woniesong92 / aiyabot

A neat Discord bot for AUTOMATIC1111's Web UI

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

AIYA

A Discord bot interface for Stable Diffusion

Setup requirements

  • Set up AUTOMATIC1111's Stable Diffusion AI Web UI.
    • AIYA is currently tested on commit 685f9631b56ff8bd43bce24ff5ce0f9a0e9af490 of the Web UI.
  • Run the Web UI as local host with api (COMMANDLINE_ARGS= --listen --api).
  • Clone this repo.
  • Create a text file in your cloned repo called ".env", formatted like so:
# .env
TOKEN = put your bot token here
  • Run AIYA by running launch.bat (or launch.sh for Linux)

Usage

To generate an image from text, use the /draw command and include your prompt as the query.

Currently supported options

  • negative prompts
  • swap model/checkpoint (see wiki)
  • sampling steps
  • width/height (up to 1024)
  • CFG scale
  • sampling method
  • seed
  • img2img
  • denoising strength
  • batch count
  • Web UI styles
  • face restoration
  • high-res fix
  • CLIP skip

Bonus features

  • /settings command - set per-server defaults for the following (see Notes!):
    • negative prompts
    • model/checkpoint
    • sampling steps / max steps
    • sampling method
    • batch count / max batch count
    • CLIP skip
  • /identify command - create a caption for your image.
  • /stats command - shows how many /draw commands have been used.
  • /tips command - basic tips for writing prompts.
  • /upscale command - resize your image.
  • buttons - certain outputs will contain buttons.
    • ๐Ÿ–‹ - edit prompt, then generate a new image with same parameters.
    • ๐ŸŽฒ - randomize seed, then generate a new image with same parameters.
    • ๐Ÿ“‹ - view the generated image's information.
    • โŒ - deletes the generated image.

Notes

Credits

AIYA only exists thanks to these awesome people:

About

A neat Discord bot for AUTOMATIC1111's Web UI

License:GNU General Public License v2.0


Languages

Language:Python 99.7%Language:Shell 0.1%Language:Batchfile 0.1%