\/www.1ai.net\/en\/tag\/liblibai\" title=\"_Other Organiser\" target=\"_blank\" >LiblibAI<\/a>How websites experience Flux.<\/p>\n<blockquote>\n<ul>\n<li><strong>LiblibAI Web site<\/strong>:: https:\/\/www.liblib.art\/<\/li>\n<\/ul>\n<\/blockquote>\n<p>I won't go into detail about the LiblibAI website here, so if you haven't learned about it, you can refer to my previous post.<a href=\"https:\/\/www.1ai.net\/en\/20223.html\/\">Stable Diffusion [Fundamentals] [Introduction to SD]: A Quick Start to SD Painting with LiblibAI<\/a><\/p>\n<p>In the LiblibAI site provides WebUI and workflow 2 ways to use Flux, the way to use the Web UI and the previous way to use the SD Web UI does not have much difference, here will not expand the description.<\/p>\n<p>Today we mainly share how to use LiblibAI's online workflow to experience Flux. we don't mention workflow is a big headache, don't have to, at present the official Flux workflow is more general, LiblibAI has integrated Flux online workflow function, you can directly run Flux online directly on top of LiblibAI workflow, we don't need to build our own workflow, greatly reducing the threshold of AI painters. workflow, we do not need to build their own workflow, greatly reducing the threshold of the use of AI painters.<\/p>\n<p><strong>I. A quick taste of Flux workflows<\/strong><\/p>\n<p>Flux One-Click Run Workflow Address<\/p>\n<blockquote>\n<ul>\n<li>https:\/\/www.liblib.art\/modelinfo\/ec6223dccd7b47658464eaf7b94d7dc5<\/li>\n<\/ul>\n<\/blockquote>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20204\" title=\"d48d679ej00sk1gf80024d000u000h8m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/d48d679ej00sk1gf80024d000u000h8m.jpg\" alt=\"d48d679ej00sk1gf80024d000u000h8m\" width=\"1080\" height=\"620\" \/><\/p>\n<p>Clicking on the \"Run Workflow Online\" button in the image above will bring you to the<a href=\"https:\/\/www.1ai.net\/en\/tag\/comfyui\" title=\"_Other Organiser\" target=\"_blank\" >ComfyUI<\/a>of the workflow interface.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20205\" title=\"7f8f010fj00sk1gf8000ud000u000f6m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/7f8f010fj00sk1gf8000ud000u000f6m.jpg\" alt=\"7f8f010fj00sk1gf8000ud000u000f6m\" width=\"1080\" height=\"546\" \/><\/p>\n<p>In general, we only need to enter the prompt in the CLIP text editor node box, and then directly click on the picture above the upper right corner of the \"start generating\" button, you can generate the corresponding picture. You see is not very convenient ah.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20206\" title=\"b5ac539bj00sk1gf9001jd000u000epm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/b5ac539bj00sk1gf9001jd000u000epm.jpg\" alt=\"b5ac539bj00sk1gf9001jd000u000epm\" width=\"1080\" height=\"529\" \/><\/p>\n<p>Below we give a brief introduction to workflow related nodes.<\/p>\n<p><strong>(1) UNET loader<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20207\" title=\"1dc724ffj00sk1gf80005d00094003bm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/1dc724ffj00sk1gf80005d00094003bm.jpg\" alt=\"1dc724ffj00sk1gf80005d00094003bm\" width=\"328\" height=\"119\" \/><\/p>\n<p>This node is mainly used to set up the Flux big model, about the UNET node, here is a little clarification, the UNET loader is used to load a specific UNET model individually, this node doesn't have any inputs, only an output of the model, which we can think of as a Checkpoint big model inside SD. Of course there is still a difference with Checkpoint node in workflow (Checkpoint node has 3 outputs: model, CLIP and VAE). In ComfyUI, UNet models exist in the \\ComfyUI\\models\\unet directory.<\/p>\n<p>When we click on the model's selection box, a selection box pops up where we can choose the desired Flux large model.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20208\" title=\"076332d5j00sk1gf80019d000u000gvm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/076332d5j00sk1gf80019d000u000gvm.jpg\" alt=\"076332d5j00sk1gf80019d000u000gvm\" width=\"1080\" height=\"607\" \/><\/p>\n<p>You can add Flux big models to my model library, so that the pop-up box will have our corresponding big models. The way to add Flux big model is as follows: Go to the detail page of Flux big model, click the \"Add to Model Library\" button as below, then you can add big model to my model library.