{"id":17795,"date":"2024-08-12T10:15:16","date_gmt":"2024-08-12T02:15:16","guid":{"rendered":"https:\/\/www.1ai.net\/?p=17795"},"modified":"2024-08-12T10:15:16","modified_gmt":"2024-08-12T02:15:16","slug":"stable-diffusion%e7%ba%bf%e7%a8%bf%e8%bd%ac%e7%bb%98%ef%bc%8c%e5%bb%ba%e7%ad%91%e5%9b%be%e7%89%87%e7%9a%84%e7%ba%bf%e7%a8%bf%e8%bd%ac%e7%bb%98%e5%88%b6%e4%bd%9c%e6%95%99%e7%a8%8b%e6%9d%a5%e4%ba%86","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/17795.html","title":{"rendered":"Stable Diffusion line drawing transfer, architectural picture line drawing transfer production tutorial is here"},"content":{"rendered":"

aboutLine drawing transfer<\/a>Earlier, I shared with you two ways to implement text-generated graphs and image-generated graphs.<\/p>\n

Stable Diffusion [Application] [Line drawing to drawing]: Convert image to line drawing in one minute<\/a><\/p>\n

Stable Diffusion [Application] [Line drawing transfer]: No need to use loar, transfer pictures to line drawings in one minute<\/a><\/p>\n

The first two methods are implementedBuilding pictures<\/a>Most of them are not very good at transferring line drawings. Today I will share my personal practice on transferring line drawings of architectural pictures. If you have good ideas for implementation, you can leave a message or add WeChat for private communication.<\/p>\n

1. The Wensheng diagram uses the large model RealisticVisionV2.0<\/strong><\/p>\n

When we converted the line drawing of the picture in the first article, we used ReVAnimated for the big model. I tried to change the big model to RealisticVisionV2.0. When other parameters are configured exactly the same, the effect of the architectural picture is much better, mainly because the lines are very natural and obvious. The current picture clarity still needs to be improved. Let's take a look at the effect of using RealisticVisionV2.0 to convert the picture to the line drawing.<\/p>\n\n\n\n
\n
\"4caf9bc0j00si316p002nd000sg00sgm\"<\/div>\n<\/td>\n
\n
\"409d9cccj00si316p003zd000sg00sgm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

It seems that more attempts are needed to achieve better results. Of course, you can try it yourself to see whether the effect of converting real-life pictures to line drawings is better after changing to RealisticVisionV2.0.<\/p>\n

The above production method is still lacking in the effect of transferring the line drawing of the picture, mainly because the lines are too thin and the overall picture is white.<\/p>\n

2. Method of converting architectural pictures into line drawings<\/strong><\/p>\n

Let\u2019s first take a look at the effect of converting architectural pictures into line drawings.<\/p>\n\n\n\n
\n
\"d18ef062j00si316q004xd000sg00sgm\"<\/div>\n<\/td>\n
\n
\"348543f7j00si316q005bd000sg00sgm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Overall, the lines of the picture are quite obvious. Let\u2019s take a look at the production method.<\/p>\n

[Step 1]: Selection of large model<\/strong><\/p>\n

It is recommended to use: Essential Model for Realism | RealisticVisionV2.0.<\/p>\n

Model download address (you can also get the network disk address at the end of the article)<\/p>\n

\n

LiblibAI<\/strong>:https:\/\/www.liblib.art\/modelinfo\/8210b3f729fba1ec171698f73eb6f5e3<\/p>\n<\/blockquote>\n

\u3010Step 2\u3011\uff1aWriting prompt words<\/strong><\/p>\n

Positive prompt words<\/strong><\/p>\n

\n

Prompt<\/a><\/strong>\uff1aBondyStudio,monochrome,greyscale,Dotted line,line shadow,exquisite,clean white background,masterpiece,best quality,fine detail,8K,UHD,wallpaper<\/p>\n

Prompt word<\/strong>: BondyStudio, monochrome, grayscale, dotted lines, line shadows, exquisite, clean white background, masterpiece, best quality, fine details, 8K, UHD, wallpaper<\/p>\n<\/blockquote>\n

Reverse prompt word<\/strong><\/p>\n

\n

negative<\/p>\n<\/blockquote>\n

Related parameter settings<\/p>\n

    \n
  • Sampler: Euler a<\/li>\n
  • Sampling iteration number: 60<\/li>\n
  • Image width and height: 512*768 (same as the original image to be transferred)<\/li>\n
  • Prompt word guidance coefficient (CFG): 5<\/li>\n<\/ul>\n

    \u3010Step 3\u3011\uff1aSetting up the Loar model<\/strong><\/p>\n

    Here we use a LORA model mainly used for architecture to line draft:<\/strong><\/p>\n

    lora1: Photo to Line Drawing - Line Drawing Model<\/strong><\/p>\n

    \n

    LiblibAI<\/strong>: https:\/\/www.liblib.art\/modelinfo\/4eb802a26fbd1715f148d770be470c61<\/p>\n<\/blockquote>\n

