LoRA for Illustrious generating in the style of doujinshi artist Puranpuman
Anima
Make sure to use keyword @Puranpuman
Tested on turbo and hires loras and without them.
Tested on natural language, CLIP styled prompts and mix of them.
All of examples are made between 0.8 and 1.
If you are using it without turbo lora add "whit borders" to the neg, it was trained on multiple images with that tag.
Quality tags masterpiece, best quality, score_7 and such are important.
Illustrious
Make sure to use keyword puranpuman_style
Made compatible with Illustrious 1.0 still works with 0.1
Works with strength between 0.7-1, 1 can be glitchy depending on complexity of the prompt. All of examples are made in 0.9, you need to be specific about the scene.