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20209\" title=\"62e01420j00sk1gf9002hd000u000ljm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/62e01420j00sk1gf9002hd000u000ljm.jpg\" alt=\"62e01420j00sk1gf9002hd000u000ljm\" width=\"1080\" height=\"775\" \/><\/p>\n<p>weight_type parameter: set to fp8_e4m3fn<\/p>\n<p><strong>(2) Dual CLIP loader<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20210\" title=\"80bb95bej00sk1gf80006d0008b0043m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/80bb95bej00sk1gf80006d0008b0043m.jpg\" alt=\"80bb95bej00sk1gf80006d0008b0043m\" width=\"299\" height=\"147\" \/><\/p>\n<p>Here it is generally sufficient to keep the default parameters.<\/p>\n<p><strong>(3) CLIP Text Encoder<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20211\" title=\"d06dac14j00sk1gf8000bd000bm005jm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/d06dac14j00sk1gf8000bd000bm005jm.jpg\" alt=\"d06dac14j00sk1gf8000bd000bm005jm\" width=\"418\" height=\"199\" \/><\/p>\n<p>This node is mainly used for outputting cue words. It is also the node we use the most.<\/p>\n<p><strong>(4) Empty Latent<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20212\" title=\"6d84b661j00sk1gf80005d0008t003zm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/6d84b661j00sk1gf80005d0008t003zm.jpg\" alt=\"6d84b661j00sk1gf80005d0008t003zm\" width=\"317\" height=\"143\" \/><\/p>\n<p>This node is mainly used for the image width and height settings. Here to note that Flux supports any resolution, if the generated image is not ideal, you can adjust the appropriate aspect ratio to try, the most commonly used personal aspect ratio is 1024 * 1536 (1536 * 1024).<\/p>\n<p><strong>(5) Sampler, Sampling Iteration Steps, Random Number Seeds<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20214\" title=\"adec834aj00sk1gf9000fd0009400b1m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/adec834aj00sk1gf9000fd0009400b1m.jpg\" alt=\"adec834aj00sk1gf9000fd0009400b1m\" width=\"328\" height=\"397\" \/><\/p>\n<ul>\n<li>Sampler recommendation: Euler, at present no special circumstances, it is recommended to use euler uniformly.<\/li>\n<li>Scheduler: recommended simple<\/li>\n<li>Number of steps: recommended between 20-30<\/li>\n<li>Control_after_generate: the way the random number is generated, it is recommended to randomize, i.e. generate a different random number each time.<\/li>\n<\/ul>\n<p><strong>(6) VAE Loader<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20213\" title=\"e5c6e602j00sk1gf80004d00091002lm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/e5c6e602j00sk1gf80004d00091002lm.jpg\" alt=\"e5c6e602j00sk1gf80004d00091002lm\" width=\"325\" height=\"93\" \/><\/p>\n<p>Flux large model paired with VAE model, currently only ae.sft, just keep the default settings here.<\/p>\n<p><strong>II.  How to add a loar node to a workflow<\/strong><\/p>\n<p>\u3010<strong>initial step<\/strong>\u3011<strong>Add LoRA loader node<\/strong><\/p>\n<p>Double-clicking on the mouse in a blank space in the ComfyUI interface will pop up a search dialogue box in which you enter the lora keyword and you find the loar node. Here we select the first node of the search result, the LoRA Loader\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20215\" title=\"2dcbe500j00sk1gf9000sd000mn0084m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/2dcbe500j00sk1gf9000sd000mn0084m.jpg\" alt=\"2dcbe500j00sk1gf9000sd000mn0084m\" width=\"815\" height=\"292\" \/><\/p>\n<p>This is when an extra LoRA loader is added to the ComfyUI interface\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20216\" title=\"757281f8j00sk1gf80005d0007r0045m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/757281f8j00sk1gf80005d0007r0045m.jpg\" alt=\"757281f8j00sk1gf80005d0007r0045m\" width=\"279\" height=\"149\" \/><\/p>\n<p>\u3010<strong>second step<\/strong>\u3011<strong>Select the lora model and set the weights of the lora model.<\/strong><\/p>\n<p>Adds the LoRA Loader node and does not automatically add the Lora model. A default LoRA name value of \"undefined\" can be seen from the figure above, indicating that the LoRA model is not added\u3002<\/p>\n<p>Click on the LoRA name to pull down and pop up my model library dialogue box, and you can select the Lora model that I added in my model library. The LoRA model is added to my model library in the same way as the large Flux model above\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20218\" title=\"eb236a8bj00sk1gf90021d000m500j0m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/eb236a8bj00sk1gf90021d000m500j0m.jpg\" alt=\"eb236a8bj00sk1gf90021d000m500j0m\" width=\"797\" height=\"684\" \/><\/p>\n<p>Here we take the example of the LoRA model, the LoRA model, and click on the One Key Application button\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20219\" title=\"6bf8a836j00sk1gf90024d000ma00ivm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/6bf8a836j00sk1gf90024d000ma00ivm.jpg\" alt=\"6bf8a836j00sk1gf90024d000ma00ivm\" width=\"802\" height=\"679\" \/><\/p>\n<p>So the loar model is added to the LoRA loader node\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20217\" title=\"7d724ae6j00sk1gf80006d0009a004bm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/7d724ae6j00sk1gf80006d0009a004bm.jpg\" alt=\"7d724ae6j00sk1gf80006d0009a004bm\" width=\"334\" height=\"155\" \/><\/p>\n<p>For different LoRAs we need to adjust the parameter value of model strength, which is also known as the weight parameter of the LoRA model.