aiyabot  by Kilvoctu

Discord bot for Stable Diffusion via AUTOMATIC1111's Web UI or SD.Next

created 2 years ago
309 stars

Top 88.0% on sourcepulse

GitHubView on GitHub
Project Summary

AIYA is a Discord bot designed to provide a comprehensive interface for interacting with AUTOMATIC1111's Stable Diffusion Web UI and SD.Next. It allows users to generate images from text prompts, create prompts from keywords, manage generation parameters, and perform post-processing tasks like upscaling and image captioning directly within Discord.

How It Works

AIYA connects to the Stable Diffusion Web UI's API, enabling it to send generation requests and receive results. It supports a wide array of parameters, including negative prompts, sampling steps, CFG scale, sampling methods, and advanced features like LoRA and ControlNet integration. The bot also offers interactive elements such as buttons for regenerating images with modified seeds or prompts, and dropdowns for selecting specific images from batches for upscaling or downloading.

Quick Start & Requirements

  • Install/Run: Clone the repository and run launch.bat (Windows) or launch.sh (Linux). Docker deployment is also available.
  • Prerequisites: Requires AUTOMATIC1111's Stable Diffusion Web UI or SD.Next running with the API enabled (--api command-line argument). Tested on specific commits for both UIs.
  • Setup: Create a .env file with your Discord bot token.
  • Docs: Wiki

Highlighted Details

  • Supports live preview of image generation.
  • Allows swapping models/checkpoints and using extra networks (hypernetworks, LoRA).
  • Includes a /settings command for per-channel defaults and limits.
  • Offers image captioning via the /identify command.

Maintenance & Community

The project acknowledges contributions from AUTOMATIC1111, SD.Next, and other community members. Further community interaction details are not explicitly provided in the README.

Licensing & Compatibility

The repository does not explicitly state a license. Compatibility with commercial or closed-source projects is not specified.

Limitations & Caveats

The /identify command requires a specific Web UI script, detailed on the wiki. The bot uses the Web UI's legacy high-res fix method, which requires a specific setting to be enabled in the Web UI. The /generate command may be disabled if torch, nvidia, or transformers are not installed.

Health Check
Last commit

9 months ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
2 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.