bytedance/seedream/4.0

Name: Bytedance Seedream v4
Author: Bytedance

Seedream 4.0 by Bytedance - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.

Input

Prompt(string)

The text prompt used to generate the image

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Seed(integer)

Random seed to control the stochasticity of image generation.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDbytedance/seedream/4.0

Input Schema

3 parameters · 1 required · 2 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The text prompt used to generate the image
`seed`	integer	Optional	Random seed to control the stochasticity of image generation.
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 · Default: "16:9" 21:916:93:24:35:41:14:53:42:39:16

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "bytedance/seedream/4.0",
  "prompt": "A trendy restaurant with a digital menu board displaying \"Seedream 4.0 is available on fal\" in elegant script, with diners enjoying their meals.",
  "aspect_ratio": "16:9"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Bytedance Seedream v4

API README

Seedream 4.0

Seedream 4.0 is an image creation model built for complex visual instructions, polished aesthetics, and knowledge-rich compositions. Its generation system combines strong prompt following with capable text rendering and stable visual structure.

This endpoint is the text-to-image route: it creates a new image from a required prompt and does not accept reference images. Choose the separate edit route when a task needs reference images or changes to existing artwork.

Highlights

Knowledge-driven visuals. Produces educational illustrations, professional diagrams, charts, and other information-dense images that depend on visual reasoning.
Advanced text rendering. Handles complex layouts containing labels, formulas, tables, and structured written content for posters and explanatory graphics.
Strong prompt alignment. Follows detailed scene instructions while maintaining coherent structure, lighting, color, and overall aesthetics.
Versatile visual styles. Moves across photographic, illustrative, watercolor, cyberpunk, and design-oriented looks without requiring a reference image.

Pricing

Unit	Price
Per request	$0.030000

When to Use

Good fit	Consider alternatives
Educational diagrams and knowledge-rich illustrations	Editing an existing image; use the Seedream 4.0 Edit route
Posters and graphics with prominent text	Multi-reference composition or subject transfer
Detailed campaign concepts from written briefs	Workflows that require multiple outputs in one request
Stylized editorial and commercial artwork	Pixel-level masking or region-specific retouching
Wide, square, or vertical text-to-image deliverables	Video or animation generation

Prompt Guide

State the deliverable and audience, then specify the subject, layout, exact text, visual hierarchy, and style. For diagrams or posters, enumerate required sections and quote every label. Add an integer seed when you want to revisit a generation starting point.

{
  "prompt": "Create a clean museum-style educational poster explaining the water cycle. Arrange four labeled stages clockwise around a central landscape: \"EVAPORATION\", \"CONDENSATION\", \"PRECIPITATION\", and \"COLLECTION\". Use precise arrows, readable bold labels, soft blue and green colors, balanced negative space, and a polished editorial infographic style.",
  "aspect_ratio": "4:3",
  "seed": 42
}

Technical Specs

Spec	Value
Model ID	bytedance/seedream/4.0
Input	Required text prompt
Aspect ratios	21:9, 16:9 (default), 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
Optional controls	Integer seed
Reference images	Not accepted by this route
Output	One downloadable image URL
Execution	Async

Seedream 4.0 Edit — Edit or transform images with the matching model generation
Seedream 4.5 — Newer text-to-image generation in the Seedream family