MidJourney’s new AI model promises faster, smarter image generation

Midjourney

MidJourney, which was one of the first AI image-generating providers globally, has now released its first new AI image model in nearly a year. Dubbed V7, the model is currently available as a beta, and Midjourney has invited its community to test the model and provide feedback. The firm promises two areas of improvement in V7: the first is better images, and the second is new tools and improved workflows.

MidJourney’s V7 image generator: All new features

The new V7 model comes with a feature called Draft Mode, which can render images at half the speed of the previous models. Although users are reporting a rougher and less detailed output, it costs half of what the standard generation costs. Still, it requires users to complete a personalization process by ranking at least 200 pairs of images to build individual profiles.

The V7 model also promises much higher coherence and consistency for hands, fingers, body parts, and other objects. It also offers much more detailed and realistic textures for highly detailed materials like skin wrinkles or artwork in a ceramic pot. The new model is focused on adapting to your user’s personal tastes and likings.

Other than the Draft Mode, V7 comes with two more modes: Turbo and Relax. Turbo generates final images quickly but is twice as expensive in terms of credit use. Meanwhile, the Relax mode has a slower output but is half as expensive. The company has also teased more features, promising upgrades to the editing, upscaling, retexture capabilities, and object references with future updates.