Expand image
Extend the canvas beyond the frame
Add space on any side and a generation model paints the new area to match. Turn a portrait into a landscape, or give a crop room to breathe.
Model
price of the model you pick, per run
$0
on your own machine
Any side
Drag the frame left, right, up or down.
The original stays
Only the new area is painted, the image itself is kept as is.
Free locally
On your GPU it costs nothing. In the cloud, the model's price.
Reference
Inputs and parameters
The same on every surface: the desktop app, Claude through MCP and the API. Unknown parameters are refused, so a typo never runs with a default.
Inputs
| Name | Type | Limits | Notes |
|---|---|---|---|
| image required | image | 30 MB, 4 MP | Source image |
Parameters
| Name | Type | Default | Accepted | Notes |
|---|---|---|---|---|
| model required | string | · | up to 128 characters | Generation model (a catalog model name that accepts an image input). |
| prompt | string | · | up to 4000 characters | Prompt (default: empty; reuse the image's original prompt for best results). |
| negative_prompt | string | · | up to 2000 characters | |
| left | int | 0 | 0 to 2048 | |
| right | int | 0 | 0 to 2048 | |
| top | int | 0 | 0 to 2048 | |
| bottom | int | 0 | 0 to 2048 | |
| seed | int | · | 0 to 4294967295 | Fixed seed for a reproducible result (default: random). |
Outputs
- imageimage
API
Run Expand image from the API
curl https://imference.com/tools/outpaint \
-H "Authorization: Bearer $IMFERENCE_API_KEY" \
-F image=@image.png \
-F 'params={"model": "anima-aesthetic", "prompt": "a red vintage car"}'
Files go in multipart fields named after the inputs; JSON works too, with {"inputs": {...}, "params": {...}} and https URLs or base64 data: URIs. The answer is a request_id: poll GET /status?request_id=... until it returns the outputs. Pay per call from a wallet instead at POST /ondemand/tools/outpaint. A run that fails is refunded to your credits. Details in the reference.
Specs
The details
- Price
- Same as a generation with the model
- Model
- Any image model that takes an image input (not an instruction-edit model).
- Runs
- Local and cloud
- License
- License of the selected model
- Tool id
- outpaint 1.0.0
- MCP tool
- outpaint
More tools
Often used with it
Edit with instructions
Edit an image by describing the change in plain words (Qwen-Image-Edit): change the background, add or remove objects, restyle, fix text. Optional reference images.
Model price
Vary
Make a variation of an image with a generation model (img2img). Subtle keeps the composition, strong reimagines it.
Model price
FAQ
Good to know
Which models work best?
Photo-real models like Z-Image give the most natural extensions. A prompt that describes the scene helps.
How much can I add?
Up to 2048 pixels per side, within 16 megapixels in total.