🚀 Midjourney Office Hours Highlights: May 14th

Midjourney’s roadmap remains ambitious, with an emphasis on user-driven priorities and ongoing innovation across reference systems, video, image quality, and interface design. The next few months promise to be busy—and potentially transformative—for the creative AI platform.

🖼️ S-Ref and Mood Boards: Big Overhaul Incoming

During the latest Midjourney Office Hours, significant updates were shared about the much-anticipated S-Ref and mood board system. The new version is now in testing with guides and moderators. If the process goes smoothly, the broader community could see access as soon as next week, though there’s a small chance it could stretch to two. The expectation is improved accuracy and image quality, along with hints of a potential S-Ref randomization feature soon after the initial launch.

🔗 Omni-Reference: Towards Seamless Multi-Reference

Midjourney’s team is also working on major upgrades for their omni-reference system, allowing users to blend multiple image references more efficiently. This enhancement is already undergoing independent tests, with a combined version to follow soon. The projected rollout is within about two weeks, contingent on the results of ongoing testing.

🌅 Quality and Aesthetics: Incremental Improvements

For those focused on visuals, the company discussed incremental improvements in image quality and aesthetics. While these updates may be subtle, they’re part of broader research and may eventually incorporate community-driven rating events to help steer aesthetic direction.

🎥 Video Model: Progress and Caution

Video generation continues to progress behind the scenes. Text-to-video performance has reached a solid level internally, but public release is held back by UI complexities. The image-to-video model is currently being fine-tuned and is projected to match or outperform text-based results. Final training should conclude by month’s end, followed by an intensive round of testing. The initial video model already shows strong dynamic motion and positive user experiences, though the team admits further refinement will be needed for version two.

⚡ V7 Rollout: Optimizations First

The much-discussed Version 7 (V7) update isn’t yet the default for all users. The primary obstacle is GPU availability, with the current setup unable to handle immediate full-scale adoption. Further optimization and server scaling are underway, aiming to make V7 the standard within the next few weeks.

🚀 V8 on the Horizon: Community’s Call

Looking ahead, development on Version 8 (V8) is poised to kick off soon. With a fresh dataset and major architectural changes made possible by upcoming server infrastructure, the goal is to release V8 in about three months. Notably, the community will have a voice in determining whether rapid deployment or additional features take priority, with plans for a voting mechanism.

🖥️ Advanced Interface and Upscaling: For the Pros

Professional users can look forward to new, advanced interface designs tailored for large 4K screens. These early prototypes enable work with multiple images and more complex controls, showing promise for serious creative workflows. Faster image generation is also in the works, though balancing speed with usability remains a challenge. New upscaling techniques are under consideration, but decisions will hinge on their impact on the V8 release timeline.

📱 Mobile and Secret Projects: Quiet but Significant

Finally, the team is exploring mobile-focused enhancements, though nothing has been finalized for public release. There are also several confidential projects approaching key milestones, but details remain under wraps for now.

TL;DR

• 🖼️ S-Ref & Mood Boards: Testing new system with mods; public release likely next week.

• 🔗 Omni-Reference: Multi-reference upgrade in testing, aiming for two weeks till launch.

• 🌅 Image Quality: Minor boosts and planned future aesthetic upgrades with community input.

• 🎥 Video Models: Text-to-video works internally; image-to-video in tuning, release soon.

• ⚡ V7 Default: V7 optimization ongoing, default rollout in weeks pending GPU/server upgrades.

• 🚀 V8 Plans: New model, big architecture changes, target launch in ~3 months, community vote on features vs. speed.

• 🖥️ Pro Interface & Upscaling: Early 4K/pro interface prototypes; exploring faster image modes and new upscalers.

• 📱 Mobile/Secret: Mobile enhancements and confidential projects approaching big milestones.

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!