Midjourney Unveils V7: First AI Image Model Update in Nearly a Year
Midjourney, one of the earliest AI image generators on the web, just dropped its first new model in almost a year. They're calling it V7, and it started rolling out in alpha around midnight ET last Thursday. This comes hot on the heels of OpenAI's new image generator in ChatGPT, which went viral for its Ghibli-style photo creations.
Now, V7 isn't specifically tuned for Ghibli vibes, but hey, it still manages to whip up some pretty cool images, at least from what I've seen.
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
To get started with V7, you'll need to rate about 200 images to create your Midjourney "personalization" profile. This helps the model get a feel for your visual tastes, and it's the first time Midjourney's switched personalization on by default with a new model.
Once you've set up your profile, you can toggle V7 on or off on their website or, if you're part of their Discord community, through their Discord bot. On the web app, just look for the drop-down next to the "Version" label and pick V7.

Image Credits:Midjourney Midjourney's CEO, David Holz, says V7's got a "totally different architecture." He's pretty excited about it, saying on X that it's much better at handling text prompts. Over on Discord, he mentioned that image prompts are looking great, the image quality is up with some sweet textures, and it's doing a better job with details on bodies, hands, and objects.
V7 comes in two versions: Turbo, which is pricier to run, and Relax. It also introduces a new tool called Draft Mode, which cranks out images 10 times faster and at half the cost of the standard mode. Sure, the draft images aren't as sharp, but you can always enhance them with a click.
Holz did mention that some usual Midjourney features like image upscaling and retexturing aren't ready for V7 yet, but they're on the way, maybe within the next couple of months.
“This is an entirely new model with unique strengths and probably a few weaknesses,” Holz wrote on Discord. “[W]e want to learn from you what it’s good and bad at, but definitely keep in mind it may require different styles of prompting. So play around a bit.”

My prompt: “A dragon with a spiky tail.”Image Credits:Midjourney I gave V7 a quick spin, and it seemed to follow my prompts pretty well, though I didn't have time to really test its limits.

My prompt: “A Ghibli-style character.”Image Credits:Midjourney Midjourney's a bit of an oddball in the tech world. Founded by Holz, who also started Leap Motion, they've never taken a penny from outside investors. They were expecting to rake in about $200 million in revenue by the end of 2023. Recently, they announced they're setting up a hardware team for some mysterious projects and are still working on video and 3D object generation models.
But it's not all smooth sailing. Midjourney's facing some legal heat for allegedly using images scraped from the web without permission to train their AI, which has artists up in arms.
Related article
Tencent's Xiaolongxia Surges Beyond Expectations, Team Expands Capacity 10x, Apologizes and Compensates
Tencent has officially launched WorkBuddy, an all-scenario AI intelligent agent, marking a new phase in the large model application layer race with high integration and a low deployment threshold.The product drew immediate industry attention on its l
Suno Lead Investor: Deleting Posts Won't Plug Copyright Lawsuit Hole
The much-anticipated AI music generation platform Suno is facing a tough copyright battle, and a candid remark from its lead investor may have handed the opposing side exactly the evidence they were hoping for. C.C. Gong, a partner at Menlo Ventures
Claude Opus 4.7 Launches with Reliability Valued Over Intelligence
Anthropic has maintained an aggressive pace this year, rolling out new features almost every other day. The much-anticipated Claude Opus 4.7 has just been officially released, and interestingly, Anthropic was upfront in the announcement: "This is not
Related Special Topic Recommendations
Comments (38)
0/500
Wow, Midjourney's V7 sounds like a game-changer! Been almost a year, and now they drop this right when OpenAI's stealing the spotlight? Bold move! Can't wait to see how it stacks up. 🖼️
Whoa, Midjourney's V7 dropping after a year feels like a plot twist! That alpha release timing is sneaky, but I’m hyped to see how it stacks up against OpenAI’s viral image generator. 😎 Anyone tried it yet?
Wow, Midjourney's V7 sounds like a game-changer! Been a while since their last update, but this alpha release has me curious. How does it stack up against OpenAI's viral image generator? Can't wait to try it out! 😎
Midjourney's V7 is finally here! It's been a while, but the wait was worth it. The images are sharper and more detailed than ever. I'm loving the new features, though I wish there were more customization options. Still, it's a solid update! 🎨
O Midjourney V7 é incrível! Os detalhes estão muito mais nítidos e as cores são vibrantes. É uma grande evolução em relação à versão antiga. A única coisa é que ainda está em alpha e tem alguns bugs. Mal posso esperar pelo lançamento completo! 🎨
Midjourney, one of the earliest AI image generators on the web, just dropped its first new model in almost a year. They're calling it V7, and it started rolling out in alpha around midnight ET last Thursday. This comes hot on the heels of OpenAI's new image generator in ChatGPT, which went viral for its Ghibli-style photo creations.
Now, V7 isn't specifically tuned for Ghibli vibes, but hey, it still manages to whip up some pretty cool images, at least from what I've seen.
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
To get started with V7, you'll need to rate about 200 images to create your Midjourney "personalization" profile. This helps the model get a feel for your visual tastes, and it's the first time Midjourney's switched personalization on by default with a new model.
Once you've set up your profile, you can toggle V7 on or off on their website or, if you're part of their Discord community, through their Discord bot. On the web app, just look for the drop-down next to the "Version" label and pick V7.

