Model trained on NoobAI-XL V-Pred-1.0 to imitate the style of Bebebe (Pepegakii)=====Support the artist: <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/2888764">https://www.pixiv.net/en/users/2888764</a>=====Their primary OC is tagged 'kousaka airi' with the mother character tagged as 'kousakamama'. Dunno how well they'll work, didn't put effort into actually training it on the characters specifically. NOTE: All the images I generate for the showcase are done with base NoobAI-XL without the use of any Adetailer or Inpainting, only Hires. fix to do 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!

Bebebe Style (NoobAI vPred)

Minor changes that improve style adherence. It does lose some detail in backgrounds and such as a trade-off (a bit overfit, but more or less intentionally). It isn't major and the first version still works perfectly well.

Bebebe_Style_V2(NoobAI).safetensors

v2.0

v1.0

Model trained on NoobAI-XL V-Pred-1.0 to imitate the style of Bebebe (Pepegakii)=====Support the artist: <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.pixiv.net/en/users/2888764">https://www.pixiv.net/en/users/2888764</a>=====Their primary OC is tagged 'kousaka airi' with the mother character tagged as 'kousakamama'. Dunno how well they'll work, didn't put effort into actually training it on the characters specifically. NOTE: All the images I generate for the showcase are done with base NoobAI-XL without the use of any Adetailer or Inpainting, only Hires. fix to do 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: ea02e0f5da08dc08bec0eb56c401cfb30d227dbcef269493044dd92e0700370c