Let me start off by saying I'd really appreciate a like and follow, if possible. It would help a lot for me to make even better models in the future.
Read the following for a better idea how to use this LoRA:
Don't forget to use the trigger words.
Start using the LoRA at 0.75 - 0.80 strength.
Landscape resolutions are recommended (1216 x 832). Very consistent at 0.8 strength and 1216 x 832. Maybe better retention of model style at 0.7-0.75.
My prompts for the showcase won't work as I have used three different prompt descriptions for 33% of the image individually using my ComfyUI node. (Basic Regional Prompting).
To achieve results similar to to the ones I created for the showcase, you need some implementation of a regional prompting system. (I use ComfyUI and some nodes I forked and modified from ComfyCouple node). I divide the image into three regions and define the character for each region separately. For A1111/Forge, there are extensions for regional prompting easily available. Perhaps inpainting would also work.
If you use the LoRA as is, you will still get three girls without any form of regional prompting, but it is very difficult to prompt each character without bleeding their features into each other.
This LoRA allows for ****, vaginal, and variations of poses for each girl (Front/Back) if you can specify each part using a regional prompting method. Otherwise, it will be random if not specified. You can experiment with prompting to get different variations.
Feel free to discuss any doubts in the comments!
If you want to support more models like this, or you just like what you see: ko-fi (｡♥‿♥｡)
Also, I don't plan on charging buzz for my LoRAs. So, I'd really appreciate if by any chance you could tip the model.