<h2 id="the-refiner-upscaler-version-is-not-intended-for-direct-txt-2-img-use-if-you-use-it-here-you-will-be-disappointed.-0o9q84cgh">THE REFINER UPSCALER VERSION IS NOT INTENDED FOR DIRECT TXT-2-IMG USE -- IF YOU USE IT HERE YOU WILL BE DISAPPOINTED.</h2>I've left it enabled if people want to experiment with combining it with other NSFW loras, but don't complain that it doesn't work if you didn't read this. It was trained to upscale only.DIFFERENT VERSIONS - click on version names above to view:<ul><li>FLUX NSFW Refiner Upscaler - Us with a img2img workflow (not here...)!!!!NOT INTENDED FOR DIRECT TXT2IMG USE!!!!! - The closest thing to a 'NSFW Unlock' I'm going to be willing to make. It took a good while to get working. It's not great for direct use, It's meant to be used with the workflow.workflow here: <a target="_blank" rel="ugc" href="https://civarchive.com/models/968235?modelVersionId=1084090">https://civarchive.com/models/968235?modelVersionId=1084090</a></li><li>HANDSFREEBJ - baked scene, one keyword: handsfreebj 3.5 guidance/20-35 steps/832x1216 size/deis sampler/simple scheduler</li><li>WOMAN-FRONT-NSFW</li><li>WOMAN-BACK-NSFW</li><li>TGIRL FRONT NSFW</li></ul>Training flux for nsfw is tricky, for small scale training, it was having trouble distinguishing between front and back, so I separated nude images of women from the front and back into separate loras and got some great results. I also did a set of futa images as well (best from the front). I've not had good luck mixing them into the same image (for the same reason I trained them separately in the first place I'm guessing...) Datasets were 600-1000 images, training was on a runpod H100 for over 10k steps on each.

FLUX NSFW (Pony-inspired)

flux-nsfw-refiner-upscaler-lora.safetensors

RefineUpscale-NOT-TXT2IMG

Files with SHA256: 5a6638e071933beee93e939fd8d7412b28a2b894efb406d1847475c9b37fc852