L666 (LoRA)

This is the LoRA version of my L666 model. You have the flexibility to create lingerie-clad girls with any model you choose (though it seems to work very well with F222.)

I recommend starting with a strength of 1.0 and adjusting as needed depending on your model, prompt, etc.

This model supports most Danbooru tags related to people, women, fashion, lingerie, etc.

Recommended tags:

• Asian or European. If you specify Asian, you'll get Asian girls. If you specify European, you'll get white girls. If you don't specify either, you might get either or mixed-race girls. Although the model wasn't trained on other races, I've been able to prompt for them (i.e. black girls) but you may need to add "Asian" and/or "European" to the negative prompt for best results.

• bra, panties, underwear, etc: that's the main thing this model is trained to produce.

• good aesthetic, good quality, good blur, good noise, good contrast - Put any or all of these in your prompt if you want to the image to look better. Note: I've programmatically labeled images this way, similar to how WD1.5 was trained.

• pntyad: Some of the images were trained on lingerie/panty ads which may result in higher quality images but with a greater possibility of watermarks, text, signatures, and other artifacts appearing. Highly recommended that you add the appropriate negative prompt.

• (Negative Prompt): poor aesthetic, poor quality, poor blur, poor noise, poor contrast -Put any of these in your negative prompt if your images aren't looking as great.

• (Negative Prompt): bad-hands-5 - this textual inversion seems to work very well when you're not getting great hands.

• (Negative Prompt): bad_prompt - similarly, this textual inversion works great when you're not getting properly formed limbs.

• (Negative Prompt): text, logo, signature, username, watermark - A lot of images in the training set contained logos and watermarks so you'll want these in the negative prompt.