doubao-seedream-5-0-lite-260128
doubao-seedream-5-0-lite-260128 Image Editing API
Seedream 5.0 Lite supports lightweight reference-image editing and is well suited for low-latency image revisions and batch sketch iteration.
curl -X POST "https://api.routescope.ai/v1/images/edits" \ -H "Content-Type: application/json" \ -d '{ "model": "doubao-seedream-5-0-lite-260128", "prompt": "Generate a new image based on these two reference images.", "images": [ { "image_url": "https://example.com/a.png" }, { "image_url": "https://example.com/b.png" } ], "size": "1024x1024" }'{
"created": 1,
"data": {}
}Authorization
BearerAuth
Model relay endpoint authentication. Header: Authorization: Bearer .
In: header
Request Body
application/json
Model name. The Tencent TokenHub channel maps it inside the gateway to the upstream model name.
"doubao-seedream-5-0-lite-260128"Image editing prompt.
Recommended JSON URL image input. Each item is a single image URL object.
Compatibility field: accepts a single URL string, a URL array, or an object. Prefer images[].image_url.
Compatibility field: a URL string array. Prefer images[].image_url.
Optional. Mask image URL; transparent areas mark the regions to edit.
uriNumber of images to generate.
int321 <= valueOutput image size.
"1024x1024"Image quality. Allowed values depend on the upstream model.
Response format. Supports url or b64_json; can be omitted by default and support varies across upstream channels.
"url" | "b64_json"Background fill mode. Support depends on the model.
"auto""transparent" | "opaque" | "auto"Output format. Allowed values depend on the upstream model.
Output compression level. Applies to jpeg and webp only.
90int320 <= value <= 100Moderation strength. Support depends on the model.
"auto""auto" | "low"Whether to add a watermark. Support depends on the upstream channel.
falseEnd-user identifier; useful for abuse monitoring.
Response Body
application/json
Request Parameters
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Yes | None | Fixed to doubao-seedream-5-0-lite-260128. |
prompt | string | Yes | None | Edit instruction. |
image | string or string[] | Yes | None | Source/reference image URL or Base64. |
size | string | No | 1920x1920 | Use an explicit <width>x<height> value such as 1920x1920; the total pixel count must be at least 3686400, and actual availability still depends on the provider channel. |
response_format | string | No | None | Supports url or b64_json. Omit by default unless you need a specific return format. |
watermark | boolean | No | true | Whether to add an AI-generated watermark. |
Example Code
curl https://api.routescope.ai/v1/images/edits \
-H "Authorization: Bearer $ROUTESCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedream-5-0-lite-260128",
"prompt": "Change the picture to a flat picture style and keep the main picture.",
"image": "https://example.com/input.png",
"size": "1920x1920"
}'import requests
response = requests.post(
"https://api.routescope.ai/v1/images/edits",
headers={"Authorization": "Bearer YOUR_ROUTESCOPE_API_KEY"},
json={
"model": "doubao-seedream-5-0-lite-260128",
"prompt": "Change the picture to a flat picture style and keep the main picture.",
"image": "https://example.com/input.png",
"size": "1920x1920",
},
)
print(response.json())const response = await fetch("https://api.routescope.ai/v1/images/edits", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.ROUTESCOPE_API_KEY}`, "Content-Type": "application/json" },
body: JSON.stringify({
model: "doubao-seedream-5-0-lite-260128",
prompt: "Change the picture to a flat picture style and keep the main picture.",
image: "https://example.com/input.png",
size: "1920x1920",
}),
});
console.log(await response.json());Response Example
{
"created": 1777432320,
"data": [
{
"url": "https://api.routescope.ai/assets/images/seedream-lite-edit.png",
"b64_json": null,
"revised_prompt": "Flatshot style, keep the main diagram"
}
]
}Notes
Billing follows the configured model and channel ratios. The Lite variant is better for lightweight edits; for more complex consistency editing, prefer a non-Lite model.
Last updated on