Midjourney provided updates on feature releases, ongoing development for upcoming model versions, infrastructure optimization, and project timelines, while indicating some adjustments and delays may occur as priorities are reassessed and resources allocated.

🚀 Release Updates

Several new features and improvements are being rolled out, including the implementation of smaller batch size videos and the availability of HD video mode for all standard subscription users. Mood boards are receiving more prominent placement through a dedicated sidebar for streamlined access. Video thumbnails will now display the end frame instead of the beginning, with plans to introduce middle-frame thumbnails soon to better differentiate looped clips.

🧪 Version 7.1 and 8 Model Development

Development on Version 7.1 is underway, focusing on enhanced prompt interpretation, improved OREF capabilities, and the consideration of a more advanced draft mode. These features are in preliminary testing and evaluation phases and may not be finalized soon. There is potential for select features originally slated for Version 8 to be integrated into Versions 7.1 or 7.2, reflecting an adaptive approach to release planning. Meanwhile, the primary focus has shifted to developing Version 8, described with optimism due to its anticipated significant improvements. Following V8, a new V2 video model is on the roadmap, though details on most long-term initiatives are still confidential.

🧭 Style Explorer Roadmap

The Style Explorer feature is scheduled for release by the end of the month, with the initial version expected to offer substantial functionality. However, there is a possibility of minor delays extending slightly past the month's end as final refinements are completed.

⚙️ Infrastructure and Pricing Adjustments

Midjourney continues to optimize the underlying infrastructure for video features, aiming to support broader use while maintaining performance. As these optimizations progress, pricing adjustments for video capabilities are anticipated in the coming weeks. The timing and specifics of these changes depend on the success of the ongoing infrastructure improvements.

📅 Timeline and Prioritization Notes

An upcoming team off-site may temporarily delay new releases by about a week. Internal discussions are ongoing to reassess and clarify the company's medium-term priorities. While audio feature development is under consideration, it is not currently a top priority relative to other initiatives.

TL;DR

🚀 Release Updates: Key new features include smaller batch videos, HD mode for all, mood boards in a sidebar, and improved video thumbnails, enhancing user experience and accessibility.

🧪 Version 7.1 and 8 Model Development: V7.1 is in active testing for smarter prompts and OREF, with some V8 features possibly backported. V8 development is the major focus, with further video advancements on the horizon.

🧭 Style Explorer Roadmap: The Style Explorer is expected by month-end, though a small delay is possible as the first release nears completion.

⚙️ Infrastructure and Pricing Adjustments: Ongoing video infrastructure improvements may soon lead to pricing changes for video features, contingent upon optimization results.

📅 Timeline and Prioritization Notes: A team off-site may create short delays, and ongoing strategy discussions are influencing the prioritization of new projects; audio features are not prioritized at this time.

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!

The latest Midjourney office hours focused on major upgrades to video quality and core features, while candidly addressing ongoing operational and engineering hurdles. The leadership outlined release priorities, explained delays, and reaffirmed their commitment to foundational improvements despite setbacks and technical challenges.

🎥 High-Resolution Video Model Expansion

Midjourney is preparing to release a significantly higher-resolution video generation mode, raising output to approximately 720p. This feature will be exclusive to Pro and Mega subscribers due to a threefold increase in operational costs, rendering it impractical for Relaxed mode or broader deployment. Feedback from early testers indicates clear quality advantages over traditional upscaling methods, making it especially valuable for professional users. The decision to proceed was primarily driven by the feature's deployability despite its higher user cost.

⚡ Turbo Video Feature and Technical Debt

Plans for a Turbo video mode have encountered substantial engineering setbacks caused by accumulated technical debt, leading to major delays and uncertainty about the feature's future. The difficulties proved more extensive than anticipated, with leadership suggesting the possibility of skipping or indefinitely postponing Turbo mode to avoid further complications.

⏳ Reevaluating 2.5-Second Video Clips

The team is reconsidering the addition of a 2.5-second video generation option. Technical issues arise due to incompatibility with existing video extension increments (currently 1 or 4 seconds), leading to awkward extension experiences for users. Based on these challenges and anticipated community feedback, the feature might be abandoned or substantially modified.

📁 Mood Boards: Boosting Discoverability

Mood boards, previously underused due to lack of visibility, will soon be promoted to their own dedicated tab in the interface. This change aims to encourage broader adoption and easier access, addressing current discoverability shortcomings.

🏢 Data Center Transition and Challenges

Midjourney is in the midst of transitioning between two data centers to support increased capacity and lower operational costs. While one facility is meeting expectations, the other is hampered by ongoing reliability issues. The team may ultimately abandon the problematic data center to prevent further engineering disruption and maintain service quality.

🛠️ Version 7.1 and Version 8 (V8) Development

Efforts are underway to integrate select Version 8 (V8) features into the upcoming Version 7.1 (V7.1) release, targeted for the end of August. Leadership estimates a 50% chance of successful partial integration. Meanwhile, the full launch of V8 is slated for several months out, as the team prioritizes quality and foundational improvements over incremental updates to V7.

🖌️ New Style Explorer Feature

A Style Explorer tool is scheduled for introduction in V7.1 by the end of the month. The feature will start as a simple utility, with plans for further enhancement and expansion over time, paving the way for richer creative control.

🎯 Additional Stretch Goals and Improvements

Potential upgrades such as improved friend-centric collaboration and enhanced Draft mode are under discussion but remain uncertain for the V7.1 release. These features are currently considered stretch goals and their delivery is not guaranteed at this stage.

🔔 Summary and Release Focus

Confirmed upcoming releases include the high-resolution video mode for higher tiers, the initial Style Explorer, and possible limited V8 feature integration in V7.1. The development strategy centers on focused delivery and foundational improvements, even as the team navigates technical and operational setbacks.

TL;DR

🎥 High-Resolution Video Model Expansion: A 720p video mode is coming for Pro and Mega users, offering superior output but at a higher operational cost.

⚡ Turbo Video Feature and Technical Debt: Turbo mode faces indefinite delay or cancellation due to severe technical debt and engineering difficulties.

⏳ Reevaluating 2.5-Second Video Clips: The planned 2.5-second video option is being reconsidered or may be altered in response to technical and usability concerns.

📁 Mood Boards: Boosting Discoverability: Mood boards will become more accessible with a new dedicated tab, aiming to increase usage.

