Image Editor

• Grok Imagine
• Grok Imagine Quality
• Nano Banana 2
• Nano Banana Pro

Examples

Before

After

Before / After

Add a prop: Pyra's cozy scarf

Grok Imagine Quality. One instruction wraps Pyra in a hand-knitted violet scarf: a single prop added, the same dragon underneath, same violet eyes and glowing infinity crest.

ReproduceOpen

Articles about this pipeline

• Best AI Image Generators: A Practical Model Comparison

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.

import { createClient } from "@pipe2-ai/sdk";

const client = createClient(process.env.PIPE2_TOKEN!);

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "image-editor",
  input: {
    image_urls: ["https://example.com/product.jpg"],
    instructions: "Remove the background and place the product on a soft grey studio backdrop",
    model: "grok-imagine-image-quality",
  },
});

import asyncio
import os

from pipe2 import Pipe2Client

client = Pipe2Client(token=os.environ["PIPE2_TOKEN"])

run = asyncio.run(client.run_pipeline(
    pipeline_slug="image-editor",
    input={
        "image_urls": ["https://example.com/product.jpg"],
        "instructions": "Remove the background and place the product on a soft grey studio backdrop",
        "model": "grok-imagine-image-quality",
    },
))

client := pipe2.NewClient(os.Getenv("PIPE2_TOKEN"))

input := json.RawMessage(`{
  "image_urls": ["https://example.com/product.jpg"],
  "instructions": "Remove the background and place the product on a soft grey studio backdrop",
  "model": "grok-imagine-image-quality"
}`)

run, err := pipe2.RunPipeline(context.Background(), client, "image-editor", input)
if err != nil {
    log.Fatal(err)
}

pipe2 pipelines run \
  --pipeline image-editor \
  --input-json '{"image_urls": ["https://example.com/product.jpg"], "instructions": "Remove the background and place the product on a soft grey studio backdrop", "model": "grok-imagine-image-quality"}' \
  --wait

Get an API token →

Parameters

image_urls required

Images to edit. Give one image to edit it on its own, or several to be edited together into a single result. How many you may send depends on the model: Grok Imagine Quality accepts 3, Grok Imagine 5, the Gemini models 14.

array

instructions required

What to change, in plain language — the edit is applied to the whole image.

string

aspect_ratio

Output aspect ratio. Leave unset to keep the source image's ratio.

1:116:99:164:33:4 default 1:1

Use it from an AI agent

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_pipelines
• get_pipeline_schema
• run_pipeline
• get_pipeline_run_status
• request_upload

{
  "mcpServers": {
    "pipe2ai": {
      "url": "https://mcp.pipe2.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}

Full API reference→ MCP setup→ CLI reference→

Frequently Asked Questions