Muse Image. Meta's image model that plans before it draws.
Meta's agentic image model generates from a prompt or edits from reference images, working out the picture before it renders it.
- Text and image input
- Framing chosen by the model
- Reference image edits
Muse Image is Meta's image generation and editing model. Where most image models render in a single pass, Muse Image reasons about the request first and then draws. It takes a prompt, or a prompt plus reference images, and chooses the framing itself: there is no aspect ratio or resolution setting to pick.
In our tests a prompt came back in 9 seconds as a 1920 by 1280 landscape, and an edit with one reference in 14 seconds as a 1600 pixel square that kept the product in its new scene. Each billed one cent. On Treza it sits in the Image Generation node's model picker. It bills from prepaid credits, and a failed generation costs nothing.
Reasons, then renders
Muse Image works out the request before drawing it, which suits briefs with several parts that all have to land.
Edits from references
Attach a product or a character and describe the new scene. Our edit kept the subject and changed the set.
One cent per image
Both of our test renders, a prompt and an edit, billed one cent each.
Large output
Our renders came back at 1920 by 1280 and 1600 by 1600 pixels, big enough to crop for most placements.
What to make with Muse Image
Real prompts, and what comes back. Every one runs as a node on the Treza canvas.
“A ceramic cup of coffee on a sunlit wooden cafe table, steam rising, shallow depth of field”
A warm landscape still with latte art.
“The same folded shirt (attached) on a white marble counter in a bright studio”
Your product moved into a new set.
“A cozy reading nook with a green armchair, a stack of books and a sleeping cat, rain on the window”
A multi-part scene with every item in place.
“A travel collage of Lisbon: a yellow tram, tiled facades and a pastel de nata”
Several subjects arranged into one image.
“This sneaker (attached) on a wet city street at night, neon reflections”
A product shot with mood.
“An illustrated map of a fantasy island with a harbor, a forest and a volcano”
A planned composition from a long brief.
Muse Image is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with Muse Image
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
Muse Image as an API, priced per image
The Muse Image API
Build a pipeline with Muse Image on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
Muse Image pricing
Prepaid credits, no subscription. Each image is charged at Muse Image's own rate from your balance, shown before you run, and a failed generation costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
Muse Image, answered
What does Muse Image cost?
OpenRouter lists no per-image price for Muse Image. In our tests a prompt and an edit with one reference each billed one cent. Treza quotes that before a run and bills from prepaid credits; a failed generation costs nothing.
Can I choose the aspect ratio?
No. Muse Image takes no aspect ratio or resolution setting and picks the framing itself. Our prompt came back as a 3:2 landscape and our edit as a square. Describe the shape in the prompt if it matters, or crop downstream.
Is Muse Image the same as Meta's Muse assistant?
Muse Image is Meta's image model, available through OpenRouter. On Treza it is a model in the Image Generation node, separate from Meta's Muse app.
How much does Muse Image cost on Treza?
Treza uses prepaid credits with no subscription. Each image is charged at Muse Image's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Muse Image through an API?
Yes. Build a pipeline that uses Muse Image and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.