temp testing how model works from received file, will change description as more is known. Anyways...So far on the little testing I've done: (&lt;10 generations here, about ~50 elsewhere)<ul><li>0.65-1.35 of 2.0, appears fairly consistent, though weighting seems more sensitive here. (1.15 or there about's may be best?), up in the higher weight mixing lora had more troubles.<ol><li>Hair length doesn't always follow prompt, hair color seems okay, a few miss-steps</li><li>need to explore facial gesture/expression some, I've added some to prompts and they have somewhat held; they weren't set in the trigger words, but captions may have caught the expressiveness.</li></ol></li><li>Mixed bag with playing nice with other lora, results are passable or mostly passable if with one and neither is set too high, things start to fall apart with two or more, though it is probably problematic images in the other sets.<ol><li>Problems seen with multi-mixing: (fur-ish blobs, unusual textures, but mainly resolution reductions and disfiguring of face and hands/feet, arms and torsos less so.</li><li>Interesting to see if adding with other racial or nationality lora work and the weightings.</li></ol></li><li>As for steps I'm thinking 30+, it probably is fine down to 20, over 42/44 things over-processed. I haven't tested using the same seeds to verify.</li></ul>

Files with SHA256: 559e5313f7a45c86817a73af3b6f10dad37304f3c18ae202bed7ef8a0fd2bbff