Conflictx's picture
Update README.md
10516c3
|
raw
history blame
1.89 kB
metadata
license: creativeml-openrail-m

Textual Inversion Embedding by ConflictX For SD 2.0 trained on 768x768 images from midjourney.

It is slightly overfit on 150 steps so some concepts/keywords will be harder to prompt for but it works amazing for cityscapes, people, gods, and other scifi genres. Very stylized on ancient Egypt, scifi, and orange/blue color scheme.

Use keyword: Kipaki

00401-2324710412-a beautiful woman with a biolumenscent mask and glowing eyes,  very detailed, best quality, soft lighting, Kipaki style, very de.png

00404-3141178668-a beautiful woman with a biolumenscent mask and ((glowing eyes)),  very detailed, best quality, soft lighting, Kipaki style, ver.png

00383-4169954247-full view of star wars tie-fighter in space,  very detailed, best quality, soft lighting, Kipaki style, very detailed, intricate.png

00415-2206533630-a cozy modern interior living room, blue lighting, very detailed, best quality, soft lighting, Kipaki style, very detailed, intr.png

00427-1769024071-a woman in a cozy modern interior swimming pool, blue lighting, very detailed, best quality, soft lighting, stylized Kipaki styl.png

00414-3392484879-a rocket launching from a launch pad, blue lighting, very detailed, best quality, soft lighting, Kipaki style, very detailed, in.png