Seedream 5.5
Text to image · Image editing
Starting price $0.05 / image
Meta Muse Image makes images from a detailed description or edits them from up to 10 reference images, in any aspect ratio you type.
meta/muse-image/text-to-imageThis model has other modes with their own ids: meta/muse-image/edit.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta/muse-image/text-to-image",
"input": {
"prompt": "A vintage travel poster of a seaside town with pastel houses on a hill, a sailboat in the bay and the words \"Summer by the Sea\" in bold letters across the top."
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "meta/muse-image/text-to-image", "quote_id": "QUOTE_ID", "input": {"prompt":"A vintage travel poster of a seaside town with pastel houses on a hill, a sailboat in the bay and the words \"Summer by the Sea\" in bold letters across the top."}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | The text prompt used to generate or edit the image. |
aspect_ratio | string | Any custom output aspect ratio as "width:height", for example "16:9", "5:4", or "1920:1200". Common presets are "21:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:21". The ratio must be between 1:16 and 16:1, the range Muse supports. Only the ratio is used: Muse renders it at its own fixed resolution of roughly 2.5 megapixels, so "1920:1200" and "960:600" both return the same 1920x1200 image. If omitted, Muse chooses the output dimensions automatically. |
num_images | integer | The number of images to generate. |
output_format | string (enum) | The format of the generated image. |
sync_mode | boolean | If `True`, the image is returned as a data URI and is not persisted in the request history. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Meta Muse Image renders every image at about 2.5 megapixels; you choose only the shape, by typing any ratio from 1:16 to 16:1 or leaving it to the model. It makes up to 10 images per run, as JPEG, PNG or WebP.
The edit mode takes one to 10 images and a written instruction, so you can change a photo or build a new image from several references.
Read every label, verify plotted values and scan any QR code before relying on it.