V7 comes in two versions: Turbo, which is pricier to run, and Relax. It also introduces a new tool called Draft Mode, which cranks out images 10 times faster and at half the cost of the standard mode. Sure, the draft images aren't as sharp, but you can always enhance them with a click.
Holz did mention that some usual Midjourney features like image upscaling and retexturing aren't ready for V7 yet, but they're on the way, maybe within the next couple of months.
“This is an entirely new model with unique strengths and probably a few weaknesses,” Holz wrote on Discord. “[W]e want to learn from you what it’s good and bad at, but definitely keep in mind it may require different styles of prompting. So play around a bit.”


But it's not all smooth sailing. Midjourney's facing some legal heat for allegedly using images scraped from the web without permission to train their AI, which has artists up in arms.
Tencent's Xiaolongxia Surges Beyond Expectations, Team Expands Capacity 10x, Apologizes and Compensates
Tencent has officially launched WorkBuddy, an all-scenario AI intelligent agent, marking a new phase in the large model application layer race with high integration and a low deployment threshold.The product drew immediate industry attention on its l
Suno Lead Investor: Deleting Posts Won't Plug Copyright Lawsuit Hole
The much-anticipated AI music generation platform Suno is facing a tough copyright battle, and a candid remark from its lead investor may have handed the opposing side exactly the evidence they were hoping for. C.C. Gong, a partner at Menlo Ventures
Claude Opus 4.7 Launches with Reliability Valued Over Intelligence
Anthropic has maintained an aggressive pace this year, rolling out new features almost every other day. The much-anticipated Claude Opus 4.7 has just been officially released, and interestingly, Anthropic was upfront in the announcement: "This is not
Wow, Midjourney's V7 sounds like a game-changer! Been almost a year, and now they drop this right when OpenAI's stealing the spotlight? Bold move! Can't wait to see how it stacks up. 🖼️
Whoa, Midjourney's V7 dropping after a year feels like a plot twist! That alpha release timing is sneaky, but I’m hyped to see how it stacks up against OpenAI’s viral image generator. 😎 Anyone tried it yet?
Wow, Midjourney's V7 sounds like a game-changer! Been a while since their last update, but this alpha release has me curious. How does it stack up against OpenAI's viral image generator? Can't wait to try it out! 😎
Midjourney's V7 is finally here! It's been a while, but the wait was worth it. The images are sharper and more detailed than ever. I'm loving the new features, though I wish there were more customization options. Still, it's a solid update! 🎨
O Midjourney V7 é incrível! Os detalhes estão muito mais nítidos e as cores são vibrantes. É uma grande evolução em relação à versão antiga. A única coisa é que ainda está em alpha e tem alguns bugs. Mal posso esperar pelo lançamento completo! 🎨





Home






