agenthub · image.edit
Edit Image
Image-to-image editing: an existing image plus a prompt, out comes an edited one. It chains straight after Generate Image.
Why the node earns its place
The same capability as generation — the adapter branches to its edit path when an input image is present — so it bills identically and needs no separate pricing. It exists as its own node because the required inputs differ: editing without an image is meaningless, and making the port required is what stops that misconfiguration reaching a provider.
How it works at run time
- 1Take the required image and prompt.
- 2Call the image capability with both; the adapter routes to editing.
- 3Return the edited image, the full array, and usage.
What you wire
Inputs
- image *string
- prompt *string
Outputs
- imagestring
- imagesarray
- usageobject
Configuration
| Key | Type | Default & options | What it does |
|---|---|---|---|
| provider * | string | choices from model-library:providers | Provider of the image model (e.g. google) |
| model * | string | choices from model-library:image_models | Image model to edit with |
What usually goes wrong
Watch for this
Wire the image output of a Generate Image node straight into this node's image input — that is the intended chain. If you only want variations of a prompt, use Generate Image with a higher count instead; it is one call rather than two.
Behaviour & provenance