Psst. Don’t tell anybody, but the answer to your question is in the second paragraph in the article:
Similar to outpainting—an AI imagery technique introduced by OpenAI’s DALL-E 2 in August 2022—Midjourney’s zoom-out feature can take an existing AI-generated image and expand its borders while keeping its original subject centered in the new image. But unlike DALL-E and Photoshop’s Generative Fill feature, you can’t select a custom image to expand. At the moment, v5.2’s zoom-out only works on images generated within Midjourney, a subscription AI image-generator service.
How’s that different from outpainting, which has been a thing for a very long time?
https://openai.com/blog/dall-e-introducing-outpainting
https://stable-diffusion-art.com/outpainting/
Psst. Don’t tell anybody, but the answer to your question is in the second paragraph in the article:
Haha, you got me :)
For some reason, midjourney is getting more hype than the alternatives, which is especially sad for stable-diffusion being open-source and all.