Midjourney Releases V7 Image Model

Midjourney has unveiled its new image generation model, V7.

The model entered testing on Thursday — just a week after OpenAI launched its own image generator in ChatGPT, which quickly went viral for producing visuals in the style of Studio Ghibli.

To get started, users are prompted to rate around 200 images, allowing the model to tailor results to their personal preferences. V7 is the first Midjourney model to include personalization by default.

It’s available in two modes: Turbo and Relax. V7 also supports a new Draft Mode that generates images 10x faster and at half the cost of standard generation. While draft images are lower in quality, they can be enhanced with a single click.

This is an entirely new model with unique strengths — and probably a few weaknesses, said Midjourney CEO David Holz.