
bytedance/ seedream-5-lite/ text-to-image
Text to ImageGenerate images from text with ByteDance Seedream 5.0 Lite on MuseSpan, including typography-led posters and detailed visual concepts. Use this API for advertising ideas, illustrated scenes, product compositions and social media artwork. Write a prompt describing the subject and layout, then specify materials, lighting and the text to appear in the image. Choose an aspect ratio or an automatic 2K, 3K or 4K preset to suit the intended canvas. This capability starts from a text prompt; no reference image is required. Keep num_images and max_images at 1 for one output. Higher image-count settings can produce additional billable images. Generated text and fine details should be reviewed before publication.
More settings (2)
$0.035 / image · ~28 images per $1

Design a premium editorial poster for an imaginary botanical exhibition. A luminous apricot glass butterfly rests on a folded ivory porcelain fan, surrounded by three delicate fern fronds and a small polished pebble. Pale sage green background, warm side lighting, realistic glass caustics, crisp porcelain ridges, elegant negative space. At the top, render the exact large headline "SMALL WONDERS" in beautifully spaced dark green serif letters. Below it, render the exact small subtitle "A STUDY OF LIGHT AND NATURE". Balanced vertical composition, refined art direction, highly detailed materials. No other text, logos, signatures or watermarks.
Pricing
Unit price $0.035 / image
Billed by the number of images actually generated.
~28 images per $1
Each request temporarily reserves $0.035; you are charged for actual usage, usually within a minute: any unused amount is released and any usage above it is charged to your balance, even if that takes it below zero; while your balance is below zero, new requests are paused until a top-up covers it.
Failed generations are not charged.
API
Submit generation requests with this model ID.
/v1/model-tasksbytedance/seedream-5-lite/text-to-image{
"model": "bytedance/seedream-5-lite/text-to-image",
"input": {
"prompt": "Design a premium editorial poster for an imaginary botanical exhibition. A luminous apricot glass butterfly rests on a folded ivory porcelain fan, surrounded by three delicate fern fronds and a small polished pebble. Pale sage green background, warm side lighting, realistic glass caustics, crisp porcelain ridges, elegant negative space. At the top, render the exact large headline \"SMALL WONDERS\" in beautifully spaced dark green serif letters. Below it, render the exact small subtitle \"A STUDY OF LIGHT AND NATURE\". Balanced vertical composition, refined art direction, highly detailed materials. No other text, logos, signatures or watermarks.",
"image_size": "auto_2K",
"max_images": 1,
"num_images": 1
}
}Input schema
| Parameter | Type | Requirement | Default |
|---|---|---|---|
| prompt | string | Required | — |
| image_size | object | string | Optional | auto_2K |
| max_images | integer | Optional | 1 |
| num_images | integer | Optional | 1 |
Response
The API returns a result or a pollable asynchronous task. See the examples and Schema below for the response mode and result fields.
Code examples
Async submission returns a task ID. Poll until status is completed, then retrieve the generated content from the result. Get your API key in the console.
# Use a new directory for each new generation. Rerunning here continues this task.
set -eu
test -s model-task-id.txt || python3 -c "import uuid; print(uuid.uuid4())" > model-task-id.txt
REQUEST_ID=$(cat model-task-id.txt)
# Idempotent: resending the same bytes with the same ID never charges twice.
curl --fail-with-body --retry 3 --retry-connrefused --request POST 'https://api.musespan.com/v1/model-tasks' \
--header "Authorization: Bearer $MUSESPAN_API_KEY" \
--header "X-Request-Id: $REQUEST_ID" \
--header "Content-Type: application/json" \
--data '{"model":"bytedance/seedream-5-lite/text-to-image","input":{"prompt":"Design a premium editorial poster for an imaginary botanical exhibition. A luminous apricot glass butterfly rests on a folded ivory porcelain fan, surrounded by three delicate fern fronds and a small polished pebble. Pale sage green background, warm side lighting, realistic glass caustics, crisp porcelain ridges, elegant negative space. At the top, render the exact large headline \"SMALL WONDERS\" in beautifully spaced dark green serif letters. Below it, render the exact small subtitle \"A STUDY OF LIGHT AND NATURE\". Balanced vertical composition, refined art direction, highly detailed materials. No other text, logos, signatures or watermarks.","image_size":"auto_2K","max_images":1,"num_images":1}}'
# Poll every 5 seconds for up to 25 minutes until status is completed or failed.
# Still queued (with queue_position) 5 minutes after submission: failed with queue_timeout, not charged.
# No result 15 minutes after acceptance (or no confirmation 15 minutes after submission): failed with generation_timeout, not charged.
# Any failure is final: generate again in a new directory (a new X-Request-Id).
# A 404 means the POST did not arrive: rerun this script to resend it with the same ID.
curl --fail-with-body 'https://api.musespan.com/v1/model-tasks/'"$REQUEST_ID"'' --header "Authorization: Bearer $MUSESPAN_API_KEY"