This is a merge of some of the best (in my opinion) models on Civitai, with some loras, and a touch of magic. 🪄😏Some of the images were generated with 1 clip skip<h3 id="heading-126">Recommended settings:</h3><ul><li>Sampler: DPM++ 2M SDE or 3M SDE or 2M with Karras or Exponential</li><li>CFG: 5 - 8</li><li>Steps: 30+</li></ul><h3 id="heading-127">Some of the checkpoints I merged:</h3><ul><li>AlbedoBase XL</li><li>⋅ ⊣ Realities Edge XL ⊢ ⋅</li><li>Realistic Freedom - SFW and NSFW</li><li>Explicit Freedom - NSFW Waifu</li><li>Colossus Project XL</li><li>WoW_XL</li></ul><h3 id="heading-128">Some of the loras I merged:</h3><ul><li>LUT Diffusion XL</li><li>DetailedEyes_XL</li><li>NSFW POV All In One SDXL</li><li>Envy Cute XL 04</li><li>Perfect Eyes XL</li></ul>🪄 The final touch of magic is that I used multiple "bad loras" with negative strength to push the model toward greater "goodness".

Better than words

Improvements:<ul><li>Even better NSFW</li><li>Even better human anatomy</li><li>More stable, at least for portraits</li><li>Better image quality</li><li>No more plastic look which often happened with long prompts</li></ul>After days of concentrated effort and several setbacks, I finally noticed substantial improvements. I made an entirely new merge, merged it with v1.5, added loras, and stabilized it by merging it once again with v1.5.This version would be labeled as v3.2 if I uploaded all the versions in between 😎

Files with SHA256: 620a5cd2ff1a3aec1141ba7b83697a78593119cd5c66f56b6685960b59b1552c