Skip to main content
The Edit Image node modifies an existing image based on text instructions and returns a new image.

​
When to use

  • Refining generated assets
  • Inpainting-style edits
  • Iterating on a base image
Common patterns: generate_image → edit_image, or upload_image → edit_image.

​
Inputs

​
image
required
The image to edit. Required.
​
text
required
Text describing how to edit the image. Required.
Inline instructions. You don’t need a separate Text Prompt node for fixed instructions — type them directly on the node. The inline field appears whenever the instructions input is unconnected and disappears once you wire a text input in. Connect a Text Prompt node only when you want to drive the instructions from upstream or expose them as an app input. Type @ to mention a connected input by name — text inputs insert their content into the instructions, media inputs insert their name.

​
Outputs

​
image
The edited image.

​
Configuration

​
number
default:"0.7"
How strongly the edit is applied, from 0 to 1.
​
number
default:"1"
How many images to generate per run.
Pick the model in the node’s config panel. See Image models for the options, and Model settings for what each setting does. Additional model-specific options (such as resolution and guidance) appear depending on the model you choose. Runs consume credits.