Do I need an API key or special access to use this?

If MetaMuseImageTextToImageApi is configured to call a hosted Muse Image 1.0 endpoint, you’ll need valid access credentials (API key or token). Configure them in the node or your ComfyUI settings as directed by the node’s documentation. If your setup uses a local or proxied backend, follow that provider’s setup instructions instead.

How can I control output size or aspect ratio?

Output dimensions are determined by the MetaMuseImageTextToImageApi node (if those controls are exposed). SaveImageAdvanced only manages file saving, not image generation size. If size controls aren’t available, guide composition via prompt language (e.g., "vertical poster", "ultra-wide panorama") and optionally add a separate upscaler or resize node downstream if you need larger outputs.

Can this workflow use image references or edit existing images?

This workflow is text-only and takes no file inputs. To use image references or perform image-to-image edits, start from a workflow that includes image input nodes and reference/conditioning modules compatible with Muse Image 1.0.

How do I get repeatable or varied results?

If the MetaMuseImageTextToImageApi node exposes a seed parameter, set a fixed seed for repeatable outputs or switch to a new seed for variations. Without an explicit seed, results may vary between runs. Keep prompts versioned so you can return to a prior configuration easily.

Muse Image 1.0: Text to Image

This ComfyUI workflow turns plain-language prompts into polished images using Meta’s Muse Image 1.0 model. The MetaMuseImageTextToImageApi node is the core of the pipeline: it takes your text prompt, sends it to the Muse Image 1.0 backend for inference, and returns a single generated image. Muse Image 1.0 is strong at following detailed instructions and composing multiple elements from text, making it well-suited for scenes with multiple subjects, specific styles, and clearly defined constraints—all without requiring any file inputs.

Once the image is generated, SaveImageAdvanced handles the final render to disk. You control where the file is written, how it’s named, and the output format, making it easy to organize iterations and compare variations. The minimal two-node design keeps the workflow fast and focused: edit the prompt in MetaMuseImageTextToImageApi, run, and collect results from SaveImageAdvanced. This is ideal for concept exploration, rapid prototyping, and producing on-brand visuals for marketing or social channels.

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.

cbca4aa41ae7.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