Skip to content
Agentmart
Submit a tool

comfyui

Drive ComfyUI (local Stable Diffusion / image-gen pipeline) via its HTTP API to generate and edit images.

Skill by metaspartan

IndexedMIT★ 32
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/metaspartan-comfyui

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Drive ComfyUI (local Stable Diffusion / image-gen pipeline) via its HTTP API to generate and edit images. Use when the user has ComfyUI running and wants image generation/upscale/img2img workflows.

Use cases: backend, data, writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/comfyui

What's inside

Skill name
comfyui
Description
Drive ComfyUI (local Stable Diffusion / image-gen pipeline) via its HTTP API to generate and edit images. Use when the user has ComfyUI running and wants image generation/upscale/img2img workflows.
License
MIT
Instructions
42 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# ComfyUI

ComfyUI is a node-based Stable Diffusion pipeline with an HTTP API. Generate images by posting a workflow (prompt graph) and polling for results.

## When to use

- "generate an image of … (via ComfyUI)"
- img2img, inpainting, upscaling, or custom SDXL/Flux workflows.
- The user references ComfyUI explicitly or has it installed.

## How it works

1. **Build a workflow graph** as JSON (`prompt` API). Each node has a `class_type` and `inputs`. A minimal txt2img graph: CheckpointLoader → CLIPTextEncode (pos/neg) → EmptyLatentImage → KSampler → VAEDecode → SaveImage.
2. **Submit:** `POST /prompt` with `{"prompt": <graph>, "client_id": <id>}`. Returns a `prompt_id`.
3. **Poll history:** `GET /history/<prompt_id>` until the output image(s) appear, then fetch from `/view?filename=…`.
4. Save outputs to the workspace and state their paths.

## Minimal node template (txt2img)

```json
{
  "3": { "class_type": "KSampler", "inputs": {
      "seed": 42, "steps": 25, "cfg": 7, "sampler_name": "euler", "scheduler": "normal",
      "denoise": 1, "model": ["4",0], "positive": ["6",0], "negative": ["7",0],
      "latent_image": ["5",0] } },
  "4": { "class_type": "CheckpointLoaderSimple", "inputs": { "ckpt_name": "sdxl_base.safetensors" } },
  "5": { "class_type": "EmptyLatentImage", "inputs": { "width": 1024, "height": 1024, "batch_size": 1 } },
  "6": { "class_type": "CLIPTextEncode", "inputs": { "text": "<prompt>", "clip": ["4",1] } },
  "7": { "class_type": "CLIPTextEncode", "inputs": { "text": "<negative>", "clip": ["4",1] } },
  "8": { "class_type": "VAEDecode", "inputs": { "samples": ["3",0], "vae": ["4",2] } },
  "9": { "class_type": "SaveImage", "inputs": { "filename_prefix": "cybara", "images": ["8",0] } }
}
```

## Notes

- Default server: `http://127.0.0.1:8188` (override via the request URL).
- Use the `http` tool to submit/poll; you don't need raw `fetch`.
- For img2img/inpaint, add `LoadImage` + replace `EmptyLatentImage`; lower `denoise` (~0.5–0.75) to keep structure.
- Always state the server URL and output path in your response.

From metaspartan/cybara, MIT.

More from metaspartan/cybara

Signals

Stars
32
Forks
9
Open issues
0
Last commit (this folder)
Jun 24, 2026 (4 months ago)
Last release
Oct 24, 2026 (4 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Website
cybara.ai
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from metaspartan

Cite this page

comfyui skill. Agent Mart. https://agentmart.dev/skills/metaspartan-comfyui (last updated 2026-10-24)