🏢 Data Center Transition and Challenges: The ongoing data center shift is improving capacity but is marred by issues at one location, which may be abandoned.

🛠️ Version 7.1 and Version 8 (V8) Development: Select V8 features may make it into V7.1 by August's end, though full V8 is several months away as foundational quality is prioritized.

🖌️ New Style Explorer Feature: A simple but expandable Style Explorer tool will launch with V7.1 to empower creative workflows.

🎯 Additional Stretch Goals and Improvements: Collaboration and Draft mode upgrades are being explored but have not been confirmed for V7.1.

🔔 Summary and Release Focus: The team is committed to focused feature delivery and strong foundations despite operational and technical difficulties.

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!

Midjourney’s latest office hours highlighted a strong focus on expanding user experience through smarter content discovery, enhanced video and image generation capabilities, and ongoing model innovation. The team is balancing rapid feature deployment with thoughtful long-term development, while also exploring new product categories and community engagement initiatives.

Explore Feed & Midjourney.tv Launch 🚀

Midjourney introduced a new recommendation algorithm for the Explore feed, aiming to help users discover images and videos tailored to their interests. Alongside this, Midjourney.tv—a new background video streaming site—was launched, continuously displaying public Midjourney videos and adapting to various browser window sizes. Users can view prompts by hovering, and future updates will bring personalized TV channels powered by the recommendation engine.

Upcoming Video Mode Enhancements 🎬

Several significant video mode updates are set for release next week. These include a 2,5-second mode at half price for shorter, potentially loopable animations, and a 720p mode offering higher resolution for professional use, initially limited to higher-tier users. A new Turbo mode will enable ~10-second generation times for rapid iteration, available to users on the $60+ tier. Additionally, an "extend from any frame" feature is planned, enhancing creative flexibility.

Model & Version Updates 🧠

Version 7.1 is anticipated within the next month, promising improvements such as a better draft mode, enhanced text understanding, greater coherence, and improved styleref capabilities. Work on Version 8 is underway, featuring a fundamentally new architecture that will boost both image and video quality, with major editing features planned for its release.

Future Development & Community Initiatives 🔮

The team is actively debating the scope of audio and sound effect integration, considering both quick solutions and more comprehensive options including voice. Styleref 2 is in development, and hardware plans have been confirmed (though not for TVs specifically). Midjourney-branded merchandise is on the horizon, and several secret projects are in progress. The team reiterated that no further retextures or edits will be made to V7, as focus shifts to image-related improvements and upcoming storytelling features expected by the end of next month.

TL;DR

• 🚀 Explore Feed & Midjourney.tv: New recommendation algorithm and background video streaming site launched; personalized channels coming soon.

• 🎬 Video Mode Enhancements: Shorter, cheaper video mode, higher resolution, faster generation, and new creative features rolling out next week.

• 🧠 Model & Version Updates : V7.1 with improved capabilities coming soon; V8 in development with major architectural and editing upgrades.

• 🔮 Future Development & Community: Audio features, Styleref 2, hardware, merchandise, and secret projects in the pipeline; focus remains on image and video quality, with storytelling features arriving next month.

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!

Midjourney’s latest office hours highlighted ongoing advancements in video and model capabilities, a strong focus on Version 8 development, and thoughtful consideration of new features and ecosystem openness. The team is balancing rapid innovation with careful rollout strategies, while also seeking broader community input for upcoming demographic-driven features.

Video Features & Model Updates 🎥

Midjourney is preparing to launch new video features, though there may be a slight delay. The upcoming release will introduce start/end frame control, looping, a 720p mode, and potentially a turbo mode for faster processing. In parallel, a recommendation engine for both video and images is under development, aiming to enhance user experience. The video model and upscaler are also being improved, supported by a new training cluster, indicating a significant investment in infrastructure and model quality.

Version 8 Development 🚀

The primary focus of the team is on Version 8 (V8), which is described as an exceptionally strong model that has generated considerable excitement internally. Some of V8’s features may be backported to create a V7.1 release, but the main development energy is directed at making V8 a major leap forward for the platform.

Style Explorer & Demographics Feature 🌏

Following the video updates, Midjourney plans to introduce new style explorer features. A survey is currently active to analyze aesthetic preferences based on style, age, gender, and country, with a particular need for more global participation, especially from regions like Japan. This feature aims to provide insights into how different demographics influence visual preferences, supporting more personalized and culturally aware outputs.

API Development & Rollout Strategy 🛠️

The API development process is progressing, with survey responses now under analysis. The rollout will prioritize the largest API customers, followed by smaller clients, and eventually offer a limited version for regular users. The team is also addressing concerns about appropriate versus inappropriate use cases, reflecting a commitment to responsible deployment.

Partnership Philosophy & Ecosystem Openness 🤝

Midjourney is actively debating whether to maintain a closed, high-standard ecosystem similar to Apple’s approach or to open up more broadly. While there is clear demand for greater access, the team is cautious about the potential for "tasteless" applications. No final decision has been made, but the discussion underscores the importance of balancing quality control with community and partner engagement.

Secret Projects & Announcement Timeline 🕵️

Several unannounced projects are in the works, with the team currently deciding whether to reveal them within the next month or wait a few months. The current inclination is toward a faster announcement schedule, suggesting that users can expect more news and features in the near future.

TL;DR

🎥 Video Features & Model Updates: New video controls, looping, 720p, and recommendation engine are on the way, with ongoing model and upscaler improvements.

🚀 Version 8 Development: V8 is the main focus and promises significant advances; some features may be backported to V7.1.

🌏 Style Explorer & Demographics: Upcoming features will analyze aesthetic preferences by demographic, with a call for broader global participation.

🛠️ API Development: API rollout will start with large customers, with a limited version for regular users; responsible use is a priority.

🤝 Partnership Philosophy: The team is weighing ecosystem openness against quality control, with no final decision yet.

🕵️ Secret Projects: Multiple new projects are in development, with announcements likely coming sooner rather than later.

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!

Midjourney’s latest office hours revealed major progress on the V8 model and new creative tools, signaling a strong focus on quality and innovation. Even with summer slowdowns, the team is pushing forward on features that promise to enhance both user experience and creative possibilities.

