[Experimental!!! Read Problems section to see limitations]

If you have problems with this check out this alternative by @Gentlemanbunny : https://civarchive.com/models/772191/blacked-bleached-whatever-underwear-read-description

Generate Images of women wearing BLEACHED underwear.

Ask Flux for 'woman/character wearing BleachedWear' and maybe 'wearing underwear that says "Bleached" on it'.

V3 Update:

• less nipples

• can now do black or white underwear

• higher lora rank => higher file size (not sure this actually helped that much)

• text garbled at the edges quite often

• plays nice with some loras and absolutely not with others, not sure what thats about

Have fun!

Problems:

1. Nipples poking through: You might have noticed the nipples staring at you, this is consistently a problem.

   Solution: There is a lot of uncaptioned nipple poking in the dataset, captioning that and retraining should fix it.

2. Style Control: The LoRA overwhelmingly tends towards a 3d render faux realism. This is because the majority of the dataset is in that style.

   Solution: ¯\_(ツ)_/¯ availability of other images is limited, i'll see what i can do. V3 somewhat more flexible, but not that much

3. Text quality: It's hit or miss. Adding 'wearing underwear that says "Bleached" on it' to the prompt seems to help. Maybe try higher step counts.

   Solution: ¯\_(ツ)_/¯ I can try: a higher Rank LoRa, training at a higher resolution (currently 512x512), Longer Training. All of these require more GPU time, and I am not made of VRAM.