Microsoft Integrates OpenAI’s DALL-E 3 into Bing Image Creator

Bing image creator integrates DALL-E 3's advanced features to ensure user content adheres to guidelines.

Bing-Chat-Bing-Image-Creator

's Bing Image Creator is already incorporating 's new DALL-E 3 text-to-image model with higher precision and improved quality output. While 3's official release to ChatGPT Plus and Enterprise subscribers is slated for October, some users are already exploring its advanced features.

Deepening Ties Between Microsoft and OpenAI

Mikhail Parakhin from Microsoft confirmed the early integration of , highlighting the collaborative spirit between Microsoft and OpenAI. Bing Image Creator, with its unique feature of crafting non-existent images from user descriptions, now benefits from DALL-E 3's enhanced capabilities, ensuring user-generated content remains within set guidelines.

A Glimpse into the Future

Parakhin's hints suggest that a select group is already experiencing DALL-E 3's prowess within Bing Image Creator. With OpenAI's plans to integrate its chatbot with DALL-E 3, users can anticipate richer functionalities and a more immersive experience in the near future.

ChatGPT is now integrated with DALL·E 3, a major update that lets users interact with the chatbot to refine their image requests. Users can now see the generated images right in the chat app. DALL·E 3 will be available for and enterprise customers in October, and for the public and API customers later this fall.

DALL·E 3 can produce high-quality images that match user queries closely. It can follow complex descriptions and generate text within images, such as labels and signs, which was hard for previous models. DALL·E 3 can also render objects with little distortion, following the prompts faithfully.

OpenAI has also emphasized its commitment to safety and ethical considerations. The company has introduced measures to enhance the safety of DALL·E 3 and minimize algorithmic bias. In response to concerns raised by artists about image generators, DALL·E 3 has been programmed to decline requests that seek images in the style of living artists. Moreover, artists now have the option to exclude certain or all of their images from being used in training future OpenAI image generation models.