- Imagine Weekly – The only Midjourney Newsletter you need
- Posts
- 🚀 Midjourney Office Hours Highlights: February 12th
🚀 Midjourney Office Hours Highlights: February 12th

Midjourney, is gearing up to introduce a series of significant advancements that could transform digital content creation. With the development of their Version 7 (V7) model and explorations into video and real-time 3D, Midjourney is pushing the boundaries of what's possible in the digital art space. This post provides a straightforward look at the upcoming innovations and what they mean for the future of creative technology.
For a quick overview, head straight to the TL;DR; section otherwise keep on reading.
Extended Recap
🖼️ Version 7 (V7) Model Development
The much-anticipated V7 model is currently under rigorous research, with multiple potential versions in the pipeline. A standout feature under consideration is "Omni-reference," which aims to seamlessly integrate supplied images—such as logos and characters—into new outputs. While the team is focused on enhancing image quality and achieving significant speed gains, they are also balancing these improvements with the introduction of new capabilities. The release of V7 hinges on finding the optimal balance between speed, quality, and innovation. In the event of delays, some features like Omni-reference might be integrated into the existing V6 model.
🎥 Video Feature Explorations
Midjourney is exploring three distinct paths for video feature development: partnering with external companies, adapting open-source models, or crafting a proprietary solution. Cost efficiency remains a priority, ensuring that video generation remains accessible. Recent advancements in video model research have exceeded expectations, making the launch of a video product more likely this year. The goal is to deliver a high-quality, consistent video product that aligns with Midjourney's aesthetic standards.
🕹️ Potential Real-Time 3D Innovations
Real-time 3D generation is seen as a natural evolution from image and video models. Although research is ongoing, the lack of dedicated personnel means progress is slower compared to 2D and video development. Nonetheless, there is potential for real-time 3D features to emerge this year, although timelines remain uncertain.
🖥️ Website & Editor Enhancements
Midjourney is planning to introduce a new folder and workspace system, akin to organized "channels" for user projects. Enhancements to the built-in editor, such as improved selection tools, are also in the works. While large batch generation interfaces are being considered, they may be postponed until V7. These interface refinements aim to streamline user workflows and project organization.
☁️ Infrastructure & Server Partnerships
Negotiations are underway to potentially expand or relocate cloud infrastructure, aiming for better performance and cost management. Server enhancements could reduce image generation times and impact the affordability of resource-intensive features like video. The focus is on achieving efficiency gains to enable faster rendering and more ambitious features.
🔧 Secret/Hardware Projects
Midjourney is also venturing into hardware, with initiatives including the acquisition of a large warehouse for constructing "devices." Two major hardware projects are in development: one wearable or body-used device and another requiring significant space for assembly. These projects are in early R&D stages, with public announcements planned once they progress beyond the conceptual phase. The aim is to explore unique intersections of AI, creativity, and physical technology.
🔮 Long-Term Research & Vision
Operating as a community-supported research lab, Midjourney prioritizes impactful and sometimes unconventional projects. Their long-term vision includes seamless real-time generation of images, video, and 3D worlds. Development roadmaps span multiple years, with a gradual rollout of advanced AI modalities. The emphasis remains on continuous improvement of 2D image features alongside future-oriented projects.
TL;DR
🖼️ V7 Model: Multiple versions in research; key feature "Omni-reference" for image integration. Balancing speed, quality, and new capabilities.
🎥 Video Features: Exploring partnerships, open-source models, or proprietary solutions. Cost efficiency and high quality are priorities.
🕹️ Real-Time 3D: Natural progression from 2D and video; ongoing research with potential features this year.
🖥️ Website/Editor: New folder system, improved tools, and interface refinements planned for better user experience.
☁️ Infrastructure: Cloud expansion for better performance; server enhancements for faster rendering.
🔧 Hardware Projects: Early-stage R&D on wearable and large-scale devices exploring AI and creativity intersections.
🔮 Long-Term Vision: Community-supported lab focusing on real-time generation of images, video, and 3D worlds.
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!