Training does not require a dataset, only words. Trained in 2400 steps (about 7 hrs on 2 a6000s) using only text with: <a target="_blank" rel="ugc" href="https://github.com/ntc-ai/conceptmod">https://github.com/ntc-ai/conceptmod</a> Training prompt for the first 2000 steps: "=trending on artstation, 8k, ultra hd|boring=exciting|drab=captivating|1woman%generic woman wearing generic clothes:0.003|1woman%woman wearing many unique tasteful accessories and a cute outfit:-0.003|@monochrome--|@black and white--|@text--|@written words--"<ul><li>Pulls the unconditional towards "trending on artstation, 8k, ultra hd"</li><li><s>Replaces</s> Pulls "boring" to "exciting" and "drab" to "captivating". Update: this doesn't replace. It pulls towards. Replace needs an additional % term, see the readme.md</li><li>Reduces the occurrence of "monochrome", "black and white", "text", and "written words".</li><li>Slightly blends 1woman away from "generic woman wearing generic clothes"</li><li>Slightly blends 1woman towards "woman wearing many unique tasteful accessories and a cute outfit" Update: I think these terms might be backwards. LOL</li></ul> Training prompt for the next 400 steps: "@#|1woman=ugly manly sad wretched:-0.1|1woman=woman wearing many unique tasteful accessories and a cute outfit|nipples--:0.1|cleavage--:0.01"<ul><li>Freezes the unconditional concept using the "@#" operator.</li><li>Reduces the occurrence of "nipples" by 0.1 and "cleavage" by 0.01. </li></ul>Technique based on <a target="_blank" rel="ugc" href="https://github.com/rohitgandikota/erasing">https://github.com/rohitgandikota/erasing</a> Model based on <a target="_blank" rel="ugc" href="https://civarchive.com/models/13565/criarcys-fantasy-to-experience">https://civarchive.com/models/13565/criarcys-fantasy-to-experience</a>

Files with SHA256: ce6dc0f635d195b56045d883134cacbe9ce4393e24786feffbf0b29bffd4d135