seedream-5-lite
Seedream 5 Lite is ByteDance's fast image generation and editing model — text-to-image plus example-based editing, optional sequential group generation (up to 15 coherent variants in one call), and built-in reasoning that handles complex briefs without verbose prompting.
Input
Describe the image to generate, or the edit to apply when input images are provided.
Optional reference images for editing or multi-reference generation (up to 14).
0 / 14
Output resolution. `2K` is 2048 px on the long side; `3K` is 3072 px.
Output aspect ratio. `match_input_image` inherits from the first reference image.
Group generation mode. `disabled` returns a single image; `auto` lets the model emit a coherent set of related images from one prompt (set the cap via `max_images`).
Maximum number of images when `sequential_image_generation` is `auto`. Ignored in disabled mode.
Output file format.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/bytedance/seedream-5-lite \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'