Skip to main content

Midjourney’s new zoom-out feature is becoming the next big AI sensation

Midjourney is creating a sensation with its recently released 5.2 update. The popular generative AI service announced several upgrades, most notably, the ability to zoom out from images.

Rowan Cheung shared a video on Twitter demonstrating what’s possible. Even though Midjourney quickly generates the stills, you need 30 to 60 images for each second of video. With fewer stills, the zoom-out effect would be stuttery instead of smooth.

Midjourney v5.2 just dropped, and it's incredible.

This new AI feature allows anyone to "Zoom Out" of any photo.

Here are 10 mind-blowing examples, with a tutorial at the end 🧵: pic.twitter.com/8zszZMUjsS

— Rowan Cheung (@rowancheung) June 26, 2023

Nick St. Pierre was among the first to post examples of the zoom feature employed for video. He suggests using the interpolative zoom available in some video editors to reduce the number of images needed for a smooth zoom.

Zoom out + interpolation = magic

Only an hour into v 5.2 and I could cry

This is an incredible Midjourney update pic.twitter.com/hTzeSpt2uv

— Nick St. Pierre (@nickfloats) June 23, 2023

Pierre later tweeted a step-by-step guide to get the most out of this feature by adjusting the prompt and aspect ratio between generations. You can start with an AI-generated macro of a bee, add flowers to the zoom-out, then continue.

Base prompt to get you started. Super simple, just one word and an emoji.

Prompt: macro {🐝}

I used the bee emoji, but you can use any emoji you want. The insect emojis are great for this, but have fun with it. The eye emoji is really cool too 👁️ pic.twitter.com/6PYiCoDYcT

— Nick St. Pierre (@nickfloats) June 25, 2023

Matt Wolfe shared an interesting twist via Twitter, using Midjourney 5.2’s zoom feature to create varying backgrounds while the subject remains fixed.

When done right, I feel like this new zoom out feature could be the key to getting a consistent character in MidJourney.

1. Generate a super closeup of a face.
2. Do a custom zoom with whatever scenario you want.
3. Zoom out 2x again on the resulting image. pic.twitter.com/wWMovgi3rx

— Matt Wolfe (@mreflow) June 24, 2023

It’s easy to see why social media is buzzing about Midjourney. To be fair, this is a variation on outpainting which arrived in Dall-E in August of 2022. With outpainting, you can generate additional imagery anywhere on a canvas surrounding your original picture.

While Midjourney’s zoom feature keeps roughly the same number of pixels in the finished AI artwork, Dall-E’s outpainting increases the resolution as it generates new content.

Each AI platform has its strengths and weaknesses. The number of options continues to grow, and Adobe recently joined in on the fun. The beta version of Photoshop can do outpainting as well. The future of image and video creation is exciting.

Alan Truly
Alan is a Computing Writer living in Nova Scotia, Canada. A tech-enthusiast since his youth, Alan stays current on what is…
This new Photoshop tool could bring AI magic to your images
A mountainous landscape at night with the Northern Lights in the sky, a lake in the foreground, and a person standing under a rock archway on the right. This image was made with Adobe Photoshop's Generative Fill tool.

These days, it seems like everyone and their dog is working artificial intelligence (AI) into their tech products, from ChatGPT in your web browser to click-and-drag image editing. The latest example is Adobe Photoshop, but this isn’t just another cookie-cutter quick fix -- no, it could have a profound effect on imagery and image creators.

Photoshop’s newest feature is called Generative Fill, and it lets you use text prompts to automatically adjust areas of an image you are working on. This might let you add new features, adjust existing elements, or remove unwanted sections of the picture by typing your request into the app.

Read more
These 2 new ChatGPT features are about to change everything
OpenAI's website open on a MacBook, showing ChatGPT plugins.

ChatGPT Plus subscribers will soon get a much more powerful version of OpenAI's large language model, allowing it to access plugins and the internet. This will dramatically expand the capabilities and usefulness of the world's most famous chatbot.

OpenAI shared the news via a tweet linking to the latest ChatGPT release notes. Web browsing and plugin access will begin as an optional beta feature that can be enabled in settings.

Read more
5 things AI image generators still struggle with
Dall-E was an early AI leader but hands are not its thing.

AI image generators like Dall-E, Stable Diffusion, Midjourney, and Bing Image Creator produce amazing results, but sometimes they can be incredibly frustrating. With simple prompts containing just a few words, an AI can output impressive images that appear to be professional photographs and convincing art in various styles. However, the same prompt will occasionally create some horrific creature or hilariously flawed rendering.

Negative prompts might help reduce the likelihood of these errors, but complexity can't always save you. Even AI experts struggle with misshapen creatures and unworldly scenes, requiring long hours of refining prompts or touching-up images with a traditional photo editor. For the time being, if you look carefully in the right areas of an image, there's a good chance you'll be able to identify if it was made by a machine.
Hand salad and balls of fingers
AI developers have made progress in the struggle to teach artificial intelligence tools how human hands should look, but there's plenty of room for improvement. If fingers aren't featured prominently, it's easy to miss errors, but it's an ongoing problem.

Read more