Thank you for the kind words!
I try to keep the consistency, I use a local installation of Stable Diffusion.
I don't have big tricks, I just start with a general description of the character, trying to add some distinctive elements (like the hair color or some face shapes), and then, after having the base, I use the img2img tool.
That lets me keep a level of resemblance with the base image, and after manually checking each of the outputs, I can reach a good enough result.
I only use Lora's for concepts like the leaf clothing, sometimes I use one to make better muscles or for some special poses.
I can't give you exact names, but you can find Lora's for almost anything in Civitai, for free!