Like the work I do and want to say thanks? <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/socalguitarist">Buy me a coffee</a> or <a target="_blank" rel="ugc" href="https://www.patreon.com/user?u=33487230">Support me on Patreon for exclusive early access to my models and more!</a><a target="_blank" rel="ugc" href="https://discord.gg/SKrfwWNa9u">Join us on SCG-Playground where we have fun contests, discuss model and prompt creation, AI news and share our art to our hearts content in THE FLOOD! 💖💖💖</a><hr />This is a very rough first attempt at an anatomy model that can create semi-decent artful nude women and men. When it hits, it can be really good, even with dudes. When it misses, it can be pretty ugly. I'll be working on better versions, need to dial in training settings and get a feel for how to train flux for quality output. I'm finding that you get best results using this lora in the 0.65 to 1.2 model strength range (leaving clip strength at 1.0). keep your guidance at 3.0 and CFG at 1.0, any more than that and it will fry and get bad looking really fast. I use DEIS and ddim_uniform at 25 steps<h2 id="trigger-words:-wyyzlcs4i">trigger words:</h2> naked, naked woman, naked man with his penis outI'll be working on a few different versions of this, as the first one is a combo version, I'll release a female only/male only version in a bit, as there is some crossover from time to time, annoyingly.

SCG-Anatomy-Flux1.d - NSFW LoRA for Flux!

I am releasing 3 different checkpoints for this LoRA.3000 is more flexible and arty, lets you get more interesting styles.4000 is more strict about enforcing nudity and poses5000 is right on the edge of being overtrained. It has some pretty warm output and a lot of contrast, even when you drop guidance down super low. That said, it can really create some amazing stuff, especially if you "overdrive it" at 1.20 weight (tho it cooks the output too like this)toy around with weights and checkpoints, you're gonna get some magic and some freakshows. I'm sorry that not all of the nipples will look perfect yet, or that it will sometimes confuse bits and bobs. This model has very little nipple references and almost no genitalia references, so it's going to be some time and effort to bring this stuff back.This version now has a specific keyword that you can use to boost output, scg-anatomy-female. The lora also has a much wider variety of dataset images that provide a bit more variety in output. It's really good at nipples now, and you can bias breast sizes {small, large, huge, round, voluminous, saggy, tiny, silicon implants} breasts, boobs, tits. It also has a marginal understanding of the concepts of "vagina, anus, pussy, asshole, pubic hair" and even can give you {small, large, dark, light, pale, black, pink, puffy, erect} areolas and nipples. it can do ages young adult (I didn't test younger and you shouldn't either) to elderly, obese to rail thin, muscular to pregnant to on her knees, bent over, (lots more, have fun trying it). The list goes on.This version was trained on a little over 800 images, about 80% scraped vs 20% AI (AI was used to add racial and size variety, I was super super picky on what I used for inputs). All of the inputs were captioned first with Florence2, then hand processed to "remove the AI goofiness" and add explicit captioning to help add more natural keywording (just referring to a subject as "naked" and/or "nude" is usually enough, if you have a stubborn subject you can try describing more detailed features to bias the results).These loras are not anywhere near "explicit ready" yet, and I'm not training it with any pony style commands, no easter eggs there, sorry. It's an honest first try now that I'm starting to get a feel for how flux trains with a cleaner female gender focused train. I recommend running these loras in the 0.4 to 1.2 range. While there is the occasional body horror hiccup, 9 times out of ten if I check the same seed without the lora the problem is on base flux as well, so 🤷🏻Finally, I just want to mention that this took a lot of time and effort, especially the hand captioning work, as you really can't get ChatGPT to describe explicit material, and even the ablated VLMs suck at captioning naughty bits. I really appreciate it if you could give this a like and post some samples below. You get buzz, I get buzz, and hey, if you want to see more flux content (and I have A LOT more coming, not just nsfw stuff either) give me a follow, and if you're feeling really generous, click that coffee button and <a target="_blank" rel="ugc" href="https://buymeacoffee.com/socalguitarist">buy me a coffee</a>, the tips I earn I put right back into my creations here. 💖💖💖

Files with SHA256: a465907f81a562013aa3372dd48bbcdf198353c34c8f7c0fd03ef342c51fa30a