Generate image with SeeDream 4.5
ByteDance SeeDream 4.5 — text-to-image, plus image editing and multi-reference composition from up to 9 reference images. Strong aesthetics, 2K/4K output.
Asynchronous. Returns a job id (the image is not in this response). Poll GET /v1/images/{id} until status is succeeded — the generated image URLs are in that response’s images array (each { url, position }).
Authorizations
API key as a bearer token: Authorization: Bearer bpx_live_xxx
Body
Text description of the image to generate.
Output aspect ratio.
1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9, 9:21 Ceiling for grouped generation when sequential_image_generation is "auto": the model returns up to this many related images and decides the exact count (not guaranteed to be exactly this many). You are billed per image returned.
1 <= x <= 4Number of images to generate.
1 <= x <= 4Optional reference images (up to 9) for image editing and multi-reference composition. Each item is a public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. Omit for text-to-image.
9Set to "auto" to return a group of related images (up to max_images); "disabled" (default) returns a single image.
disabled, auto Output resolution.
2K, 4K