🚀 Midjourney Office Hours Highlights: May 7th

The latest Midjourney Office Hours gave the community a glimpse into the platform’s ongoing evolution, revealing fresh updates, ambitious plans, and a renewed focus on user-driven development. Here’s a clear-eyed summary of the key topics discussed, covering everything from recent launches to the roadmap for V7, V8, and beyond.

🚀 Recent Releases: Fast Mode, Omni Reference & Style Accuracy

Midjourney has been rolling out a steady stream of improvements. The new Fast mode promises speedier generations, while the Omni Reference feature brings added versatility for image referencing. Notably, users are seeing improved style accuracy, making outputs more reliable and visually compelling.

🛠️ In-Progress Features: Personalization, Speed, and Utility

Development is ramping up on several fronts. A personalized explore page—designed to surface content tailored to individual users—is in the works. There’s ongoing testing for a higher-quality image mode, and long-awaited flip and rotate functionalities are expected soon.

Looking ahead to the coming weeks, features like multiple Oref support, new S-ref options, and mood boards are in the pipeline. Meanwhile, the team is refining speed optimizations and working to streamline the personalization process, aiming to reduce onboarding to under 200 reference images.

🎨 Aesthetic Updates: Ranking Parties and Final V7 Tweaks

Major aesthetic upgrades are planned following upcoming ranking parties, with the first event set for Friday or Monday, and another a week or two later. These sessions will focus on comparing different Midjourney versions (V1–V7) to integrate the best aspects of earlier models, and on fine-tuning the EXP parameter for optimal detail. Importantly, these will be the final major visual updates for V7 for the foreseeable future.

🧭 Style Exploration: Helping Users Find Their Look

Midjourney plans to roll out new tools to help the community navigate and experiment with styles more effectively. The popular sref random feature will remain, and upcoming improvements aim to make style discovery easier and more intuitive for all users.

✍️ Draft Mode: Consistency and Enhancement

Draft mode is set for significant improvements next month, with the goal of making it virtually indistinguishable from normal mode in both speed and quality. Enhanced and draft modes will become more reliable, directly addressing recent user concerns about consistency and aesthetics.

💬 Community Feedback: Surveys and Idea Ranking

User feedback continues to shape Midjourney’s priorities. A new survey invites feature requests, available via Discord and the website, while an idea ranking exercise will launch Friday at midjourney.com/ideas. The team is also gathering demographic data to better understand the needs of different user groups.

⚖️ V7 vs. V8: Roadmap and Model Priorities

A strategic decision is underway: whether to keep adding to V7 or shift focus to V8. V7 is likely to become the default within the next month, but improvements are being designed to benefit both current and future versions. Core goals include new upscalers, oref enhancements, and infrastructure upgrades, all while V8 is architected around a new server cluster.

🎞️ Video Model: Release on the Horizon

The upcoming video model is nearing readiness, aiming for the signature Midjourney aesthetic and outperforming existing solutions in consistency. While the launch isn’t set for next week, a release as soon as next month is possible. Multiple usage modes and an accessible pricing structure are being finalized. The model is currently in the optimization phase, with controllability and broader testing next in line.

🖥️ Server Infrastructure: Foundation for the Future

A major server upgrade is scheduled for the next 30 days, forming the backbone of V8 and supporting improvements in turbo and draft modes. The video model may depend on these upgrades for a smooth rollout.

🔮 What’s Next? Upscalers, In-Painting, and Community-Driven Features

Finally, several new features—like advanced upscalers and in-painting updates—are under consideration. Community input will determine which get prioritized, keeping users at the heart of Midjourney’s direction.

TL;DR

• 🚀 Big Release: Multiple features launched at once, including editor redesign and fast mode changes.

• 🖌️ Editor: Improved interface and editing experience.

• 🎨 Aesthetics: Minor update for prompt accuracy and consistency, impacting ~1% of prompts.

• 🤖 Omni Reference: New reference tool for combining people, objects, and styles—requires prompt precision.

• 🧪 Experimental Parameter: “–exp” makes images more detailed and creative but less precise.

• 🛡️ Moderation: Stricter rules for reference images, especially real people.

• 🔮 Future: Q4/S-REF features, upscaler improvements, V8/video work, and user-driven voting coming soon.

• 🎥 Video: Team working on dataset quality and deciding model direction.

• 🤝 Community: Continued focus on feedback and collaborative feature development.

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!