IF YOU ARE USING THE NEW BETA GIVE ME FEEDBACK, YOU HEATHANS!
Seriously though, lemme know what's working and what isn't! Also, get a little creative, there is new stuff in the training data. ;) Beta 2 is coming soon, and it's going to have EVEN MORE surprises! Also, send me your photos! IDC if you don't post them here, just send em to me so I can see how it's working with different workflows!
INTRODUCING SEND NUDES V4.1
Welcome to SEND NUDES 4.1, with better prompt adherence, better body shapes, higher resolution training data, and finally, better genitalia.
When I first started working with Flux, my only real goal was to fix the tragic meat button nipples that Flux was infamous for. I am a tattoo artist, and use AI for rapid model prototyping. It's so much faster to get a pose by typing in what I want rather than posing a model in an app. I had created a LoRA called "JUST THE TITS" to remedy the issue, but it soon started to bother me that the output still had Barbie doll parts and that cleft chin. Enter "SEND NUDES" my attempt to rectify those issues. For some reason, female genitalia was a lot harder to train than one would expect, but I think I've got it this time.
SEND NUDES is NOT trained on XXX and will NOT give you all that "Pony Penetration" a lot of you are looking for, but it WILL cut some nice figures for you.
SEND NUDES PRO is a new evolution of this project. The plan is creating the concise dataset needed to properly finetune QWEN into a much better anatomical checkpoint. As the LoRA progresses and my training data becomes more complete, I get closer and closer to being ready for a full finetune. Your tips help me create some of the best and cleanest tunes, thank you for your help!
THANK YOU to all of the BUZZ supporters and LoRA testers that have helped me work on this project, I could not have gotten this far without you!
[QWEN] This lora works well from 0.2 to 1.0 depending on what you need.
[FLUX] This LoRA works well from strength 0.6 to 1.0, but I find 0.8 to give me the most reliable results. YMMV
You can find "REALWOMEN" here"
https://civarchive.com/models/826002/realwomen
You can find "JUST THE TITS" here:
https://civarchive.com/models/708319
Thank you for all the BUZZ and support!
Description
Testing CivitAI lora creation with a slightly updated dataset. After a fair amount of testing, I'll be training on CivitAI from here on out. My results simply have better output, soooo if yall dig the work, buzz me. Civit costs more than my previous service, so dono's are certainly appreciated.
FAQ
Comments (10)
I seem to get better results running this locally. The on-site results render way more "weird nipples" But, thanks I'll keep using this.šš
Do me a favor and try 2.1, it was trained on Civit and should yield better results. Also, I found that prompting 'erect nipples' reduces that possibility. I think I need to add some specific nipple types to the training data.
Also, out of curiousity, what is your workflow locally?
Yeah, what stuff are you using? I still get weird nipples pretty often. And I got the same weird nipples even without this Lora. Seems like I just forget to turn it on :D But of course it's enabled, I know how to use loras. I'll try new versions.
@MisterGachiMuchiĀ If you look at his other post, he's using "Erect Nipples" in the prompt to bypass and it clears that issue right up.
@ColdNorthMenaceĀ thanks! I tried this key many times, but I'll try it with upper cases one thousand times more :)
@MisterGachiMuchiĀ are you using both "SendNudes" and "Erect Nipples" and keep your LoRA weight at .8
@ColdNorthMenaceĀ yeah, and tried many combinations of them. But you know what? I tried last version of SendNudes and last 20 pictures were with normal nipples! So I guess it works right now. Thanks for your help and thanks for your work again.
Could you (if it's possible) in the future make your Lora not to change girls' faces? I mean, in original Flux girls can be pretty realistic, with a lot of facial details. But with your Lora they're turning in Playboy models with tones of photoshop and kind of blurry faces :) That's alright, that's having a right to be, but who knows maybe you can do something about this in the future...
@MisterGachiMuchiĀ Ill do what I can!
here are some test images I did on-site running v2.1
https://civitai.com/posts/7417354
https://civitai.com/posts/7417121
these are with V 2.0 locally on my PC
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.