Image Editor
Edit any image with AI. Change style, remove objects, modify elements, or transform the entire look.
Runs on
Examples
Botanical fan in a Koh Samui repair shop
Grok Imagine. A natural-language edit turns a vintage desk fan into a banana-leaf sculpture while keeping the roadside workshop photorealistic.
Image Editor API
Call this pipeline from your own code. One request dispatches a run; the model is an input field, not a separate endpoint.
Get an API token- inputs
- 5
- required
- 2
- Pricing
- 1.9 to 5.3 credits
| Input | Type | default | Description |
|---|---|---|---|
image_urls | array | default— | Images to edit. Give one image to edit it on its own, or several to be edited together into a single result. Grok models accept up to 3 images; Gemini models accept up to 14. |
instructions | string | default— | What to change, in plain language — the edit is applied to the whole image. |
aspect_ratio | enum | default— | Output aspect ratio. Leave unset to keep the source image's ratio.1:1 · 16:9 · 9:16 +21:116:99:164:33:4 |
enhance_prompt | boolean | defaulttrue | Improve the prompt for the selected model before generation. Turn off to send your prompt unchanged. |
model | enum | defaultgrok-imagine-image-quality | Image engine to use. Leave unset and Pipe2 picks one that supports your edit.grok-imagine-image-quality · grok-imagine-image · gemini-3-1-flash-image +1grok-imagine-image-qualitygrok-imagine-imagegemini-3-1-flash-imagegemini-3-pro-image |
Point any MCP client at pipe2 and your agent gets these tools. It finds this pipeline, reads the same schema above, then runs it.
list_pipelinesget_pipeline_schemarun_pipelineget_pipeline_run_statusrequest_upload
https://mcp.pipe2.ai/mcp {
"mcpServers": {
"pipe2ai": {
"url": "https://mcp.pipe2.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_TOKEN" }
}
}
}Recipes using this pipeline
Show all recipes-
An ordinary box opens onto a tiny impossible world
Create a silent reveal of a tiny moonlit ocean inside a hinged wooden box: build the open scene, close its lid with an image edit, then animate the discovery.
-
One product, three worlds: a match-cut campaign
Design an original product, restage it in two contrasting worlds, then turn the three connected images into a nine-second vertical campaign.
Frequently Asked Questions
What kinds of edits can I make?
Will the edit preserve the original composition?
What aspect ratios are supported?
How many credits does it cost?
Can I chain this with other pipelines?
Image Editor: AI-Powered Image Editing
Describe what you want to change and AI edits your image. Remove objects, change backgrounds, alter styles, add elements, or completely transform the look, all from a text prompt.
What You Can Do
- Remove objects: erase unwanted elements seamlessly
- Change backgrounds: swap any background with a described scene
- Style transfer: convert to painting, sketch, cinematic, or any style
- Add elements: insert objects, people, or effects into the scene
- Color grading: adjust mood, tone, and lighting with words
Choose a Model
- Grok Imagine: fast, natural-language edits at the lowest cost
- Grok Imagine Quality: higher fidelity and detail preservation
- Gemini 3.1 Flash Image: strong instruction following with multi-reference detail
- Gemini 3 Pro Image: premium tier for precise text and complex layouts