Image Generation Model

Generate images on WhatsApp with a Gemini model that returns text and image modalities.

image_generation_model.py

"""
Image Generation Model
======================

Demonstrates image generation model.
"""

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.google import Gemini
from agno.os.app import AgentOS
from agno.os.interfaces.whatsapp import Whatsapp

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

agent_db = SqliteDb(db_file="tmp/persistent_memory.db")
image_agent = Agent(
    id="image_generation_model",
    db=agent_db,
    model=Gemini(
        id="gemini-3-pro-image-preview",
        response_modalities=["Text", "Image"],
    ),
    add_history_to_context=True,
    num_history_runs=3,
)


# Setup our AgentOS app
agent_os = AgentOS(
    agents=[image_agent],
    interfaces=[Whatsapp(agent=image_agent)],
)
app = agent_os.get_app()


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    agent_os.serve(app="image_generation_model:app", reload=True)

Run the Example

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 "agno[os]" google-genai
   
3. Export environment variables

   Mac/Linux

   export GOOGLE_API_KEY="your_google_api_key_here"
   export WHATSAPP_ACCESS_TOKEN="your_whatsapp_access_token_here"
   export WHATSAPP_APP_SECRET="your_whatsapp_app_secret_here"
   export WHATSAPP_PHONE_NUMBER_ID="your_whatsapp_phone_number_id_here"
   export WHATSAPP_VERIFY_TOKEN="your_whatsapp_verify_token_here"
   

   $Env:GOOGLE_API_KEY="your_google_api_key_here"
   $Env:WHATSAPP_ACCESS_TOKEN="your_whatsapp_access_token_here"
   $Env:WHATSAPP_APP_SECRET="your_whatsapp_app_secret_here"
   $Env:WHATSAPP_PHONE_NUMBER_ID="your_whatsapp_phone_number_id_here"
   $Env:WHATSAPP_VERIFY_TOKEN="your_whatsapp_verify_token_here"
   
4. Use the stable image model

   Before running the source-fidelity code, change gemini-3-pro-image-preview to gemini-3-pro-image. The preview model has been shut down.

5. Run the example

   Save the code above as image_generation_model.py, then run:

   python image_generation_model.py
   

Full source: cookbook/05_agent_os/interfaces/whatsapp/image_generation_model.py