Clay cafe conversationExample 01
Seedream 5.0 Flash
Seedream 5.0 Flash API by Seedream on TTAPI supports text-to-image, image editing, reference-driven creation, and async image workflows at a fixed per-image price.
InputsText + imageup to 10 references
Output2KPro and Flash
FlowAsync + Syncid or image result
Price1.8 quota/ image
Clay cafe conversationExample 01
Four-style portrait transferExample 02
Flower arrangement compositeExample 03
Sixteen puppy scenesExample 04Examples
Seedream official image examples
Place two people at a café table, chatting and laughing in a charming clay-animation advertisement style.
Create a single 4×4 panel image of one puppy across sixteen scenes, changing style while preserving the same subject.
Create an elegant close portrait of a pale-brown deer against a dark background with soft natural expression.
Design a minimalist Plant Killer emblem with white circular radial linework against a solid black field.
Apply four contrasting reference-image styles to one male subject while keeping his recognizable appearance.
Design a trendy blind-box app screen with violet gradients, a clean search bar, commerce icons and playful cards.
Design an upscale travel-resort flyer on deep teal with a subtle diamond grid and thin flowing white lines.
Arrange flowers from the supplied references in the provided vase, then place it on the reference table.
Compose a warm overhead scene around an oversized white round table with blue central ornament and scattered objects.
Capabilities
What you can build with Seedream 5.0 Flash
Text to image
Create high-density visuals, posters, illustrations, and realistic photography from a prompt.
Image editing
Edit one reference image with a natural-language instruction while preserving its structure.
Multi-image fusion
Combine two to ten reference images into a unified composition.
Layer and interactive editing
Split an image into layers or use coordinates and annotations for targeted edits.
Pricing
Per-action, in quota
Usage is metered in quota by model, action, and output settings.
API request
Headers and submit parameters
Use the endpoint below with your TTAPI key and the request fields shown.
/sd/api/v3/images/generations/tasksSubmit Seedream text, reference, fusion, layer, or interactive-edit task.
Official reference/sd/api/v3/images/generations/tasks/{id}Retrieve a Seedream asynchronous task using the returned id.
Official reference/sd/api/v3/images/generationsGenerate a Seedream image synchronously from text.
Official referenceHeaders
TT-API-KEYstringrequiredTTAPI API key sent in the request header.
Content-Typestringrequiredapplication/json.
Body
modelenumrequiredSeedream model ID: doubao-seedream-5-0-pro-260628 or doubao-seedream-5-0-flash-260915.
promptstringrequiredPrompt describing the image or edit.
imagestring | string[]conditionalRequired for image workflows: one URL string for image-to-image, interactive edit, or layer decomposition; an array of 2–10 URLs for multi-image fusion. Image-to-image supports jpeg/png/webp/bmp/tiff/gif/heic/heif, aspect ratio 1:16–16:1, up to 30 MB.
sizestringoptionalGeneration: 1K, 1.5K, 2K (default), or pixel values such as 2048x1024. Layer decomposition: 1K, 1.5K, 2K, or auto (default, preserves input size); pixel values are not supported for layers.
output_formatenumoptionalpng or jpeg; defaults to jpeg.
response_formatenumoptionalurl or b64_json; defaults to url. Download URLs are valid for 24 hours.
backgroundenumoptionaltransparent or opaque (default). Transparent backgrounds are for image-to-image with an alpha-channel input; output defaults to png. Not listed in the text-to-image, multi-image, interactive-edit, or layer-decomposition workflow schemas.
watermarkbooleanoptionalWhether to add the AI Generated watermark; defaults to true.
optimize_prompt_optionsobjectoptionalmode defaults to standard. fast reduces generation time but is not supported by Seedream 5.0 Flash.
layer_decompositionbooleanconditionalDefaults to false. Set true with image and a prompt using <bbox> coordinates for layer decomposition, up to 16 layers. Both Pro and Flash are listed. output_format controls the base image; layers are always png.
execution_expires_afterintegeroptionalTask timeout in seconds, 3600–259200; defaults to 172800.
priorityintegeroptionalExecution priority from 0 to 9; defaults to 0.
safety_identifierstringoptionalHashed end-user identifier, maximum 64 characters.
Integrate
From key to first result
Copy the resolved endpoint, authentication headers, and request body for this model.
curl --request POST \
--url https://api.ttapi.io/sd/api/v3/images/generations/tasks \
--header 'TT-API-KEY: $TTAPI_KEY' \
--header 'Content-Type: application/json' \
--data '{"model":"doubao-seedream-5-0-flash-260915","prompt":"A high-density infographic explaining the six major types of tea, with a watercolor flavor wheel and labeled brewing temperatures.","size":"2K","output_format":"jpeg","response_format":"url","watermark":false}'