V8 Model Development 🚀

V8 has become the central focus for Midjourney’s technical efforts, with early internal testing already underway as of July. The team plans extensive training runs over the next 2–3 months, aiming for significant leaps in text rendering, scene composition, and overall image quality. Notably, V8 will be partially backward-compatible with V7, enabling some features to be released ahead of the full launch. If initial results are promising, the team intends to refine V8 for several months rather than moving quickly to a V9 iteration, prioritizing stability and quality.

Video Features and Roadmap 🎬

Significant progress has been made on video features, including looping and start/end frame controls, which are now complete and in testing. A high-resolution video mode (likely 720p) is built but remains expensive to run, so initial trials will focus on professional users. The video upscaler is still in early development and months away from release. Turbo mode, offering faster video rendering, is now live but is also resource-intensive and targeted at professionals. Additionally, a post-processing sound effects layer for videos is being considered. Some delays in video feature rollout are attributed to ongoing compute cluster deployment issues.

V7.1 Possibility

There is a possibility of a V7.1 release emerging as a byproduct of the V8 training process, depending on the compatibility and performance of early V8 components. However, this is not guaranteed and is described as a hopeful intermediary step rather than a planned milestone.

Omnireference & Character Consistency

Efforts are underway to enhance datasets for improved character consistency across different poses, outfits, and settings. These improvements are not expected to appear in V7, but are more likely to be incorporated into V8 or later versions, reflecting a longer-term commitment to addressing this challenge.

Mega Model & Scaling Goals

Looking ahead, the development of even larger “mega models” (V9, V10, V11, etc.) will depend on securing new partnerships or significantly increasing compute resources. Current models are trained with substantially less compute than industry leaders, and scaling up is seen as a key lever for boosting performance and competitiveness.

Style Explorer & Mood Boards 🎨

The Style Explorer tool is in active development, with two competing concepts currently under review. Mood boards have received silent updates to improve their performance and weighting behavior. There is also consideration for a dedicated mood/style tab to enhance discoverability and user engagement with these creative tools.

Enterprise API Investigation 🏢

Midjourney is officially exploring the development of a commercial API, having launched a public survey to assess demand and gather contacts. A second, more detailed survey is planned to better understand the specific needs of companies of all sizes. Notably, the Twitter announcement uses a separate form to mitigate spam.

Discovery & Recommendations 🔍

Work is ongoing to build content recommendation features aimed at improving image and video discovery. The goal is to create a more personalized and engaging creative experience for users, making it easier to find relevant and inspiring content.

Secret Projects & Internal Demos 🕵️‍♂️

Several stealth and experimental projects are currently in development. The upcoming team offsite will feature internal demos, serving as preparation for future public announcements and releases.

Storytelling Labs 📚

More story-driven Labs experiments are on the way, intended as creative testbeds rather than official products. The team has noted some user confusion regarding the purpose and status of these Labs, and may clarify their experimental nature moving forward.

Team, Timeline & Operations

July has been a slower month due to team vacations and post-launch recovery. Some staff are traveling to Europe for meetings, and work continues on future editor tools, which are likely to integrate with V8. Operational pace is expected to pick up after this period of rest and regrouping.

TL;DR

• 🚀 V8 Model Development: V8 is now the main focus, with early testing and major improvements planned; backward compatibility with V7 will allow some features to roll out early.

🎬 Video Features and Roadmap: Looping and frame controls are in testing; high-res video and turbo mode are available for professionals, with further enhancements and upscaling in progress.

🌀 V7.1 Possibility: A V7.1 release may occur if early V8 components are compatible, but this is not guaranteed.

🧑‍🤝‍🧑 Omnireference & Character Consistency: Improved character consistency is in development, targeted for V8 or later.

📈 Mega Model & Scaling Goals: Future mega models depend on increased compute power and partnerships, aiming for industry-leading performance.

🎨 Style Explorer & Mood Boards: New style exploration tools and improved mood boards are being developed to enhance creative workflows.

🏢 Enterprise API Investigation: Midjourney is surveying demand for a commercial API, with further research planned to address business needs.

🔍 Discovery & Recommendations: Personalized content recommendations are being built to improve discovery and engagement.

🕵️‍♂️ Secret Projects & Internal Demos: Experimental projects are underway, with internal demos planned for the next team offsite.

📚 Storytelling Labs: More Labs experiments are coming, serving as creative testbeds rather than official products.

🗓️ Team, Timeline & Operations: July is slower due to vacations and recovery, with ongoing work on editor tools and European team meetings.

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!

Midjourney’s latest office hours highlighted a temporary slowdown in new releases as the team focuses on a major server migration to boost future performance and reduce costs. Meanwhile, work continues on creative tools, video features, and web improvements, with several confidential projects and model experiments underway for larger updates after the migration.

Mood Boards & Style Tools 🎨

A silent update has improved the performance of mood boards, particularly when using weight factors, with a formal announcement forthcoming. The team is considering adding a dedicated mood-board tab to increase feature visibility. Additionally, a simple version of the “Style Explorer” is targeted as the next major release, with more advanced style-control features planned for future iterations.

Video Model Roadmap 🎬

Significant progress has been made on video features: start/end frames and looping are now in testing, and a new Turbo mode dramatically reduces video generation time (from ~68s to ~20s), though at higher cost and aimed at professional users. Native 720p video mode is being tested, likely reserved for “Mega Plan” subscribers due to its expense, and is being benchmarked against upscalers. If server upgrades proceed smoothly, video pricing may drop. Other enhancements under consideration include new prompt options, “chaos” controls, and audio post-processing layers, though some features remain speculative or in early discussion.

Resolution & Upscaling 🖼️

There is ongoing internal debate between adopting native 720p video or relying on high-quality external upscalers. The team plans a few more days of testing to determine the best balance of quality and cost. The in-house upscaler is about a month behind schedule but may launch soon unless an external solution is chosen.

Infrastructure & Pricing 🖥️

A massive server migration, involving tens of thousands of machines, is underway and expected to take about 30 days. This transition is temporarily slowing research and new releases but is essential for unlocking faster speeds and lower costs in the long term. Once completed, management hopes to reduce video pricing and maintain the $60 Relax mode. These infrastructure overhauls occur every 1–2 years and are currently absorbing most engineering resources.

Web & Community Features 🌐

The team is exploring new website features, including a revamped front page and “explore” tools for video content. User profile enhancements are in testing, though no release date is set. Additional video exploration formats are in early concept stages, and the Storytelling team is piloting new features internally with guides and moderators.

