Sign In

Tsuda Nanafushi Style

117
735
4
Updated: Oct 5, 2024
stylefemale
Verified:
SafeTensor
Type
LoRA
Stats
735
Reviews
Published
Jun 3, 2023
Base Model
Other
Hash
AutoV2
B2E5E81B68
default creator card background decoration
AnyKey's Avatar
AnyKey

A colorful drawing style LoRA.

How to use
Prompt as usual, dataset contains a wide mix of females mainly biased towards fit, curvy, busty characters with some animal girls sprinkled in.
The artist really likes drawing blushing and sweaty women so you may need to put either or both in negatives if it's too pronounced.
For users of AOM2 or other models with photorealism in it I highly recommend using "3D" and/or "realistic" in negatives. DIMM and DPM++ 2M Karras will recreate the drawing style closer while Euler A gives a more "clean" look.

Don't forget to review and upload your own images, it's always fun to see what you're creating!
Like my LoRAs and want more? Please consider a small tip towards my electricity bill and further training >.<

Misc
Dataset of 370 all manually cleaned and processed. 512 resolution trained on NAI without noise offset option for best LoRA compatibility.
All images are raw txt2img upscaled without any helper embeddings.