{"id":17678,"date":"2024-08-10T10:19:32","date_gmt":"2024-08-10T02:19:32","guid":{"rendered":"https:\/\/www.1ai.net\/?p=17678"},"modified":"2024-08-10T10:19:32","modified_gmt":"2024-08-10T02:19:32","slug":"ai%e7%bb%98%e7%94%bb%e6%89%8b%e7%bb%98%e7%a8%bf%e5%bf%ab%e9%80%9f%e7%94%9f%e6%88%90%ef%bc%8c%e7%94%a8stable-diffusion%e5%b0%86%e5%9b%be%e7%89%87%e8%bd%ac%e6%88%90%e7%ba%bf%e7%a8%bf","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/17678.html","title":{"rendered":"AI painting hand-drawn drafts are quickly generated, and stable diffusion is used to convert images into line drafts"},"content":{"rendered":"

In the previous article, I shared with you how to convert line drawings of pictures into Wensheng drawings.<\/p>\n

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

The conversion of image to line drawing can also be achieved by using the method of image generation. Let's first look at the effect of using the method of image generation to convert image to line drawing.<\/p>\n

1. How to convert pictures into line drawings<\/strong><\/p>\n

[Step 1] Upload the raw image with white background<\/strong><\/p>\n

Here we use Meitu XiuXiu to create a pure white background image. Upload this white background image in the Image Generator menu.<\/p>\n

\"\"<\/div>\n

[Step 2]: Selection of large model<\/strong><\/p>\n

Recommended here: majicMIX realistic V7.<\/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\/bced6d7ec1460ac7b923fc5bc95c4540<\/p>\n<\/blockquote>\n

Step 3:Prompt word<\/a>Writing<\/strong><\/p>\n

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

\n

Prompt<\/strong>\uff1alineart,line drawing,sketching,blank and white,clean white background,masterpiece,best quality,fine detail,8K,UHD,wallpaper,<\/p>\n

Prompt word<\/strong>: line art, line drawing, sketch, blank and white, 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: 20<\/li>\n
  • Image width and height: 512*768 (same as the original image to be transferred)<\/li>\n
  • Prompt word guidance coefficient (CFG): 7<\/li>\n
  • Redraw amplitude: 0.75<\/li>\n<\/ul>\n

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

    \"\"<\/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: 1<\/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
      \"ac19de46j00shzct60013d000e800lcm\"<\/div>\n<\/td>\n
      		\n
      \"0f4905c7j00shzct60013d000e800lcm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      2. Related comparison<\/strong><\/p>\n

      (1) The image generation method does not need to use the loar model of the line drawing type. I have tried using lora Anime Lineart\/Manga-like, and I personally feel that the effect is not very good. However, different people may have different opinions. You can refer to the following pictures for comparison.<\/p>\n\n\n\n\n
      \n

      No loar used<\/strong><\/p>\n<\/td>\n

      		\n

      Use loar<\/strong><\/p>\n<\/td>\n<\/tr>\n

      \n
      \"0f4905c7j00shzct60013d000e800lcm\"<\/div>\n<\/td>\n
      		\n
      \"6d8919cej00shzct6001gd000e800lcm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      (2) According to current tests, the effect of transferring real-life pictures is relatively good. However, when transferring line drawings of architectural pictures, the lines are very thin, which makes the pictures look unclear.<\/p>\n\n\n\n
      \n
      \"30c65097j00shzct7005jd000sg00sgm\"<\/div>\n<\/td>\n
      		\n
      \"6970f798j00shzct70029d000sg00sgm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      After adding the AnimeLineart\/Manga-like loar, the image clarity has improved. However, there is still room for optimization and improvement in the architectural re-drawing.<\/p>\n\n\n\n\n
      \n

      No loar used<\/strong><\/p>\n<\/td>\n

      		\n

      Use loar<\/strong><\/p>\n<\/td>\n<\/tr>\n

      \n
      \"b46bd549j00shzct7001zd000sg00sgm\"<\/div>\n<\/td>\n
      		\n
      \"a038b504j00shzct70033d000sg00sgm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      (3) I personally feel that the method of realizing the picture-based drawing is better than the method of realizing the text-based drawing. The lines are clearer and simpler, and the line drawing effect is more realistic.<\/p>\n\n\n\n\n
      \n

      Vincent Figure<\/strong><\/p>\n<\/td>\n

      		\n

      Figure 1<\/strong><\/p>\n<\/td>\n<\/tr>\n

      \n
      \"75b373a5j00shzct6001fd000e800lcm\"<\/div>\n<\/td>\n
      		\n
      \"0f4905c7j00shzct60013d000e800lcm\"<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\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>\n

       <\/p>","protected":false},"excerpt":{"rendered":"

      The previous article shared with you the way to realize the image line drawing transcription of the text born map. Stable Diffusion \u3010Application\u3011\u3010Line drawing\u3011: one minute to realize the picture to draw line drawing Picture line drawing can also be realized using the way of the graph to achieve. Let's take a look at the effect of using the graph to realize the picture to line drawing. I. Picture to line drawing production method [Step 1] Tugraphics white base image upload Here we use the beauty of the show to create a pure white background of the base image. Upload this white background image in the Tupelo function menu. Step 2: Select a large model Here we recommend the use of: majicMIX realistic MAGICMIX Realistic V7. Model download address (the end of the article can also get the address of the network disk) LiblibAI.<\/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":[491,197,198,837],"collection":[302,262],"class_list":{"0":"post-17678","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-jiaocheng","7":"category-baike","8":"tag-ai","9":"tag-stable-diffusion","11":"tag-837","12":"collection-prompt","13":"collection-stablediffusion"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/17678","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=17678"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/17678\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=17678"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=17678"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=17678"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=17678"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}