This LoRA works better for INPAINT, but it does a good job on txt2img too. May break sometimes.

The Innie Shaved lora may not work properly ... but it is what it is.

The Piercing lora may lose definition and shape at distance... It's far from perfect.

Types of trained on General: (Not trigger words, but the types of images used to train)

• bush - / with hair on top / landing strip
• with lips that resembles butterfly- / with big lips
• hairy - Hairy /, simple as that
• - /, in the style of (innie)
• with dark lips - Dark lips / on a white skin woman
• pink - Pink delicate /

Adding "showing her from the back" or something similar to show a rear view may work, as I trained rear view too for every trigger above. I may need to train another one focused on rear view to improve this.

You can combine more than one. Inpainting them to improve the result is a good option.