BIG DISCOUNT! - 25% Discount Coupon "CLEARSTOCK"
BOMZAI.STORE – CHEAPEST ON THE MARKET
Game Accounts • Banks • OnlyFans • Proxies • Giftcards • Streaming Accounts • VPN'S • Other And Much More Cheap As
All for CENTS – way below market prices!
Thousands of REAL reviews • Years on the market
Revolut • Wise • Binance • Bybit + many more
Grab it before prices go up!
https://bomzai.store
-Only works on Windows 10/11
-You need a powerful gpu with at least 4-6 gbs of vram and at least 16 gb of ram
-The tool will use your gpu and (to my expieriences) can use up to 98% of the gpu (I use a 3060 TI)
Install stable diffusion
https://github.com/AUTOMATIC1111/stable-diffusion-webui click "Code" and then "Download ZIP"
Extract and run
After the extraction run the "webui-user-first-run.cmd" and just wait, its installing stuff.
Run the main program
After running "webui-user-first-run.cmd", run "webui-user.bat" and wait a little, after some time a window named
Stable Diffusion in your browser will open, looks like this: https://prnt.sc/tResU0KiedxN. Run the "webui-user.bat" everytime you want to use this!
(if you closed the tab just go to http://localhost:7860/ in any browser, only works if running "webui-user.bat"!
Installing the AI models
Realistic Vision InPainting:
Go to https://civitai.com/models/4JUdGzvrMFDWr...1a1boZVthe dropdown at files and download Pruned Model fp16 (1.99 GB) (safetensor). Put the "realisticVisionV13_v13-inpainting.safetensors" to \stable-diffusion-portable-main\models\Stable-diffusion.
Uber Realistic Porn Merge
Go to https://civitai.com/models/2661/uber-rea...merge-urpm (account required) and select the "URPMv1.2-inpainting" version. Then at the dropdown menu named files download "Pruned Model SafeTensor" and the config and also put them to \stable-diffusion-portable-main\models\Stable-diffusion
Extra embeddings for better quality
Add the following files in the "\stable-diffusion-portable-main\embeddings"
https://gofile.io/d/N7t8AS
https://gofile.io/d/az0mmz
Makes you able to choose "small_tits" and "Style-Unshaved" (untested)
To include Lora (Lora is the small tits and unshaved stuff) models click on the following icon at the right side, under the "Generate" button.
https://prnt.sc/rY3Hd3ejGfu7 (here a pic of what it looks like)
This will show an extra panel at the left, including a "Lora" tab. Clicking on any of the Lora's you have will add them to the prompt. You can move it to the front or back of the prompt to give it more 'focus', and you can also increase/decrease the number at the end "<..:1)" to give it more (e.g. 1.5) or less (e.g. 0.5) focus.
Loading models
In the webui, at the top left, "Stable Diffusion checkpoint", hit the 'Refresh' icon.
Now you should see the uberRealisticPornMerge_urpmv12 model in the list, select it.
Deepfaking it!
Go to the 'img2img' tab, and then the 'Inpaint' tab.4r
In the first textarea (positive prompt), enter
RAW photo of a nude woman, naked?
In the second textarea (negative prompt), enter
((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?
If not otherwise mentioned, leave default,
Masked content: fill (will just fill in the area without taking in to consideration the original masked 'content', but play around with others too)?
?
Inpaint area: Only masked?
?
Sampling method: DPM++ SDE Karras (one of the better methods that takes care of using similar skin colors for masked area, etc)?
?
Sampling steps: start with 20, then increase to 50 for better quality/results when needed. But the higher, the longer it takes. I have mostly good results with 20, but it all depends on the complexity of the source image and the masked area.?
?
CFG Scale: 7 - 12 (mostly 7)?
?
Denoise Strength: 0.75 (default, the lower you set this, the more it will look like the original masked area)?
These are just recommendations / what works for me, experiment / test out yourself to see what works for you.
Stable Diffusion models work best with images with a certain resolution, so it's best to crop your images to the smallest possible area.
ou can use any photo manipulation software, or use https://www.birme.net/
Open your preferred image in the left area.
Masking
Now it's time to mask / paint over all the areas you want to 'regenerate', so start painting over all clothing. You can change the size of the brush at the right of the image.
I've experienced that painting a little bit outside the 'lines / borders' is the best for the model, else you will get visible remnants / distortions at the edges of the mask in the generated image.
Tips / Issues:
Mask more, go outside of the edges of the clothes. If you only mask clothes, the generator doesn't know about any skin colors, so it's best you include parts of the unclothed body (e.g.. neck, belly, etc).
And sometimes: you forgot to mask some (tiny) area of the clothes.. this is esp. difficult to find with clothes that are dark. But look at the "in progress" images that are generated during the process.. you should normally see where it is.
Optimization
When the model is generating weird or unwanted things, add them to the 'Negative Prompt'. I've already added some, like hair, water, etc. In some cases you need to add 'fingers', since Stable Diffusion is quite bad at generating fingers.
Sometimes it's needed to add extra words to the (positive) prompt, i.e. sitting, standing, ..
