Model trained on NoobAI-XL V-Pred-1.0 to imitate the style of Okura-chan (@nya5)Starting with this model, I'm going to try and show these style LORAs in an even more raw and accurate form by excluding almost all quality tags (such as "very awa" and "masterpiece") from the prompts and just getting it as a baseline. As a result, they may, once again, not look nearly as good as the generations you can get with the LORA, but they will be a more accurate representation of its usual tendencies (and I've found, if I did everything else right, the quality tags are often not needed anyway).=====Support the artist: <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/75618515">https://www.pixiv.net/en/users/75618515</a>=====NOTE: All the images I generate for the showcase are done with base NoobAI-XL without the use of any quality tags, Adetailer, or Inpainting, only Hires. fix to do very basic upscaling. My results do not look as good as you can get quite easily with more stylized checkpoints or better finetuning, but I wanted to show the baseline (and that the LORA works). Try out what works best for you!

Files with SHA256: db041537809a14c52869c661dfb44832aca6fcf7bed03b8dcf53273abddf399d