Microsoft unveiled its first in-house AI image generator, MAI-Image-1 to generate “photorealistic” images, which the company claims is faster and produces better quality images compared to other large AI models, El.kz reports citing thehindu.com.

The AI model excels in portraying light in the images it generates with reflections and image bouncing off in landscape output. 

The AI model was trained to deliver “genuine value for creators” by steering clear of repetitive and generic results, the company said in its blog. The team did their data selection carefully and evaluated the tasks while taking continuous feedback from creative professionals. 

Earlier in August, Microsoft AI also unveiled their first homegrown AI models for speech, MAI-Voice-1 AI and chatbot MAI-1-preview.

While Microsoft had previously solely relied on OpenAI’s models, the company has been showing signs of weaning off. Besides investing in training their own AI models, the Satya Nadella-led company has also included rival firm Anthropic’s AI models onto Microsoft 365 recently. 

The MAI-Image-1 will be made available in Copilot and Bing Image Creator soon. Users can test it in LMArena currently, Microsoft said. The model has already secured a spot in the top 10 on the AI benchmark.