<\/p>\n<p>For the CLIP intensity parameter, we just maintain the default value of 1.<\/p>\n<p>\u3010<strong>third step<\/strong>\u3011<strong>Add the LoRA loader node to the Flux workflow.<\/strong><\/p>\n<p>Let's adjust the connectivity between the nodes according to the following rules.<\/p>\n<ul>\n<li>Model output node of the UNET loader Connects to the model input node of the LoRA loader.<\/li>\n<li>CLIP output node of the dual CLIP loader connects to the CLIP input node of the LoRA loader<\/li>\n<li>The model output node of the LoRA loader connects both the model input node of the base bootstrap and the model input node of the base scheduler<\/li>\n<li>The CLIP output node of the LoRA loader connects to the CLIP input node of the CLIP text encoder.<\/li>\n<\/ul>\n<p>In the process of adjusting node connections, the system will automatically delete the original node connections. The deleted node connections are shown in the following figure.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20220\" title=\"6c195a27j00sk1gf9001rd000lp00mtm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/6c195a27j00sk1gf9001rd000lp00mtm.jpg\" alt=\"6c195a27j00sk1gf9001rd000lp00mtm\" width=\"781\" height=\"821\" \/><\/p>\n<p>The final effect of the added LoRA loader node wiring is as follows.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20221\" title=\"8cc63782j00sk1gf9001ud000kj00msm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/8cc63782j00sk1gf9001ud000kj00msm.jpg\" alt=\"8cc63782j00sk1gf9001ud000kj00msm\" width=\"739\" height=\"820\" \/><\/p>\n<p><strong>[Step 4] Preparation of cue words and related parameter settings.<\/strong><\/p>\n<p>I won't expand on this here, but you can refer to the previous section.<\/p>\n<p><strong>[Step 5] Image generation.<\/strong><\/p>\n<p>Click the \"Start Image Generation\" button in the upper right corner to generate the corresponding image.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-20222\" title=\"2767639fj00sk1gf9001jd000u000eym\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/09\/2767639fj00sk1gf9001jd000u000eym.jpg\" alt=\"2767639fj00sk1gf9001jd000u000eym\" width=\"1080\" height=\"538\" \/><\/p>\n<p>For the average average user, Flux's basic workflow and the addition of LoRA loader node workflow can meet most of the demand for the use of Flux to generate images scenarios.<\/p>\n<p>Okay, that\u2019s all for today\u2019s sharing. I hope that what I shared today will be helpful to you.<\/p>","protected":false},"excerpt":{"rendered":"<p>Given that many partners who just started AI painting want to play Flux, but on the one hand, the computer configuration is not enough, on the other hand, the unfamiliarity of the workflow, so that many partners are deterred. Today, I'd like to share with you how to experience Flux on the LiblibAI website. LiblibAI website: https:\/\/www.liblib.art\/ About the LiblibAI website here is not a detailed description of the small partners who have not understood it can refer to my previous article. Stable Diffusion [Basic] [Introduction to SD LiblibAI\uff1aUsing LiblibAI to quickly start the SD painting journey in the LiblibAI website provides a WebUI and workflow 2 ways to use Flux, the use of Web UI and the way of the<\/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":[491,1989,3853,819],"collection":[],"class_list":["post-20203","post","type-post","status-publish","format-standard","hentry","category-jiaocheng","category-baike","tag-ai","tag-comfyui","tag-flux","tag-liblibai"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/20203","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=20203"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/20203\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=20203"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=20203"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=20203"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=20203"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}