17/11/26:
Its been noted that any adult image in the gallery has been removed. That is not my doing. A moderator has confused "Cute" with "underage" (I did appeal the removal of my own images, that each had an age specified in the prompt. but by the time the appeal was heard the images were mysteriously deleted not simply hidden) That is why I haven't made a moss or qwen version. I still have yet to receive an apology for the moderators accusation. I think the age of being able to share loras without misconception is over. If anyone knows an alternative place, I am all ears.
22/09/26:
Moderators: Please note there is a difference between cute and young, ALL images created for the gallery had very specific and legal ages in the prompt. I am unsure if i want to post more lora's here after the actions of one of you that clearly failed to read the prompt.
Users: Note a moderator has locked the ability to use this lora for NSFW use, this was after they failed to read the actual prompt for an image that was a topless woman holding a sign that said "Mandatory Nude image" or something along those lines. This is not my choice, simply censorship with out logic.
Krea2 v2.0:
So yeah I trained again, same data set, though this time i redid the captions with ai tool kit's auto caption.
side note training krea2 taxes the old 3090 a lot, depressing that 24gb of vram is not really enough these days.
Ok the example images, I used a few random prompts and some of the old prompts too, the workflow embedded is a lora testing work flow i created, so may not be of use to anyone. I do have a version of this lora that did better in some cases, but this one did the best over all.
For nsfw you will want to use a nsfw check point. My training data includes a few nudes, but its more about the facial structure and shape of the woman than anything "naughty".
Use responsibly, enjoy. As always its free... as all lora's should be!
May be the start of me making more....may be a one off, lets se