DALL-Everse

DALL-E

by

The first image generator created by OpenAI was called DALL-E and revealed in a blog post on 5 January 2021.

The name DALL·E is a creative blend of :

🎨 Salvador Dalí (the surrealist artist)

and

🤖 WALL·E (the animated robot from the 2008 Pixar movie)

🧠 It symbolizes :

  • Dalí → Represents creativity, surrealism, and imagination — aligning with the AI’s ability to generate fantastical and artistic images.
  • WALL·E → Represents technology, intelligence, and a lovable machine — highlighting the AI/robotic aspect of the model.

The AI model DALL-E was never made available to the public. DALL-E2 and DALL-E3 were the successors of DALL-E and they were both accessible by ordinary people.

In July 2021, Boris Dayma developed an open-source image generator called DALL-E Mini.

Crayon alias DALL-E mini

by

Boris Dayma initially created and launched DALL·E Mini during a hackathon organized by Hugging Face, in collaboration with Google in July 2021. This community event brought together around 800 participants, during which Boris Dayma built the first iteration of what would become a viral, open-source text-to-image model. This image generator was based on smaller, open-source AI models like VQGAN and CLIP. It was trained on publicly available datasets. It brought AI art to the masses long before full access to other image generators like DALL·E 2, Midjourney, or Stable Diffusion was common.

After it gained popularity, OpenAI reportedly asked them to rebrand to avoid misleading people that it was affiliated with, or endorsed by, OpenAI. The project was renamed Crayon, a simple and amicable rebranding, without a legal lawsuit.

DALL-E2

by

OpenAI officially unveiled the second version of it’s famous AI image generator DALL·E 2 on April 6, 2022, marking its debut to the public and the broader AI community.

📅 Key Launch Timeline:

  • April 6, 2022 – DALL·E 2 introduced, showcasing its significantly improved image quality and resolution .
  • July 20, 2022 – Entered beta with invites to approximately 1 million users
  • September 28, 2022 – Made publicly accessible by removing the waitlist

Among the first DALL-E2 images created by beta tester were the two following pictures published on July 22, 2022 :

Prompt : A Picasso-style painting of a parrot flipping pancakes ; Credit : IEEE Spectrum July 2022

Prompt : New Yorker-style cartoon of an unemployed panda realizing her job eating bamboo has been taken by a robot ; Credit : IEEE Spectrum July 2022

I was admitted as beta Tester by OpenAI on August 15, 2022. Here is my first image generated with the prompt cartoon of an elephant and a giraffe riding a bicycle on the beach. I posted it the same day on Facebook.

In the following days I generated more images and posted them as Image of the Day on Facebook. Here is a small gallery :

My first prompt became my favorite one to test new image generators when they became available. During your visit of posts about other images generators in the present knowledge section of the KI-Léierbud you will discover more images showing elephants and giraffes riding bicycles.