Midjourney, the AI-powered image synthesis model, has unveiled version 5.2, which includes a new “zoom out” feature that has wowed AI artists with its camera-like capabilities. The feature allows users to maintain a central synthesized image while automatically building out a larger scene around it, simulating zooming out with a camera lens. David Holz, the creator of Midjourney, announced the new v5.2 features and improvements on the Discord server Thursday night.
Aside from “zoom out,” the most significant additions include an overhauled aesthetic system, promising better image quality, and a stronger “–stylize” command that effectively influences how non-realistic an image looks. There’s also a new “high variation mode,” activated by default, that increases compositional variety among image generations.
Despite the excitement over the new features among Midjourney enthusiasts, image synthesis remains highly controversial among some artists due to how these AI systems are trained, utilizing millions of scraped images from the web without proper attribution. However, the Midjourney team has stated that they are working on ways to address these concerns and improve the ethical use of their technology.
The “zoom out” feature has been particularly impressive to AI artists, as it allows them to create more complex and detailed images with ease. The feature has been described as “stunning” and “amazing” by those who have tried it out.
Midjourney’s image synthesis technology has been used for a variety of applications, including creating realistic-looking images of people who do not exist and generating photorealistic landscapes. The addition of the “zoom out” feature is expected to open up even more possibilities for the technology, allowing users to create more immersive and detailed scenes.
