After launching generative AI models that create images based on text inputs provided by users, OpenAI is now upgrading its offerings with more prowess. The company that launched ChatGPT is bringing the third version of its AI image creator DALL-E 3. Here’s what is new.
OpenAI claims that DALL-E 3 understands significantly more nuance and detail (in text prompts) than its previous systems. This in turn allows users to create images more accurate to the idea users have in their minds.
“Modern text-to-image systems have a tendency to ignore words or descriptions, forcing users to learn prompt engineering. DALL-E 3 represents a leap forward in our ability to generate images that exactly adhere to the text you provide,” the company said.
OpenAI CEO Sam Altman shared some examples of images created by DALL-E 3 emphasising the accuracy of the results produced on the basis of text prompts.
DALL-E 3 built natively on ChatGPT
OpenAI said that DALL-E 3 is built natively on ChatGPT, which means that users can use the AI chatbot to create images as well as refine their prompts – from a simple sentence to a detailed paragraph in a conversational manner.
“When prompted with an idea, ChatGPT will automatically generate tailored, detailed prompts for DALL-E 3 that bring your idea to life. If you like a particular image, but it’s not quite right, you can ask ChatGPT to make tweaks with just a few words,” the company noted.
DALL-E 3 availability
DALL-E 3 will be available to ChatGPT Plus and Enterprise customers in early October. Images created with DALL-E 3 can be reprinted, sold or merchandised.
OpenAI has also said that DALL-E 3 will still not generate violent, adult, or hateful content. It has mitigations to decline requests that ask for a public figure by name.
For more such updates, keep reading @techinnews