>>53855534I've only used AnyOrangeMix - Anything + AbyssOrangeMix so far,
https://civitai.com/models/21503/anyorangemix-anything-abyssorangemix That's the one that seems to be most commonly
used.in Ai pictures. I might download a few more to try them but I don't want to use too much hard drive space.
>>53855537The Jasmine LoRa I've been using gets her physical traits correct the vast majority or the time without them being put in the tag. Even the outfit usually doesn't need to be specified. Though it does need a bit of coaxing in the right direction from time to time if you try to do more complex scenarios.
https://civitai.com/models/38355/pokemon-jasmineHere is the info for this one for anyone curious,
<lora:JasmineLora:0.8>, jasmine \(pokemon\), aqua dress, sailor hat, ((on a boat)), sailing, (open ocean), wind, sailboat, anchor, porthole, outdoors, water, sea
Negative prompt: (low quality, worst quality:1.4), (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit, fewer digits, (extra arms:1.2), land, beach, indoors,
Steps: 30, Sampler: Euler a, CFG scale: 12, Seed: 1465037186, Size: 512x512, Model hash: 0c365dad00, Model: anyorangemixAnything_453A1B, Version: v1.2.1
(I wish there were a way for the tags of outputs to be automatically saved with the image).