Surveys & API Plans 📊

A forthcoming survey will assess demand for a standard commercial API and identify which user segments require it. Multiple survey rounds are planned, following the iterative approach used for video product refinement. The new questionnaire format will also allow the community to submit questions via Twitter.

Secret Projects & Future Directions 🔒

Several confidential projects are in development, with internal demos scheduled over the next month and larger public reveals planned for later in the year. Experimentation with the V8 model continues but is delayed due to the server migration. Users should expect a quieter month with fewer releases until the migration is complete, after which more substantial updates are anticipated.

TL;DR

🎨 Mood Boards & Style Tools: Performance improvements deployed; more discoverability and richer style controls are on the roadmap.

🎬 Video Model Roadmap: Major video features (looping, Turbo mode, 720p) are in testing; pricing and prompt enhancements are under review.

🖼️ Resolution & Upscaling: Native 720p vs. external upscalers is being tested; in-house upscaler may launch soon.

🖥️ Infrastructure & Pricing: Large-scale server migration is temporarily slowing releases but will enable faster, cheaper service and possible price drops.

🌐 Web & Community Features: Website and community tools are being expanded and piloted internally, with no firm release dates yet.

📊 Surveys & API Plans: API demand survey coming soon, with community input encouraged.

🔒 Secret Projects & Future Directions: Multiple confidential projects and V8 model work are ongoing; expect a slow month followed by larger updates.

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!

Welcome to Issue 41 of Imagine Weekly 👋

The Midjourney team is hard at work on a range of new features and improvements. Upcoming enhancements include advanced video controls, looping, and turbo mode, plus an HD image-to-video option for film professionals. Model development continues with V8 and real-time generation, and a new enterprise API is on the way. Ambient sound effects, platform upgrades, and sustainability efforts are also in progress, all aimed at making Midjourney more powerful and versatile for the community.

How do you like Imagine Weekly? Is there anything I can do differently? Anything you want to see more or less of? Just shoot me an email hello@imagine-weekly.com ✉️

In this issue you’ll find:

• 📖 Office Hours TL;DR

• 🛠️ Related & Tools to explore

• 🎨 Some new srefs to tinker with and other sources of inspiration

📖 TL;DR

🎬 Video Model Enhancements: New controls, looping, and turbo mode are in development; upscaler delayed due to backend changes.

🎥 Professional Video Features: HD image-to-video mode targets film professionals, restricted to high-tier plans due to cost.

🧠 Model Development Updates: V7.1 mixed results; V8 and real-time generation in progress; faster voice integration being tested.

💼 Business API Launch: Enterprise API applications opening soon with premium pricing and a gradual rollout.

🔊 Audio & Sound Features: Ambient sound effects under consideration; no speech yet; community may help prioritize features.

🖥️ Platform Updates: Mood board, style explorer, user profiles, and mobile improvements are upcoming; better office hours integration planned.

🌱 Infrastructure & Sustainability: Video service reaches break-even; cost optimizations and new revenue streams support sustainable growth.

🌈 Related & Tools

Twitter tweet

Twitter tweet

🎨 Inspiration, Prompts and Srefs

Twitter tweet

Twitter tweet

Frankly, over the last couple of weeks, I was a bit disappointed with what --sref random was producing. | Didier Quarroz 郭荻

Frankly, over the last couple of weeks, I was a bit disappointed with what --sref random was producing. But finally, today I managed to get a bunch of truly outstanding codes for v7. Try this one: --sref 1280556643 It’s extremely unique, hand-drawn, with a striking red element. Follow Didier Quarroz 郭荻 for more MidJourney --sref codes.

www.linkedin.com/posts/guodi_frankly-over-the-last-couple-of-weeks-i-activity-7348007601583910913-A2o5

Directing art or what? | Gizem Akdağ

Directing art or what? //Midjourney

www.linkedin.com/posts/gizakdag_directing-art-or-what-midjourney-ugcPost-7348692159404896256-khdx?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAugk7cBg0eSGpHWmDDIOn_mOG6LnzlIf7g

Animating a vintage image my grandmother as a young woman... | Sherry Horowitz

Animating a vintage image my grandmother as a young woman...

www.linkedin.com/posts/sherry-horowitz-1b9178204_genai-midjourney-ugcPost-7348690212912304129--O7o

See you next week 👋🤖

I hope you enjoyed this issue of Imagine Weekly. If you found it helpful, we'd be thrilled if you could share it with your colleagues and friends. Please feel free to reach out with any suggestions or feedback.

To support me:

☕️  I’d be happy about a coffee

😘 Recommend the newsletter to your friends: it really helps!

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

Midjourney continues to advance its platform with significant enhancements to video capabilities, professional-grade features, and infrastructure, while also preparing for a controlled business API rollout and exploring new audio functionalities. The team is balancing rapid innovation with sustainability, focusing on both user experience improvements and long-term growth.

Video Model Enhancements 🎬

Midjourney is actively developing several new features to improve video generation. Upcoming capabilities include start and end frame controls for greater creative direction, as well as looping functionality for seamless video playback. Motion quality improvements are a longer-term focus, aiming to deliver more natural and consistent movement. The video upscaler, intended to enhance output resolution, has been delayed by a month due to necessary server backend changes. Additionally, a "turbo mode" is in the works, promising significantly faster video generation for users.

Professional Video Features 🎥

A native HD image-to-video mode is now ready for testing, targeting professional film production needs. This mode is approximately 20 times more expensive than the standard offering and will likely be restricted to "mega" subscription plans (€120+/month), reflecting its suitability for high-budget projects. The team emphasizes that the best quality-to-value ratio will depend on individual use cases, with this feature designed to meet the demands of professionals seeking top-tier output.

Model Development Updates 🧠

The V7.1 model candidate demonstrated improvements in coherence, hand, and body rendering but suffered from reduced texture quality and style, prompting further experimentation before any release. Meanwhile, V8 development is underway and showing more promise. The team is also exploring real-time image generation, aiming for speeds surpassing the current draft mode, and testing faster voice integration partners to enhance the platform's capabilities.

Business API Launch 💼

Midjourney is preparing to launch its business and enterprise API, initially targeting the 10–1.000 largest customers. Pricing will start at a premium and gradually decrease as the rollout progresses and feedback is incorporated. The approach is intentionally slow and controlled, with an application form and screening questions to ensure a tailored onboarding process.

