Dall-E, an automated imaging tool, is now open to everyone

OpenAI breaks down corpses. An American company specializing in artificial intelligence now allows any Internet user to use its impressive Dall-E tool. This deep neural network is able to generate high-resolution images in seconds from a text query such as “two people were discussing on the terrace of a Parisian cafe, in autumn, in the manner of Gauguin.»

Until now, access to Dall-E was reserved only for professionals who had to register on a waiting list. Before opening to the general public, 1.5 million people were creating 2 million images every day on the OpenAI website.

.fig-i-e05979b31544b1761e7fb517f4717055.fig-placeholder::before {padding-top:32.537788385044%}<div class=”fig-media__container fig-placeholder fig-i-e05979b31544b1761e7fb517f4717055 fig-lazy fig-placeholder–with-dimensions” data-module=”fig-photo” data-context=”was @visible” data-modal-image=’‘data-modal-image-credit=”Open AI” aria-label=”Enlarge Image”>

The general public already got a taste of image-generating AI this summer thanks to free sites like Craiyon, often with hilarious results. But Dall-E’s neural network is more powerful and capable of producing professional-looking visuals, some of which have already made magazine covers.

Filters to avoid distractions

OpenAI has restricted the use of Dall-E. New users get 50 free survey credits after signing up. They will then be entitled to 15 free text inquiries per month. Beyond that you will have to pay. Price, non-decreasing, $15 for 115 credits.

The US company initially took a cautious approach, restricting access to Dall-E, fearing that its tool could be used by malicious people for disinformation, propaganda or cyberattacks. This gradual openingenabled us to strengthen our security systems. Our filters have become more robust and reject requests to create visuals that are violent, sexual, or violate our content policy.” explains OpenAI. For example, it is impossible to create images about the war in Ukraine or public figures.

OpenAI is also trying to correct the bias of its artificial intelligence, which reproduces the clichés it has been subjected to by “digesting” huge visual databases. For example, if a user doesn’t specify the gender or ethnicity of the characters they want to see in their image, OpenAI will add the terms “female,” “black,” or “Asian” to diversify the results. .

Source: Le Figaro

David

I am David Wyatt, a professional writer and journalist for Buna Times. I specialize in the world section of news coverage, where I bring to light stories and issues that affect us globally. As a graduate of Journalism, I have always had the passion to spread knowledge through writing.