Skip to content

This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements.

License

Notifications You must be signed in to change notification settings

ilkayisik/self-artify

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Welcome to Self-Artify

Based on invoke-ai/InvokeAI and CompVis/stable-diffusion we developed a web app that lets users to create fantasy avatars.

Webapp Usage

Avatar-Generator

The user uploads a selfie (ideally an image with a clear frontal face, half torso with a natural background). If the user selects "keep the original face in the generated image option" the face in the image is identified and masked. Then, the original image and the masked image are used as the inputs to the stable diffusion's inpaint functionality with preselected prompts for each fantasy character option.

If the "keep the original face in the generated image option" is not selected, then only the original image and the respective prompts is used with stable diffusion's image to image functionality.

Avatar-Generator Advanced

This feature gives the user a bit more freedom to add a free prompt and change the values of the Classifier Free Guidance (CFG) Scale and the Strength parameters to optimize the generated image.

Movie-Poster Generator

This bonus feature lets the user input a movie name and a predefined style and creates a unique movie poster.

Installation

This repository is a fork of invoke-ai/InvokeAI which is based on the open source text-to-image generator CompVis/stable-diffusion

The developers of invoke-ai/InvokeAI created a streamlined process with various new features and options to aid the image generation process. It runs on Windows, Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.

To use our webapp we recommend following the installation notes from invoke-ai

Authors

Get in touch with us if you have any questions!

About

This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 86.3%
  • Python 13.3%
  • Other 0.4%