Anonymous commission. Want a LoRA like this one for your favourite character or original design? Check out my Fiverr gig.

Trained on PonyXL with 36 images, mix of SFW & NSFW so this should generate both.

Trained over 514 epochs with adafactor optimizer & cosine scheduler on 4x NVIDIA Tesla P40 GPUs.

This LORA will not work with SD 1.5 or SDXL. You need to use it with PonyXL or a PonyXL-based checkpoint.

Note: This LoRA still struggles with the tail despite over 4,000 training steps. If I ran it for any more steps it started to burn really hard. This is easy to fix by either generating large batch sizes or using img2img, I think the reality is just SDXL isn't smart enough to understand the tail.

Suggested strength: 0.9

Basic prompt: alolanraichu

Other useful prompts: pokemon

For original model tag feral, for anthro/monster girl tag anthro and source_furry

Reviews are appreciated, please let me know if there's something I could improve.

Alolan Raichu is owned by The Pokémon Company, this LoRA is not suitable for commercial uses. I am not responsible for what you do with this LoRA.