Do I have to use JSON, or can I just type plain text?

Plain text works fine. If you do provide a JSON string, the JsonExtractString node can pull a specific field (e.g., "style") to help auto-assemble the prompt. Otherwise, set the style with the ComfySwitchNode.

Which model does this workflow use, and can I change it?

The generation happens inside the CustomCombo and the generator node (ID e46f5b18-9edb-4755-bec5-b38521684b4c). If your setup exposes a model selector in that combo, you can swap it. Otherwise, replace the combo/generator with your preferred text-to-image node configured for tattoo-friendly outputs.

My results look too photographic or colorful. How can I get cleaner tattoo linework?

Use a line-focused style in the ComfySwitchNode (e.g., blackwork or fine-line), and add prompt terms like "line art, high contrast, minimal shading, no gradients." Avoid watercolor or painterly styles for strict stencil-ready looks.

Where are images saved?

SaveImage writes to your ComfyUI output directory (by default, ComfyUI/output). You can adjust the filename or subfolder settings in the SaveImage node if needed.

Tattoo Generator - ComfyUI Workflow

This ComfyUI Tattoo Generator turns written ideas into clean tattoo concept images using a streamlined, prompt-first pipeline. You type your idea in a PrimitiveStringMultiline node, optionally provide a small JSON snippet, choose a style with a ComfySwitchNode, and the workflow assembles a polished prompt with StringConcatenate. A ResolutionSelector lets you pick a canvas size that suits patch-style, sleeve elements, or flash-sheet compositions. The core image is produced by the generation node identified as e46f5b18-9edb-4755-bec5-b38521684b4c, wrapped by a CustomCombo that encapsulates the underlying text-to-image model and default inference settings. You can preview instantly with PreviewAny and export final images via SaveImage.

Technically, the prompt flow is handled by string utilities and simple logic: JsonExtractString can pull a field (for example, a preferred style) from a JSON string if you supply one; ComfySwitchNode toggles between built-in tattoo aesthetics (e.g., blackwork, fine-line, geometric) and feeds that choice into StringConcatenate to form the final prompt. ResolutionSelector passes width/height to the generator, ensuring the model inside the CustomCombo receives consistent parameters. The result is a focused, tattoo-oriented text-to-image workflow that encourages clear subject descriptions and style discipline, ideal for iterating fast on client briefs or exploring variations before committing to a stencil.

API

Use this workflow from code

Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.

90d086fef9e3.json

Fetching workflow JSON…

Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.

// Install (beta)
npm i @comfyorg/sdk

// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");

The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).

Comfy Cloud API access requires a plan with an API key.

SDK docs Get an API key

FAQ

Frequently Asked Questions