Code Monkey home page Code Monkey logo

a8r8's Introduction

A8R8 (Alternate Reality)

An opinionated interface for SD (Stable Diffusion) image generation, and more.

Links: [Discord]

  Interface Unified interface

 

 

Features

  • Works with existing A1111 and ComfyUI SD installations; NO NEED to reinstall yet another SD implementation
  • Runs in browser
  • Full Controlnet support
  • Open canvas with unified interface
  • Inpainting/Outpainting with masking and scaling
  • VRam usage info
  • Scaling and hires like built in solution
  • Integration with TiledVAE, Tiled Diffusion and Self Attention Guidance
  • Integration with Ultimate Scale with A1111 and ComfyUI
  • Sketch, mask and Controlnet layers
  • Image info support (on import only for now)
  • Text editor with auto complete for installed LORAs & embeddings
  • Color picker for mask color and brush color
  • Edit detection map on canvas
  • Copy support for base layer and copy/paste support for CN layers
  • Drag and drop images from disk
  • On canvas generation live preview
  • Initial support for synchronized sessions across tabs/machines connected to the same server
  • Potential to add any A1111 extension in the future

 

 

Scaling
Editor autocomplete for LORAs and embeddings

 

Scaling
Scaling controls

 

Outpainting Outpainting / Inpainting

 

Layers
Layers

 

Scribbling Scribbling

 

Scribble over canvas Scribble over canvas

 

Toggle layer visibility Toggle layer visibility

 

Getting started

Installation

  1. Install Automatic1111 webui and/or ComfyUI if you haven't yet
  2. Install Docker Compose
  3. Clone this repo and open a terminal at the root directory
  4. Run docker compose build
  5. Start the SD backend of your choice
    1. Automatic1111 webui and make sure to add --api --listen to COMMANDLINE_ARGS under webui-user.sh or webui-user.bat depending on the operating system
    2. ComfyUI
      1. Install A8R8 supporting nodes
      2. Add --preview-method auto --listen to the run command, ex: python main.py --preview-method auto --listen
      3. Install https://github.com/ssitu/ComfyUI_UltimateSDUpscale
      4. Install https://github.com/Fannovel16/comfyui_controlnet_aux
    3. Currently the VAE choice is hardcoded depending on the version of the selected model; it'll be configurable through the interface in a future update. Make sure you have these VAE files in the configured paths in either backend:
      1. sdxl_vae.safetensors for SDXL
      2. vae-ft-mse-840000-ema-pruned.ckpt for SD 1.5

Running

  1. Run docker compose up
  2. Point your browser to http://localhost:4000, it's preferred to use a chromium based browser (Brave, Chromium, Chrome)

Updating

  1. Run docker compose build
  2. Run docker compose up

Key Shortcuts

Key/Combo/Action Fuctionality
- zoom out canvas
+ zoom in canvas
1 reset zoom
Middle Mouse Button click pan canvas
[ decrease brush size
] increase brush size
← → ↑ ↓ arrows + SHIFT move selection box and increase movement amount by pressing shift
s toggle selection box and paint modes
t toggle tool between brush and eraser
p toggle brush color selector
h hide mask layer
c clear mask, sketch or controlnet brush strokes of the active layer
m toggle between mask and sketch layers
CTRL + z undo generation image addition, mask paint, sketch paint
CTRL + SHIFT + z, CTRL + y redo generation image addition, mask paint, sketch paint
CTRL + c copy image to clipboard within selection box bounds from the base layer
CTRL + v paste image from clipboard at the selection box top left corner position to the base or active controlnet layer. Generation info will be applied if found when pasting to base layer
CTRL + s save image within selection box bounds to disk
Drop PNG image to canvas add image at the selection box top left corner position to the base or active controlnet layer. Generation info will be applied if found when pasting to base layer

Development Environment

To be added...

 

 

Sample Generations

ex1

 

lion head

 

ex2

 

ex3

 

ex4
Outpainting in hires

a8r8's People

Contributors

ramyma avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.