Midjourney has launched V7, its first new AI image model in nearly a year, introducing major improvements in image quality and text prompt accuracy.

The model, which rolled out in alpha on Thursday, features enhanced textures, better coherence in generating bodies and objects, and a new personalization system that tailors results to individual users.

To access V7, users must first rate around 200 images to create a personalised profile, a feature enabled by default for the first time.

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

The new model is available in two versions: Turbo, which generates images at a higher cost, and Relax, a more budget-friendly option. A new Draft Mode also allows users to create lower-quality images at ten times the speed and half the cost of standard mode, with the option to enhance them later.

Some existing Midjourney features, such as image upscaling and retexturing, are not yet available in V7 but are expected within two months.

Midjourney remains an independent company, having raised no external funding since its launch in 2022. The San Francisco-based firm is reportedly generating around$200 million in revenue and is expanding into hardware, video, and 3D object generation.

However, the company faces ongoing legal challenges, with multiple lawsuits accusing it of using copyrighted images without permission to train its AI models.