A command for generating an image from a text description using ComfyUI, a tool for running image-generation models locally.

Checking available image models and generating an image from a supplied prompt.

It helps create images from prompts without requiring the user to manually choose or download a model when none is installed.

gen — Command by sandyup

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/sandyup/comfyui-mcp/gen

Clone the repo

git clone --depth 1 https://github.com/sandyup/comfyui-mcp

Or install comfy, the plugin that ships this one along with the rest of its 32 skills, 11 commands, 4 agents, 2 hooks.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,450 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 89% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00011	$0.01450
Opus 5	$0.00005	$0.00725
Sonnet 5	$0.00002	$0.00290
Haiku 4.5	$0.00001	$0.00145

Measured 2d ago against content hash 863e436b838d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

89% identical to gen — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugin/commands/gen.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/comfy-gen — Generate an Image

The user wants to generate an image using ComfyUI. Their prompt is provided as the argument to this command.

Instructions

Parse the user's prompt. The argument after /comfy-gen is the image description: $ARGUMENTS

If no argument was provided, ask the user what they'd like to generate.
Check available models. Use the list_local_models tool with model_type: "checkpoints" to see what checkpoints are installed.
If no checkpoints are installed — acquire one automatically.

Do NOT ask the user to download a model. Instead, find and download one yourself:

Option A — CivitAI (preferred if CIVITAI_API_TOKEN is set):
- Use WebFetch to search CivitAI's REST API: https://civitai.com/api/v1/models?query=SDXL&types=Checkpoint&sort=Most+Downloaded&limit=5
- Pick the top result that matches the user's needs (SDXL for general, Flux for quality, etc.)
- Get the download URL from the model version: https://civitai.com/api/download/models/{modelVersionId}?token={CIVITAI_API_TOKEN}
- Use download_model with target_subfolder: "checkpoints" to download it
Option B — HuggingFace (default):
- Use search_models to find a suitable checkpoint (e.g., query "SDXL" or "stable diffusion xl")
- Find the direct .safetensors download URL from the model page (typically https://huggingface.co/{repo}/resolve/main/{filename})
- Use download_model with target_subfolder: "checkpoints" to download it
Sensible defaults by category:
- General purpose: SDXL base (stabilityai/stable-diffusion-xl-base-1.0)
- Fast generation: SDXL Turbo or Lightning
- High quality: Flux.1 schnell or dev (if user has enough VRAM)
- Anime: Anything-XL or similar
Tell the user what you're downloading and why. Large checkpoints can be 2-7 GB.
Create the workflow. Use the create_workflow tool with:
- template: "txt2img"
- params: Include positive_prompt from the user's input. Set checkpoint to the model filename. Use sensible defaults (1024x1024 for SDXL, 20 steps, cfg 8).

Read the full file on GitHub · 111 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 111 lines · 11 tokens per session scan A 863e436b838d

Subscribe to this mod's changes

gen is a command published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,450 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to gen, differing in 22 lines, and is treated as a copy.

Creative and media

gen

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

/comfy-gen — Generate an Image

Instructions

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

converge