MUSTAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAARRRRRRRD<h3 id="if-you-like-it-consider-buying-me-a-coffee-i'm-poor.-qb49tbeab">If you like it, consider buying me a <a target="_blank" rel="ugc" href="https://ko-fi.com/meghanmild">coffee</a>, I'm poor.</h3><h3 id="a-few-details:-lzp1be8js"> A few details:</h3>It was trained on Stable Diffusion 1.5 as a base model, so it might work on most checkpoints without many alterations, my favorite checkpoint for this was <a target="_blank" rel="ugc" href="https://civarchive.com/models/462367/real-dream-legacy-sd15">Real Dream Legacy SD1.5</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/139300/realistic-digital-genius">RealisticDigital</a> produces some good results too. Generation parameters:Clip Skip: 2 Best weight: 0.95Sampler: DPM++ 2M Automatic/Karras, 35 stepsAdetailer: mediapipe_face_full, mediapipe_face_mesh_eyes_only, hand_yolov, all with detection at 0.85HiResfix: 2x, denoise 0.25, steps 15, using <a target="_blank" rel="ugc" href="https://huggingface.co/gemasai/4x_NMKD-Siax_200k">4x_NMKD-Siax_200k</a> as upscaler.img2img (optional but it'll yeld the best results)Just rescale,Ultimate SD upscale: 2x, using 4x NMKD as well, no types. I realized now that it'd be better to share the entire process of what do I do to achieve my results.

Files with SHA256: 787ecf6eb018250b5732e069867bf39b968d353b5ce30e511d4c3b6909dd009a