Image Model Output

Return generated images from model responses.

Similar to providing image inputs, you can also get image outputs from an agent. Take a look at the compatibility matrix to see which models support image as output.

Image Output Modality

The following example demonstrates how some models can directly generate images as part of their response.

image_agent.py

from io import BytesIO

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

agent = Agent(
    model=Gemini(
        id="gemini-3.5-flash",
        response_modalities=["Text", "Image"], # Generate both images and text in the response
    )
)

# Print the response in the terminal
run_response = agent.run("Make me an image of a cat in a tree.")

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 = Image.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")

You can find all generated images in the RunOutput.images list.

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U google-genai pillow agno
   
3. Export your Google API key

   Mac/Linux

     export GOOGLE_API_KEY="your_google_api_key_here"
   

     $Env:GOOGLE_API_KEY="your_google_api_key_here"
   
4. Run Agent

   python image_agent.py
   

Developer Resources

• More examples