OpenAI has announced wider availability of its DALL-E 3 text-to-image generator. It is now available to ChatGPT Plus and Enterprise customers, the company announced in a blog post.
“ChatGPT can now create unique images from a simple conversation—and this new feature is available to Plus and Enterprise users today. Describe your vision, and ChatGPT will bring it to life by providing a selection of visuals for you to refine and iterate upon. You can ask for revisions right in the chat. This is powered by our most capable image model, DALL·E 3,” writes OpenAI.
DALL-E 3 which was announced recently comes with “several research advancements, both from within and outside of OpenAI” over its predecessor. The
model has been praised for its ability to generate realistic and high-quality images from text prompts. According to the company, DALL·E 3-generated images are rich in details. It is particularly good at responding to extensive, detailed prompts, and it can support both landscape and portrait aspect ratios.
To make sure DALL·E 3 doesn’t create harmful stuff, OpenAI has implemented safety checks. It looks at what users ask and what DALL·E 3 makes before users see it. It is especially to find gaps in safety, especially for things like sexual or misleading stuff.
OpenAI is also testing a tool to see if an image was made by DALL·E 3. In its early evaluation, the tool was 99% accurate in telling if an image is likely from DALL·E when it’s not changed. Even when people changed a bit such as cropping, resizing, JPEG compression, or when text or cutouts, it’s still pretty good with about 95% accuracy. But it can’t be 100% sure yet. This tool might help people know if an image or sound is made by AI.
Follow FE Tech Bytes on Twitter, Instagram, LinkedIn, Facebook.
