Midjourney has launched its newest image-generation AI model, known as V7, which became available in alpha version on Friday. The release comes nearly one year after the introduction of its predecessor, V6. Users can now test the capabilities of the V7 model, which is notable for having personalisation features activated by default. Furthermore, this version introduces a new “Draft Mode,” designed to operate at half the cost of the standard mode while providing a speed advantage of ten times.
Midjourney’s V7 Introduces New Modes and Features
The announcement of V7 was made via a post on X (formerly Twitter), where Midjourney’s official account outlined the enhancements over V6. The new model boasts improved adherence to text prompts along with superior image quality and textures. Additionally, the company stated that the coherence of various elements in images has been significantly increased compared to its earlier version.
With V7, model personalisation is turned on by default. To access the AI model, users must first rate a wide array of images to create a personalisation profile. This profile allows the model to better understand a user’s preferences and tailor outputs accordingly. However, users have the option to deactivate personalisation after accessing V7.
Another key feature being launched with the V7 model is Draft Mode. This mode allows users to generate images at a cost that is half of the standard mode while delivering images much faster. Draft Mode acts as an iteration tool, enabling users to provide multiple prompts and make real-time edits to images, even incorporating voice input for a more interactive experience.
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
To enable Draft Mode, users can either select the option on the web client or include “–draft” at the end of their prompts. While the quality of images produced in Draft Mode is lower than that of the standard mode, the model’s behaviour and aesthetic output remain consistent.
The V7 model is available in both Turbo and Relax variants, with Turbo mode priced at twice the cost of standard output generation. It is important to note that the current version does not support tasks related to upscaling, editing, or retexturing, which will redirect users to V6 for those functionalities.
In the coming weeks, Midjourney plans to roll out new features for the V7 model every week or two over the next two months. Upcoming enhancements include capabilities for character and object reference.
