skills.rest
timchap
timchapCOMMUNITY
Explore all skills by this author →
GitHub

comfyui

Generate images, video, and audio by running ComfyUI workflows via REST and WebSocket APIs.

Updated Jul 10, 2026
Search Tags:#workflow automation#image generation#rest api#video generation#flux#comfyui#stable diffusion
One-click install
npx skills add https://github.com/timchap/dot-hermes --skill comfyui-timchap
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/timchap/dot-hermes/tree/main/skills/creative/comfyui
Command: npx skills add https://github.com/timchap/dot-hermes --skill comfyui-timchap

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, websocket-client, comfy-cli, and includes scripts (resource) and references (resource) components.

What problem does it solve? Running ComfyUI generative pipelines programmatically requires juggling installation, model downloads, custom node dependencies, workflow JSON formats, and execution monitoring — the official CLI covers setup but not workflow execution. This Skill bridges that gap with scripts for parameter injection, batch runs, dependency checking, and output download against local or Comfy Cloud servers. ## Core Features & Use Cases - Workflow Execution: Inject parameters (prompt, seed, steps, dimensions) into API-format workflow JSON, submit to a local or cloud server, monitor progress via WebSocket, and download outputs safely. - Setup & Dependency Management: Hardware checks route users to local install or Comfy Cloud, while check_deps and auto_fix_deps detect and install missing custom nodes and models. - Batch Generation: Run a workflow N times with randomized seeds and parallel submissions up to your cloud tier limit. - Use Case: A user asks for eight variations of an SDXL image with a given prompt; the Skill verifies the server and checkpoint, injects the prompt with random seeds, runs the batch, and returns the output file paths. ## Quick Start Ask the AI to generate an image with a specific prompt using the included SDXL workflow, and it will check the server, inject your parameters, and return the output files.

Frequently Asked Questions about comfyui

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a ComfyUI workflow from the command line?▼

Use run_workflow.py with an API-format workflow JSON and a JSON args string, for example --workflow sdxl.json --args '{"prompt": "...", "seed": -1}'. The script injects parameters, submits to the server, monitors execution, and downloads outputs to your chosen directory.

How do I generate images with ComfyUI without a GPU?▼

Use Comfy Cloud, which hosts workflows on RTX 6000 Pro GPUs with common models preinstalled. Set the COMFY_CLOUD_API_KEY environment variable and pass --host https://cloud.comfy.org to the scripts; a paid subscription is required to run workflows via the API.

What hardware do I need to run ComfyUI locally?▼

Local ComfyUI needs an NVIDIA GPU with at least 6 GB VRAM (8 GB for SDXL, 12 GB or more for Flux and video), an AMD GPU with ROCm on Linux, or an Apple Silicon Mac with at least 16 GB unified memory. The hardware_check.py script probes your machine and recommends local or cloud.

Why does my ComfyUI workflow fail with class_type not found?▼

This error means a required custom node is not installed on the server. Run check_deps.py against the workflow to list missing nodes with install commands, or use auto_fix_deps.py to install them automatically via comfy node install.

Can I use editor-format workflow JSON with the ComfyUI API?▼

No, the /api/prompt endpoint and these scripts require API-format JSON where each node has a class_type field. Editor-format files with top-level nodes and links arrays must be re-exported from the ComfyUI web UI using Workflow → Export (API).

How do I run img2img or inpainting with ComfyUI scripts?▼

Pass --input-image image=./photo.png to run_workflow.py, which uploads the file and injects its server-side filename into the workflow's image parameter. For inpainting, pass a second --input-image mask_image=./mask.png alongside a denoise value around 0.4 to 0.7.

Related Skills

Explore More Design & Creative Skills→
dawsonblockdawsonblock

cli-anything-comfyui

Manage ComfyUI workflow queues and download generated images via REST API.

Community
Intermediate
artokunartokun
530

director

Orchestrate a full short film production pipeline from a text story into a final video.

Community
Advanced
SnoopiamSnoopiam

comfyui-workflow-builder

Generate production-ready ComfyUI workflow JSON files from text descriptions.

Community
Advanced
taracodlabstaracodlabs
799

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers or Inference API.

Official
Intermediate