Seedream 5.5
Text to image · Image editing
Starting price $0.05 / image
By ByteDance
ByteDance's Seedream 5 Flash is the quick tier of Seedream 5: it creates images from text and edits or combines up to 10 images from an instruction.
bytedance/seedream/v5/flash/editThis model has other modes with their own ids: bytedance/seedream/v5/flash/text-to-image.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "bytedance/seedream/v5/flash/edit",
"input": {
"prompt": "Put the backpack from the second image on the person in the first image, and change the background to a forest trail. Keep the person'\''s face and clothes unchanged.",
"image_urls": [
"https://example.com/input.png"
]
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "bytedance/seedream/v5/flash/edit", "quote_id": "QUOTE_ID", "input": {"prompt":"Put the backpack from the second image on the person in the first image, and change the background to a forest trail. Keep the person'\''s face and clothes unchanged.","image_urls":["https://example.com/input.png"]}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | The text prompt used to edit the image. |
image_size | string (enum) | The size of the generated image. Total pixels must be between 921600 and 4624220, with aspect ratio between 1/16 and 16. |
num_images | integer | Number of separate model generations to run with the prompt. |
output_format | string (enum) | The file format of the generated image. |
watermark | boolean | Whether to add a visible watermark. |
sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
background | string (enum) | Use `transparent` with exactly one alpha-channel reference and PNG output to preserve transparency. |
image_urlsrequired | array of image URLs | List of URLs of input reference images. Up to 10 images are supported; if more are sent, only the last 10 are used. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Seedream 5 Flash renders one to six images per run. Choose a square, portrait or landscape preset, or an automatic size at 1K, 1.5K or 2K, where the model picks the shape; Auto 2K is the default.
The edit mode takes up to 10 reference images and a written instruction, so you can change one photo or put elements from several into one scene.
Inspect small lettering, object boundaries and changes to details you asked to preserve.