Available now

Seedream 5 Lite: text to image

By ByteDance

ByteDance's Seedream 5 Lite creates images from a written prompt and edits the images you upload, at automatic sizes of 2K, 3K or 4K.

Model ID
Maker
ByteDance

Input

Fields marked * are required. Review the price before generating.

The text prompt used to generate the image

Example prompt. Edit it or write your own.

Number of separate model generations to be run with the prompt.

Additional settings

The file format of the generated images.

Whether to add a visible watermark.

Generate related images with auto, or one image per generation with disabled.

Estimated total$0.06

You sign up first. Your settings are kept.

About this model

Overview

Seedream 5 Lite is the Lite version of Seedream 5. It makes up to six images per run, as JPEG or PNG, in preset shapes or at Auto 2K, Auto 3K or Auto 4K.

Its edit mode works from up to 10 images and a written instruction. Turn on sequential generation to get a set of related images instead of separate ones.

What you can build

  • Related image sets, such as one product in several scenes
  • Large images for print and wide screens
  • Your photos with a new background or style
  • Scenes that combine several reference images

Prompting tips

  • Use sequential generation for a series that should look like one set; turn it off for unrelated variations.
  • When combining images, say which picture provides which part of the scene.

What to check

Check requested wording, repeated details and whether editing preserved the intended objects.

Inputs

  • Prompt (required): The text prompt used to generate the image.
  • Image Size (optional): The size of the generated image. Custom dimensions within the model's pixel and aspect limits are sent unchanged. Other sizes use compatible scaling. The model's native pixel range is 2560x1440 to 4096x4096, with aspect ratio between 1/16 and 16. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto 2K, Auto 3K, Auto 4K.
  • Number of Images (optional): Number of separate model generations to be run with the prompt. From 1 to 6.
  • Output Format (optional): The file format of the generated images. Options: jpeg, png.
  • Watermark (optional): Whether to add a visible watermark.
  • Sequential Image Generation (optional): Generate related images with `auto`, or one image per generation with `disabled`. Options: auto, disabled.

Output and limits

  • Image sizes: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto 2K, Auto 3K, Auto 4K.
  • File formats: JPEG, PNG.
  • Up to 6 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 image: $0.06 / image