Seedream 4.5 Text-to-Image
Supports models including seedream-4-5-251128. This document covers text-to-image and sequential image generation scenarios. Supported fields include model, prompt, size, seed, sequential_image_generation, sequential_image_generation_options, response_format, and watermark.
Authorizations
Pass Authorization: Bearer <token> in the request header.
Body
Image generation model name. Supported models include seedream-4-5-251128.
seedream-4-5-251128 Image generation prompt. Recommended to be no more than 300 Chinese characters or 600 English words.
Output image size.
- seedream-5-0-260128: supports 2K/3K or custom (total pixels 3686400-10404496, aspect ratio 1/16-16)
- seedream-4-5-251128: supports 2K/4K or custom (total pixels 3686400-16777216, aspect ratio 1/16-16)
- seedream-4-5-251128: supports 1K/2K/4K or custom (total pixels 921600-16777216, aspect ratio 1/16-16)
"2048x2048"
Response format.
url, b64_json Random seed. Supported by some Seedream models. Range [-1, 2147483647].
-1 <= x <= 2147483647Sequential image generation toggle. auto enables automatic detection mode, disabled turns off sequential generation (single image only). All currently supported Seedream models can use this capability.
auto, disabled Sequential image generation options. Only effective when sequential_image_generation=auto.
Whether to add a watermark.