Providers and ModelsByteDance

Seedream 5.0 Pro

Seedream 5.0 Pro
ByteDance · Image Generation
POST /v1/images/generations

Premium Seedream image model that splits one image into editable layers, edits by coordinate or sketch marker, and fuses up to 10 references.

At a glance

FieldValue
Model idseedream-5-0-pro
Model release date2026-07-08
Input modalitiesText, Image
Output modalitiesImage
Context window-
Weight precision-
RegionMalaysia
Featuresimage_generation, image_editing, layer_decomposition, interactive_editing, multi_reference, text_rendering, multilingual_text, transparent_background
Native inferenceNo
NewYes
Supported endpointsPOST /v1/images/generations
Alternate model idsbytedance/dola-seedream-5-0-pro-260628, bytedance/seedream-5-0-pro, byteplus/dola-seedream-5-0-pro-260628, byteplus/seedream-5-0-pro, dola-seedream-5-0-pro-260628, seedream-5-0-pro-260628, seedream-5-pro, seedream-5.0-pro

Pricing

ChargeSpecRate
Output up to 2.61MPper image$0.075
Output above 2.61MPper image$0.150
Layer decomposition up to 2.61MPper image$0.0375
Layer decomposition above 2.61MPper image$0.075
Extra input imageper input image after the first$0.005

Example request

$curl https://api.empiriolabs.ai/v1/images/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "seedream-5-0-pro", "prompt": "a misty forest at dawn", "size": "1024x1024"}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Text prompt. With image attached, becomes an editing or fusion instruction.
imagearrayno-Reference image URL, data URI, or uploaded image object. Seedream 5.0 Pro supports up to 10 reference images, and exactly one for layer decomposition or a transparent background.
imagesarrayno-Alias for image. Use this for multiple uploaded image references.
layer_decompositionbooleannofalseSplit one input image into a base image plus up to 16 transparent PNG layers, each returned with its stacking order, its position in the base image, a name, and a description. Requires exactly one input image. The prompt is optional and can name the elements or coordinate regions to separate.
aspect_ratioenumno"auto"Auto lets the model choose dimensions within the selected resolution tier. Explicit ratios use the preset size for that tier. · Allowed: auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9
prompt_optimization_modeenumno"standard"Standard prioritizes prompt adherence and image quality. Fast reduces generation latency with slightly lower image quality. · Allowed: standard, fast
qualityenumno"2K"Seedream Pro resolution tier. 1.5K has the same price as 1K and provides higher resolution. Defaults to 2K. In layer decomposition, leaving this unset matches the input image instead. · Allowed: 1K, 1.5K, 2K
sizestringno-Resolution tier or explicit pixel size such as 1K, 1.5K, 2K, or 2048x1152. Explicit pixels override aspect_ratio and quality. Layer decomposition accepts tiers or auto only.
use_custom_sizebooleannofalseUse custom_width and custom_height instead of preset aspect_ratio and quality.
custom_widthnumberno-Custom output width in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1]. · Range: 15 – 8600
custom_heightnumberno-Custom output height in pixels. Total area must be in [0.92MP, 4.62MP] and aspect must be in [1:16, 16:1]. · Range: 15 – 8600
watermarkbooleannofalseWhen enabled, the generated image includes an AI-generated provenance watermark. EmpirioLabs does not add a separate watermark.
output_formatenumno"png"Output image file format. In layer decomposition this sets the base image format, and layers are always returned as PNG. · Allowed: jpeg, png
response_formatenumno"url"Return signed image URLs by default, or include base64 image data when b64_json is requested. · Allowed: url, b64_json
backgroundenumno"opaque"Transparent keeps the alpha channel so the output has no background. Supported when editing exactly one input image that already has an alpha channel, and requires png output. · Allowed: opaque, transparent

Notes

Modes

  • Text to image
  • Single or multi-image to image
  • Interactive editing with coordinate or sketch markers
  • Layer decomposition into a base image plus up to 16 layers

Interactive editing

Mark the region to change directly on the input image with a sketch, circle, or arrow, then describe it in the prompt. For exact placement, use coordinate tags on a 0 to 1000 normalized grid:

Place the subject from image 1 <bbox>179 283 796 986</bbox> at the position in image 2 <bbox>118 331 933 871</bbox>.

Layer decomposition

Set layer_decomposition to true with exactly one input image to split it into a base image plus up to 16 transparent PNG layers. Every returned image carries its stacking order as z_index, and each layer also carries its position in the base image as bounding_box.absolute and bounding_box.normalized, plus a name and a description. Leave the prompt empty to let the model choose the elements, or name the elements or coordinate regions to separate. Resolution accepts 1K, 1.5K, or 2K, and matches the input image when unset.

Prompt optimization

  • Standard (default): prioritizes prompt adherence and image quality
  • Fast: reduces generation latency with slightly lower image quality

Limits

  • One output image per request, except layer decomposition, which returns the base image plus its layers
  • Up to 10 reference images, and exactly one for layer decomposition or a transparent background
  • 1K, 1.5K, and 2K resolution tiers
  • PNG or JPEG output, and layers are always PNG
  • A transparent background needs one input image that already has an alpha channel, and PNG output
  • No grouped output, streaming, or web search

Billing

Layer decomposition bills every returned image, the base image and each layer, at half the standard per-image rate, tiered on the pixel count of that image.

Content safety

Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/seedream-5-0-pro.