The magician who creates digital images from the text: DALL-E

In this article, I share my thoughts on some of the images created by DALL-E.

The magician who creates digital images from the text: DALL-E
A magician creating an explosion of a nebulla from his wand. 3D rendering digital art. Created with the help of DALL-E.

Recently, I have received an invitation to create with DALL-E.

In simple terms, DALL-E is a platform which generates digital images from the text provided to it.

I had a lot of fun experimenting with this platform.

Here are the few images which I created with DALL-E.

The text I have entered to DALL-E is under the caption.


An impressionist painting containing an Indian male adult in his 20s before standing before Eiffel Tower with water canal visible on a nice sunny day

My thoughts about the image:

The description is quite complex, with so many elements, and DALL-E created this image with all the details. Besides, there is a spelling mistake in the text based on the outcome of the image. I am sure DALL-E corrected the text before creating the image.

Besides describing the text form, I can also specify the type of painting I want to create. The above image is an impressionist painting.


Mid 20s male Indian enjoying life having Belgium waffles. Face not clearly visible and he's in peace with life, gouche painting

My thoughts about the image:

The text provided to DALL-E is quite simple, and the image reached my expectations. Besides the description, there are a few elements, like the person wearing a smartwatch and the way the person is eating the Waffles, which I thought was terrific.

he's in peace with life is a text I intentionally added to identify if DALL-E understood or not. Based on the way the person is eating, I think it has understood.

I didn't understand why tomato sauce was on the bottom left of the table. I mean, do people have tomato sauce with Belgium Waffles? ๐Ÿ˜…๐Ÿ˜œ

The input for this image was to create a Gouache Painting. There was a spelling mistake, but I think DALL-E figured it out.



A goutche painting containing an Indian male adult in his mid 20s before cycling in the most scenic place of Amsterdam

My thoughts about the image:

This painting is a simple text yet a complex creation. Why? Because I have asked DALL-E to paint the subject in the most scenic place of Amsterdam.

DALL-E did the job nicely here as well. DALL-E knew that canals are the most scenic places in Amsterdam and painted the subject precisely near a canal.


Mid 20s male Indian standing and in the background landmarks of Berlin city. Face not clearly visible and he's in peace with life, gouche painting

My thoughts about the image:

There are two famous landmarks of Berlin in this picture. One is Brandenburg Gate, and the other is Berliner Fernsehturm (the tower to the right in the centre). The instructions for this creation were simple, yet they were complex for DALL-E.

Only thing which I felt was missing in this photo was he's in peace with life. There's not much information available to identify that the person in the subject is at peace with life.


๐Ÿ’ญFinal Thoughts

I would say I am having a blast using DALL-E. But there are still a lot of things I have not tested. Mainly, I want to try and analyse the elements
from Indian culture's perspective.

From an Indian cultural perspective, the initial inputs I gave to DALL-E weren't that satisfactory. But since this is an AI, I am optimistic that it would also evolve to support this segment.


๐ŸŽ‰How to get access to DALL-E

In case you would like to get access to DALL-E and try it out, you can sign up on openai website. It's pretty straight forward. I signed up for it and got the invitation to access in 10 days time. But this was during it's early days. Now, it might take some time.