A8R8 (Alternate Reality)

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

Links: [Discord]

 

Unified interface

 

• A8R8 (Alternate Reality)
  • Features
  • Getting started
    • Installation
      • One-Click Windows WSL2 (RECOMMENDED)
      • Docker (not actively updated)
      • Windows (EXPERIMENTAL / BROKEN)
      • Mac
      • Linux (Debian based)
    • Running
      • One-Click Windows WSL2
      • Docker
      • Windows (EXPERIMENTAL / BROKEN)
      • Linux (Debian based)
    • Updating
      • One-Click Windows WSL2
      • Docker
      • Windows (EXPERIMENTAL / BROKEN)
      • Mac & Linux (Debian based)
  • Key Shortcuts
  • Development Environment
  • Sample Generations

 

Features

• Works with existing Forge, A1111 and ComfyUI SD installations; NO NEED to reinstall yet another SD implementation
• Runs in browser
• Full Controlnet support
• Controlnet mask layers with Forge
• Attention mask layers with Forge & Forge Couple
• 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

 

 

Editor autocomplete for LORAs and embeddings

 

Scaling controls

 

Outpainting / Inpainting

 

Layers

 

Scribbling

 

Scribble over canvas

 

Toggle layer visibility

 

Getting started

Installation

Update - 2024/04/07: Added one-click installer or Windows (WSL2), check installation steps for details.

Update: Added one click installer for Windows install-docker.ps1, check installation steps for details.

Keep in mind this hasn't been tested, please report any issues here

One-Click Windows WSL2 (RECOMMENDED)

1. Install Forge and/orAutomatic1111 webui and/or ComfyUI if you haven't yet
2. Download latest One-Click Installer from latest release
3. Unzip the downloaded archive
4. Run .\one-click-installer-wsl.bat
5. Set the WSL user name and password if it's your first time using it. Make sure you remember the password you entered
6. To start the application open run-windows-wsl.bat
7. Start the SD backend of your choice
   1. Forge/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 --max-upload-size 500
      3. Install https://github.com/ssitu/ComfyUI_UltimateSDUpscale
      4. Install https://github.com/Fannovel16/comfyui_controlnet_aux
      5. Install https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet
      6. Install https://github.com/Acly/comfyui-inpaint-nodes and follow steps on to download required models
      7. Install https://github.com/cubiq/ComfyUI_IPAdapter_plus and follow steps on to download required models

 

NOTE: To use regional prompting with Forge, make sure to install the Forge Couple extension >= v1.5.0 to your Forge installation

NOTE: You can copy the example_user.sh file and rename it to user.sh to configure tha application.

NOTE: If you're running the stable diffusion backend (Forge / A1111 / ComfyUI) on a remote machine, make sure to set the remote address in user.sh and uncomment the URL entries.

NOTE: You can define the default backend selected on startup by setting DEFAULT_BACKEND in user.sh.

 

Docker (not actively updated)

1. Install Automatic1111 webui and/or ComfyUI if you haven't yet
2. Clone this repo and open a terminal at the root directory
3. On Windows you can run install-docker.ps1 in a powershell window (recommended) or:
   1. Install Docker Compose
   2. Run docker compose build
4. 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 --max-upload-size 500
      3. Install https://github.com/ssitu/ComfyUI_UltimateSDUpscale
      4. Install https://github.com/Fannovel16/comfyui_controlnet_aux
      5. Install https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet
      6. Install https://github.com/Acly/comfyui-inpaint-nodes and follow steps on to download required model
      7. Install https://github.com/cubiq/ComfyUI_IPAdapter_plus and follow steps on to download required model

 

Windows (EXPERIMENTAL / BROKEN)

1. Clone this repo and open a terminal at the root directory
2. Run install.ps1 in a powershell window

 

Mac

1. Download latest One-Click Installer from latest release
2. Run xcode-select --install to install developer tools, and follow the installation prompts
3. Install Homebrew from https://brew.sh/
4. Run CLONE_REPO=true ./install-mac.sh (preferably from a terminal window)

Or

1. Run xcode-select --install to install developer tools, and follow the installation prompts
2. Install Homebrew from https://brew.sh/
3. Clone repo
4. Run ./install-mac.sh within the cloned directory (preferably from a terminal window)

 

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 --max-upload-size 500
   3. Install https://github.com/ssitu/ComfyUI_UltimateSDUpscale
   4. Install https://github.com/Fannovel16/comfyui_controlnet_aux
   5. Install https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet
   6. Install https://github.com/Acly/comfyui-inpaint-nodes and follow steps on to download required model
   7. Install https://github.com/cubiq/ComfyUI_IPAdapter_plus and follow steps on to download required model

 

Linux (Debian based)

Ubuntu 22.04:

1. Download latest One-Click Installer from latest release
2. Run ./install-packaged.sh

Or

3. Download latest One-Click Installer from latest release
4. Run CLONE_REPO=true ./install.sh

Or

1. Clone repo
2. Run ./install.sh

 

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 --max-upload-size 500
   3. Install https://github.com/ssitu/ComfyUI_UltimateSDUpscale
   4. Install https://github.com/Fannovel16/comfyui_controlnet_aux
   5. Install https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet
   6. Install https://github.com/Acly/comfyui-inpaint-nodes and follow steps on to download required model
   7. Install https://github.com/cubiq/ComfyUI_IPAdapter_plus and follow steps on to download required model

 

NOTE: To use regional prompting with Forge, make sure to install the Forge Couple extension >= v1.5.0 to your Forge installation

 

Running

One-Click Windows WSL2

1. Make sure you followed the installation steps
2. Go to the installation folder
3. Run run-windows-wsl.bat
4. Run your stable diffusion backend (Forge/A1111/Comfy)
5. Open http://localhost:4000 in your browser

NOTE: You might need to change your firewall settings to allow WSL to connect to the host machine correctly. Please open an issue if you're having trouble connecting the application to your backend of choice.

 

Docker

On Windows you can run run-docker.ps1 in a powershell window

Or

Run docker compose up

 

Point your browser to http://localhost:4000, it's preferred to use a chromium based browser (Brave, Chromium, Chrome)

   

Windows (EXPERIMENTAL / BROKEN)

1. Run run.ps1 in a powershell window

Keep in mind this hasn't been tested, please report any issues here

Update: one of the dependencies doesn't work with Windows at the moment, so it won't run successfully

 

Linux (Debian based)

Run ./run.sh or ./run-packaged.sh if you used the package installation

 

Updating

One-Click Windows WSL2

1. Run update-windows-wsl.bat

Docker

On Windows you can run install-docker.ps1 in a powershell window

Or

1. Run git pull
2. Run docker compose build

Windows (EXPERIMENTAL / BROKEN)

1. Run install.ps1 in a powershell window
2. Keep in mind this hasn't been tested, please report any issues here

Update: one of the dependencies doesn't work with Windows at the moment, so it won't run successfully

 

Mac & Linux (Debian based)

Run ./update.sh or ./update-packaged.sh if you used the package installation.

   

Key Shortcuts

Key/Combo/Action	Fuctionality
-	zoom out canvas
+	zoom in canvas
1	reset zoom
Middle Mouse Button click	pan canvas
[ with optional CTRL or Shift for fine control	decrease brush size
] with optional CTRL or Shift for fine control	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, or any layer brush stroke
CTRL + SHIFT + z, CTRL + y	redo generation image addition, mask paint, sketch paint, or any layer brush stroke
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

 

 

 

 

 

 

Outpainting in hires