> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-service-account.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Google Image Editing

> Send an image to Gemini and get back an edited version using image response modalities.

```python image_editing.py theme={null}
"""
Google Image Editing
====================

Cookbook example for `google/gemini/image_editing.py`.
"""

from io import BytesIO

from agno.agent import Agent, RunOutput  # noqa
from agno.media import Image
from agno.models.google import Gemini
from PIL import Image as PILImage

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

# No system message should be provided (Gemini requires only the image)
agent = Agent(
    model=Gemini(
        id="gemini-3.5-flash",
        response_modalities=["Text", "Image"],
    )
)

# Print the response in the terminal
response = agent.run(
    "Can you add a Llama in the background of this image?",
    images=[Image(filepath="tmp/test_photo.png")],
)

# Retrieve and display generated images using get_last_run_output
run_response = agent.get_last_run_output()
if run_response and isinstance(run_response, RunOutput) and run_response.images:
    for image_response in run_response.images:
        image_bytes = image_response.content
        if image_bytes:
            image = PILImage.open(BytesIO(image_bytes))
            image.show()
            # Save the image to a file
            # image.save("generated_image.png")
else:
    print("No images found in run response")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    pass
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno google-genai pillow
    ```
  </Step>

  <Step title="Export your Google API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export GOOGLE_API_KEY="your_google_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:GOOGLE_API_KEY="your_google_api_key_here"
      ```
    </CodeGroup>
  </Step>

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

    ```bash theme={null}
    python image_editing.py
    ```
  </Step>
</Steps>

Full source: [cookbook/90\_models/google/gemini/image\_editing.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/google/gemini/image_editing.py)