OpenAI presented the new version of the DALL-E artificial intelligence image generator, which acquires a greater comprehension capacity to understand and recreate what the user requests in detail.

DALL-E is the generative AI tool that creates an image from a text description provided by the user. The new version, as reported by OpenAI, is built natively in ChatGPT and will work together with this ‘chatbot’.

The technology company ensures that DALL-E 3 “understands many more nuances and details” than text descriptions, so it can “easily translate ideas into exceptionally precise images”, improving the result in the same proposal offered to DALL-E 2, as stated in its official blog.

OpenAI ensures that DALL-E 3 has protections that prevent it from generating violent, adult or hateful images. It also rejects requests from public figures and harmful biases, and work is being done internally to help identify images that have been generated with this AI tool.

DALL-E 3 is currently available to researchers in a preview, and will be rolled out to ChatGPT Plus and Enterprise in October.

K. Tovar

Source: The Verge

(Reference image source: OpenAI, Europa Press)

Visit our news channel on Google News and follow us to get accurate, interesting information and stay up to date with everything. You can also see our daily content on Twitter and Instagram

La entrada OpenAI released a new version of DALL-E apareció primero en Bitfinance.