MCP / Models / Image generation

Muse Image MCP: pictures with accurate text and plots

Meta's Muse Image follows instructions faithfully and renders fine details such as text, plots and QR codes, one to four pictures a request. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

No API key$0.01 / imageText to imageMetaCommercial use
Muse Image sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Muse Image in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/muse-image-text-to-image.md. Help me connect the FlyMy.AI MCP to this assistant, then run Muse Image (flymyai/muse-image-text-to-image) for this task: Generate a 9:16 product photo of a pair of running shoes over a wet city street at night with Muse Image.
Open FlyMy.AIDownload brief

What Muse Image does

Describe the picture in prompt, up to 10,000 characters, including any text to show. aspect_ratio sets the shape (1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, 9:21, 5:4, 4:5, 16:10 or 10:16); Muse draws at its own fixed resolution of roughly 2.5 megapixels whatever the ratio, and chooses the shape itself when you leave it out. num_images makes one to four pictures in one request and output_format is webp (the default), jpeg or png. Output: images, one file per picture.

It is billed per picture, times num_images, and the shape and the format do not change the price. It makes new pictures from text: it does not edit a picture you send (Muse Image Edit does), take custom pixel sizes or make video.

Muse Image inputs

Every input of flymyai/muse-image-text-to-image as its live schema lists them. Returns images (array).

InputType, values and default
# prompt
string required What to draw: the subject, the scene, any text to show and the style, up to 10,000 characters
# aspect_ratio
string optional Allowed: 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, 9:21, 5:4, 4:5, 16:10, 10:16 The shape: 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, 9:21, 5:4, 4:5, 16:10 or 10:16. Muse draws at its own fixed resolution of roughly 2.5 megapixels whatever the ratio; left out, it chooses the shape itself. The same price
# num_images
integer optional Allowed: 1 to 4 Default: 1 How many pictures to make, 1-4; the price is $0.01 each
# output_format
string optional Allowed: webp, jpeg, png Default: webp webp (default), jpeg or png; the same price

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Generate a 9:16 product photo of a pair of running shoes over a wet city street at night with Muse Image.”runs flymyai/muse-image-text-to-image
“Make three versions of a poster for a tech meetup about AI agents with Muse Image in one run and send me the links.”runs flymyai/muse-image-text-to-image
“Create an isometric 3D illustration of waves crashing on a cliff during a storm with Muse Image.”runs flymyai/muse-image-text-to-image

Muse Image price

$0.01 per image. A run at the default settings costs $0.01. A run costs $0.01 to $0.04, depending on num_images. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

SettingPrice
Any$0.01 per image

Call Muse Image from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/muse-image-text-to-image",
  "input": {
    "prompt": "A ceramic mug on a sunlit kitchen counter, product photo"
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/muse-image-text-to-image/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/muse-image-text-to-image/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'

Questions about Muse Image

Do I need a Meta API key for Muse Image?

No. Muse Image runs on FlyMy.AI's account, so you need no Meta key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Muse Image cost?

$0.01 per image. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

How do I use Muse Image in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Generate a 9:16 product photo of a pair of running shoes over a wet city street at night with Muse Image." Your agent reads the inputs with get_model_schema and runs flymyai/muse-image-text-to-image with run_model.

What does Muse Image need as input?

Muse Image requires prompt; it also takes 3 optional inputs, each listed on this page with its allowed values and default.

Can I call Muse Image from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/muse-image-text-to-image/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.