OpenAI has introduced a new version of the image generator DALL-E 3 and plans to integrate it into ChatGPT. This generator is able to better understand queries, analyze complex instructions and create more highly detailed images compared to the previous version of DALL-E 2.
DALL-E 3 has improved its skills in detail processing, including images of human hands. The results of its work, according to the developers, are significantly superior to DALL-E 2.
DALL-E 3 is planned to be integrated into ChatGPT Plus and Enterprise chatbots, which will give users the ability to create more accurate images and customize queries based on the results.
DALL-E 3 is currently in research preview and will be available to ChatGPT Plus and Enterprise subscribers in October via API.
It is noted that images created using DALL-E 3 belong to the users and they do not require permission to use them. However, the generator will limit the creation of images related to public figures or containing harmful biases to reduce the risk of spreading misinformation.