comfyui-mcp
01Plugin Claude Code
ComfyUI integration for Claude Code — workflow execution, visualization, model management, and skill generation.
Plugin Claude Code
ComfyUI integration for Claude Code — workflow execution, visualization, model management, and skill generation.
Plugin Claude Code
Claude Code plugin for ComfyUI — generate images, visualize workflows, manage models, and explore custom nodes.
Agent
Diagnoses ComfyUI workflow failures by analyzing logs, history, and node definitions.
Agent
Explores ComfyUI custom node packs and generates complete skills.
Agent
Analyzes ComfyUI workflows for performance issues and suggests optimizations.
Agent
Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.
Command
Parameter sweep generation across multiple values.
Command
Diff two ComfyUI workflows to see what changed.
Command
Convert between ComfyUI UI format and API format workflows.
Command
Diagnose why a ComfyUI workflow failed.
Command
Direct a short film from a story. Generates scenes, frames, and video clips.
Command
Browse and inspect generated ComfyUI outputs.
Command
Generate an image with ComfyUI from a text prompt.
Command
Install a ComfyUI custom node pack.
Command
Generate a Claude skill for a ComfyUI custom node pack.
Command
Run a multi-step generation recipe (portrait, hires-fix, style-transfer, etc.).
Command
Visualize a ComfyUI workflow as a mermaid diagram.
Hook
Runs before the agent uses a tool for mcp__plugin_comfy_comfyui__enqueue_workflow and mcp__plugin_comfy_comfyui__restart_comfyui tool calls, executing vram-check.mjs and save-warning.mjs via node (2 commands). From artokun/comfyui-mcp.
Hook
Runs after a tool call finishes for mcp__plugin_comfy_comfyui__.* tool calls, executing job-complete-notify.mjs via node. From artokun/comfyui-mcp.
Skill Claude CodeCodex
Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.
Skill Claude CodeCodex
Anime/illustration text-to-image (ANIMA 1.0, 2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNet.
Skill Claude CodeCodex
Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup, dataset prep, training params, and using the result in the anima-base workflow.
Skill Claude CodeCodex
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
Skill Claude CodeCodex
Diagnose and fix video/image color OBJECTIVELY with the getimage (action:"analyzecolor") tool (scopes/stats such as black/white points, contrast, saturation, clipping, cast) instead of eyeballing a contact sheet. Covers the "washed out" signature, why reference color-match (mkl/ColorMatch/ColorMatchAdobe) CAN'T add…