Home › Meta Model API lesson 3: Muse Image

Meta Model API lesson 3: Muse Image

Last checked

Muse Image creates and edits images in a conversation: describe an image, get it back, then refine it turn by turn, or edit an existing image and keep the rest intact.

Step by step

  1. Call client.responses.create(model="muse-image-1.0", input="…") with your description.
  2. Read the image from the response output.
  3. Send a follow-up in the same conversation to refine it (colours, framing, text).
  4. To edit, send an existing image with an instruction; it changes only what you ask.
  5. For one-off jobs, use the /v1/images/generations and /v1/images/edits endpoints.

Try it: examples

Good to know

Sources (official pages, read Nov 8, 2026)

Written from Meta's official documentation and product pages; we don't run hands-on tests. Features and limits vary by plan and country.

Report an error on this page