Mika Pikazo style LoRAMaking models is expensive. Do you like what I do? Feel free to buy me a coffee ☕ A great artist. While some of her recent works are basically impossible to replicate with SD alone on the current architecture (who knows in 2.1 or later? Stay tuned for that), the lora came out good and can replicate her style pretty well, mainly for her work that have lest post processing effect and abstract coloring. I used this on Anything4.5 and AbyssOrangeMix2 at 0.65 weight. I also suggest using mika pikazo in your prompts. How to use LoRA's in auto1111: Update webui (use git pull like here or redownload it) Copy the file to stable-diffusion-webui/models/lora Select your LoRA like in this video Make sure to change the weight (by default it's :1 which is usually too high)
|