Now your Z-Image's models can generate Nipples. Trained on BASE, but works also on TURBO!!!
Z-Image by default thinks that areolas are a textureless layered disk shape. Let's fix that!
Works on Turbo with 1.4 strength
I was tired of other LoRAs without the areolas textures and details. Most of the nipples I got until now using Flux was some soulless plain areolas without the depth it requires.
Then I curated a mid-size dataset with the best breasts and areolas I could find today in the internet.
Types of breasts trained: (Not trigger words, but the types of images used to train)
big areolas - Rounded medium to big areola size
dark nipples - Dark nipples with more contrast to the natural skin
ghost nipples - Pale nipples that appears slightly
long nipples - Nipples that you can bite easily
puffy nipples - Small breasts with the tip of them covered with a dense nipple
saggy breasts - breasts hanging a bit due to the gravity
small areolas - Areolas with a small radius
veiny areolas - Veins appearing under the skin
banana tits - Similar to puffy, but focused on breast shape instead of nipples only
silicone tits - The spheres from the 90s. It focuses on shape
empty tits - Similar to saggy, but empty
flat tits - Flat chested woman
oval areolas - When it's cold, the areola shape may change to oval. Good texture
bumpy areolas - When it's cold, the areola texture becomes bumpy. Good texture
wrinkled areolas - When it's cold big areolas becomes wrinkled! Good texture
Z-Image does what it wants LOL. I trained different concepts, but flux does not always follow them. Flux seems doing a breast based on the overall girl appearance, but it's possible to achieve using inpainting and some prompt engineering.
Bonus that I added in case the full body appears, to have something right down there:
hairy pussy - hairy pussy of a woman standing
shaved pussy - shaved pussy of a woman standing
Description
FAQ
Comments (5)
It looks like you have trigger words under concepts in the description. You should put your trigger words in the trigger words. There are nodes / extensions that get the trigger words from civitai and displays them so that the user does not have to remember them.
The new text encoders understands better natural language, then I train based on the prompt and not trigger words. There are no trigger words basically. Just describe the breasts you want and based on overall woman body it will do something near what you prompted.
The "concepts" are only the types of images I used to train, not that I stored those trigger words :)
Works amazing on Turbo! Thank you for the great work.
Are PussyDiffusion and Female Asshole coming too to zbase?















