At a time when all eyes are on ChatGPT, Midjourney has just demonstrated that it remains a strong contender in the race for generative image AI. The independent laboratory has unveiled V7, its new model with enhanced understanding and coherence capabilities, which is also particularly focused on customization.
We are now beginning the alpha-test phase of our new V7 image Model. It is 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
We are now beginning the alpha-test phase of our new V7 image Model. It is 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
Midjourney has activated V7 for its Turbo and Relax creation speed modes; the standard mode is still being optimized to accommodate this AI. It is important to note that artworks generated with Turbo speed cost twice the usual credits.
Unfortunately, Midjourney does not offer free versions and to be able to test its technology, you must subscribe to one of its paid plans: the Basic for $11/month ($8/month with the annual plan), the Standard for $33/month ($24/month with the annual plan), the Pro for $66/month ($48/month with the annual plan), and the Mega for $132/month ($96/month with the annual plan).
You can activate V7 in the Midjourney version selector, or switch it for a previous model if at any point you no longer wish to use it.
The V7 model from Midjourney is the company’s most intelligent to date, being able to better understand text prompts introduced by the user. Furthermore, the quality of the generated images has also seen a remarkable jump in quality, which is especially noticeable in the textures and the coherence of details (bodies, hands, objects, etc.).
In addition to revealing a superior evolution regarding the standard capabilities of its predecessors, V7 has also incorporated new features. Among these, the “Draft Mode” stands out, a generative tool with which to create initial sketches of an idea, which according to the company, costs half and is ten times faster.
Artworks created with the “Draft Mode” have a lower quality than those of the standard model, but it is possible to enhance this aspect and re-render the ones that have convinced you. A simple way not to spend many resources until achieving the desired result.
“It is so fast that, when you use it on the web, we change the prompt bar to a “conversational mode”. You can tell it to swap a cat for an owl or turn it into a nighttime scene, and it will automatically do so by modifying the prompt and launching a new task,” explains Midjourney.
Additionally, the “Draft Mode” can also be used from the voice function of the platform, allowing you to unleash your imagination naturally while speaking.
V7 is Midjourney’s first generative image AI that activates model customization by default. This means that to use it, you must first unlock your customization profile, in case you have not done so already.
To create a customization profile on the platform, you will need to rate about 200 images, so the AI internalizes your visual preferences. “You can activate or deactivate it at any time. We believe that customization elevates the level of interpretation of what you want and what you consider beautiful.”
For now, V7 does not include features such as “Upscaling,” retexturing, or image editing. To make use of these options, you must continue using one of the previous versions, such as the V6 model.
The developers claim their intention is to introduce new features every one to two weeks over the next 60 days. They highlight that “the most significant novelty will be a new reference system for characters and objects for V7.”
Photo: Midjourney
Your email address will not be published. Required fields are marked *
Δ