infery
← All models

Seedream 4

seedream-4

Image generationby ByteDance

Seedream 4 from ByteDance: next-generation image creation model that combines text-to-image generation and image editing into a single architecture. It offers fast, high-resolution image generation, rich prompt understanding, and support for multi-reference and batch workflows.

images

Details

Accepts
text + image

Pricing

Price
3.75 cr / image

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
sizeenum: 1K, 2K, 4K, customImage resolution: 1K (1024px), 2K (2048px), 4K (4096px), or 'custom' for specific dimensions.
widthintegerCustom image width (only used when size='custom'). Range: 1024-4096 pixels.
heightintegerCustom image height (only used when size='custom'). Range: 1024-4096 pixels.
promptrequiredstringText prompt for image generation
max_imagesintegerMaximum number of images to generate when sequential_image_generation='auto'. Range: 1-15. Total images (input + generated) cannot exceed 15.
image_inputarrayInput image(s) for image-to-image generation. List of 1-10 images for single or multi-reference generation.
aspect_ratioenum: match_input_image, 1:1, 4:3, 3:4, 16:9, 9:16Image aspect ratio. Only used when size is not 'custom'. Use 'match_input_image' to automatically match the input image's aspect ratio.
enhance_promptbooleanEnable prompt enhancement for higher quality results, this will take longer to generate.
sequential_image_generationenum: disabled, autoGroup 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).