Home › Meta Model API lesson 3: Muse Image
Meta Model API lesson 3: Muse Image
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
- Call client.responses.create(model="muse-image-1.0", input="…") with your description.
- Read the image from the response output.
- Send a follow-up in the same conversation to refine it (colours, framing, text).
- To edit, send an existing image with an instruction; it changes only what you ask.
- For one-off jobs, use the /v1/images/generations and /v1/images/edits endpoints.
Try it: examples
- Generate
a red fox trotting through fresh snow, golden hour
- Edit
Keep this product photo exactly the same but change the background to a white marble counter.
Good to know
- Muse Image can look up real places, products and facts on its own before drawing; that search is included in the per-image price.
- Muse Image costs US$0.01 per image on the Model API page.
- Only upload reference images you have the right to use.
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.