bytedance/seedream-4.5

Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge

Capabilities

1:14:33:416:99:162:33:2Reference Images

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`prompt`*	string	Text prompt for image generation. Maximum 4000 characters. BytePlus recommends keeping prompts under 600 English words for best results.	`—`	—
`aspect_ratio`	string	Image aspect ratio. Only used when size is not 'custom'. Use 'match_input_image' to automatically match the input image's aspect ratio.	`"match_input_image"`	match_input_image1:14:33:44:55:416:99:163:22:321:99:21
`disable_safety_checker`	boolean	Disable the safety checker for generated images. When enabled, input moderation is relaxed to only block illegal content (CSAM). Use responsibly.	`false`	—
`height`	integer	Custom image height (only used when size='custom'). Range: 1024-4096 pixels.	`2048`	min: 1024, max: 4096
`image_input`	array	Input image(s) for image-to-image generation. List of 1-14 images for single or multi-reference generation.		—
`max_images`	integer	Maximum number of images to generate when sequential_image_generation='auto'. Range: 1-15. Total images (input + generated) cannot exceed 15.	`1`	min: 1, max: 15
`sequential_image_generation`	string	Group image generation mode. 'disabled' generates a single image. 'auto' lets the model decide whether to generate multiple related images (e.g., story scenes, character variations).	`"disabled"`	disabledauto
`size`	string	Image resolution: 2K (2048px), 4K (4096px), or 'custom' for specific dimensions. Note: 1K resolution is not supported in Seedream 4.5.	`"2K"`	2K4Kcustom
`width`	integer	Custom image width (only used when size='custom'). Range: 1024-4096 pixels.	`2048`	min: 1024, max: 4096

promptrequiredstring

Text prompt for image generation. Maximum 4000 characters. BytePlus recommends keeping prompts under 600 English words for best results.

aspect_ratiostring

Image aspect ratio. Only used when size is not 'custom'. Use 'match_input_image' to automatically match the input image's aspect ratio.

Default: "match_input_image"

match_input_image1:14:33:44:55:416:99:163:22:321:99:21

disable_safety_checkerboolean

Disable the safety checker for generated images. When enabled, input moderation is relaxed to only block illegal content (CSAM). Use responsibly.

Default: false

heightinteger

Custom image height (only used when size='custom'). Range: 1024-4096 pixels.

Default: 2048min: 1024, max: 4096

image_inputarray

Input image(s) for image-to-image generation. List of 1-14 images for single or multi-reference generation.

Default:

max_imagesinteger

Maximum number of images to generate when sequential_image_generation='auto'. Range: 1-15. Total images (input + generated) cannot exceed 15.

Default: 1min: 1, max: 15

sequential_image_generationstring

Group image generation mode. 'disabled' generates a single image. 'auto' lets the model decide whether to generate multiple related images (e.g., story scenes, character variations).

Default: "disabled"

disabledauto

sizestring

Image resolution: 2K (2048px), 4K (4096px), or 'custom' for specific dimensions. Note: 1K resolution is not supported in Seedream 4.5.

Default: "2K"

2K4Kcustom

widthinteger

Custom image width (only used when size='custom'). Range: 1024-4096 pixels.

Default: 2048min: 1024, max: 4096

Version: 9fe3b8282dcbUpdated: 8/12/202631.8M runs