Bytedance Seededit V3

Playground

SeedEdit 3.0 by Bytedance enables prompt-guided image editing for precise object, scene, and layout changes without disrupting composition. Ready-to-use REST API, high performance, no coldstarts, affordable pricing.

Features

SeedEdit v3 — bytedance/seededit-v3

SeedEdit v3 is a prompt-based image editing model for fast, high-quality transformations. Provide a source image and a short instruction, and the model performs targeted edits—such as changing hair, clothing, colors, backgrounds, or adding/removing elements—while keeping the overall composition and identity stable.

Key capabilities

Prompt-driven image editing from a single input image
Strong preservation of subject identity and scene structure for everyday edits
Works well for localized edits (hair, face details, clothing) and global adjustments (color/lighting)
Efficient for rapid iteration with controllable randomness via seed

Use cases

Portrait edits: hair color/style changes, light makeup tweaks, accessory edits
E-commerce variants: recolor outfits/products, background cleanup, consistent product shots
Marketing creatives: quick visual iterations (color mood, props, text-free adjustments)
Photo cleanup: remove small distractions, fix minor inconsistencies, improve overall clarity
Content localization: adapt visual details (e.g., wardrobe color/style) while keeping the same subject

Pricing

Output	Price
Per image	$0.027

Inputs

image (required): the source image to edit
prompt (required): the edit instruction

Parameters

prompt: what to change (and optionally what to keep)
image: input image (upload or URL)
guidance_scale: how strongly the edit follows the prompt (higher = stronger edit)
seed: random seed (-1 for random; fixed value for reproducible results)

Prompting guide

For clean edits, be explicit about what must stay the same:

Template: Keep [identity/pose/background]. Change [target]. Maintain [lighting/style realism].

Example prompts

Keep the face and pose unchanged. Change the hair to short, curly, rainbow-colored hair. Keep natural lighting and realistic texture.
Keep the subject identity and background unchanged. Change the jacket color to black and add subtle fabric texture.
Remove the object in the background and keep the subject sharp and unchanged.

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/seededit-v3" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "guidance_scale": 0.5,
    "seed": -1,
    "enable_base64_output": 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.
image	string	Yes		-	The image to edit, can be a URL or base64 encoded image.
guidance_scale	number	No	0.5	0.0 ~ 1.0	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.

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 Seedance V1.5 Pro Video Extend Fast Bytedance Seedream V3