AIイラストおじさん

Version 2.1 aims to adapt to different types of styles, which are not compatible with 3D and realistic.main compatibility: WAI-NSFW-illustrious-SDXLRecommended CFG Scale: 3.0 - 9.0Recommended sampler: Euler a for softer tone and DPM++ 2M Karras for stronger or heavier tones.Steps will depend: 24 - 50 LoRA tries to maintain quality.recommendations for a well-defined image: request Priorit - high +10 or higher.upscale: the recommended option is Hi-res fix - between - 0.35 and 0.55 (higher ones will make the image more diverse and strange), second option if the image is good (if the eyes are not deformed), Face fix - between - 0.45 and 0.80parameters to be placed:DO NOT ADD "UNCENSORED" IN THE PROMPT, CHOOSE TO PUT "mosaic censoring" in the negative prompt!In case of adding many LoRAs, it is believed that this LoRA will become unstable due to its high definition and configurations.This LoRA generates high resolution images, so spending more Buzz is the best option for an excellent image!If you have any doubts or find faults, report them immediately! (warning: Version 2.1 uses another user's style. V2.5 will be in progress if V2.1 is too glitchy)