Midjourney has released a new shi-generator of images V7

One of the first services to create images using artificial intelligence Midjourney has released a new V7 Shi Model.

We’re Now Beginning The Alpha-Test Phase of Our New V7 Image Model. I Our Smartest, MOST BEAUTIFUL, MOST COHERENT MODEL YET. Give It A Shot and Expert Updates Every Week or Two for the Next Two MONHS. pic.twitter.com/ogqt0fgiy7

– Midjourney (@midjourney) April 4, 2025

“This is our smartest, most beautiful and humble model,” the announcement reads.

V7 is available in two variants – Relax and more expensive Turbo. Additionally presented DRAFT MODE mode, which is twice cheaper and 10 times faster than the standard plan. Rough work is of poor quality, but they can be improved immediately. The company recommends to think aloud, talking different ideas to generate images.

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 Best Way to Iteate on Ideas Ever. TRY iting voice, Think Out Loud and Let Our Ideas Flow Like Liquid Dreams. pic.twitter.com/anftmc6ej1

– Midjourney (@midjourney) April 4, 2025

Before starting to work with V7, you need to provide a neural network of about 200 images to create a personalized profile. It adjusts the model according to the user’s individual preferences.

Midjourney V7 is Out!

On My Usual Benchmark Prompts, IT Only (Kinda) Gets One, Thought 😕 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 it is necessary to play with a hint for a while – there is a completely different architecture,” David Holtz said CEO.

A number of standard Midjourney features like scaling and retracting images is not available for V7. They will appear later.

The latest development of Midjourney was introduced more than a year ago-then the company announced a new SI model to create images that was able to generate meaningful text.

The new tool appeared a week after Openai added to Chatgpt and Sora image generator based on GPT-4O. The service has gained wide popularity and has led to a lack of productive capacity.

Recall that in April, Startap Sam Altman closed the new round of funding, receiving $ 40 billion for estimates of $ 300 billion.

The gun