g-diffuser-bot  by parlance-zz

Discord bot for Stable Diffusion

created 2 years ago
279 stars

Top 94.1% on sourcepulse

GitHubView on GitHub
Project Summary

G-Diffuser-Bot provides a Discord interface and command-line tools for Stable Diffusion image generation, targeting users who want to integrate AI art creation into their Discord communities or automate image generation tasks. It simplifies the setup and operation of Stable Diffusion models, including advanced features like in/out-painting and infinite zoom video generation.

How It Works

The bot leverages Stable Diffusion models, offering features like img2img ("riffing"), in/out-painting, and negative prompts. Recent updates include a faster compositing script for infinite zoom videos and support for clip-guided models, though the latter currently incurs a performance penalty. The project aims for a user-friendly experience with an all-in-one installer and a system tray icon for managing components.

Quick Start & Requirements

  • Install: Download and extract the "G-Diffuser AIO Installer" for Windows 10+ 64-bit. Run install_or_update.cmd.
  • Prerequisites: Windows 10+ (1903+), NVIDIA GPU with at least 8GB VRAM, ~40GB free space for models, Hugging Face account and access token. Developer mode may need to be enabled.
  • Usage: Run run.cmd to start the system; interact via the system tray icon.
  • Links: Releases, Demo Gallery

Highlighted Details

  • All-in-one installer for simplified setup and updates.
  • System tray icon for managing bot components and server.
  • CLI scripts for generating infinite zoom videos.
  • Support for in/out-painting and img2img ("riffing").
  • Negative prompt and clip-guided model support.

Maintenance & Community

The project has seen recent updates, with the latest release focusing on an all-in-one installer. Information on community channels or active contributors is not readily available in the README.

Licensing & Compatibility

The README does not explicitly state a license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is Windows-specific and requires a high-end NVIDIA GPU. Clip-guided models have a performance penalty. A GUI is listed as "coming soon(tm)".

Health Check
Last commit

2 years ago

Responsiveness

1 day

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

Explore Similar Projects

Feedback? Help us improve.