    The author of this lora model is trained mainly to produce architectural line drawings, and supports 2 modes.<\/p>\n

      \n
    • One is the exquisite line draft mode. The keywords are: "BondyStudio, monochrome, greyscale, Dotted line, line shadow, exquisite." The recommended sampling steps are more than 60 steps and the Lora weight is about 0.75. You can test it yourself.<\/li>\n
    • The other is the conceptual line draft mode, the keywords are: "archline, sketch, perspective,<\/li>\n
    • monochrome, greyscale, white background,\u201d the recommended sampling step is about 40 steps. It is recommended that the control model of cotrolnet should be Scribble\/sketch, and the preprocessor should be scribble-xdog mode.<\/li>\n<\/ul>\n

      The trigger word is sketch or exquisite<\/p>\n

      Here we produce a delicate line drawing, and we set the weight to 0.75.<\/p>\n

      [Step 4]: ControlNet settings<\/strong><\/p>\n

      \"563cdbd1j00si316p0024d000u000kym\"<\/div>\n

      The relevant parameter settings are as follows:<\/p>\n

        \n
      • Control type: Select \"Lineart\"<\/li>\n
      • Preprocessor: lineart_realistic<\/li>\n
      • Model: control_v11p_sd15_lineart<\/li>\n
      • Control weight: 0.65<\/li>\n<\/ul>\n

        \u3010Step 5\u3011Image generation<\/strong><\/p>\n

        Click the [Generate] button and let\u2019s take a look at the final generated image effect.<\/p>\n\n\n\n
        \n
        \"4caf9bc0j00si316q002nd000sg00sgm\"<\/div>\n<\/td>\n
        		\n
        \"80355313j00si316q0052d000sg00sgm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

        3. Architectural picture to sketch effect<\/strong><\/p>\n

        The loar model above: photo to line drawing - line drawing model, can also support line drawing sketches. Let's experience it. Here we need to modify 2 configurations.<\/p>\n

        Positive prompt words:<\/strong><\/p>\n

        \n

        Prompt<\/strong>\uff1aarchline,sketch,perspective,monochrome,greyscale,white background,masterpiece,best quality,fine detail,8K,UHD,wallpaper,<\/p>\n

        Prompt word<\/strong>: arch lines, sketch, perspective, monochrome, grayscale, white background, masterpiece, best quality, fine details, 8K, UHD, wallpaper<\/p>\n<\/blockquote>\n

        ControlNet Settings:<\/strong><\/p>\n

        \"07187824j00si316p0021d000u000m4m\"<\/div>\n

        The relevant parameter settings are as follows:<\/p>\n

          \n
        • Control type: Choose \"Scribble\/sketch (paint\/script)\"<\/li>\n
        • Preprocessor: scribble-xdog<\/li>\n
        • Model: control_v11p_sd15_scribble<\/li>\n
        • Control weight: 1<\/li>\n<\/ul>\n

          Let's take a look at the generated image.<\/p>\n\n\n\n
          \n
          \"4caf9bc0j00si316q002nd000sg00sgm\"<\/div>\n<\/td>\n
          		\n
          \"967dc74bj00si316p002fd000sg00sgm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

          4. Related instructions<\/strong><\/p>\n

          Today I will introduce the line drawing transfer of architectural pictures. If used on a real-life model, the effect will not be very good, so I will not post the comparison picture here. If you are interested, you can try it yourself.<\/p>\n

          Okay, that\u2019s all for today\u2019s sharing. I hope that what I shared today will be helpful to you.<\/p>\n

          The model is placed in the network disk, and those who are interested can take it!<\/p>\n

          https:\/\/pan.quark.cn\/s\/b3df771404e2<\/p>","protected":false},"excerpt":{"rendered":"

          Regarding the line drawing, we have shared with you the 2 ways to realize the text-to-diagram and the diagram-to-diagram. Stable Diffusion \u3010Application\u3011\u3010Line drawing\u3011: one minute to realize the picture to draw line drawing Stable Diffusion\u3010Application\u3011\u3010Line drawing\u3011: without the help of loar, one minute to realize the picture to draw line drawing The first two ways, in the realization of architectural pictures of the line drawing to draw on the performance of the performance of the picture is not very good, today specifically for architectural pictures of line drawing to share a personal practice, if you have a good idea, you can leave a message or private exchange. Transpainting to share a personal practice, if you have a good realization of the idea, you can leave a message or add micro-blogging private exchanges. I. Vincennes figure using a large model RealisticVisionV2.0 In the first Vincennes figure to realize the picture line drawing, our large model to make 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":[192,197,198,493,3970,3969],"collection":[302,262],"class_list":{"0":"post-17795","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-jiaocheng","7":"category-baike","8":"tag-prompt","9":"tag-stable-diffusion","12":"tag-3970","13":"tag-3969","14":"collection-prompt","15":"collection-stablediffusion"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/17795","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=17795"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/17795\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=17795"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=17795"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=17795"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=17795"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}