OpenAI DALL-E 3 text-to-image generator now available for ChatGPT Plus and Enterprise users
OpenAI has rolled out the DALL-E 3 text-to-image generator that generates AI-powered images as per user text prompts to ChatGPT Plus and Enterprise customers.
OpenAI has rolled out the DALL-E 3 text-to-image generator that generates AI-powered images as per user text prompts to ChatGPT Plus and Enterprise customers.
According to the company, ChatGPT can now create unique images from a simple conversation. The feature is powered by the image model, DALL•E 3 and is currently available for Plus and Enterprise users. To create images from text, you just need to describe what you want and ChatGPT will provide a list of visuals that you can select or further refine by giving more details.
OpenAI has made various improvements and advancements for DALL-E 3 over its predecessor.
DALL-E 3 is currently very popular among users for its ability to generate realistic and high-quality images from text descriptions. DALL-E 3 is capable of responding to extensive, detailed prompts, and it can support both landscape and portrait aspect ratios.
OpenAI has taken caution to take steps to prevent the misuse of DALL-E 3. The company has implemented safety rules and checks so that the DALL-E 3 doesn’t create harmful stuff. The AI-image generator will first inquire what the user wants and if it is suitable for image generation or not.
DALL•E 3 makes sure to find gaps in safety, especially for things like sexual or misleading stuff.
To check the authenticity of images created by DALL-E 3, OpenAI is also developing a tool, that will see if an image was made by DALL•E 3.
As per OpenAI, the tool was 99% accurate in checking whether the image is from DALL-E or not. 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 not 100% successful yet. This tool might help people know if an image or sound is made by AI.