We've now added blending to model personalization and style reference codes. Just put both codes together like --p code1 code2 or --sref code1 code2. Try blending your personalized models with those of friends and let's explore new frontiers of mutual aesthetic harmony
We're opening orders for "Midjourney Year One" a archival book showcasing our community's explorations over the past year. It's a beautiful & physical snapshot as well as a fusion of many issues from our official Magazine you may have missed. Order here:
We're releasing model personalization today. Get at least 200 image ratings and then add --p after your prompt. Personalization completely changes the way our system interprets your prompts and we think you'll really like the new direction it takes. Have fun!
We've just pushed a small update for Niji V6 (our model for Anime & Eastern aesthetics) that greatly improves Japanese and Chinese character rendering. You may also notice improved image quality. Enjoy!
We're now testing 'private creation rooms' on our website! For all MJ members with >100 images, just click 'rooms' and then 'create room'. This lets you make private spaces to create and explore with friends or coworkers. Have fun and let us know what you think!
If you've made >100 images with Midjourney you can now help us alpha-test image creation on our website. We've also added a 'rooms' feature where you can create in real-time with people around the world. Give it a shot and let us know what you think!
We're now giving away free copies of Midjourney Magazine for Schools, Stores, and Community Groups, if this sounds like you apply at . For everyone else don't worry you can still get magazines for 4$/month at
We're testing a new algorithm today to help you have "consistent characters" across your images. Check out our announcement channel for more instructions. It works for both MJ6 and Niji6 models. We hope this helps you play with telling stories and building new worlds <3
We're testing a new version of /describe today. Basically, show it an image and it'll try to describe it. This new algorithm is made to give longer, more detailed prompts, in the style of our community and is specifically tuned for our V6 models. Enjoy!
We're launching v6 turbo mode tonight. Make images at 3.5x the speed (for 2x the cost) with the fastest GPUs in the world. Great for brainstorming, playing with friends, or anytime you have the need for speed. Just type /turbo. Have fun!
If you've made >1000 images on Midjourney you can now help us alpha-test our image creation website at . Design and features will rapidly change for a while and as things mature we will expand access. Desktop is the focus for now, but mobile is coming too.
We're testing a new algorithm today to help you form "consistent styles" across your images. Check out our announcement channel for more instructions. It's a totally new & non-lingual way to work with styles & we think it pushes forward the frontiers of aesthetic exploration
V6 of Niji-Journey is now live! Niji V6 is a version of our latest model specifically tuned for Anime. To enable it type /settings and click "Niji Model 6" on any of our bots. Enjoy!
Our first major update to V6 alpha is now live. All major qualities of the model are improved; aesthetics, coherence, prompt adherence, image quality, and text rendering. Higher values of --stylize also work much better and upscaling is now ~2x faster. Enjoy!
We're now alpha-testing our V6 models Midjourney. Just type /settings and click V6 or add --v 6 after your prompt. Image coherence and prompt understanding are greatly improved. You can draw text and dolphins and there's new upscalers too. Happy holidays everyone!
We're rolling out a GPU cluster upgrade today. Pro and Mega users should see speedups of ~1.5x (/imagine from ~50 sec to ~30 sec). These renders should also be ~1.5x cheaper. Any spare GPU capacity will randomly accelerate actions for other member tiers. Enjoy!
We're now testing V1 of our Midjourney "Style Tuner". Type /tune and render a custom web tool that controls our model's personality. Everything from colors to character detail. Explore aesthetics like never before and share resulting style codes and tuning URLs with friends.
We've updated our default member website. The new one is a faster, cleaner, brand-new codebase that'll get regular updates as we build a complete standalone native web experience. If needed, you can get to the old website here