pipelines-beta/hello-replicate – Run with an API on Replicate

pipelines-beta / hello-replicate

Give the model an image and it will attempt to generate a copy using Claude and Flux dev

Public
12 runs
CPU
GitHub

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=pipelines-beta/hello-replicate

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run pipelines-beta/hello-replicate using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "pipelines-beta/hello-replicate:0819c7a0c6a047ab9d32895d09c748c8eda200416c417569580cdd935222ddbf",
  {
    input: {
      image: "https://replicate.delivery/pbxt/N5mdDFqO5Ml4vbhar7y1tKRxIS7nPf7eNZOsuPo3hd2wsLIY/4327926-3392095804.jpg"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run pipelines-beta/hello-replicate using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "pipelines-beta/hello-replicate:0819c7a0c6a047ab9d32895d09c748c8eda200416c417569580cdd935222ddbf",
    input={
        "image": "https://replicate.delivery/pbxt/N5mdDFqO5Ml4vbhar7y1tKRxIS7nPf7eNZOsuPo3hd2wsLIY/4327926-3392095804.jpg"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run pipelines-beta/hello-replicate using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "pipelines-beta/hello-replicate:0819c7a0c6a047ab9d32895d09c748c8eda200416c417569580cdd935222ddbf",
    "input": {
      "image": "https://replicate.delivery/pbxt/N5mdDFqO5Ml4vbhar7y1tKRxIS7nPf7eNZOsuPo3hd2wsLIY/4327926-3392095804.jpg"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

output

Generated in

85.0 seconds

Tweak it ShareReport

Steps

ID	Model	Status
w0thjyvpz1rma0cq3dgvz2pr00	black-forest-labs/flux-dev	Succeeded
3nf7mv1psdrmc0cq3dgaw6g4pc	anthropic/claude-4-sonnet	Succeeded

Examples

View more examples

Run time and cost

This model runs on CPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

“Telephone” for images. Pass an image as the image parameter and the model will ask Claude to describe the image and Flux dev to generate a copy.

def run(
    image: Path = Input(description="Input image to test"),
) -> Path:
    replicate = Client()
    claude_prompt = """
You have been asked to generate a prompt for an image model that should re-create the
image provided to you exactly. Please describe the provided image in great detail
paying close attention to the contents, layout and style.
    """
    prompt = replicate.run(
        "anthropic/claude-4-sonnet", input={"prompt": claude_prompt, "image": image}
    )
    output = replicate.run(
        "black-forest-labs/flux-dev", input={"prompt": "".join(prompt)}
    )

    with tempfile.TemporaryDirectory(delete=False) as tmpdir:
        dest_path = os.path.join(tmpdir, "output.webp")
        with open(dest_path, "wb") as file:
            file.write(output[0].read())
        return Path(dest_path)