Docs

Start

Docs

Start

All Models

Seedream 5.5 API

Seedream 5.5 turns written briefs into detailed scenes and revises supplied images with natural-language direction. Create photographic concepts, develop a reference through targeted changes, or generate a subject with a transparent background for use in another design.

Try in Studio

Mode

Prompt *

Aspect ratio

Format

Resolution

More options (1)

Background

Generate

Pricing depends on the selected inputs. See the rates below.

A glass observatory glows among silver dunes beneath a crescent moon.

Seedream 5.5 Text to Image API example

curl -X POST https://api.protoface.com/v1/run/bytedance/seedream-5.5 \
  -H "Authorization: Bearer $PROTOFACE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "image.generate",
  "prompt": "A red fox resting beside a woodland stream, soft morning light.",
  "aspect_ratio": "1:1",
  "background": "auto",
  "output_format": "png",
  "resolution": "1k"
}'

Replace example input URLs with your own public URLs or uploaded asset IDs. This request uses the selected mode and settings.

Seedream 5.5 Edit API example

curl -X POST https://api.protoface.com/v1/run/bytedance/seedream-5.5 \
  -H "Authorization: Bearer $PROTOFACE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "image.edit",
  "images": "https://example.com/your-image.png",
  "prompt": "A red fox resting beside a woodland stream, soft morning light.",
  "background": "auto",
  "output_format": "png",
  "resolution": "1k"
}'

Replace example input URLs with your own public URLs or uploaded asset IDs. This request uses the selected mode and settings.

API documentation: submit a run and retrieve its output →

Supported modes

Text to Image

Describe a scene, subject and visual treatment. Choose a solid background for a complete image or transparent PNG for an isolated asset.

image.generate

Edit

Supply images and describe what to change and preserve. Use transparent PNG to extract a subject for another composition.

image.edit

Image examples

Original image before editing — A reference edit changes the interior glow to cyan and the traveler’s cloak to violet.

A reference edit changes the interior glow to cyan and the traveler’s cloak to violet.

An isolated glass jellyfish with native transparency.

The observatory extracted from its setting with a transparent background.

What you can create

Atmospheric world building

Explore cinematic environments with directed lighting, materials and composition. Describe the scene, focal subject and mood together to develop a coherent visual concept.

Transparent creative assets

Create isolated subjects with native alpha for composites, illustrations and design systems. Use transparent PNG output when the subject needs to sit on another background.

Reference-guided revisions

Provide an image and explain the changes to make, along with the geometry, subjects and details to retain. Multiple references can guide a combined composition.

Pricing

Image generation

Price per run for each listed option.

Offering	Price (USD)
Resolution: 1K	$0.02 / run
Resolution: 1.5k	$0.02 / run
Resolution: 2K	$0.04 / run

Background: auto, transparent, opaque (same price).

Image editing

Price per run for each listed option.

Offering	Price (USD)
Images count: 1 · Resolution: 1K	$0.03 / run
Images count: 1 · Resolution: 1.5k	$0.03 / run
Images count: 1 · Resolution: 2K	$0.05 / run
Images count: 2 · Resolution: 1K	$0.04 / run
Images count: 2 · Resolution: 1.5k	$0.04 / run
Images count: 2 · Resolution: 2K	$0.06 / run
Images count: 3 · Resolution: 1K	$0.05 / run
Images count: 3 · Resolution: 1.5k	$0.05 / run
Images count: 3 · Resolution: 2K	$0.06 / run
Images count: 4 · Resolution: 1K	$0.06 / run
Images count: 4 · Resolution: 1.5k	$0.06 / run
Images count: 4 · Resolution: 2K	$0.07 / run

Background: auto, transparent, opaque (same price).

Text to Image options

Option	Details	Default
Prompt * `prompt`	The positive prompt for the generation.	`—`
Aspect ratio `aspect_ratio`	The aspect ratio of the generated image. Defaults to 1:1. Options: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9.	`"1:1"`
Background `background`	Whether the image has a transparent background. 'auto' lets the model decide from your prompt and output format; 'transparent' returns an image with an alpha channel (needs output_format png); 'opaque' always returns a solid background. Options: auto, transparent, opaque.	`"auto"`
Format `output_format`	The format of the output image. PNG is the default; a transparent background needs PNG. Options: jpeg, png.	`"png"`
Resolution `resolution`	The output resolution tier. 1k and 1.5k cost the same; 2k is the highest. Options: 1k, 1.5k, 2k.	`"1k"`

Edit options

Option	Details	Default
Images * `images`	Public URLs, data URIs, or asset ids.	`—`
Prompt * `prompt`	The positive prompt for the generation.	`—`
Aspect ratio `aspect_ratio`	The aspect ratio of the generated image. If not specified, it is determined automatically from the input image. Options: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9.	`—`
Background `background`	Whether the image has a transparent background. 'auto' lets the model decide from your prompt and output format; 'transparent' returns an image with an alpha channel (needs output_format png); 'opaque' always returns a solid background. Options: auto, transparent, opaque.	`"auto"`
Format `output_format`	The format of the output image. PNG is the default; a transparent background needs PNG. Options: jpeg, png.	`"png"`
Resolution `resolution`	The output resolution tier. 1k and 1.5k cost the same; 2k is the highest. Options: 1k, 1.5k, 2k.	`"1k"`

Run Seedream 5.5 on Protoface

Use Seedream 5.5 in Protoface Studio without writing code. Choose your inputs and generation settings, then generate with affordable, usage-based pricing. For your own AI app or workflow, use the Protoface API to submit generations and retrieve their outputs.

Create in Studio →Integrate the API →Protoface pricing →

Model publisher

About ByteDance

ByteDance’s Seed organization develops AI models for visual generation, audio creation and multimodal interaction. Its research includes the Seedance, Seedream and Seed Audio families. Seed models also support creative and productivity applications, connecting research with tools for exploring ideas, producing media and assisting everyday work.