# Image To Image (/examples/agents/multimodal/image-to-image)



Image To Image.

<Warning>
  This example constructs `FalTools()` with `enable_image_to_image=False`, the toolkit default, so the `image_to_image` tool is unavailable as written. Apply the migration below before running it.
</Warning>

```python title="image_to_image.py"
"""
Image To Image
=============================

Image To Image.
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.fal import FalTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    id="image-to-image",
    name="Image to Image Agent",
    tools=[FalTools()],
    markdown=True,
    instructions=[
        "You have to use the `image_to_image` tool to generate the image.",
        "You are an AI agent that can generate images using the Fal AI API.",
        "You will be given a prompt and an image URL.",
        "You have to return the image URL as provided, don't convert it to markdown or anything else.",
    ],
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "a cat dressed as a wizard with a background of a mystic forest. Make it look like 'https://fal.media/files/koala/Chls9L2ZnvuipUTEwlnJC.png'",
        stream=True,
    )
```

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno fal-client openai
    ```
  </Step>

  <Step title="Export environment variables">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export FAL_API_KEY="your_fal_key_here"
        export FAL_KEY="your_fal_key_here"
        export OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```bash
        $Env:FAL_API_KEY="your_fal_key_here"
        $Env:FAL_KEY="your_fal_key_here"
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

  <Step title="Enable image-to-image">
    Replace `tools=[FalTools()]` with `tools=[FalTools(enable_generate_media=False, enable_image_to_image=True)]` in the saved file.
  </Step>

  <Step title="Run the example">
    Save the code above as `image_to_image.py`, then run:

    ```bash
    python image_to_image.py
    ```
  </Step>
</Steps>

Full source: [cookbook/02\_agents/12\_multimodal/image\_to\_image.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/02_agents/12_multimodal/image_to_image.py)