Available now

Seedream 5 Flash: image editing

By ByteDance

ByteDance's Seedream 5 Flash is the quick tier of Seedream 5: it creates images from text and edits or combines up to 10 images from an instruction.

Model ID
Maker
ByteDance

Input

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

The text prompt used to edit the image.

Example prompt. Edit it or write your own.

Total pixels must be between 921600 and 4624220, with aspect ratio between 1/16 and 16.

Number of separate model generations to run with the prompt.

Input reference images. Up to 10 images are supported; if more are sent, only the last 10 are used.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

The file format of the generated image.

Estimated total$0.05

You sign up first. Your settings are kept.

About this model

Overview

Seedream 5 Flash renders one to six images per run. Choose a square, portrait or landscape preset, or an automatic size at 1K, 1.5K or 2K, where the model picks the shape; Auto 2K is the default.

The edit mode takes up to 10 reference images and a written instruction, so you can change one photo or put elements from several into one scene.

What you can build

  • Many drafts of a campaign idea
  • Product photos in a new setting
  • Group scenes assembled from separate photos
  • Quick variations for social posts

Prompting tips

  • Leave the size on Auto 2K unless the layout needs a fixed shape.
  • When combining images, refer to them by order, such as the first or second image.
  • Ask for six images at once and keep the strongest as a base for the next prompt.

What to check

Inspect small lettering, object boundaries and changes to details you asked to preserve.

Inputs

  • Prompt (required): The text prompt used to edit the image.
  • Image Size (optional): The size of the generated image. Total pixels must be between 921600 and 4624220, 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 1K, Auto 1.5K, Auto 2K.
  • Number of Images (optional): Number of separate model generations to run with the prompt. From 1 to 6.
  • Output Format (optional): The file format of the generated image. Options: jpeg, png.
  • Images (required): List of URLs of input reference images. Up to 10 images are supported; if more are sent, only the last 10 are used.

Output and limits

  • Image sizes: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9, Auto 1K, Auto 1.5K, Auto 2K.
  • 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: $0.05 / image