Midjourney launches new image generator V7 following OpenAI’s GPT-4o release

Midjourney has started testing its new model V7 Alpha, which promises personalization and a faster way to generate images.

The company touts the model as the first to have personalization turned on by default. Prior to trying it, users must rate 200 hundred images, which are required to build a personalization profile.

Another new feature is Draft Mode, which renders images at 10 times the speed and supports voice queries.

Users can choose options like “enhance” or “vary” on the image, which will re-render it at full quality. However, draft images are of lower quality than those in standard mode.

One of the most exciting new features for our new V7 model is something we call undefinedDraft Modeundefined. Draft mode is half the cost and 10 times the speed and it might be the best way to iterate on ideas ever. Try it with voice, think out loud and let our ideas flow like liquid dreams. pic.twitter.com/ANfTMC6Ej1

undefined Midjourney (@midjourney) April 4, 2025

Upscaling, editing, and retexturing will currently fall back to V6 models and will be updated in the future.

In its blog post, Midjourney claims it will release new features every week or two for the next two months. The biggest incoming feature will be a new V7 character and object reference.

“Sometimes you have to play with the prompt for a while – it's a totally different architecture,” said David Holz, the founder and CEO of Midjourney, in a post on X.

The V7 Alpha release comes a week after Open AI released its image generator, 4o. This new tool, which allows users to create Ghibli-style images based on the hand-drawn style of the famed Japanese animation outfit, quickly went viral.

“The ChatGPT launch 26 months ago was one of the craziest viral moments I'd ever seen, and we added one million users in five days. We added one million users in the last hour," OpenAI CEO Sam Altman said in a post on X after the release.