Audio & Sound Features 🔊

The team is considering the addition of low-quality sound effects, such as ambient noises (wind, water, traffic, footsteps), to enrich generated content. Speech synthesis is not planned at this stage, and high-quality audio remains a longer-term objective. To involve the community, a sound effects ranking contest may be organized, allowing users to influence feature development priorities.

Platform Updates 🖥️

Several user experience improvements are on the horizon. A mood board update is set to launch this week, and a style explorer tool is in development, starting with basic functionality and expanding over time. User profiles will soon be available on the website, and enhancements to the mobile experience are under consideration. Additionally, efforts are underway to better integrate office hours content into the website for easier access.

Infrastructure & Sustainability 🌱

The video service is transitioning from operating at a loss to breaking even, thanks to ongoing server cost optimizations. New revenue initiatives are being introduced to support the development of larger video models. The overarching goal is sustainable growth, ensuring that continuous improvements to the models and services can be maintained over time.

TL;DR

• 🎬 Video Model Enhancements: New controls, looping, and turbo mode are in development; upscaler delayed due to backend changes.

• 🎥 Professional Video Features: HD image-to-video mode targets film professionals, restricted to high-tier plans due to cost.

• 🧠 Model Development Updates: V7.1 mixed results; V8 and real-time generation in progress; faster voice integration being tested.

• 💼 Business API Launch: Enterprise API applications opening soon with premium pricing and a gradual rollout.

• 🔊 Audio & Sound Features: Ambient sound effects under consideration; no speech yet; community may help prioritize features.

• 🖥️ Platform Updates: Mood board, style explorer, user profiles, and mobile improvements are upcoming; better office hours integration planned.

• 🌱 Infrastructure & Sustainability: Video service reaches break-even; cost optimizations and new revenue streams support sustainable growth.

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!

Welcome to Issue 40 of Imagine Weekly 👋

It's been a while since we last connected. I apologize for the absence. I hope the weekly Office Hours digests helped you get through the break. Some incredible updates have just been released on the live website of Midjourney, surpassing many of our expectations. Midjourney Video is outstanding, even though it's "just" a V1. Additionally, you might have noticed that V7 is now the default model for Midjourney. Next to that many other video models have dropped and it’s hard to keep track.

How do you like Imagine Weekly? Is there anything I can do differently? Anything you want to see more or less of? Just shoot me an email hello@imagine-weekly.com ✉️

In this issue you’ll find:

• 📺 Midjourney Video V1

• 🥊 Midjourney V7 vs V6.1

• 📖 Office Hours TL;DR

• 🛠️ Related & Tools to explore

• 🎨 Some new srefs to tinker with and other sources of inspiration

📺 Midjourney Steps Into Video: First AI Animation Model Now Live

Big news from the world of AI creativity: Midjourney, best known for pushing the boundaries of image generation, has just launched its very first video model. This marks their first step toward a much larger and ambitious goal—real-time, open-world AI simulations where users can move through 3D spaces, interact with characters, and control dynamic environments on the fly.

For now, the offering is called “Image-to-Video”, and it’s exactly what it sounds like. Users can take any image they’ve created in Midjourney and animate it with just one click. There’s an automatic mode, where the AI decides how the scene should move, as well as a manual mode, where users can write out their own motion prompts to describe the type of animation they want.

Midjourney has also introduced two motion styles: one for subtle, ambient movements (ideal for still-life or atmospheric scenes) and another for high-motion scenarios where both the subject and camera are in motion. Users can even upload images from outside Midjourney and use them as starting frames for animation.

The videos are short—just a few seconds per clip—but users can extend them in small increments, up to 20 seconds total. The pricing is refreshingly accessible: the cost of generating a video works out to about the same as upscaling an image, making it one of the most affordable AI video tools currently available.

For now, the feature is web-only, but Midjourney has hinted at ongoing improvements, including possible relax modes for video generation and expanded functionality in the future.

This is a major milestone—not just for Midjourney, but for the entire AI creative space. It’s exciting to see how quickly the gap between static images and full-motion, interactive AI worlds is starting to close.

If you want to learn more or try it yourself, head over to Midjourney’s official site.

🥊 What’s New in Midjourney V7 vs V6.1?

TL;DR: V7 is faster, smarter, more consistent, and gives you better control over both style and subject.

V7 brings smarter image generation with higher image quality, better prompt understanding, and more coherent compositions. Scenes feel more intentional, and characters and objects stay consistent thanks to the new Omni-reference (–oref) feature.

If speed matters, there’s now a Draft mode (–draft) which delivers results up to 10x faster than standard generation—perfect for quick explorations.

For style and mood control, V7 introduces updated sref and moodboard algorithms, giving you more precision and control than ever before.

Finally, personalization profiles have been upgraded. According to Midjourney, 85% of users now prefer the new system for getting results that match their style.

📖 TL;DR

📹 Video Infrastructure & Costs: Efforts are underway to reduce video generation costs through server optimizations, aiming for faster and cheaper production.

🕒 Relax Mode Changes: Changes in Relax mode are being implemented due to heavy usage by top users, impacting financials.

💼 Business Model & Funding: 80% of revenue is reinvested in models; company is community-funded and exploring AI lab partnerships for resources.

🎥 Video Features in Development: New features like Video Upscaler, Start/End Frame Generation, and Turbo Mode are in development to enhance video capabilities.

🖼️ Image Model Updates: Version 7.1 and 8 are in progress, with ambitious integration goals and testing for mood board improvements.

🌐 Platform Growth & Stability: Smooth platform launch with a growing team; new user growth steady but limited by paid model.

🔮 Future Outlook: Combining image and video capabilities, exploring mobile features, and two secret projects nearing announcement.

