Style lora based on LilAndy/Andava.

I removed all the watermarks manually from 100+ images before training, so this wont have the issue other models of the same artist have.

Depending on the model you might need to up the strength to higher than 1 numbers or use a higher cfg for the style to show properly.

Some IL models already recognize the artist artstyle, so puting "Andava" on your prompt will give you a really accurate version of the style, but will also bring back the watermark issue, so use a low strength like (andava:0.5)

I would appreciate if you could like and post your images, as that help me get more buzz to keep making more models.

Pos: (detailed background:1.1), thick outlines, outdoors, park, , (andava:0.5), BREAK (1girl, solo:1.2), (blonde hair, medium hair, curly hair , blunt bangs , yellow eyes ), standing, leaning forward, arms behind back, grin, dutch angle, skinny, narrow waist, BREAK sundress, sun hat, long dress, BREAK flat chest

Neg: bad quality, worst quality, worst detail, sketch, censor, monochrome, simple background, extra digits, long fingers, (bad hands:1.1), signature, watermark, (censored, bar censor:1.2), patreon username, patreon logo, web address, twitter username, 3d, text, dialogue box, veins, (see-through:1.2), dark-skinned male, long torso, nipples, nsfw, nude,

Guidance: 4 Steps: 30 Sampler: DPM++ 2M