The samples are generated with the following negative embeddings i found here and there on the internet: bad-artist, bad-hands-5, bad-image-v2-39000, bad_prompt_version2.
Besides the trigger words, tags like "shiny_hair" or other description tags can be useful.
The models i use to generate images are: AnythingV3, abyssOrangeMix2_hard and MacaronMix_v10.

Try mixing this LORA with other characters or styles for some interesting results, as you can see in the example images!

If you like this model, consider offering me a coffee! :D https://ko-fi.com/erentil