About Seedream 5.5
ByteDance Seedream 5.5 generates and edits images with more consistent edits, more realistic detail and more accurate in-image text than Seedream 5.0. It renders transparent and semi-transparent backgrounds directly from a text prompt, so product shots, stickers, logos and UI assets come out as ready-to-use PNG cutouts.
It edits from up to 10 reference images (recolor, material swap, object replacement, multi-image fusion, in-image text edits) and outputs up to 4K across a range of aspect ratios. To split an image into editable layers, use Seedream 5.5 Layers.
See what this model can do
A handful of real prompts and their outputs.
Ready to build with Seedream 5.5?
Try Seedream 5.5 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/images/edit \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "bytedance-seedream-5-5",
"prompt": "A cat sitting on a chair",
"background": "auto",
"aspect_ratio": "auto",
"size": "2K",
"output_format": "png",
"watermark": false
}'Request parameters
Every field Seedream 5.5 accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/images/edit| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text prompt for image generation, or the instruction for editing the input images. Use @Image1, @Image2, etc. to reference the input images. |
input_image | array<string> | No | — | Optional reference images for editing. Provide one image for single-image editing or several for multi-reference fusion; reference them in the prompt as @Image1, @Image2, etc. |
background | string | No | "auto" | Transparent renders a PNG with an alpha channel. Auto makes the background transparent when the prompt asks for it.autotransparentopaque |
aspect_ratio | string | No | "auto" | auto1:14:33:416:99:163:22:321:9 |
image_size | object | No | — | Pixel dimensions sent to Seedream, looked up from aspect_ratio and size in the size table below. |
size | string | No | "2K" | 1K2K4K |
output_format | string | No | "png" | Output image format.pngjpeg |
watermark | boolean | No | false | Whether to add an 'AI generated' watermark. |