So, today I celebrate the publication of my 250th model, Emma.
Emma was trained, like all my MXAI models, entirely on prompted images.

Because a lot of people have asked me, with tears in their eyes, big, manly nerds who have never cried in their lives (in the Trumpian sense), to share my prompts, here it is.

The prompt I used for the training material plus wildcards, is as follows:

"RAW photo, 1girl, 20 years old, \"Emma Masters\", (American:0.7, Danish:0.3), cute, huge eyes, \"breasts too big for her frame\", fresh-faced-teen, round rosy cheeks, voluminous wavy glamorous platinum blonde hair, huge green eyes, tan skin, magazine ready pose, close-up portrait, detailed high contrast background, bright vivid high contrast colours, <lora:breasts_slider_v2:1>, (((Ultra-HD-details, Ultra-HD-detailed, Ultra-HD-realistic, Ultra-HD-photo-same-realistic-quality-details))), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, SK_CINEMATIC, ziprealism",

Negative Template: "cleft chin, watermark, logo, (hands:1,3), (((asymmetry, asymmetrical-shapes, snap-fingers, HD-logo, unprofessional-bodies, grey-in-grey, bulging-fingers, elongated, unprofessional-joints, far-away-ugliness))) , perfect skin, (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), ziprealism_neg, BeyondSDXLv3",