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

# Dalle

> Legacy DalleTools reference for configuring deprecated DALL-E models.

This page preserves the v2.7.2 `DalleTools` example as a legacy reference.

<Warning>
  DALL-E models are deprecated. This `DalleTools` example is retained as a legacy reference and no longer runs against the current OpenAI API. Use `OpenAITools` with GPT Image 2 in [Image Generation Agent](/models/providers/native/openai/responses/usage/image-generation-agent).
</Warning>

## Legacy Source

This example expected the `openai` package and an `OPENAI_API_KEY`. Its `DalleTools` calls no longer run against the current OpenAI API.

```python theme={null}

from pathlib import Path

from agno.agent import Agent
from agno.tools.dalle import DalleTools
from agno.utils.media import download_image

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


# Example 1: Basic DALL-E agent with all functions enabled
agent = Agent(tools=[DalleTools(all=True)], name="DALL-E Image Generator")

# Example 2: Enable specific DALL-E functions
agent_specific = Agent(
    tools=[
        DalleTools(
            enable_create_image=True,
            model="dall-e-3",
            size="1024x1024",
            quality="standard",
        )
    ],
    name="Basic DALL-E Generator",
)

# Example 3: High-quality custom DALL-E generator
custom_dalle = DalleTools(all=True, model="dall-e-3", size="1792x1024", quality="hd")

agent_custom = Agent(
    tools=[custom_dalle],
    name="Custom DALL-E Generator",
)

# Test basic generation

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "Generate an image of a futuristic city with flying cars and tall skyscrapers",
        markdown=True,
    )

    response = agent_custom.run(
        "Create a panoramic nature scene showing a peaceful mountain lake at sunset",
        markdown=True,
    )
    if response.images and response.images[0].url:
        download_image(
            url=response.images[0].url,
            output_path=str(Path(__file__).parent.joinpath("tmp/nature.jpg")),
        )
```

## Current Alternative

Follow [Image Generation Agent](/models/providers/native/openai/responses/usage/image-generation-agent) to generate and save images with `OpenAITools` and GPT Image 2.

For details, see [Dalle cookbook](https://github.com/agno-agi/agno/blob/main/cookbook/91_tools/dalle_tools.py).