This repository provides a visual interface for selecting artistic styles, artists, and camera/film types to generate Stable Diffusion prompts. It targets users, especially beginners, who find traditional text-based prompt engineering overwhelming, offering a preview-driven approach to achieve desired artistic outputs.

How It Works

The project integrates with ComfyUI, offering a gallery of reference images categorized by artists, art movements, styles, cameras, and film types. Users select an image from these categories, and the system automatically generates corresponding weighted prompts (e.g., (Picasso:1.03)), facilitating a more intuitive and visual prompt creation process compared to manual text input.

Quick Start & Requirements

• Install via ComfyUI Manager or manually: cd custom_nodes && git clone https://github.com/ZHO-ZHO-ZHO/ComfyUI-ArtGallery.git
• Requires ComfyUI.
• Restart ComfyUI after installation; a second restart may be needed if previews don't appear.
• Links: Project Assets, Workflow V1.0

Highlighted Details

• Features 280 artists, 138 art movements, 115 art mediums, 83 film types, and 47 camera lenses.
• Includes comparative tests and art style visualizations for SD3 and SDXL models.
• Supports custom image additions to the img_lists directory.
• Offers weighted prompt generation based on visual selection.

Maintenance & Community

• Active development with regular updates, including recent additions for SD3.
• Community support via QQ group (839821928).
• Project is sponsored by several individuals.
• Credits artist Rikkar for foundational work.

Licensing & Compatibility

• The repository does not explicitly state a license.
• Compatibility with commercial or closed-source projects is undetermined without a specified license.

Limitations & Caveats

The project's license is not specified, which may impact commercial use. Some image libraries were recently updated and may still be in the process of being fully uploaded or optimized for download and loading pressure.