<h3 id="heading-83">This a merge between Darksushi and Maijikmix realistic. </h3>you can make anime to realistic portraits and much moreOriginal Models credits goes to <a target="_blank" rel="ugc" href="https://civarchive.com/models/24779/dark-sushi-mix-mix">https://civarchive.com/models/24779/dark-sushi-mix-mix</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/43331?modelVersionId=176425">https://civarchive.com/models/43331?modelVersionId=176425</a> you can check images for generation prompts.<h3 id="heading-15">Recommended settings</h3>Sampling steps: 15-30 (Only use more steps as a last resort for very complex images, as an excessive number of steps tends to ruin the image)CFG Scale: 5-12<h3 id="heading-84">Optional settings</h3>Hires. FixUpscaler: 4x-UltraSharpHires Steps: 15-20Denoising Strength: 0,20-0,40 (The more force, the cleaner the image, but the more the original quality is lost.)Upscale By: 1,5 - 2,0<h3 id="heading-85">Must use adetailer for better faces</h3>Adetailer:Adetailer Model: face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a>Inpaint denoising strength: 0,25 - 0,40ADetailer steps: 15 - 20it works with most of the portraits &amp; dress Lora's. just need to tweak Lora's settings and you're good to go.<h2 id="heading-86">some notes about myself:</h2>I am new to stable diffusion and Civitai so I don't know much about it I am just using my mid-end PC to generate images. which has an AMD card and it did not support stable diffusion so I had to make it with CPU only. which took 45 min to 1 hour for a single image. I want to create my own checkpoint in the future. So I need support from the community. it's all on you if you want to help. it will be a huge support. thank you guys.and enjoy.support here if you want: <a target="_blank" rel="ugc" href="https://ko-fi.com/showywharf">https://ko-fi.com/showywharf</a>

Files with SHA256: 45bc1050b682da9b34e01469d1c6bb0631e3ab984f300b61002a432522afbc65