<h1>READ THE DESCRIPTION</h1><p><br />Do not download LoRa (NOT NECESSARY)<br /><br /><br />This is a simple and powerful tutorial, I uploaded a LORA file because it was mandatory to upload something, it has nothing to do with the tutorial. Tribute and credit to <a target="_blank" rel="ugc" href="https://github.com/hnmr293/sd-webui-cutoff">hnmr293</a>.</p><h2><br />Step 1: Install this <a target="_blank" rel="ugc" href="https://github.com/hnmr293/sd-webui-cutoff">extension</a><br /></h2><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/998e8f16-41dc-4493-e59d-1621aab10d00/width=525/998e8f16-41dc-4493-e59d-1621aab10d00" /><h2>Step 2: Restart Stable Diffusion (close and open)</h2><h2><br />Step 3: Enable Cutoff (in txt2img under controlnet or additional network)<br /></h2><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3a8d91bf-84e1-4cfc-3432-83b81b07cc00/width=525/3a8d91bf-84e1-4cfc-3432-83b81b07cc00" /><p></p><h2>Step 4: Put in positive prompt: <strong><em>a cute girl, white shirt with green tie, red shoes, blue hair, yellow eyes, pink skirt</em></strong></h2><h2><br />Step 5: Put in negative prompt: <strong><em>(low quality, worst quality:1.4), nsfw</em></strong></h2><p></p><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2ccda179-bfd6-410c-6862-41518dacd700/width=525/2ccda179-bfd6-410c-6862-41518dacd700" /><h2><br />Step 6: Put in Target tokens (Cutoff): <em>white, green, red, blue, yellow, pink</em><br /><br />Step 7: Put 2 of weight. Leave everything else as the image.<br /></h2><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9c85be1e-71a9-4206-b6bf-c384eae4fb00/width=525/9c85be1e-71a9-4206-b6bf-c384eae4fb00" /><p></p><p>Tips:<br /><br />0# Give priority to colors, first them and then everything else, 1girl, masterpiece... but without going overboard, remember tip #3<br /></p><p>1# The last Token of Target Token must have "," like this: white, green, red, blue, yellow, pink, <a target="_blank" rel="ugc" href="https://www.bing.com/ck/a?!&amp;&amp;p=02e0f5d8a419ac99JmltdHM9MTY3ODU3OTIwMCZpZ3VpZD0zMzY1NjM0Ny05YWUyLTY0MWMtM2NlZC03MTIwOWI4ZTY1YTAmaW5zaWQ9NTMxMQ&amp;ptn=3&amp;hsh=3&amp;fclid=33656347-9ae2-641c-3ced-71209b8e65a0&amp;psq=mano+apuntando+emoji&amp;u=a1aHR0cHM6Ly9lbW9qaXRlcnJhLmNvbS9lcy9pbmRpY2UtaGFjaWEtaXpxdWllcmRhLw&amp;ntb=1">👈 </a><strong>ATTENTION:</strong> For some people it works to put a comma at the end of the token, for others this gives an error. If you see that it has an error, delete it.<br /></p><p>2# The color should always come before the clothes. Not knowing much English happened to me that I put the colors after the clothes or the eyes and the changes were not applied to me.<br /><br />3# Do not go over 75 token. It is a problem if they go to 150 or 200 tokens.<br /><br />4# If you don't put any negative prompt, it can give an error.<br /><br />5# Do not use token weights below 1 eg: (red hoddie:0.5)<br /><br />20 images were always worked on and in most of the tests it was 100%. If they put, for example, green pants, some jean pants (blue) can appear, also with the skirts a black skirt can appear. These "mistakes" can happen.<br /></p><p>That's why I put 95% in the title because 1 or 2 images out of 20 images may appear with this error.</p>

Files with SHA256: c9bf7fada8ee21ee2136f217597003595b04f8680c830d699a3f4e1a30e0852a