MEMORIAL DAY - JOIN BRAZZERS FOR FREE - CLICK HERE!
Guide - Installing Stable Diffusion Webui & Nudifying (Inpainting) Guide | Page 18 | SimpCity Forums

Guide Installing Stable Diffusion Webui & Nudifying (Inpainting) Guide

  • Welcome to the Fakes / AI / Deepfakes category
    When posting AI generated content please include prompts used where possible.
Sort By Date Sort By Reaction Score
Y

youngbuck277

Bathwater Drinker
Jul 29, 2022
38
1,358
1,239
0fya082315al84db03fa9bf467e3.png
Anyone looking for settings in auto111 try these and report back:

model (checkpoint): any photorealistic inpainting model from civitai
mask blur: 3
resize mode: just resize
masked content: original
inpaint area: whole picture (try to find the largest dimension your GPU can handle and still generate quickly. I set height around 1000 and use the width slider to match the picture size)
sampling steps: 25
sampling method: DPM++ 3M SDE Exponential / DPM++ 2M SDE Karras
cfg scale: 1.5
denoise str: 1.0

When drawing the mask on the picture in inpaint tab, mask pretty liberally over all clothing parts. When you get a good output, save it and open it in any type of photoshop with the original picture. Paste your output over the original photo and free transform it to the same size as the original. Use eraser to erase any parts of the output photo that is the same as the original if you really want eyes/face to be lossless detail.
 
scott_hall

scott_hall

Superfan
Oct 24, 2022
41
598
742
0fya082315al84db03fa9bf467e3.png
Any way to make img2img so that it removes clothes from photo leaving the rest as it was with a prompt?
 
S

sxxtan

Casual
Mar 17, 2022
15
36
229
0fya082315al84db03fa9bf467e3.png
is there any problem with black cloth?
mine doesn’t generate like it used to be, its fine when the model use anything besides black cloth, even they use bikini, its just generate another bikini
 
S

shadylane89

Lurker
Dec 15, 2022
6
2
58
0fya082315al84db03fa9bf467e3.png
i'm trying to follow the tutorial.
around the 50% mark the model appears de-clothed for a second, but then blurs out. What am I doing wrong here?
I turned on all the inpaint extra image save settings (pretty sure..) but none of the in progress saves catches it
 
S

shadylane89

Lurker
Dec 15, 2022
6
2
58
0fya082315al84db03fa9bf467e3.png
youngbuck277 said:
Please, Log in or Register to view quotes
Click to expand...


Please, Log in or Register to see links and images

I've tried other settings or sutff but it's always the same thing.

model: uberRealisticPornMerge_urpmv13.safetensors [40f9701da0]
prompt "RAW photo of a nude woman, naked, breasts, nipples. standing"
neg. prompt "((clothing), (monochrome:1.3), (deformed, distorted, disfigured:1.3), (hair), jeans, tattoo, wet, water, clothing, shadow, 3d render, cartoon, ((blurry)), duplicate, ((duplicate body parts)), (disfigured), (poorly drawn), ((missing limbs)), logo, signature, text, words, low res, boring, artifacts, bad art, gross, ugly, poor quality, low quality, poorly drawn, bad anatomy, wrong anatomy"
Resize mode- just resize
mask blur- 3
mask mode- inpaint masked
masked content- fill
inpaint area- only masked
only masked padding pixels- 32
Sampling Method- DPM++ SDE Karras
Sampling Steps- 40
Refiner- null
Resize to- 512x512 (og image size_
Batch count 1, batch siz 1
CFG Scale- 7
Denoising strength- .75
seed -1
 
kamikazenojihadist

kamikazenojihadist

Lurker
Oct 24, 2022
2
0
81
0fya082315al84db03fa9bf467e3.png
I got this error help

"A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check."

Where i put the "--no-half commandline"?
 
You must log in or register to reply here.
Top Bottom