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

# Dalle

> Legacy DalleTools parameters and examples for OpenAI's deprecated DALL-E models.

**DalleTools** is retained as a legacy reference for generating images with OpenAI's deprecated DALL-E API.

<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 Requirements

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

## Example

The pinned agent used DALL-E to generate an image from a text prompt.

```python cookbook/91_tools/dalle_tools.py theme={null}
from pathlib import Path

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

# 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",
)

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")),
    )
```

## Toolkit Params

| Parameter             | Type            | Default       | Description                                                             |
| --------------------- | --------------- | ------------- | ----------------------------------------------------------------------- |
| `model`               | `str`           | `"dall-e-3"`  | The DALL-E model to use                                                 |
| `enable_create_image` | `bool`          | `True`        | Enable the create image functionality                                   |
| `n`                   | `int`           | `1`           | Number of images to generate                                            |
| `size`                | `str`           | `"1024x1024"` | Image size (256x256, 512x512, 1024x1024, 1792x1024, or 1024x1792)       |
| `quality`             | `str`           | `"standard"`  | Image quality (standard or hd)                                          |
| `style`               | `Optional[str]` | `None`        | Image style (vivid or natural). Only sent to the API when set           |
| `api_key`             | `Optional[str]` | `None`        | The OpenAI API key for authentication. Uses OPENAI\_API\_KEY if not set |
| `all`                 | `bool`          | `False`       | Enable all functionality when set to True                               |

## Toolkit Functions

| Function       | Description                               |
| -------------- | ----------------------------------------- |
| `create_image` | Generates an image based on a text prompt |

## Developer Resources

* [Tools](https://github.com/agno-agi/agno/blob/main/libs/agno/agno/tools/dalle.py)