Merge of different models/LoRAs I've used and enjoyed previously.This merge is created with the primary goal of generating pretty ladies in NSFW situations, but should be flexible enough for other themes due to the strength of the base models used.Resources Used:<a rel="ugc" href="https://civarchive.com/models/25831/sxz-luma">SXZ Luma</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/95086?modelVersionId=101451">ForgottenMix - Animation</a><a rel="ugc" href="https://civarchive.com/models/116788?modelVersionId=149612">thepit LoRA</a>Images generated using <a target="_blank" rel="ugc" href="https://huggingface.co/AIARTCHAN/aichan_blend/blob/main/vae/Berry's%20Mix.vae.safetensors">Berry's Mix VAE</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/konohashinobi4/4xAnimesharp/blob/main/4x-AnimeSharp.pth">4X AnimeSharp Upscaler </a>at Clip Skip 2My typical settings for images:<ul><li>Sampler - DPM++ SDE (recommend playing around with this)</li><li>Sampling Steps - 35 to 40</li><li>HiRex Fix - Upscaled by 2 at 15 to 20 steps, 0.35 Denoising Strength</li><li>Dimensions - 512x512, 512x768, or 768x512</li><li>CFG Scale - 5.5 to 7</li><li>ADetailer for eyes/hands<ul><li>ADetailer does a lot of work here</li></ul></li></ul>See images for examples of how I prompt. There is probably a lot of room for flexibility/improvement hereAll credit goes to the original model authors, please check them out.

Files with SHA256: beac2c31d929be99e7d61e6fd2438bc3121de33dd01427c5b66486c4e7c83e9c