🌈 Related & Tools

Twitter tweet

Use Gen-4 References within your traditional VFX workflows to create new environments for existing footage. | Runway

Use Gen-4 References within your traditional VFX workflows to create new environments for existing footage. | 36 comments on LinkedIn

www.linkedin.com/posts/runwayml_use-gen-4-references-within-your-traditional-activity-7340448000441237506-ap4i

Twitter tweet

🎨 Inspiration, Prompts and Srefs

Twitter tweet

Oh, you wanted more Midjourney style codes? | Drew Brucker

Oh, you wanted more Midjourney style codes? Okay, okay… Since the new --sref system dropped, I’ve unlocked thousands of style codes. 95%? Forgettable. But the top 5%? 🔥 These ones made my shortlist. ▶ For artists: they're style accelerators. Load one and instantly shift your visual language. ▶ For marketers: think of them as brand filters—tools to test moodboards, campaign direction, or concept art without the wait. Whether you're building a brand world or just experimenting, there’s something in here for every creative brain running too hot to sit still. 20 style codes. Handpicked. -- ✌️ You can also find me here X: @dcbruck IG: @dcbruck | 50 comments on LinkedIn

www.linkedin.com/posts/drewbrucker_20-new-midjourney-style-codes-for-v7-activity-7345080129552850944-ia17

Your Midjourney portraits still look fake | Ross Symons

Your Midjourney portraits still look fake You’re not alone. Most creatives hit a wall when it comes to realism. The lighting feels flat. The skin looks plastic. The emotions missing entirely. Here’s the problem: You’re describing a face, not a feeling. To create images that feel real, you need to do more than add detail. You need to craft emotion, texture, mood, and atmosphere. Realism isn’t in the subject, it’s in the story you’re telling. Take this prompt for example: Prompt Example: Close-up portrait of a young woman with damp hair softly clinging to her face, distant gaze, tear-streaked cheeks, soft overcast lighting casting moody shadows, subtle freckles and visible skin pores, cinematic film grain, blurred rainy window in the background with cool blue-gray tones. –ar 3:4 –style raw –quality 2 Why it works: • Emotional expression: “distant gaze, tear-streaked cheeks” gives the AI something to feel, not just render. • Texture and skin detail: “freckles and pores” break the polished, synthetic look that ruins realism. • Lighting for depth: Overcast lighting with shadows creates form, contrast, and atmosphere. • Environmental storytelling: A rainy window in the background adds mood and narrative context. • Photographic imperfection: Film grain makes it feel captured, not generated. If your AI portraits still feel lifeless, it’s not your concept, it’s your prompt. I break this down step by step in the ZenRobot masterclass. Learn how to go from not bad to “wait… is this a photo?” DM me and I’ll send you the link. | 72 comments on LinkedIn

www.linkedin.com/posts/rossmsymons_your-midjourney-portraits-still-look-fake-activity-7344248459882868738-QpS_

This style is vector-ready, just one click and it’s done 🖤 | Olga Volosin

This style is vector-ready, just one click and it’s done 🖤 Illustration [prompt] --ar 2:3 --exp 80 --sref 3193937836 --profile fbichjd --v 7 #midjourneyv7 #srefcode

www.linkedin.com/posts/olga-voloshin_midjourneyv7-srefcode-activity-7345434688624230401-tpG2

Twitter tweet

See you next week 👋🤖

I hope you enjoyed this issue of Imagine Weekly. If you found it helpful, we'd be thrilled if you could share it with your colleagues and friends. Please feel free to reach out with any suggestions or feedback.

We want everyone back to the office 😅

Twitter tweet

To support me:

☕️  I’d be happy about a coffee

😘 Recommend the newsletter to your friends: it really helps!

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

Midjourney is optimizing its video infrastructure to cut high cloud costs and improve performance, especially in Relax Mode, which faces usage-based restrictions due to financial strain. Operating without investors, the company relies on community subscriptions—80% of revenue funds model training and operations. New video tools like a Video Upscaler, Turbo Mode, and Start/End Frame Generation are in development, alongside major image model updates (v7.1 and early v8). Platform growth remains steady but capped by its paid model, with new user incentives like fast-hour rewards. Looking ahead, Midjourney plans deeper image-video integration, larger model training via partnerships, mobile feature rollouts, and the reveal of two secret projects.

📹 Video Infrastructure & Costs

Midjourney's recent office hours shed light on the company's ongoing efforts to optimize video generation infrastructure. The team is focusing on reducing cloud infrastructure costs, as the video model is currently expensive to operate. Efforts throughout the month are dedicated to server optimizations, which, if successful, could result in faster generation times, reduced costs, and enhanced performance in Relax mode.

🕒 Relax Mode Changes

Relax mode, originally designed to utilize excess capacity, is facing changes due to its heavy use by the top 1% of users, which is causing financial losses. The Midjourney team is implementing changes such as increased wait times, more variable wait times, or adjusted concurrent job limits to address this issue. The previously available capacity has diminished, necessitating these adjustments.

💼 Business Model & Funding

Midjourney operates on a community-funded model, with approximately 80% of subscription revenue going towards running and training models. Unlike many tech companies, Midjourney does not rely on investors. Despite training their current video model with significantly less compute than giants like Google, they are exploring partnerships with other AI labs to access additional compute resources. Higher-tier subscriptions are crucial for funding the training of larger models.

🎥 Video Features in Development

Exciting video features are in the pipeline. The team is working on a Video Upscaler, aiming to reduce artifacts, and developing Start/End Frame Generation to enable smooth animations and looping videos. A Turbo Mode for Video is also being developed, offering much faster generation at a higher cost for professional users. Additionally, an update using reinforcement learning promises quality improvements based on user data.

🖼️ Image Model Updates

The image model is also seeing significant updates. Version 7.1 aims to integrate video and image models, although the release bar is set high. Meanwhile, Version 8 is already in early training stages, with ambitious data preparation underway. The Niji Anime Model is on hold due to unsatisfactory quality, but potential mood board performance improvements are under testing.

🌐 Platform Growth & Stability

The recent major platform launch was the smoothest in the company's history, despite massive changes. The team has grown to around 60 people, enabling larger releases. While new user growth remains steady, it is limited by the paid-only model. A new video ranking feature now allows users to earn extra fast hours, further enhancing the platform's appeal.

🔮 Future Outlook

Looking ahead, Midjourney plans to increasingly combine image and video capabilities within its models. Partnerships may enable the training of much larger models, and mobile features for video and images are being explored. Two secret projects are nearing announcement, promising exciting developments. With a larger team, more frequent major releases are expected, driving the company's growth and innovation.

TL;DR

📹 Video Infrastructure & Costs: Efforts are underway to reduce video generation costs through server optimizations, aiming for faster and cheaper production.

🕒 Relax Mode Changes: Changes in Relax mode are being implemented due to heavy usage by top users, impacting financials.

💼 Business Model & Funding: 80% of revenue is reinvested in models; company is community-funded and exploring AI lab partnerships for resources.

