Info:<ul><li>0.95-1.45 of 2.0, appears fairly consistent, (1.25 or there about's may be best), up in the higher weight mixing lora had more troubles.-Hair length doesn't always follow prompt, esp. w/ pixie or between bald and bob</li><li>Mixed bag with playing nice with other lora, results are mixed, if with one and neither is set too high mostly ok, things start to fall apart with two or more, </li><li>As for steps I'm thinking 30+, it probably is fine down to 25 over 39/40 things over-processed.</li></ul>

Baran SD1.5

f1e8b7840dfeda6719c49f41dae72000  sd.safetensors

v1.0

first time running training elsewhere and importing model.Model is dirtier cheaper version, results show it.Base models that modestly produce:<ul><li><a rel="ugc" href="https://civarchive.com/models/25694?modelVersionId=143906">epiCRealism</a></li><li><a rel="ugc" href="https://civarchive.com/models/158734?modelVersionId=674517">realspice</a></li><li><a rel="ugc" href="https://civarchive.com/models/46422?modelVersionId=274039">Juggernaut</a></li></ul>Settings:<ul><li>Lora value- 0-2.0: 1.35 has produced consistently best, higher and features look less natural, lower and consistency of features diminish.</li><li>Steps: 30-40 seems best so far, the high-end get over processed </li></ul>

Files with SHA256: 507658787698661a3a1e737953a9d28fbc6959cef9b393db26f2989d8fb868c7