An AI artist can now give an impression of what the backdrops of famous paintings and photos might have looked like.
OpenAI, a San Francisco-based company, has developed a new tool called “Outpainting” for its text-to-image AI system DALL-E.
Outpainting allows the system to imagine what is outside the frame of famous paintings such as Girl with a Pearl Earring, Mona Lisa, and Dogs Playing Poker.
As users have pointed out, it can do this with any type of image, like the man on the Quaker Oats logo and the cover of the Beatles’ Abbey Road album.
DALL-E relies on artificial neural networks (ANNs) that Simulate how the brain works to learn and create an image from text.
CHANGED: OpenAI, a San Francisco-based company, has developed a new tool called “Outpainting” for its text-to-image AI system DALL-E. Outpainting allows the system to imagine what is outside the frame of famous paintings like Girl with a Pearl Earring
ORIGINAL: Girl with a Pearl Earring is an oil painting on canvas (c. 1665) by the Dutch artist Johannes Vermeer. Shown is the original painting without AI manipulation
Outpainting requires users to describe the new enhanced visuals DALL-E in text form before they can be “painted”.
Outpainting, which is primarily aimed at professionals who work with images, will allow users to “expand their creativity” and “tell a bigger story,” according to OpenAI.
The company said in a blog post, “Today we’re introducing Outpainting, a new feature that helps users expand their creativity by taking an image beyond its original limits – adding visuals in the same style or taking a story in new directions.” direct – simply by using a natural language description.
“Outpainting allows users to expand the original image and create large format images in any aspect ratio.
“Brushing respects the existing visual elements of the image—including shadows, reflections, and textures—to maintain the context of the original image.”
US artist August Kamp used outpainting to reinterpret Johannes Vermeer’s famous 1665 painting Girl with a Pearl Earring.
Amazingly, the tool managed to create a background that mimicked the original’s painting style.
The results show the famous girl in a home setting surrounded by dishes, houseplants, fruit, boxes and more.
It contrasts with the simplicity of Vermeer’s classic, which depicts the girl against a dark, blank background.
Other attempts are a bit more silly – one features the theme of Mona Lisa making the devil’s horn gesture with her hand, with a UFO and a killer robot in the background.
Another shows the man from the Quaker Oats logo with a large bust and in a dress, surrounded by drinks bottles.
And yet another shows a few people crossing the famous crosswalk in front of Abbey Road Studies with the Beatles, with autumn leaves scattered, although the original photo was taken in midsummer.
According to The Verge, DALL-E is available to more than 1 million people through a beta program that offers users a certain amount of free image generation.
People can join a waiting list on the OpenAI website to “build with DALL-E,” though the company said it “is sending out invites over time.”
DALL-E already allows changes within a generated or uploaded image – a skill known as inpainting.
It is able to automatically fill in details like shadows when an object is added or even adjust the background when an object is moved or removed.
DALL-E can also generate a completely new image from a text description, e.g. For example, “an armchair shaped like an avocado” or “a cross-sectional view of a walnut.”
Another classic example of DALL-E’s work is “teddy bears working on new AI research underwater using 1990s technology.”
DALL-E image from “Teddy Bears Working on New AI Research Underwater Using 1990s Technology” Call
OpenAI is also known for AI-generated audio.
In 2020, it unveiled Jukebox, a neural network that generates eerie approximations of pop songs in the vein of several artists, including Elvis Presley, Frank Sinatra, and David Bowie.
The neural network creates music, including rudimentary vocals with lyrics in English and a variety of instruments such as guitar and piano.
OpenAI scraped 1.2 million songs, 600,000 of which were sung in English, from the internet and combined them with the lyrics and metadata that were fed into the AI to generate approximations of the different artists.
HOW ARTIFICIAL INTELLIGENCE LEARNS WITH NEURAL NETWORKS
AI systems rely on artificial neural networks (ANNs) that try to simulate how the brain works in order to learn.
ANNs can be trained to recognize patterns in information – including speech, text data or visual images – and are the basis for a variety of developments in AI in recent years.
Traditional AI uses inputs to “teach” an algorithm about a certain topic by feeding it huge amounts of information.
AI systems rely on artificial neural networks (ANNs) that try to simulate how the brain works in order to learn. ANNs can be trained to recognize patterns in information—including speech, text data, or visual images
Practical applications include Google’s language translation services, Facebook’s facial recognition software, and Snapchat’s image-altering live filters.
Entering this data can be very time consuming and limited to one type of knowledge.
A new generation of ANNs called Adversarial Neural Networks pit the minds of two AI bots against each other, allowing them to learn from each other.
This approach aims to speed up the learning process and refine the output generated by AI systems.
