Getting Started with DALL-E

Learn the three main ways to generate images with DALL-E 3: ChatGPT, Bing Image Creator, and the OpenAI API.

Option 1: Using ChatGPT (Recommended)

The easiest and most powerful way to use DALL-E 3. ChatGPT enhances your prompts and allows conversational iteration.

1. Open ChatGPT

   Go to chat.openai.com and log in. You need ChatGPT Plus ($20/month) or a Team/Enterprise plan.

2. Ask for an Image

   Simply describe what you want in natural language. ChatGPT will automatically use DALL-E 3 when you ask for an image.

3. Iterate

   Ask for changes: "Make it more colorful," "Change the background to a beach," or "Create a variation in watercolor style."

You:
Create an image of a cozy reading nook by a window
on a rainy day, with a cat sleeping on a cushion
and a steaming cup of tea on the windowsill.

ChatGPT generates the image, then you can say:
Make the lighting warmer and add some bookshelves
in the background.

Or:
Create the same scene but in a Studio Ghibli
animation style.

Option 2: Bing Image Creator (Free)

Microsoft offers DALL-E 3 for free through Bing Image Creator:

1. Visit Bing Image Creator

   Go to bing.com/images/create and sign in with a Microsoft account.

2. Enter Your Prompt

   Type a description and click "Create." You get a set of boosts for faster generation. After boosts run out, generations are slower but still free.

Option 3: OpenAI API

For developers who want to integrate DALL-E into applications:

from openai import OpenAI

client = OpenAI()

response = client.images.generate(
    model="dall-e-3",
    prompt="a cozy cabin in a snowy forest at night",
    size="1024x1024",
    quality="standard",
    n=1,
)

image_url = response.data[0].url
print(image_url)

What's Next?

Now that you can generate images, the next lesson teaches you how to write effective prompts that produce exactly the results you want.