After nearly a year, Midjourney, a pioneering AI image-generating service, has launched V7, its latest AI image model, beginning its alpha rollout around midnight EST on Thursday.
To use V7, users must first rate approximately 200 images to create a Midjourney “personalization” profile, which tailors the model to individual visual preferences and is enabled by default in V7. This can be done on Midjourney’s website or via its Discord chatbot.
Midjourney CEO David Holz described V7 as having a “totally different architecture” in a post on X. He also stated in a Discord announcement that V7 is “much smarter with text prompts” and exhibits noticeably higher image quality with better coherence in bodies, hands, and objects.
V7 comes in two versions: Turbo, which is more expensive to run, and Relax, both of which support a new Draft Mode tool that renders images at 10 times the speed and half the cost of the standard mode. According to Holz, standard Midjourney features like image upscaling and retexturing are not yet available for V7 but will be added in the near future, possibly within two months.
Founded in 2022 by David Holz, also a co-founder of Leap Motion, Midjourney reportedly anticipated revenues of around $200 million in late 2023. The San Francisco-based company recently announced the formation of a hardware team for undisclosed projects and is continuing to develop previously announced models for video and 3D object generation.
Midjourney faces lawsuits alleging infringement on the rights of millions of artists by training AI tools on images scraped from the web without consent.
