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
Refined breast/nipple dataset
FAQ
Comments (17)
I'm not convinced (sn4). It also changes face of my lora.
Yep. It's trained on faces to remove that single same face that Flux is trained on. I am willing to bet it will do it with any lora trained on faces. The previous models don't have much for any facial training like this iteration does. Stick with 2.1 for no facial training.
@ColdNorthMenace please remove face training in your data sets. we all have other loras we use (flux_realism, amateur_photograph, characters, etc) for faces. focus on nudes and stop messing with faces.
@psspsspsspssspss I do not think I will be doing that. This model is not for nudes of specific people, it isn't meant to create celebrity nudes. Plain and simple. 2.1 still works incredibly well, so if you enjoy the model without facial training, you may use that one. I will not, however, have ANYONE tell me what I can and can not do with my art.
@ColdNorthMenace Why share if it's not what people want, is isn't about "your art". Someone else will create what people want and not use this, if that's what you want carry on, but again this isn't about "your art"
@sgil Except, that it is. I literally made this for rapid body prototyping for tattoo designs. Don't use it if you don't like it. IDC.
She looked so real I even sent her some nudes!
HAHA! Thats awesome!
don't bother it changes faces
Like I said, 2.1 doesn't have facial training. This isn't for your celeb nudes. Cry more.
@ColdNorthMenace You can see nobody cares about your effort.
maybe the database without facial yield better results?
@ghostincivitai This comment was for the 4.1 flux version. There was a perfectly good model without facial training for the folks who want to make their celeb nudes, and they can STILL use that.
Learn to use masks...
@soulsliver73457 I know how to use masks, make your own lora.
i don't know but, this problem is easy, just use inpaint, problem solve, it gives me good result, no altering of faces
@breadstickschuckie1990 Thank you!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.