Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
First LoRA I make for SDXL0.9, but works perfectly on XL1.0.
This should be used with Anime Art Diffusion XL (that's neutral enough) at around 0.65-0.9 weight. Trigger is arcane
.
Allow me to remind this is not a character LoRA (I didn't tag characters in the dataset). Still, as you can see, it can get pretty close to the original characters with accurate prompting. Comfy workflows are embedded in the images.
Please enjoy.