bytedance/seededit-3.0

Text-guided image editing model that preserves original details while making targeted modifications like lighting changes, object removal, and style conversion

Official
90.2K runs
Commercial use

Input

image
*string
Shift + Return to add a new line

Text prompt for image generation

*file

Input image to edit

integer

Random seed. Set for reproducible generation

number
(minimum: 1, maximum: 10)

Prompt adherence. Higher = more literal.

Default: 5.5

Output

output
Generated in

Pricing

Model pricing for bytedance/seededit-3.0. Looking for volume pricing? Get in touch.

$0.03
per output image

or around 33 images for $1

Official models are always on, maintained, and have predictable pricing. Learn more.

Check out our docs for more information about how pricing works on Replicate.

Readme

SeedEdit 3.0

SeedEdit 3.0 is an image editing model that supports editing images through text commands. Built on the Seedream 3.0 text-to-image model with enhanced data fusion methods and reward models, it specializes in preserving image subjects, backgrounds, and details while making targeted edits.

The model excels at:

  • Portrait editing
  • Background changes
  • Perspective and lighting conversion
  • Selective object removal/modification
  • Style transfer (2D to photorealistic)
  • Maintaining high fidelity in unedited areas

Usage Examples

Lighting Changes Prompt: “Change the scene to daytime” Transforms lighting and shadows across the entire scene while preserving all original details.

Object Removal Prompt: “Remove all pedestrians except the middle character” Accurately identifies and removes specified objects including their shadows.

Style Conversion Prompt: “Make the girl look realistic” Converts 2D illustrations to photorealistic images while preserving clothing, accessories, and other details.