Midjourney
@midjourney
A community supported research lab - exploring new mediums of thought and amplifying the imaginative powers of the human species.
Did you know you can drag any image into the prompt bar and animate it with our new Video model? Here's "Elizabeth I, Queen of England, France and Ireland, Defender of the Faith, Supreme Governor of the Church of England, moments before ripping a sick-ass sax solo"
It's been 3 years since we first made Midjourney available to everyone. Thank you for being a part of our story so far. We're privileged to explore this vast, unimaginable, beautiful future together <3
We're officially moving to open-beta! Join now at discord.gg/midjourney. **Please read our directions carefully** or check out our detailed how-to guides here: midjourney.gitbook.io/docs. Most importantly, have fun!
How would you describe Midjourney? And what does Midjourney mean to you?
Ever wonder what AI video models do when our researchers break them? Definitely not static like an old TV screen!
It's true. We have no investors. We're entirely supported by a huge community of everyday people. We've seen government research labs, academic and corporate research labs, but this is the first time we've ever seen a community-backed research lab. Thank you <3
Midjourney launched video to everyone at 1/10 the price per video with 4x as many vids per job generated 5x faster than leading competitors and the servers havent been down once since the rollout and they did it without ever raising a single dollar from investors
We added a right-click "Download as GIF" feature for u <3
A guide for people running out of fast-hours with our new video models: you can buy extra, but upgrading to a higher member tier gets you 2x more per dollar. Yearly subs get an extra 20% discount. Then Pro and Mega tiers can help us test a "video relax mode" (unlimited with wait)
A reminder that our V1 video models are also compatible with our Anime models called "niji". To use it just type --niji after your image prompts or select "niji 6" from version dropdowns.
midjourney / nijijourney video test
We noticed many MJ videos are getting "overly compressed" when uploaded to social media. We've created a new optimized encoder to reduce the issue. When saving videos to share, please right click the video and press "Save for Social Media". Before/after example below. Thanks!
Wow these are quite nice! Try using --sref random at the end of your prompt to explore random corners of "style space". The word "random" will get replaced with a number (as below) which you can repeatably use for consistency or share with others around the globe.
Midjourney’s new Srefs are on another level. --sref 129008186 --sref 3666111078 --sref 2673592390 --sref 3221979578
With the release of the new V7 Style References, Moodboards and Omni-reference features, we are making V7 the default model for all new and existing members of Midjourney. Have fun!
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.