Connects and controls ComfyUI via API to generate and edit high-quality images with token-saving efficiency.
This skill provides a professional interface for Claude to interact with ComfyUI, enabling seamless image generation and editing tasks directly from the command line. It features an optimized Python client that handles prompt injection, automatic asset uploads, and result polling while utilizing a template-mapping strategy to minimize token usage. Whether creating text-to-image art or performing complex image-to-image edits, this skill streamlines the creative workflow by managing local workflow JSONs and delivering outputs directly to the user without bloating the LLM context window with base64 data.
Key Features
01Extensible architecture for adding new API-formatted JSON templates
02Automated ComfyUI API integration for remote image generation
03Token-saving template mapping to avoid sending large workflow JSONs
04Customizable orientation presets for portrait and landscape outputs
05Automatic image upload handling for image-to-image editing workflows
064,226 GitHub stars
Use Cases
01Scaling AI creative workflows by integrating ComfyUI into an agentic development environment
02Performing automated image-to-image edits and style transfers
03Generating high-quality AI art from text prompts using pre-configured models
