<h1 id="bbmix-julia">BBMIX-HANNA (Semi-realstic)</h1>It is a model that can be drawn with a cute face and semi-realistic body, and it goes well with some Lora.referral prompt<ul><li>from above, from below</li><li>shiny skin, (nice leg line:1.3),thin waist</li><li>((huge breasts:1.49)) --&gt; Basically, the chest is printed small</li></ul>negative<ul><li>{1$$EasyNegative|verybadimagenegative_v1.3}</li></ul>VAE<ul><li>clearvae_main , clearvae_main2</li><li>vae-ft-mse-840000-ema-pruned</li></ul> We will continue to add sample images after finding good Loras so that we can copy and use EXIF in the sample post.<h2 id="precautions-be-sure-to-observe-this">Precautions (Be sure to observe this)</h2><ol><li>Models may not be traded or sold. Because this is free. .</li><li>Models are not available for online paid services. (Free service available)</li><li>In using the model, all responsibility lies with the user.</li></ol><h1 id="how-to-high-quality">How to high quality</h1><ol><li>You can output an image like the sample by using an extension to increase the quality. (All sample images were used with the extensions below)</li></ol><ul><li>1. Hires.fix -&gt; SwinIR_4x or R-ESRGAN 4x+ Anime6B</li><li>2. Dynamic Thresholding (CFG Scale Fix)</li><li>3. Detection Detailer (must use)</li><li>4. SD upscaler or <a target="_blank" rel="ugc" href="https://oo.pe/https://www.upscayl.org/">https://oo.pe/https://www.upscayl.org/</a></li></ul><h3 id="1hiresfix-built-in-or">1.Hires.fix ( built-in ) or</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/19b03b42-7fc2-45b6-97f9-2586f5fa353e/width=525/19b03b42-7fc2-45b6-97f9-2586f5fa353e.jpeg" /><h3 id="2-dynamic-thresholding">2. Dynamic Thresholding</h3><a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding.git">https://github.com/mcmonkeyprojects/sd-dynamic-thresholding.git</a><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a4af6e92-9d0c-4222-9131-d3445b22396f/width=525/a4af6e92-9d0c-4222-9131-d3445b22396f.jpeg" /><h3 id="3detection-detailer">3.Detection Detailer</h3><a target="_blank" rel="ugc" href="https://github.com/Bing-su/dddetailer.git">https://github.com/Bing-su/dddetailer.git</a><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6599bfa0-373f-4e9f-988e-aac60caaf6f1/width=525/6599bfa0-373f-4e9f-988e-aac60caaf6f1.jpeg" />Questions that do not use the above four cannot be answered. Please note that images printed without using the four extensions may not look good.<h1 id="tip">TIP</h1>In order to keep token 75, do not insert resolution, detail, or quality tokens. Since extension add-ons such as DD or DT handle it anyway, there is no need to insert tokens like the ones below.<h2 id="bad-prompt-do-not-use">bad prompt (do not use)</h2>Because this modelbase is a 3D and semirealistic model, it excludes the 2D highlight prompt and the flat color highlight prompt.<h1 id="notice">Notice</h1>The sample images are created with random prompts and are only examples of what these images can be generated for. Therefore, images and prompts may not match.

Files with SHA256: 28a4939d1a147cda86d6327345fd8d894931ed24f28b4e6a3d519ba8e5cf3791