Original dataset was posted on this bounty and with the permission of AAbrains I used the dataset to make this style using 35 images for 1024 using NoobAI Epsilon-pred 1.1 as a training model

• Weight: 1-2 adjust depending on which checkpoint you use

• There aren't any recommended or trigger tags for this style

If you wanna support me or request a commission ko-fi

Additional information:

• Webui I use

• MS DPipe fp32 112k Anime VAE SDXL as VAE

• Sampling method: Euler a

• Schedule type: Align Your Steps

• Sampling steps: 24-30

• Hires steps: 12-15

• Denoising strength: 0.4

• Upscale by 1.2-2.0

• Imagine dimensions vary depending on what I'm trying to do

• I use 3 to 6 CFG Scale

• ADetailer for faces