Nora from Storybooth. Commission. This model seems a little less stable than others I have produced (despite my efforts to make it more stable). NOTE: I strongly recommend using Negative embeddings CyberRealistic Negative-neg (Pony), bad-hands-5, (or Negative Hand beware of aesthetic style changing when used), and Deep Negative XL (beware of aesthetic style changing when used). This produces significantly improved images in my experience.

Suggested weight: 0.85 ~ 1.0. Value of 1.0 will be very cartoony, whereas lower values will relax and allow for other styles to be applied. I find value 0.9 to best.

HiRes Fix is NOT required, but it will make your images look nice, if you don't use too much denoise. Suggested denoise 0.22 to 0.33 but sometimes 0.7 works depending on the image.

Trigger Words (Activation)

• Nora_Storybooth, blonde hair, medium hair, freckles, black eyes, 1girl,

Extras (Strongly recommended)

• CyberRealistic Negative-neg (Pony)

• bad-hands-5, (or Negative Hand beware of aesthetic style changing when used)

• Deep Negative XL (beware of aesthetic style changing when used)

Checkpoints

Best results tested so far used checkpoints like:

• Pony V6

• Toonify

• Autism SDXL

Tested with other LoRAs

I tested this LoRA model with several other LoRAs, including the following (many all at once):

Deep Negative XL

CyberRealistic Negative (yes, even the version from SD1.5) works quite well.

ExpressiveH (Hentai LoRa Style) エロアニメ: This works, but try lower values since it might distort facial expressions.

Detail Tweaker XL

Negative Hand

NeoLight

Image Resolutions

Make your resolution images at (or larger than) 720x720 to get better results. For example, suggested image resolution is 832x1216. HiRes Fix not required but can improve image quality, usually with a 0.3 to 0.4 denoise is safe, but you can experiment higher.