This Lora basically adds sex between women and various monsters, demons, and aliens to "regular" (meaning ones NOT based on Pony) SDXL models. The list of trigger tags I've provided is by no means exhaustive, it's just the ones I feel are most important in terms of direct prompt composition.
This Lora works tends to work best if you use the relevant tag words within the context of fully formed sentences. You can refer to my sample images to get some ideas on possible ways the Lora can be prompted. It's possible there may be some photorealistic-leaning models that prefer traditional tag prompting though, so feel free to experiment.
Recommended strength is around 0.6 to 0.8, but feel free to experiment as you see fit. (1.0 is almost always clearly too high though per my testing, and 0.5 while sometimes ok tends to be not quite enough).
Do not use this Lora with the checkpoint bigASP, as it is a heavy enough finetune diverging enough from Base SDXL that I already previously released a similar Lora specifically for it (called "Enhanced Unrealistic Concepts For bigASP").
Description
Initial version. Uses exactly the same dataset as V2 of the Flux version. Trained onsite at Rank 32 / native 1024px. All dataset images were ~1.5x higher resolution to begin with than their intended output "bucket" resolution (that is, 1536x1536 for 1024x1024, 1856x1280 for 1216x832, and 1280x1856 for 832x1216). All three standard XL / Flux aspect ratios (what the CivitAI generator calls square, landscape, and portrait) are directly supported by the Lora.