MCP / Models / Image editing

Muse Image Edit MCP: precise edits of up to ten pictures

Meta's Muse Image Edit makes precise edits that change only what you ask, from one to ten pictures you send as references. 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 / imageImage editingMetaCommercial use
Muse Image Edit sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Muse Image Edit 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-edit.md. Help me connect the FlyMy.AI MCP to this assistant, then run Muse Image Edit (flymyai/muse-image-edit) for this task: Replace the background of the photo I attach with a desert road at dusk using Muse Image Edit.
Open FlyMy.AIDownload brief

What Muse Image Edit does

Send images, one to ten pictures to edit or to use as references, and say in prompt, up to 10,000 characters, what to do: the edit changes only what you ask, and several pictures can be composed into one result. 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 roughly 2.5 megapixels whatever the ratio, and chooses the shape itself when you leave it out. num_images makes one to four results and output_format is webp (the default), jpeg or png. Output: images, one file per result.

It is billed per result, times num_images, and the pictures you send are not charged for. It does not make a picture from text alone (Muse Image does), take custom pixel sizes or make video.

You need the right to use the pictures you send.

Muse Image Edit inputs

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

InputType, values and default
# prompt
string required What to change in the pictures, or how to combine them, up to 10,000 characters
# images
string required One to ten pictures to edit or to use as references, links or uploads
# 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 results to make, 1-4; the price is $0.01 each
# output_format
string optional Allowed: jpeg, png, webp 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.

“Replace the background of the photo I attach with a desert road at dusk using Muse Image Edit.”runs flymyai/muse-image-edit
“With Muse Image Edit, change the color of the jacket in my photo to deep green and keep everything else the same.”runs flymyai/muse-image-edit
“Edit the picture I attach with Muse Image Edit: add the headline "Grand opening" in clean bold type.”runs flymyai/muse-image-edit

Muse Image Edit 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 Edit 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-edit",
  "input": {
    "prompt": "Replace the background with a marble table by a sunny window",
    "images": [
      "https://example.com/front.jpg",
      "https://example.com/back.jpg"
    ]
  }
}

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-edit/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/muse-image-edit/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Replace the background with a marble table by a sunny window' \
  -F 'images=["https://example.com/front.jpg", "https://example.com/back.jpg"]'

Questions about Muse Image Edit

Do I need a Meta API key for Muse Image Edit?

No. Muse Image Edit 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 Edit 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 Edit in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Replace the background of the photo I attach with a desert road at dusk using Muse Image Edit." Your agent reads the inputs with get_model_schema and runs flymyai/muse-image-edit with run_model.

What does Muse Image Edit need as input?

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

Can I call Muse Image Edit from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/muse-image-edit/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.