Parameters
| Name | Description | Type | Required | Enums |
|---|---|---|---|---|
| size | Image size in format ‘widthxheight’. Seedream 5.0 Lite supports custom 2K/3K resolutions. | string | No | - |
| prompt | Image editing instruction, supports Chinese and English. We recommend keeping the prompt under 600 words. Excessively long prompts may scatter information, causing the model to overlook details and focus only on major elements, which can result in missing details in the generated image. | string | Yes | - |
| image | Input image array (1-14 images). Each image must be <= 10 MB. Supported formats: JPEG, PNG, WEBP, BMP, TIFF, GIF. | string[] | Yes | - |
| optimize_prompt_mode | Prompt optimization mode. Only ‘standard’ mode is supported. | string | No | standard |
| output_format | Output image format. Supported values: ‘jpeg’ and ‘png’. | string | No | jpeg, png |
| sequential_image_generation | Batch generation mode. ‘auto’: model-controlled batch generation, ‘disabled’: generate single image only. | string | No | auto, disabled |
| sequential_image_generation_max_images | Maximum number of images for batch generation. This value is an upper limit, actual generated count may be less. | integer | No | - |
Pricing
Unit: $/img
| Pricing |
|---|
| $0.0370/img |
Related Models
- bytedance/seedream-4.0-t2i: SOTA multimodal image model supporting text, single-image, and multi-image inputs for subject-consistent fusion, image editing, and group generation.
- bytedance/seedream-4.5-t2i: ByteDance’s latest image model with improved editing consistency, portrait refinement, small-text rendering, and enhanced multi-image composition.
- bytedance/seedream-5.0-lite: ByteDance Seedream 5.0 Lite text-to-image model with 2K/3K custom resolutions and configurable output format.
- bytedance/seedream-4.0-i2i: SOTA multimodal image model supporting text, single-image, and multi-image inputs for subject-consistent fusion, image editing, and group generation.
- bytedance/seedream-4.5-i2i: ByteDance’s latest image model with improved editing consistency, portrait refinement, small-text rendering, and enhanced multi-image composition.
