Bytedance Seedream V3

Playground

ByteDance Seedream V3 is a state-of-the-art text-to-image model that creates photorealistic, high-detail images with artistic flair. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedream v3 — bytedance/seedream-v3

Seedream v3 is a high-quality text-to-image model built for fast, photorealistic generation with strong composition and detail. Write a clear prompt describing subject, scene, lighting, and style, and it produces clean, lifelike images suitable for marketing creatives, portraits, lifestyle photography concepts, and general visual production.

Key capabilities

Text-to-image generation with strong realism and fine detail
Reliable composition across custom sizes (set width/height directly)
Good lighting and material rendering for lifelike results
Efficient for rapid iteration with controllable randomness via seed

Use cases

Lifestyle and street-style photography concepts
Portrait generation with realistic skin, hair, and fabric detail
Marketing creatives and ad-style key visuals
Product and brand imagery with controlled lighting
Rapid ideation for concepts, thumbnails, and mood boards

Pricing

Output	Price
Per image	$0.027

Parameters

prompt (required): Text description of what to generate
width / height: Output size
guidance_scale: Prompt adherence strength (higher = stricter; too high may reduce naturalness)
seed: Random seed (-1 for random; fixed value for reproducible results)

Prompting guide

A stable prompt structure:

Subject: who/what is in frame
Action: what they are doing
Scene: location + background details
Lighting: time of day, key light, contrast
Style: photorealistic, street photography, cinematic, etc.

Template: A [subject] [action] in [scene], [lighting], [camera/framing], [style], high detail.

Example prompts

A young girl with curly hair eating ice cream, colorful city background, realistic lighting, street-style photography look, lifelike details, shallow depth of field.
Close-up portrait of a man in soft window light, natural skin texture, 85mm lens look, subtle film grain, photorealistic.
Studio product photo of a minimalist sneaker on a clean backdrop, softbox lighting, crisp shadow, premium advertising style.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v3" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1024*1024",
    "guidance_scale": 2.5,
    "seed": -1,
    "enable_base64_output": false,
    "enable_sync_mode": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
prompt	string	Yes		-	The positive prompt for the generation.
size	string	No	1024*1024	512 ~ 2048 per dimension	The size of the generated media in pixels (width*height).
guidance_scale	number	No	2.5	0.0 ~ 20.0	The guidance scale to use for the generation.
seed	integer	No	-1	-1 ~ 2147483647	The random seed to use for the generation. -1 means a random seed will be used.
enable_base64_output	boolean	No	false	-	If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
enable_sync_mode	boolean	No	false	-	If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Bytedance Seededit V3 Bytedance Seedream V3.1