Seedream 5

Reasons over complex prompts and can search the web, assembling multi-object scenes and topical visuals. Supports example-based reference edits and output up to 3K.

Cost

from 2 tokens

ImageProvider: BytePlus

Run generation

curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"image","model":"seedream-5","input":{"prompt":"studio portrait of a red corgi, soft light","aspectRatio":"9:16","imageSize":"2K","sourceImage":"asset://asset_...","referenceAssetUris":["asset://asset_..."]}}'

Input fields

* required

Field	Type	Default	Allowed
prompt*`prompt` Image description.	string	—	string
aspectRatio`aspectRatio`	string	9:16	9:16, 16:9, 1:1, 4:3, 3:4, 2:3, 3:2, 21:9
imageSize`imageSize`	string	2K	2K, 3K
Source image`sourceImage` Asset used as the source image for image editing.	string	—	image · asset, https, data
Reference images`referenceAssetUris` Optional reference images as asset:// URIs, HTTPS URLs, or data URIs.	array	—	image · up to 14 · asset, https, data

prompt*prompt

Image description.

Type: string
Default: —
Allowed: string

aspectRatioaspectRatio

Type: string
Default: 9:16
Allowed: 9:16, 16:9, 1:1, 4:3, 3:4, 2:3, 3:2, 21:9

imageSizeimageSize

Type: string
Default: 2K
Allowed: 2K, 3K

Source imagesourceImage

Asset used as the source image for image editing.

Type: string
Default: —
Allowed: image · asset, https, data

Reference imagesreferenceAssetUris

Optional reference images as asset:// URIs, HTTPS URLs, or data URIs.

Type: array
Default: —
Allowed: image · up to 14 · asset, https, data

Cost

from 2 tokens

2Kdefault2 tokens

3K2 tokens

The variant is selected automatically from request fields, so you do not need to send it.

Capabilities

Modestext_to_imageimage_editimage_reference

Asset slotssourceImage:imagereferenceAssetUris:image[]<=14

Run Seedream 5

Get an API key and the same request shape will work across every model in the catalog.

Get API key Open in playground