Summary
- Microsoft releases new Image Generator to Bing
- Image Generator will allow Ai to generate images from text prompts
- Roll-out has begun, but the Ai is still in the preview stage
Microsoft announced on March 21st that they had developed a new AI to let users generate images from text prompts.
The announcement comes just days after ChatGPT-4 was released to much fanfare, with disappointment settling in after it was announced that the AI would not have an image creator but would, instead, have the ability to interpret image queries.
However, Bing’s new AI update, powered by OpenAI’s image-generating AI – DALL-E, will allow users to generate images using text.
“We’re excited to announce we are bringing Bing Image Creator, new AI-powered visual stories, and updated Knowledge Cards to the new Bing and Edge preview,” Microsoft said in their blog yesterday.
Though they did not reveal which DALL-E version was powering the new image creator, Microsoft said that it was an advanced version of DALL –E that allowed users to ‘create an image simply using your words to describe the picture you want to see. Now you can generate written and visual content in one place from within a chat.’
Curbing misuse
As with other AI, the Bing Image Creator also has limitations to curb misuse and prevent it from delving into the creepy fields of the previous Bing AI.
“We have put controls in place that aim to limit the generation of harmful or unsafe images. When our system detects that a potentially harmful image could be generated by a prompt, it blocks it and warns the user.” Microsoft said.
What next?
Microsoft says it will continue to make iterations to this new image generator, including optimizing existing features.
The new Bing AI Image Creator has started rolling out on Bing and Microsoft Edge. However, right now, you can access it on the preview, but that is an invite-only preview, and you can sign-up here to join the waitlist.
