Image Search

From 0.5 credits

Search museum archives and stock photo libraries with AI-targeted queries that curate the best results from five sources.

Topic

Number of Images

Still needed: Topic

How to use Image Search

A compact decision guide for placing this pipeline in a workflow.

Best for

Art, museum pieces, historical paintings and illustrations
Academic and cultural heritage images
Public domain and Creative Commons content
High-quality photos for image-motion input

Tips

Use specific visual terms: 'aerial city skyline sunset' not 'city'
Great for historical content, museum archives have unique content
Always pair results with image-motion to convert still images into video segments
Deduplicate URLs when running multiple searches

Image Search 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: 2
required: 1
Pricing: 0.5 credits

Language

TypeScript Python Go CLI

bun add @pipe2-ai/sdk

Run a pipeline

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

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

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "image-search",
  input: {
    topic: "minimalist workspace with warm morning light",
  },
});

pip install pipe2

Run a pipeline

import asyncio
import os

from pipe2 import Pipe2Client

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

run = asyncio.run(client.run_pipeline(
    pipeline_slug="image-search",
    input={
        "topic": "minimalist workspace with warm morning light",
    },
))

go get github.com/pipe2-ai/sdk-go

Run a pipeline

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

input := json.RawMessage(`{
  "topic": "minimalist workspace with warm morning light"
}`)

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

brew install pipe2-ai/tap/pipe2

Run a pipeline

pipe2 pipelines run \
  --pipeline image-search \
  --input-json '{"topic": "minimalist workspace with warm morning light"}' \
  --wait

Per page

Input	Type	default	Description
`topic`required	string	default—	Describe what images you need
`image_count`	enum	default20	How many images to return. 10 · 20 · 30 +1 `10203050`

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

https://mcp.pipe2.ai/mcp

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

MCP setup

Full API reference CLI reference

Frequently Asked Questions

How many images can I search for?

Choose 10, 20, 30, or 50. AI generates targeted queries for different angles, deduplicates the results, and returns up to your chosen count.

Are these images free to use?

Most results are public domain or Creative Commons licensed. Check the source and license for each image.

How does the AI decide what to search?

AI analyzes your topic and generates 3-5 targeted search queries, each targeting a different angle. This finds more diverse results than a single search.

Are images saved to my library?

No, results link directly to the original source. This keeps your library clean and avoids re-hosting.

How many credits does it cost?

0.5 credits per search.