breastInClass -> nudify XL.
Are you enjoying fine breasts and perverting the life work of science researchers? Consider donating a dollar to the cause. Anything is appreciated :)
tl;dr:
Nude female frontals. Shapely breasts with small nipples. Strips away layers of embedded censorship in models.
⬇️ read the instructions ⬇️
What it is
This is a LORA that I use in text2img to get better NUDE FRONTALS.
It alters the body shape, particularly the breasts.
It's best at weights under <1 with accompanying keywords.
The data set is a collection of fully nude adult women.
What it is not
The dataset is all naked women with no faces. Any effect on clothing, men, flat chests, or faces is unintended. Funny, but unintended.
While appreciated for the exposure - using this for fully clothed women defeats the purpose.
It only works when you include it in the prompt (saddened I must tell you this).
It does not bias towards asians. I just like generating them. There are no dark skinned women in the data set unfortunately, but I'm not averse to making a version for this.
Installation:
Download the file
Place it in models\Lora folder (webui)
Usage:
You can also add it to the prompt by clicking "lora" tab in automatic1111:
You can also type it into the prompt, but it will not work if you make a single typo.
ex <lora:nudify:0.5>
The XL model requires the XL base / XL base with VAE model. It doesn't seem to work with the refiner, or anything else.
Adjust the weights. 0.1 - 1.0
Tips:
This is a fairly strong LORA best used in conjunction with low weights and other keywords like "naked", "topless". Work to get your image close to NSFW first, then add this to push it over the line.
0.5weight is pretty good for most purposes.Very high weights can cause the face to crop out.
Adding "small breast" or "huge breast" keywords can add more size variation, keeping the shape.
Adding stubborn loras or conflicting terms (e.g. "shirt") to the prompt can burn the image.
Base SD models are stubborn and don't like to be made NSFW. Expect clothes, blurred nipples. Try different weights and add more keywords!
Description
I liked v1.3, but it often produced larger areolas than I wanted. v1.4 uses 3 totally new girls as the dataset, large and small breast sizes, same shape. As a tradeoff, the images used are of varying quality.
Changelog:
Different girls used than the other versions
Better at producing small areolas
Somewhat better at nipples
Stronger than v1.3 - use lower weights again
FAQ
Comments (25)
adding v1.1 soon which should tone down some artifacts
Is there a tutorial?
just add it to the prompt. instructions should cover this
Is this supposed to be nudify existing image or just generate more accurate nudity image? If you say for existing image, then this is supposed to be used at least in img2img and there's no recommendation value for denoising streght etc
it's text2img. just put it in the prompt. girl gets a nice body.
@throwawayyy111 i see~ I thought because the name is nudify, then its must be for something like nude filtering
try it with inpainting that might work
@twiisted well.., to be fair i already did, and it worked. But at first i just using prompts without this LoRA. The difference between when im using this is the simplicity of my prompts, it become more simple if im using this LoRA, no need to specify many details
Doesn't work with img2img.
Obviously
this LoRA name is kinda misleading. If you expecting to do nude filtering, my recommendation is using impainting for specific part, and adding negative prompt for clothes.
If you still want to use img2img, maybe you can play with this LoRA weight and denoising streght. Also don't forget to play with your prompts
@zetsubou is it misleading? why would a lora suddenly be able to do what you're imagining? is it because they named it "nudify"? sort of makes you imagine hitting a button and "nudifying" something but nah
@dangiorno you literally just explained why its misleading
@turtleman369 it's like someone saying they're going to cast a spell and make you rich, they call it "Moneyfying" your finances. Then later, you claim you were mislead when you don't get any money. Who's to blame? Everyone in the situation.
i think it was a fair comment, for a while i had "haven't tried it with img2img, let me know if it works" in the bio. after this comment i removed that section, and now people ask if its supposed to be in img2img again.
@throwawayyy111 Maybe update it again? It's just straightforward and obvious to me that it doesn't work with img2img because it's just not how any of this works, it would make no sense because it would mean you created some new invention or used magic. I guess people want to believe lmfao
Are you inpainting this while you do it, or are you just running img2img?
what
y'all gonna make me retitle this... lol...
i am using text2img. no frills
Renaming this and re-describing it is a big improvement. Nudify didn't really do what it claimed, but it did do ... this ... which is useful, especially at low weights.
Hmmm... I wonder what would happen if you were to use a script to merge the different versions of this LoRA that were created with different datasets? It could be worth trying I think - and in particular if you were to train in different sizes of breasts as three different concepts.
i'm not sure about any script, but it would be possible to just remake the lora featuring the 3 new girls + the model used in v1.3 & earlier. i'll try it and let you know
if can , i want have A-Cup B-Cup C D E F G ..... K-Cup ...
SD only S. M. B. just 3 Lv. this is not good choose,And this is also very unintuitive, not as good as "Cup" for writing and understanding@throwawayyy111
@WS2006 probably not possible in that sense, the easiest way for it to not be confused would be to make multiple loras for each size. the ai doesn't understand really what it's seeing. a lora with all of them would probably try to blend them all
The tool that I use to train new loras seems to be giving errors, including with v1.4. If you're getting this, read the updated instructions.
this has been fixed and v1.41 has been released
Details
Files
breastinclassBetter_v14.safetensors
Mirrors
breastinclassBetter_v14.safetensors
9025_breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
BreastInClass_V14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
bbc_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
breastinclassBetter_v14.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.