Home News OpenAI unveils DALL-E 3 with support for text and typography

OpenAI unveils DALL-E 3 with support for text and typography

by WeeklyAINews
0 comment

Head over to our on-demand library to view classes from VB Rework 2023. Register Right here


Open AI’s DALL-E 2 AI picture technology mannequin is now not cutting-edge.

As we speak, the company announced DALL-E 3, its newest text-to-image generator and confirmed off a few of its new spectacular options, together with the power to generate readable textual content baked immediately into pictures themselves — one thing that was not simple with DALL-E 2, and which different competing picture generator AI fashions similar to Midjourney nonetheless battle to realize.

“DALL·E 3 delivers important enhancements over DALL·E 2 when producing textual content inside a picture and in human particulars like arms,” OpenAI wrote on its web page explaining the brand new mannequin.

This characteristic places OpenAI in direct competitors with Ideogram, a startup from former Googlers launched final month, which additionally presents picture technology with textual content/typography baked in utilizing its personal proprietary AI mannequin.

Understands spatial relationships

Moreover, OpenAI wrote that DALL-E 3 does a a lot better job of understanding the spatial relationships that customers embrace of their immediate textual content, producing imagery that locations figures and objects the place the person has described in relation to 1 one other. Because of this descriptive prompts can now be rendered way more precisely, as seen in an instance screenshot under.

Screenshot of picture generated by OpenAI’s DALL-E 3 and the prompts used. Credit score: OpenAI

Built-in with ChatGPT

OpenAI additionally mentioned that DALL-E 3 can be coming to ChatGPT Plus, the paid $20-per-month subscription tier of its hit giant language mannequin (LLM), and its new ChatGPT for Enterprise plans introduced final month, that means that company purchasers will now have the power to generate imagery with textual content for his or her advertising or inner collateral.

See also  Korea's internet giant Naver unveils generative AI services

As well as, OpenAI says that ChatGPT will help customers refine their prompts robotically to generate the imagery that higher matches their intent.

A video posted by OpenAI co-founder and CEO Sam Altman on X, the social community previously often called Twitter, demonstrates the spectacular back-and-forth conversational prompting model that’s now attainable in DALL-E 3 because of the ChatGPT integration.

On the similar time, OpenAI wrote that “like earlier variations, we’ve taken steps to restrict DALL-E 3’s capability to generate violent, grownup, or hateful content material.”

The announcement was cheered on by OpenAI developer relations advocate Logan Kilpatrick on X (previously Twitter), who mentioned it was “completely unimaginable.”



Source link

You Might Be Interested In
See also  OpenAI chief says age of giant AI models is ending; a GPU crisis could be one reason why

You may also like

logo

Welcome to our weekly AI News site, where we bring you the latest updates on artificial intelligence and its never-ending quest to take over the world! Yes, you heard it right – we’re not here to sugarcoat anything. Our tagline says it all: “because robots are taking over the world.”

Subscribe

Subscribe my Newsletter for new blog posts, tips & new photos. Let's stay updated!

© 2023 – All Right Reserved.