• For Ad free site experience, please register now and confirm your email address. Advertisements and popups will not be displayed to registered users.Being a registered member will also unlock hidden sections and let you request for your favourite fakes.

HOW TO MAKE AI FAKES USING COLAB (FREE AND NO DISCONNECT)

IN THIS THREAD I WILL TEACH HOW TO MAKE HD FAKES USING AI (STABLE DIFFUSION)

OFCOURSE IT DOESNT DISCONNECT AN ABSOLUTELY FREE

STEP 1:

USE THIS COLAB LINK : NOCRYPT colab
ALTERNATE: Google Colaboratory

scroll down to usefull utilities

click colab mobile keep alive

after that click play:



STEP 2:

We need a porn model to create ai fakes,
if you dont know any model, heres a common porn model i use LINK : https://civitai.com/api/download/models/15670
just copy the link and paste here:
or paste ur custom model in the blank box down here


Now click start

wait for sometime until everything is downloaded (1minute)


STEP 3:
now click on the link generated here


click the gradio link only

Now we configure model and items:
change the model in stable diffusion webui

change model to uberrealisticpornmerge.

change sd vae to automatic:


change cross attention optimization to automatic:


Click on imgtoimg and then click inpaint


now scroll down and lick on these:






STEP 4:
we now upload the image, you can click and open the image or drag and drop the image here:


after the image is opened , change its size here:

change the image size as the red line mentoned should fit the image perfectly

INPAINTING THE IMAGE :
now we are here to imporant part:
click on this cursor and paint the image,
only paint where u want to edit, avoid painting faces



STEP 5:

Finally we add prompts and negative, these add features to ur picture inpaint

prompt for the picture: undressing, completely nude, detailed medium breasts, detailed nipples
negative: (low quality, worst quality:1.4), (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit, fewer digits, (extra arms:1.2)
paste prompt in prompt box and negative in negative box.

STEP 6:
GENERATION:
after you completed all the things, click generate and wait for it to generate:
what is my facebook url

a sample generation:




IF the face gets changed after generation , click masked only:


THANKS GUYS THIS IS IT, IT TOOK ME REALLY ONE NIGHT TO CREATE THIS THREAD, PLEASE SUPPORT ME, IF U HAVE ANY DOUBT U CAN SURE ASK ME ANYTIME:)
 
Click to expand...
Basically u guys missed the actual part, google wont allow extra gpu usage on notebook for free, but its not written some where, actually i am using sdwebui everyday but in a different manner, u cant abuse the gpu that's all, well i can attach some link, i am sure that's gonna work.


 
Hi ! Does someone had this error when generating and managed to fix it (rtx 3070ti) ? ty

NotImplementedError: No operator found for memory_efficient_attention_forward with inputs: query : shape=(1, 28085, 1, 512) (torch.float16) key : shape=(1, 28085, 1, 512) (torch.float16) value : shape=(1, 28085, 1, 512) (torch.float16) attn_bias : <class 'NoneType'> p : 0.0 decoderF is not supported because: max(query.shape[-1] != value.shape[-1]) > 128 xFormers wasn't build with CUDA support attn_bias type is <class 'NoneType'> operator wasn't built - see python -m xformers.info for more info [email protected] is not supported because: max(query.shape[-1] != value.shape[-1]) > 256 xFormers wasn't build with CUDA support requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old) operator wasn't built - see python -m xformers.info for more info tritonflashattF is not supported because: max(query.shape[-1] != value.shape[-1]) > 128 xFormers wasn't build with CUDA support requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old) operator wasn't built - see python -m xformers.info for more info triton is not available requires GPU with sm80 minimum compute capacity, e.g., A100/H100/L4 Only work on pre-MLIR triton for now cutlassF is not supported because: xFormers wasn't build with CUDA support operator wasn't built - see python -m xformers.info for more info smallkF is not supported because: max(query.shape[-1] != value.shape[-1]) > 32 xFormers wasn't build with CUDA support dtype=torch.float16 (supported: {torch.float32}) operator wasn't built - see python -m xformers.info for more info unsupported embed per head: 512
 
Privatefantasy said:
Basically u guys missed the actual part, google wont allow extra gpu usage on notebook for free, but its not written some where, actually i am using sdwebui everyday but in a different manner, u cant abuse the gpu that's all, well i can attach some link, i am sure that's gonna work.


Click to expand...

ive already tried these sagemaker studio lab, those were very unstable and crowded all time
 
funky_funk7 said:
I don't think it's an issue with Gradio. Because I am using Gradio in other notebook and I am not a Colab Pro user.
Click to expand...
they have blocked the free usage of automatic 111 code, google fuckers only wanto get money and steal peoples data
 
Privatefantasy said:
the main issue is in the gradio, you shoud fire it up by using ngrok auth token
Click to expand...
nah bro, this limitation only happen when ur using the gradio with automatic 111 notebooks, if ure using a gradio notebook with any other engine, u wont be disconnected
 
U dont have to use any note book any more let me give u an discord link, here u will get to know how to use sage maker, and its way more fast reliable and it can run in phone also
 
Use Getimg website, which allows free editing without the need of any GPU

getimg.ai

Everything you need to create images with AI | getimg.ai

Magical AI art tools. Generate original images, modify existing ones, expand pictures beyond their borders, and more.
getimg.ai getimg.ai



Here the complete tutorial-
1. Go to this website -
getimg.ai

Everything you need to create images with AI | getimg.ai

Magical AI art tools. Generate original images, modify existing ones, expand pictures beyond their borders, and more.
getimg.ai getimg.ai

2. Navigate to the AI canvas under the tools section for inpainting the images.
3. Upload the image
4. Use erase icon and erase the part you want to remove or change like clothes.
5. After erasing , use simple prompts like, bikini, nude, topless etc as per your needs.
6. Wait for few seconds and you will get the free edited images.
 
Thx
Someonehorny said:
Use Getimg website, which allows free editing without the need of any GPU

getimg.ai

Everything you need to create images with AI | getimg.ai

Magical AI art tools. Generate original images, modify existing ones, expand pictures beyond their borders, and more.
getimg.ai getimg.ai



Here the complete tutorial-
1. Go to this website -
getimg.ai

Everything you need to create images with AI | getimg.ai

Magical AI art tools. Generate original images, modify existing ones, expand pictures beyond their borders, and more.
getimg.ai getimg.ai

2. Navigate to the AI canvas under the tools section for inpainting the images.
3. Upload the image
4. Use erase icon and erase the part you want to remove or change like clothes.
5. After erasing , use simple prompts like, bikini, nude, topless etc as per your needs.
6. Wait for few seconds and you will get the free edited images.
Click to expand...
So much brother
 
You must log in or register to reply here.
Back
Top