More than a year since its last major update, Midjourney has finally unveiled a new image generation model — a long-awaited moment in the world of AI-powered creativity.
The journey traces back to late 2022, when OpenAI launched ChatGPT, a conversational AI built initially on the powerful GPT-3.5 language model. Its overnight success didn't just captivate tech enthusiasts — it triggered a global AI renaissance.
While ChatGPT redefined what text-based AI could do, it also ignited public fascination with generative AI across all forms of media, including art.
Riding this wave, a new breed of image-generation tools emerged. DALL·E from OpenAI had already made its debut.
But it was Midjourney—with its distinct, stylized outputs and Discord-based community—that quickly carved out a niche. Launched in 2022 by an independent research lab led by David Holz, Midjourney became synonymous with surreal, dreamlike imagery that blended human imagination with machine creativity.
Its V5, for example, is able to excel others when it comes to creating human hands, which is considered something AIs generally struggle with.
Since then, Midjourney has rolled out several iterations, each bringing more coherence, control, and realism.
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
— Midjourney (@midjourney) April 4, 2025
And this time, Midjourney introduces 'V7' of its image generation model.
The announcement marks a significant milestone for the platform, which has quickly risen to prominence as one of the most artistically refined AI tools available.
"V7 is the first model to have model personalization turned on by default. You must unlock your personalization to use it. This takes ~5 minutes. You can toggle it on/off at any time. We think personalization raises the bar for how well we can interpret what you want and what you find beautiful."
One of the most exciting new features for our new V7 model is something we call "Draft Mode". Draft mode is half the cost and 10 times the speed and it might be the best way to iterate on ideas ever. Try it with voice, think out loud and let our ideas flow like liquid dreams. pic.twitter.com/ANfTMC6Ej1
— Midjourney (@midjourney) April 4, 2025
On of the notable features, is the new 'Draft Mode.'
On its blog post and its other communication channels, Midjourney says that "Draft mode is half the cost and renders images at 10 times the speed."
Midjourney said that the Draft mode "is the best way ever to iterate on ideas."
In an example, Midjourney said that if users ask something like "enhance" or "vary" on an image, the AI will automatically re-render the chosen spot of the image "at full quality."
It's worth noting that the Draft feature generates images that are lower in quality that the standard mode. However, "the behavior and aesthetics are very consistent - so it’s a faithful way to iterate."
Initially in alpha test mode, Midjourney releases V7 in two modes: Turbo and Relax.
The Relax standard speed requires more time to work and optimize, whereas the Turbo mode is twice more expensive than the normal V6 and drafts jobs half as much.