🚀 Midjourney Office Hours Highlights: June 4th

We can look forward to the new Style Reference release, the first wave of video models (with image-to-video likely to lead), and possibly the V7.1 update—all expected within the month. Additionally, the Style Explorer tool is slated for major progress in the following month. Text-to-video features are also in the pipeline, pending satisfactory quality benchmarks.

🔍 Style Reference Update: Precision and Flexibility

This week’s Midjourney Office Hours revealed that the much-anticipated update to the Style Reference (S-Ref) feature is nearly here, with a launch targeted for the coming week. The team emphasized that this upgrade will bring not only increased accuracy in style matching but also support for random styles—a useful addition for those building mood boards or experimenting with varied visual themes. This marks a significant improvement for creators who depend on reliable style application in their workflow.

🎬 Video Model Development: Choices and Challenges

In video model development, the team is currently narrowing down their options from a whopping 24 model variations, ranging from text-to-video to image-to-video capabilities and covering several resolutions. The initial rollout will likely focus on two core options: an affordable, accessible model, and a professional-grade version for advanced users, which will come at a higher price point. There is, however, a looming concern about GPU availability once these models go live, prompting the team to approach deployment with caution.

💸 Pricing and Subscription Strategies: Balancing Access and Scale

On the business front, there’s active discussion about limiting early access to video models to annual subscribers. The rationale is to ensure a stable funding base for costly GPU resources, with about 40% of users already on annual plans. While daily usage caps are also being considered as an alternative, there’s understandable hesitation due to possible negative impacts on user experience.

🎬🛠️ Video Feature Limitations and What’s Next

Initial video models will be intentionally limited, focusing on basic features and short video clips. The immediate development goal post-launch is to enable longer videos, with further enhancements to follow as usage data and community feedback roll in.

🚀 V7 Updates and Roadmap: Quality and Coherence

Looking further ahead, Version 7.1 (V7.1) could arrive soon, with specific improvements in anatomy and overall visual coherence, especially for hands and body structure. A potential speed boost for V7 is also on the table. Perhaps most notably, there’s talk of deeper integration between image and video models to further elevate visual consistency.

🛠️ Long-Term Model Development: Toward a More Flexible Future

In the long run, Midjourney is exploring how to make future models—beginning with V8—more flexible, reducing the need for multiple specialized versions. This foundational change should allow the team to add requested features more rapidly and with less friction.

🏗️ Server Infrastructure Expansion: Scaling for Video

Server infrastructure is scaling up in anticipation of these new features. New server groups are coming online in the next few days, with more expansions scheduled throughout the month to ensure stability as video models launch.

🤝 Community Engagement and Feedback: Shaping the Future

User feedback is playing a pivotal role in Midjourney’s direction. The team is actively analyzing recent survey data and plans another video-rating event, which will help identify and resolve edge-case issues. This ongoing dialogue is clearly informing both the immediate roadmap and future enhancements.

TL;DR

🔍 Style Reference Update: New version launching soon—better accuracy, mood board support, random styles.

🎬 Video Models: Two main options coming (budget & pro); text-to-video and image-to-video; careful rollout due to GPU concerns.

💸 Pricing: Video features may start as annual-subscriber exclusive to fund GPUs; usage caps possible but not preferred.

🛠️ Features: First videos = short/basic; longer clips and more features coming soon.

🚀 V7 Roadmap: V7.1 update likely (better anatomy/coherence); possible V7 speed boost; future image/video model integration.

🛠️ Long-Term: V8 aims for flexible, extensible models—easier feature additions.

🏗️ Infrastructure: Big server upgrades rolling out this month.

🤝 Community: Feedback from surveys and rating events shaping priorities and fixing edge cases.

📅 Launches this month: S-Ref update, first video models (image-to-video), V7.1 possibly, Style Explorer progress.

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!