# Generate DALL-E Image

Image generation based on a text prompt.

<table data-header-hidden><thead><tr><th width="299" valign="top"></th><th width="320.21661376953125" valign="top"></th></tr></thead><tbody><tr><td valign="top">Text</td><td valign="top"><p>[Text] The text based on which the image needs to be generated.</p><p>For example, <code>"Astronaut on the moon"</code>.</p></td></tr><tr><td valign="top">Model</td><td valign="top">Selection of the model for image generation.</td></tr><tr><td valign="top">Image File</td><td valign="top">[Text/List] The name and path to the file for saving the image. If more than one is specified and the "dall-e-2" model is selected, a list of files can be provided.</td></tr><tr><td valign="top">Quantity</td><td valign="top"><p>[Number] The number of images to be generated. The value can range from 1 to 10.</p><p>For the "dall-e-3" model, the value is always 1.</p></td></tr><tr><td valign="top">Image Quality</td><td valign="top"><p>The quality of the image that will be generated.</p><p>"hd" creates images with finer details and greater consistency throughout the image. This option is only supported for "dall-e-3".</p></td></tr><tr><td valign="top">Image Size</td><td valign="top"><p>The size of the generated images. For "dall-e-2", it must be one of:</p><ul><li>"256x256",</li><li>"512x512",</li><li>"1024x1024".</li></ul><p>For the "dalle3" model, it must be one of the resolutions:</p><ul><li>"1024x1024",</li><li>"1792x1024",</li><li>"1024x1792".</li></ul></td></tr><tr><td valign="top">Image Style</td><td valign="top"><p>The style of the created images. It must be vivid ("vivid") or natural ("natural").</p><p>Vivid makes the model lean towards creating hyper-realistic and dramatic images.</p><p>Natural makes the model create more natural, less hyper-realistic images. This option is only supported for "dall-e-3".</p></td></tr><tr><td valign="top">Timeout</td><td valign="top">[Number] The maximum wait time for a response in seconds.</td></tr><tr><td valign="top">Result</td><td valign="top">[Text/List] If only one image is generated, it returns the name and path to the file. Otherwise, it returns a list of full paths to the files with their names.</td></tr><tr><td valign="top">Error Handling Level</td><td valign="top"><p>Selection of the error handling level. Possible values:</p><ul><li>"Default" - default;</li><li>"Ignore" - errors are ignored;</li><li>"Handle" - errors are handled.</li></ul><p>If "Default" is selected, the value from the "Start" block of this diagram will be used.</p></td></tr><tr><td valign="top">Message Level</td><td valign="top"><p>Selection of the message level that the blocks will output during operation. Possible values:</p><ul><li>"Default" - default;</li><li>"Release" - output is disabled;</li><li>"Debug" - main information output;</li><li>"Detailed" - detailed information output.</li></ul><p>If "Default" is selected, the value from the "Start" block of this diagram will be used.</p></td></tr><tr><td valign="top">Error Text</td><td valign="top">[Text] Returns detailed information about the error in case of incorrect execution of the block's work.</td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.sherparpa.ru/en/sherpa-rpa/sherpa-designer/spravochnik-blokov/mashinnoe-obuchenie-machine-learning/generirovat-izobrazhenie-dall-e-openaiimagesgenerations.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
