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

# Dall-E 3 (Image Generation)

<Warning>
  This plugin uses the DALL-E 3 model, which is deprecated by OpenAI. We recommend switching to the GPT Image Editor plugin for image generation and editing.
</Warning>

Dall-E 3 works as a plugin on TypingMind.

Please follow the steps below to use Dall-3 plugin on TypingMind

## Step 1: Open Dall-E 3 plugin setting

* On TypingMind.com, navigate the plugin menu on the left workspace bar of the app (next to the sidebar)
* Click on Plugin Store and install Dall-E 3
* Click on the installed Dall-E 3 plugin to open its settings.

<img src="https://mintlify.s3.us-west-1.amazonaws.com/typingmind/plugins/dall-e-3-(image-generation)/image.png" alt="image.png" />

## Step 2: Enter your OpenAI API key

* Switch tab to the Settings tab
* Enter your [OpenAI API key](/manage-and-connect-ai-models/openai-\(gpt-5-gpt-4.1\))
* Set up image generated resolution and quality as you want.

<img src="https://mintlify.s3.us-west-1.amazonaws.com/typingmind/plugins/dall-e-3-(image-generation)/Untitled.png" alt="Untitled" />

## Step 3: Start prompting the AI model to generate images

Beside GPT-4 Vision, which currently doesn’t support plugins, you can choose other GPT models to create images.

<img src="https://mintcdn.com/typingmind/Yn6uyYL5IeiKgLWb/plugins/dall-e-3-(image-generation)/dall-e.gif?s=7e96d72b0822dbd95b7e75c14aaa305d" alt="dall-e.gif" width="886" height="701" data-path="plugins/dall-e-3-(image-generation)/dall-e.gif" />

## Some notes

1. Download Dall-E generated image: right-click on the image > Save Image As
2. See the prompt that generates the image: on the bottom left corner of the image, click ALT

## Dall-E 3 Prompt Tips

Tips from the OpenAI community, read more [here](https://community.openai.com/t/dalle3-prompt-tips-and-tricks-thread/498040)

1. **Be Specific and Detailed**: The more specific your prompt, the better the image quality. Include details like the setting, objects, colors, mood, and any specific elements you want in the image.
2. **Mood and Atmosphere**: Describe the mood or atmosphere you want to convey. Words like “serene,” “chaotic,” “mystical,” or “futuristic” can guide the AI in setting the right tone.
3. **Use Descriptive Adjectives**: Adjectives help in refining the image. For example, instead of saying “a dog,” say “a fluffy, small, brown dog.”
4. **Consider Perspective and Composition**: Mention if you want a close-up, a wide shot, a bird’s-eye view, or a specific angle. This helps in framing the scene correctly.
5. **Specify Lighting and Time of Day**: Lighting can dramatically change the mood of an image. Specify if it’s day or night, sunny or cloudy, or if there’s a specific light source like candlelight or neon lights.
6. **Incorporate Action or Movement**: If you want a dynamic image, describe actions or movements. For instance, “a cat jumping over a fence” is more dynamic than just “a cat.”
7. **Avoid Overloading the Prompt**: While details are good, too many can confuse the AI. Try to strike a balance between being descriptive and being concise.
8. **Use Analogies or Comparisons**: Sometimes it helps to compare what you want with something well-known, like “in the style of Van Gogh” or “resembling a scene from a fantasy novel.”
9. **Specify Desired Styles or Themes**: If you have a particular artistic style or theme in mind, mention it. For example, “cyberpunk,” “art deco,” or “minimalist.”
10. **Iterative Approach**: Sometimes, you may not get the perfect image on the first try. Use the results to refine your prompt and try again.