🚀 Midjourney Office Hours Highlights: March 12th

Midjourney's office hours have painted an exciting picture of what's to come, with V7 poised to redefine the image generation landscape. From speed and quality enhancements to groundbreaking features and community-driven development, the future looks bright for Midjourney and its users.

For a quick overview, head straight to the TL;DR; section otherwise keep on reading.

Extended Recap

🖼️ Version 7: A Leap Forward in Image Generation

The development of V7 is in full swing, with the team having established a complete end-to-end system. The basic functionalities are already operational, and a potential release is anticipated within the next two weeks. A key focus for V7 is the improvement of image quality, specifically targeting the elimination of unintended artifacts and unwanted text. Users can also look forward to significantly enhanced prompt accuracy, even when using higher stylization settings. Additionally, image coherence and texture quality have seen substantial improvements, and the team is optimistic about boosting multilingual capabilities, pending further testing.

⚡ Speed Meets Quality: Striking the Perfect Balance

One of the standout features of V7 is its speed. The default speed is expected to be twice as fast as V6, with regular mode images generating in approximately 15 seconds and turbo mode in about 5 seconds. The team is also exploring the possibility of introducing a "super turbo mode," which could produce images in as little as 2.5 seconds. Looking ahead, there are considerations for allowing users to toggle between high-speed (drafting) and high-quality (slower) modes, offering flexibility based on user preferences.

🔍 Omni Reference and Upscaler Innovations

The integration of the Omni reference feature is on the horizon, initially supporting single references from input images, with plans to expand to multiple references in future updates. In addition, the team is working on a new upscaler that promises to be significantly faster—up to 10 times the current speed—and more affordable, with a potential release a few weeks after V7.

🎥 Future Video and 3D Capabilities

Midjourney is not stopping at images. A video model is actively being developed, with an expected release in about two months. The focus is on achieving a balance between quality and cost-effectiveness. Post-V7, the team aims to delve into real-time 3D model generation and interactive camera movement, expanding the creative possibilities for users.

🖥️ Interface, Control, and Secret Projects

User interface enhancements are underway, aiming to provide increased control and speed. Current control algorithms are being refined to strike a balance between user control and ease-of-use. Meanwhile, Midjourney's hardware labs are bustling with activity, featuring 3D printers, CNC machines, and other equipment for experimental projects. These ambitious physical hardware projects, including substantial infrastructure developments, remain under wraps for now, with details to be disclosed once tangible demonstrations are ready.

🤝 Community Engagement and Future Directions

Midjourney values its active and supportive community, planning post-launch polling to guide future development priorities, such as the balance between quality and speed. The team is committed to transparency and providing substantive updates, steering clear of mere hype. As they transition to higher-quality datasets post-V7, aesthetic improvements are also on the agenda, potentially receiving dedicated updates separate from the main release.

TL;DR

🖼️ V7 Development: Full system ready, release in two weeks, improved image quality, prompt accuracy, and multilingual capabilities.

⚡ Speed & Quality: V7 faster than V6, exploring "super turbo mode," future toggle between speed and quality.

🔍 Omni Reference & Upscaler: Single Omni reference at launch, faster 4K upscaler post-V7.

🎥 Video & 3D Features: Video model in two months, future 3D model generation and camera movement.

🖥️ Interface & Secret Projects: Enhanced user control, ambitious hardware projects in labs.

🤝 Community & Future: Community polling post-launch, focus on quality vs. speed, aesthetic updates post-V7.

Stay tuned for more updates as Midjourney continues to innovate and enhance its platform!

If you want to support me, feel free to buy me a coffee ☕️ 

If you’re not subscribed yet to my newsletter Imagine Weekly, I’d be thrilled to welcome you on board!