🎥 Video Features in Development: New features like Video Upscaler, Start/End Frame Generation, and Turbo Mode are in development to enhance video capabilities.

🖼️ Image Model Updates: Version 7.1 and 8 are in progress, with ambitious integration goals and testing for mood board improvements.

🌐 Platform Growth & Stability: Smooth platform launch with a growing team; new user growth steady but limited by paid model.

🔮 Future Outlook: Combining image and video capabilities, exploring mobile features, and two secret projects nearing announcement.

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!

Midjourney has launched its V1 video model, letting all users animate images with four motion modes at no extra cost, using about four fast upscales per video. Pricing is conservative for now, with faster Video Turbo modes and quality improvements like a video upscaler coming soon. Infrastructure upgrades are boosting performance, and long-term plans include real-time features and 3D models within one to two years.

🚀 V1 Video Model Launch

Midjourney has unveiled its first V1 video model, accessible directly through their website. Users can animate images by hovering over them and selecting the "Animate" option. This feature is available to all subscription tiers at no additional cost, utilizing approximately the equivalent of four upscales in fast hours per video. The model offers four different animation options, including both high motion and low motion modes. High motion mode is ideal for animations involving significant camera movement, while low motion mode caters to scenarios requiring minimal camera movement, slow motion, or less risky motion.

💰 Video Performance & Pricing

The initial pricing for video features is conservative to ensure sustainability, with potential reductions anticipated in the next one to two weeks based on usage patterns. A Video Turbo mode is slated to launch soon, offering options that are two to eight times faster. The 8x faster mode could generate videos in approximately 10 seconds but will incur higher costs. The Midjourney team is closely monitoring GPU usage to prevent server shortages.

🔧 Upcoming Improvements

Enhancements in video quality are on the horizon, with a video upscaler and improved video quality model under development. Version 7.1, currently in training, incorporates insights from the video model development. Incremental updates, V7.2 or V8, may be released before the full V8 version, focusing on updating two system components. Notably, the video model demonstrates improved hand and body coherence compared to the current image generation capabilities.

🖥️ Infrastructure Updates

Midjourney is expanding its infrastructure with new, more powerful servers and additional GPU capacity to meet demand. Some jobs are already running faster at no extra cost, thanks to these upgrades. Data centers are nearing completion, promising enhanced service delivery.

🛠️ Technical Issues & Solutions

Social media platforms are aggressively compressing 480p videos, prompting Midjourney to recommend using upscalers before posting. The team is exploring fake upscaling to 720p as a potential solution to mitigate compression issues. They are also considering reducing the number of simultaneous video generations from four to two, although four currently yields the best results.

🔮 Future Development Plans

Once current updates stabilize, Midjourney plans to resume work on 3D models and real-time features. Their long-term vision includes real-time open-world simulations with interactive environments. The goal is a seamless transition from images to videos, then to real-time and 3D integration within the next one to two years, ensuring affordability and accessibility for all users.

📢 Current Features & Tips

User feedback is crucial, and Midjourney will soon conduct surveys to gather insights on video features. Priority development includes a video upscaler based on internal requests. Future potential features might include end frames and looping capabilities.

TL;DR

🚀 Midjourney launched its V1 video model with animation options available to all users.

💰 Initial conservative pricing with potential reductions; Turbo mode to offer faster video generation.

🔧 Upcoming improvements include a video upscaler and better video quality.

🖥️ Infrastructure upgrades with new servers and GPUs to meet demand.

🛠️ Addressing social media video compression by recommending upscaling.

🔮 Future plans involve 3D models and real-time features, aiming for full integration within 1-2 years.

📢 User feedback will shape future video features, with surveys and development priorities in place.

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!

Midjourney is on the brink of what could be its most ambitious release to date—a full-fledged video model, promising to animate its iconic visual style in new, expressive ways. The upcoming updates span across style systems, video generation, infrastructure, and future roadmap, and indicate a platform steadily evolving beyond image creation. In short, this isn’t just another feature update—it’s Midjourney doubling down on creativity and interactivity. While the initial launch won’t be flawless, the focus on fun, magic, and creative empowerment signals an exciting new phase in the platform’s evolution.

🎨 Style Reference (S-Ref) System Gets Overhauled

One of the first things on deck is a significant update to the S-Ref system. This new version, expected to drop imminently, breaks compatibility with older S-ref codes—meaning users will need to append --sv4 or --sv5 to continue using legacy references. The upside? Enhanced mood board capabilities, a more refined URL handling system, and the addition of an S-ref randomization feature. By all internal accounts, this is anticipated to be a “slam dunk” release for creators who rely on aesthetic precision and variation.

🎥 Midjourney’s Video Model Is Almost Here

Internally described as “extremely beautiful” and “really fun,” Midjourney’s long-awaited video model is entering its final stages of preparation. Designed for image-to-video generation (no text-to-video—for now), the model will launch with support for visuals from versions V4 to V7, including Niji images. It won’t be shipping with high-resolution or extended video length features at launch, in part to preserve server capacity and ensure accessibility.

In a deliberate strategy to prioritize wide user adoption, Midjourney is considering a low-entry pricing model—despite the higher costs involved in running the video model. However, it won’t support relaxed mode initially, and early access may be restricted to yearly/standard members or Mega Plan subscribers.

🎞️ Features and Focus

The launch version emphasizes medium-quality videos that aim to strike a balance between aesthetic fidelity and accessibility. Notably, the video model maintains Midjourney’s distinct visual signature more effectively than early text-to-video approaches seen elsewhere. A key highlight is the planned video extension feature, set as a post-launch priority to accommodate user demands for longer clips.

🧪 Rating Parties to Tune Quality

Midjourney is involving its community early with “rating parties,” which allow users to vote on early video outputs. The initial party deliberately includes broken or quirky clips—think “heads spinning around”—to help identify bugs and refine quality thresholds. A second round will focus on honing preferences and defining success metrics. You can participate via the desktop-only ranking page.

💻 Server Hurdles and Strategy

The video model is computationally demanding—potentially doubling the current server load. Midjourney is negotiating across three different providers to scale affordably. Lower costs would enable broader rollout, while steeper pricing might lead to stricter access controls or tiered pricing in the future.

