bytedance/
Text to ImageCreate images with ByteDance Seedream 5.0 Pro on MuseSpan for multilingual posters, detailed compositions and structured graphic design. Turn a written brief into campaign artwork, packaging concepts, editorial scenes or information-rich layouts. Specify the subject, camera, materials and lighting, and quote the exact words you want in the image. Describe headings and supporting information separately to guide text hierarchy. Choose automatic 1K or 2K sizing, an aspect-ratio preset or custom dimensions, then select JPEG or PNG. Standard prompt optimization prioritizes image quality; fast mode reduces generation time. No reference image is required. Output cost depends on pixel area and image count, so review the price for the selected settings. Check generated spelling and small details before publishing.
More settings (3)
Usage-based · about $0.14 / image · $0.135 reserved per request
Pricing
Billed by actual usage; there is no fixed unit price.
Typically about $0.14 per image at default settings.
Each request temporarily reserves $0.135; 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-pro/text-to-image{
"model": "bytedance/seedream-5-pro/text-to-image",
"input": {
"prompt": "Create an original vertical poster for an imaginary urban dance and light festival. Deep midnight-blue rainy city, one adult dancer in a flowing tangerine-orange coat, dramatic rim lighting, wet pavement reflections, crisp photographic detail. Combine the cinematic image with an editorial graphic grid and generous readable margins. At the top render the exact large white title \"MIDNIGHT MOTION\" on two lines. Directly below render the exact Chinese title \"夜行节\" in bold clean lettering. At the bottom create three evenly aligned program columns, each with a small orange heading and white details: \"FRI\" above \"18:00 / LIGHT\"; \"SAT\" above \"20:00 / DANCE\"; \"SUN\" above \"19:30 / SOUND\". Keep all supplied words spelled exactly, clear hierarchy and strong contrast, coherent premium festival identity. No additional text, brands, signatures or watermarks.",
"enhance_prompt_mode": "standard",
"image_size": "auto_2K",
"num_images": 1,
"output_format": "jpeg"
}
}Input schema
| Parameter | Type | Requirement | Default |
|---|---|---|---|
| prompt | string | Required | — |
| enhance_prompt_mode | string | Optional | standard |
| image_size | object | string | Optional | auto_2K |
| num_images | integer | Optional | 1 |
| output_format | string | Optional | jpeg |
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: $REQUEST_ID" \
--header "Content-Type: application/json" \
--data '{"model":"bytedance/seedream-5-pro/text-to-image","input":{"prompt":"Create an original vertical poster for an imaginary urban dance and light festival. Deep midnight-blue rainy city, one adult dancer in a flowing tangerine-orange coat, dramatic rim lighting, wet pavement reflections, crisp photographic detail. Combine the cinematic image with an editorial graphic grid and generous readable margins. At the top render the exact large white title \"MIDNIGHT MOTION\" on two lines. Directly below render the exact Chinese title \"夜行节\" in bold clean lettering. At the bottom create three evenly aligned program columns, each with a small orange heading and white details: \"FRI\" above \"18:00 / LIGHT\"; \"SAT\" above \"20:00 / DANCE\"; \"SUN\" above \"19:30 / SOUND\". Keep all supplied words spelled exactly, clear hierarchy and strong contrast, coherent premium festival identity. No additional text, brands, signatures or watermarks.","enhance_prompt_mode":"standard","image_size":"auto_2K","num_images":1,"output_format":"jpeg"}}'
# Poll every 5 seconds for up to 25 minutes until status is completed or failed.
# Still queued (with queue_position) 5 minutes after submission: failed with queue_timeout, not charged.
# No result 15 minutes after acceptance (or no confirmation 15 minutes after submission): failed with generation_timeout, not charged.
# Any failure is final: generate again in a new directory (a new X-Request-Id).
# A 404 means the POST did not arrive: rerun this script to resend it with the same ID.
curl --fail-with-body 'https://api.musespan.com/v1/model-tasks/'"$REQUEST_ID"'' --header "Authorization: Bearer $MUSESPAN_API_KEY"