Midjourney Unveils New AI Image Generator V7

Midjourney, one of the pioneering services for AI-generated images, has launched its new AI model, V7.

We’re now beginning the alpha-test phase of our new V7 image Model. It’s our smartest, most beautiful, most coherent model yet. Give it a shot and expect updates every week or two for the next two months. pic.twitter.com/Ogqt0fgiY7

— Midjourney (@midjourney) April 4, 2025

“It’s our smartest, most beautiful, and most coherent model,” the announcement states.

V7 is available in two versions—Relax and the more expensive Turbo. Additionally, a Draft Mode is offered, which is half the cost and ten times faster than the standard plan. Drafts are of low quality but can be immediately enhanced. The company suggests “thinking out loud,” verbalizing various ideas for image generation.

One of the most exciting new features for our new V7 model is something we call “Draft Mode”. 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

— Midjourney (@midjourney) April 4, 2025

Before starting with V7, users must provide the neural network with about 200 images to create a personalized profile. This configures the model according to individual user preferences.

MidJourney v7 is out!

On my usual benchmark prompts, it only (kinda) gets one, though ? v6 was able to nail the pixel art, v7 regresses in this regard.

Prompts in alt, all were done on Fast w/o personalization pic.twitter.com/Qwme1Rt1Dc

— Xeophon (@TheXeophon) April 4, 2025

“Sometimes you have to play around with the prompt for a while—it’s a completely different architecture,” emphasized the company’s CEO, David Holz.

A number of standard Midjourney features, such as image scaling and retexturing, are currently unavailable for V7. They will be introduced later.

Midjourney’s last major development was over a year ago when the company announced a new AI model for image creation that could generate meaningful text.

The new tool emerged a week after OpenAI added an image generator based on the GPT-4o model to ChatGPT and Sora. The service gained widespread popularity, leading to a shortage of high-performance resources.

Earlier in April, Sam Altman’s startup closed a new funding round, raising $40 billion at a $300 billion valuation.