Alpha testing of image generation AI 'Midjourney V7' begins, featuring a draft mode that can generate images at explosive speeds by following voice instructions

Alpha testing of version 7 (Midjourney V7) of the image generation AI 'Midjourney' began on April 4, 2025. Midjourney V7 has improved drawing quality of hands and bodies compared to the previous version, and also has a 'draft mode' that can respond quickly to voice instructions.

V7 Alpha

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

Below is an example of a scene generated by Midjourney V7. Even complex compositions such as a face seen through a hood can be rendered without any sense of incongruity, and the blur in front of and behind the main subject is also reproduced in detail.

Below is an image of a 'hand' generated by Midjourney V7. The wrinkles and fingerprints on the hand are drawn in detail. However, the index finger seems too short.

Please Seriously Forgive me for being GOD.

@midjourney V Fucking 7 pic.twitter.com/z5HlqQM3Oi

— Tabi Yume (@U79916881747113) April 4, 2025

Midjourney V7 is equipped with a 'draft mode' that allows you to generate images one after another by following voice instructions. The following post has an embedded video showing an example of the draft mode.

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

After generating an image of a cat, the user says, 'Make it two cats.'

Then, an image was generated in which the number of cats was changed to two, based on the previous prompts.

Furthermore, when the participant said 'Both are eating strawberries,' a picture of 'two cats eating strawberries' was drawn.

Midjourney V7 also has model personalization enabled by default, allowing users to generate images tailored to their preferences.

New features are scheduled to be added to Midjourney V7 every 1-2 weeks, and the addition of 'character and object reference functionality' is also announced.