Midjourney V7 is finally here

After nearly a year since the release of V6, the long wait is finally over. Midjourney has officially begun alpha testing for its latest image generation model, V7.

After nearly a year since the release of V6, the long wait is finally over. Midjourney has officially begun alpha testing for its latest image generation model, V7. According to David Holz, the creator of Midjourney, this new iteration is brimming with exciting features that promise to elevate the platform’s capabilities.

Here’s what Holz had to say about V7:

V7 is an amazing model it’s much smarter with text prompts, image prompts look fantastic, image quality is noticeably higher with beautiful textures, and bodies, hands and objects of all kinds have significantly better coherence on all details. — David Holz

But is it an upgrade worth waiting for?

During the months of Midjourney’s relative silence, competitors have not been idle.

• Black Forest Labs has released Flux image models that generate images with more realism, less artifacts, and better text rendering.

• Google’s Gemini 2.0 Flash, ChatGPT with GPT-4o, and Grok 3 — all have introduced a feature that can generate and manipulate images natively.

ChatGPT, in particular, has recently captured widespread attention with its ability to produce images in detailed style of Studio Ghibli. Beyond that, GPT-4o demonstrates impressive photorealism, accurate text rendering, advanced photo manipulation, and the ability to seamlessly merge multiple input images.

In this article, let’s explore what’s new in Midjourney V7 and why it’s surrounded with controversy.

What’s New in Midjourney V7?

Here are the most notable updates in V7, based on the alpha release: