I got my invitation from OpenAI DALL-E a few days ago and decided to play with it a little bit.
What is OpenAI DALL-E?
DALL-E is an AI system that can generate realistic images from a description. It uses a process called diffusion to combine different objects in the same image in a cohesive way. It started as a research project and is now available in beta. You can join the waitlist to get an invite.
Using the OpenAI Front-End
You are met with a simple user interface when you sign up.
![OpenAI DALL-E](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30044057/01-user-interface-overview-1024x460.png)
You can now get creative and generate whatever you would like to see. In the following example, I entered a puppy and a kitten playing in a green field and pressed the Generate button.
Here’s what it came up with:
![Image generated by AI for the description "a puppy and a kitten playing in a green field" 1 of 4](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30044144/DALL%C2%B7E-2022-08-30-05.39.55-a-puppy-and-a-kitten-playing-in-a-green-field.png)
![Image generated by AI for the description "a puppy and a kitten playing in a green field" 2 of 4](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30044201/DALL%C2%B7E-2022-08-30-05.39.57-a-puppy-and-a-kitten-playing-in-a-green-field.png)
![Image generated by AI for the description "a puppy and a kitten playing in a green field" 3 of 4](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30044217/DALL%C2%B7E-2022-08-30-05.39.59-a-puppy-and-a-kitten-playing-in-a-green-field.png)
![Image generated by AI for the description "a puppy and a kitten playing in a green field" 4 of 4](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30044222/DALL%C2%B7E-2022-08-30-05.40.01-a-puppy-and-a-kitten-playing-in-a-green-field.png)
I think the results are quite impressive. If I didn’t know they are AI-generated, I wouldn’t be able to tell so. There are some small giveaways, but I wouldn’t read too much into it.
If you hover over the images, a button appears which shows more options:
![Button showing quick actions menu](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30044917/02-image-quick-actions.png)
You can create even more similar images from it by clicking Generate variations. For example, the variations of the above image look like this:
![Image variations created based on a previously generated image](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30044933/03-image-variations.png)
Another option to generate images is uploading your own image.
To test this feature, I uploaded a stock image:
![Stock photo for ocean sunset](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30050022/pexels-bella-white-635279.jpg)
Accepted the disclaimer:
![Dialog box showing the rules for uploading images](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30050023/04-upload-disclaimer.png)
Then I was asked to crop the image.
![Dialog box asking to crop the image](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30050156/05-crop-image.png)
I accepted the default suggestion and clicked Done.
Then I asked to pick an action:
![Dialog box asking to pick an action: Edit image or Generate variations](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30050227/06-pick-an-action.png)
If you click Edit image, you are taken to an image editor. Looks like all it does is remove some parts if you like, though.
![Image editor to remove parts of the image](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30050417/07-edit-image.png)
I then went ahead with Generate variations action. Here are the results:
![Variations of the uploaded image](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30050755/08-image-variations-for-uploaded-image.png)
It doesn’t look like there are many variations, but then again, maybe it’s too simple to allow variations. I guess at this point, you just have to play with various ideas and see what works best.
Using DALL-E Programmatically
I wanted to write some code to generate the images programmatically, but I couldn’t find anything about it in the OpenAI docs. I asked the question on their Discord server, and a bot answered my question:
![Discord's answer to the DALL-E API question](https://cdn.devpower.co.uk/wp-content/uploads/2022/08/30052329/09-dalle-api.png)
So looks like that’s not an option for the time being.
Conclusion
This is just a quick overview of the OpenAI DALL-E project. There are other projects out there that produce similar results. It’s a very active field these days, so it’s worth watching the space. I’ll likely post an update when the API is available.