BOMZAI.STORE – CHEAPEST ON THE MARKET
Game Accounts • Banks • OnlyFans • Proxies • Giftcards • Streaming Accounts • VPN'S • Other And Much More Cheap As
All for CENTS – way below market prices!
Thousands of REAL reviews • Years on the market
Revolut • Wise • Binance • Bybit + many more
Grab it before prices go up!
https://bomzai.store
[ Hidden Content! ]
-Only works on Windows 10/11
-You need a powerful gpu with at least 4-6 gbs of vram and at least 16 gb of ram
-The tool will use your gpu and (to my expieriences) can use up to 98% of the gpu (I use a 3060 TI)
Install stable diffusion
https://github.com/AUTOMATIC1111/stable-diffusion-webui click "Code" and then "Download ZIP"
Extract and run
After the extraction run the "webui-user-first-run.cmd" and just wait, its installing stuff.
Run the main program
After running "webui-user-first-run.cmd", run "webui-user.bat" and wait a little, after some time a window named
Stable Diffusion in your browser will open, looks like this: https://prnt.sc/tResU0KiedxN. Run the "webui-user.bat" everytime you want to use this!
(if you closed the tab just go to http://localhost:7860/ in any browser, only works if running "webui-user.bat"!
Installing the AI models
Realistic Vision InPainting:
Go to https://civitai.com/models/4JUdGzvrMFDWr...1a1boZVthe dropdown at files and download Pruned Model fp16 (1.99 GB) (safetensor). Put the "realisticVisionV13_v13-inpainting.safetensors" to \stable-diffusion-portable-main\models\Stable-diffusion.
Uber Realistic Porn Merge
Go to https://civitai.com/models/2661/uber-rea...merge-urpm (account required) and select the "URPMv1.2-inpainting" version. Then at the dropdown menu named files download "Pruned Model SafeTensor" and the config and also put them to \stable-diffusion-portable-main\models\Stable-diffusion
Extra embeddings for better quality
Add the following files in the "\stable-diffusion-portable-main\embeddings"
https://gofile.io/d/N7t8AS
https://gofile.io/d/az0mmz
Makes you able to choose "small_tits" and "Style-Unshaved" (untested)
To include Lora (Lora is the small tits and unshaved stuff) models click on the following icon at the right side, under the "Generate" button.
https://prnt.sc/rY3Hd3ejGfu7 (here a pic of what it looks like)
This will show an extra panel at the left, including a "Lora" tab. Clicking on any of the Lora's you have will add them to the prompt. You can move it to the front or back of the prompt to give it more 'focus', and you can also increase/decrease the number at the end "<..:1)" to give it more (e.g. 1.5) or less (e.g. 0.5) focus.
Loading models
In the webui, at the top left, "Stable Diffusion checkpoint", hit the 'Refresh' icon.
Now you should see the uberRealisticPornMerge_urpmv12 model in the list, select it.
Deepfaking it!
Go to the 'img2img' tab, and then the 'Inpaint' tab.4r
In the first textarea (positive prompt), enter
RAW photo of a nude woman, naked?
In the second textarea (negative prompt), enter
((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?
If not otherwise mentioned, leave default,
Masked content: fill (will just fill in the area without taking in to consideration the original masked 'content', but play around with others too)?
?
Inpaint area: Only masked?
?
Sampling method: DPM++ SDE Karras (one of the better methods that takes care of using similar skin colors for masked area, etc)?
?
Sampling steps: start with 20, then increase to 50 for better quality/results when needed. But the higher, the longer it takes. I have mostly good results with 20, but it all depends on the complexity of the source image and the masked area.?
?
CFG Scale: 7 - 12 (mostly 7)?
?
Denoise Strength: 0.75 (default, the lower you set this, the more it will look like the original masked area)?
These are just recommendations / what works for me, experiment / test out yourself to see what works for you.
Stable Diffusion models work best with images with a certain resolution, so it's best to crop your images to the smallest possible area.
ou can use any photo manipulation software, or use https://www.birme.net/
Open your preferred image in the left area.
Masking
Now it's time to mask / paint over all the areas you want to 'regenerate', so start painting over all clothing. You can change the size of the brush at the right of the image.
I've experienced that painting a little bit outside the 'lines / borders' is the best for the model, else you will get visible remnants / distortions at the edges of the mask in the generated image.
Tips / Issues:
Mask more, go outside of the edges of the clothes. If you only mask clothes, the generator doesn't know about any skin colors, so it's best you include parts of the unclothed body (e.g.. neck, belly, etc).
And sometimes: you forgot to mask some (tiny) area of the clothes.. this is esp. difficult to find with clothes that are dark. But look at the "in progress" images that are generated during the process.. you should normally see where it is.
Optimization
When the model is generating weird or unwanted things, add them to the 'Negative Prompt'. I've already added some, like hair, water, etc. In some cases you need to add 'fingers', since Stable Diffusion is quite bad at generating fingers.
Sometimes it's needed to add extra words to the (positive) prompt, i.e. sitting, standing, ..
Not ratedThis leak has not been rated yet, be careful when downloading.