- Midjourney has published a new AI model to produce images, Midjourney V7
- The model has improved image quality, rapid understanding and personalization
- The new draft mode generates much faster and cheaper lower quality images to allow tests
Midjourney has a new model to show fans of the AI image generator. Midjourney V7 is the first new IA image model of the company in almost a year, and it comes with important upgrades and additional features.
The company claims that the new model is much smarter to transform your words into images that you are considering, with better quality results that escape many revealing signs of artificial origin. The new model is also very adaptation to your personal taste.
So much so that you cannot even use it before first assessing around 200 images to teach your aesthetics to the model, unless, of course, that you had already done it.
We are now starting the alpha-test phase of our new V7 image model. It is our smartest, most beautiful and coherent model to date. Give him a shot and wait for updates each week or two for the next two months. pic.twitter.com/ogqt0fgiy7April 4, 2025
Once you have sailed in your own strange valley, the images that Midjourney V7 is used should please you without as much massage of your prompts.
This is the first Midjourney model to have this default functionality as well.
“”[Midjourney V7 is] Much smarter with text prompts, image prompts seem fantastic, image quality is significantly higher with beautiful textures, and bodies, hands and objects of all kinds have a clearly better consistency on all the details, “the founder of Midjourney, David Holz, wrote on Discord.” We believe that customization increases the bar for the way we can interpret what you want and what you find beautiful. “”
Write the future
The new Draft mode is the Midjourney version of Rough Sketches on a towel. The functionality promises quick, inexpensive and just good enough results to reduce your idea without burning your credits.
It works like this: you type an prompt, and Midjourney will have an image for you in seconds. The image can be a little lower or slightly less polished, but you can improve it later with one click. It’s AI for impatient people.
In particular, Draft Mode positions Midjourney as a viable tool for professionals who need speed and the option of iteration of their ideas. This type of flexibility could make Midjourney attractive far beyond his discord silo.
The V7 boost in rapid understanding, the improvement of anatomy and the project mode suggest that Midjourney plans to increase its efforts to compete with other generators of IA images.
However, it will not be as fast as the creation of images in writing mode. Dall of Openai has deep integrations with Chatgpt and Microsoft tools, as did Google Gemini with its ecosystem.
Despite this, Midjourney has always had a certain cult attraction that could register with its faster model to attract many more users. If Midjourney can continue to improve his speed, clarity and exit quality while keeping his signing flair, he could go running without losing his independent credit.
The new model has two main versions: Turbo and relax. Turbo is more expensive but provides results much faster. The mode of relaxation, on the other hand, takes its time but is cheaper.
Some features have not yet made the V7 jump. There is no scale, cutting or retacturation. Holz says they will come back soon, maybe in a few months.
