DALL-E 2 image generator OpenAI logo and examples.

DALL-E

Part of a series on AI Art. [View Related Entries]
[View Related Sub-entries]

Updated Dec 13, 2022 at 02:57PM EST by Philipp.

Added May 06, 2022 at 08:41AM EDT by Philipp.

PROTIP: Press 'i' to view the image gallery, 'v' to view the video gallery, or 'r' to view a random entry.

This submission is currently being researched & evaluated!

You can help confirm this entry by contributing facts, media, and other evidence of notability and mutation.

About

DALL-E 2 is an AI system that can create realistic images and art from a description in natural language. Unveiled by OpenAI as an improved version of DALL-E in April 2022, the AI system gained significant attention as it was used to create art and photorealistic, humorous images. In June 2022, a knock-off free version of DALL-E, DALL-E mini, went viral on social media.

History

On April 6th, 2022, AI research and deployment company OpenAI[1] unveiled DALL-E 2, an AI model able to make realistic edits to existing images, create variations of images and generate completely new images from natural language prompts. On the same day, a demonstration video for the AI system was uploaded to YouTube[2] (shown below).



Have you ever seen a polar playing bass? Or a robot painted like a Picasso? Didn't think so. DALL-E 2 is a new AI system from OpenAI that can take simple text descriptions like "a koala dunking a basketball" and turn them into photorealistic images that have never existed before.

Features

DALL-E 2 is an upgraded version of DALL-E, an AI system released by OpenAI in January 2021. DALLE-2 can create original, realistic images from a text prompt in natural language and is able to combine concepts, attributes and styles (examples[3][4] shown below).


OpenAl @OpenAl “An ibis in the wild, painted in the style of John Audubon" #dalle 10:36 AM · Apr 6, 2022 · Twitter Web App

DALL-E 2 is also able to produce realistic edits to exiting images from a natural image caption, adding and removing elements, shade, reflections and textures. Additionally, the software has the capacity to create versions of an existing image, such as variations of a painting.

Highlights

Following its limited release in April 2022, DALL-E 2 has been actively used by users with access to generate art and photorealistic images, as well as images based on humorous prompts. In April and May 2022, multiple images generated by the AI were shared on social media (examples[5][6][7] shown below).


Andrew Mayne @AndrewMayne "a raccoon wearing a hoodie working on his laptop late into the night" @OpenAl's DALL-E 2 sees the true me... 2:24 PM · Apr 6, 2022 · Twitter Web App Danielle Baskin @djbaskin Please enjoy an Al generated drink #dalle #dalle2 6:42 PM · Apr 14, 2022 · Twitter Web App Merzmensch Kosmopol ... @Merzmensch Created with DALL·E 2 by @OpenAl "An IT-guy trying to fix hardware of a PC tower is being tangled by the PC cables like Laokoon. Marble, copy after Hellenistic original from ca. 200 BC. Found in the Baths of Trajan, 1506." He just can't #DALLE // #dalle2 // #DALLEmerz 8:35 AM · Apr 27, 2022 · Twitter Web App

On April 19th, 2022, developer Ryan O'Connor posted a blog explaining in detail how DALL-E 2 functions.[10]

On April 20th, 2022, director Karen X. Cheng used the AI system to generate visuals for the song "Feeling Good" by Nina Simone. The clip received over 22,200 views on Twitter[8] and over 10,000 likes on Instagram[9] in roughly two weeks (shown below).


Similar Projects

DALL-E mini

DALL-E mini is an AI system that can create images from a description in natural language which is a knock-off, less advanced but openly available version of DALL-E by OpenAI. The project went viral on Twitter in early June 2022 as it was used to generate humorous images, such as characters in unusual settings or characters eating various foods.

Artflow.ai

Artflow.ai is a website that hosts an artificial intelligence program that allows its users to generate digital faces based on short, textual input. Interest in the website increased notably in August 2021.

NeuralBlender

NeuralBlender is a neural net-based image-generation website that generates images based on a provided description. The tool gained moderate virality on social media in early November 2021, with users often utilizing it to generate images of various characters.

Search Interest

External References

[1] OpenAI – DALL-E 2

[2] YouTube – DALL·E 2 Explained

[3] Twitter – @OpenAI

[4] Twitter – @OpenAI

[5] Twitter – @AndrewMayne

[6] Twitter – @djbaskin

[7] Twitter – @Merzmensch

[8] Twitter – @karenxcheng

[9] Instagram – karenxcheng

[10] AssemblyAI – How DALL-E 2 Actually Works

Recent Videos 3 total

Recent Images 142 total


Top Comments

Tigrerojo
Tigrerojo

Everyone always imagines that a Robot Apocalypse would involve a killer AI like Skynet or A.M., but I think this one is a FAR more realistic threat. Just think about it:

1- As an image-generating tool, of COURSE the main use people will give it is to create porn. Eventually, it will become so great at creating furry porn that it will surpass human furry artists.

2- As everyone knows, a furry can only have one of two careers: Porn creator, or IT. Once they can no longer profit from porn because their jobs were taken by robots, the endless masses of furries will flock to IT careers.

3- The sudden, drastic increase in IT workers will sharply drop the value of those jobs, and will inevitably result in a massive drop in salaries.

4- As IT suddenly becomes a non-rewarding career, workers will quickly flock to alternative careers. With most Informatic positions being left void, all of the infrastructure, government, militaries and industries that depend on them will collapse, leading to a worldwide streak of chaos, anarchy, and violence.

I think it's time for everyone to leave their differences behind and unite against the true enemy of Humanity: Image-Creating AI's.

+22

+ Add a Comment

Comments (5)


Display Comments

Add a Comment


Namaste! You must login or signup first!