🎌 Anime Fans Rejoice: Niji Video Model Incoming

A Niji-specific video variant, better aligned with anime’s stylistic rigors, is planned for release within a month after the main video rollout. Interestingly, this version may also be the first to introduce text-to-video functionality, since anime visuals are more easily trained within the structured domains of video data.

🧭 Looking Ahead: V7.1, V8, and Beyond

There’s no pause on innovation. V7.1 is expected to borrow learning from the video model to improve coherence, while V8 is under early development to boost image quality and visual understanding. A new version of Style Explore is also in progress, based on the updated S-ref system, and the notoriously tricky O-ref feature is undergoing fresh experimentation.

🗣️ Feedback-Driven Development

The Midjourney team is actively sifting through user feedback from feature votes, with character consistency topping the list of priorities. User demand for longer videos and features like angle shifting are also being factored into post-launch development.

TL;DR

🎨 Style Ref Update: New S-Ref system drops soon; better mood boards, randomization, improved URLs. Old codes need --sv4 or --sv5.

🎥 Video Model: Launching soon with image-to-video only. Beautiful, fun, but no text-to-video (yet). Works with V4–V7 + Niji.

⚙️ Features: Medium quality. Shorter videos for now. Extensions and enhancements post-launch. Maintains Midjourney’s look well.

🧪 Rating Parties: First party shows “broken” content to find flaws. Next will refine quality. Participate on desktop.

💻 Server Concerns: Video model needs 2x capacity. Negotiating server deals. Costs will impact pricing and access.

🎌 Niji Video Model: Anime-focused model due within a month. Might include text-to-video. Better fit for structured anime styles.

🧭 Future Roadmap: V7.1 to integrate video learnings. V8 in early dev. S-Ref and O-ref getting major updates.

🗣️ Community Feedback: Character consistency is top user ask. Longer video lengths and angle shifting in 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!

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!

The latest Midjourney Office Hours offered a clear-eyed look at ongoing development, upcoming releases, and the challenges the team is working to overcome. This week’s update was filled with insights about model improvements, feature rollouts, infrastructure upgrades, and the role of community feedback in shaping Midjourney’s roadmap.

🚀 Version 7 (V7) Updates:

The V7 model has received a notable speed increase—around 30% faster than before—making image generation more efficient for all users. Recent data from community image rankings is guiding a series of aesthetic improvements, signaling ongoing enhancements to the quality of generated art. However, the much-anticipated Omnireference improvements have not lived up to expectations so far. The team is weighing whether to pursue a simpler interim fix or to push a more robust overhaul to V8. Meanwhile, potential upscaling improvements are under review, with no clear timeline for release as of yet.

🎨 New Style Reference (S-ref) Development:

Big changes are nearly complete for the Style Reference (S-ref) system, promising a more user-friendly and functional experience. The new S-ref will be compatible with moodboards, which should help users manage visual themes more effectively. An early release is being considered, even if the full “S referendum” feature doesn’t make the initial cut.

🎬 Video Model Release:

A major new addition is on the horizon: Midjourney’s video model. Early tests with guides and moderators are scheduled for the coming week, followed by community-based video ranking in the two weeks after. The launch is tentatively set for June, pending the arrival of new server farms required to support the rollout. Videos will be offered in multiple resolutions with a tiered pricing structure. Relax mode for video is intentionally delayed to prevent overloading servers, and will initially be available only to higher-tier subscribers before expanding more broadly.

🖥️ Server and Capacity Challenges:

To meet surging demand—especially with the upcoming video features—Midjourney is preparing two waves of new server deployments over the next few weeks. The team is also looking at other sources for additional capacity, informed by strong community interest. Short-term restrictions on usage may be necessary if demand temporarily outpaces supply.

🔜 Version 8 (V8) and 7.1 Considerations:

While active planning for Version 8 is underway, there is no set release date. The possibility of a V7.1 update exists if certain V8 features prove feasible to backport. Internal discussions are ongoing regarding how to allocate resources between these two tracks, and the outcome may hinge on both technical evaluations and community preferences.

📢 Feature Voting and Community Input:

A new system for feature voting is set to launch soon, aiming to give the community a stronger voice in what gets prioritized. Recent updates have already drawn heavily from user-submitted image rankings, which are shaping the model’s evolving aesthetic.

🌐 Web and Social Features:

On the web front, personalized Explore pages and enhanced web-based storytelling tools are in the works. The experiment with non-Discord chat rooms on the Midjourney site hasn’t gained much traction, and may be phased out in favor of more popular or useful features.

Overall, the May 29 Office Hours revealed a team focused on concrete improvements, responsible scaling, and meaningful community engagement—even as they navigate the inevitable complexities of growth and innovation.

TL;DR

🚀 V7 Faster & Prettier: Speed up 30%, looks set to improve; Omnireference and upscale upgrades may be pushed to V8.

🎨 Style Reference Upgrade: Usability overhaul almost done, moodboard-friendly, early release likely (without full features).

🎬 Video Model Incoming: Testing starts next week, launch planned for June with tiered pricing and phased Relax mode.

🖥️ Server Crunch: New servers coming in waves, possible usage caps if demand spikes.

🔜 V8 on the Horizon: V8 in planning, small V7.1 update possible if features align; resource split undecided.

📢 Community Input Rising: Feature voting system soon, user rankings shaping model updates.

🌐 Web Features Evolving: Personalized Explore and storytelling in progress; website chat rooms may be cut.

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!

Version 7 and Beyond 🚀

In the latest Midjourney Office Hours, the team confirmed that a much faster iteration of Version 7 will be rolling out as soon as next week, aiming to make it the new default for all users. While there’s some talk about a minor update (V7.1), all indications suggest they’ll jump directly to Version 8 after this. The team’s main technical push right now centers on refining personalization and aesthetic settings, reinforcing their commitment to user control and creative flexibility.

🎨 S-Reference Upgrades

Exciting news is on the horizon for users who rely on S-Reference (Sref) for style transfer. An upgraded Sref system is nearly ready, promising marked improvements in style transfer capabilities. However, it’s worth noting that Sref randomization won’t be available at launch but is planned for a later update. Once this enhanced Sref is live, development attention will shift to new style exploration tools for even deeper creative experimentation.

🎬 Video Model Progression

The much-anticipated video model is moving closer to public release. Internal testing by guides and moderators is set to start at the end of the month. The model will offer both text-to-video and image-to-video capabilities, each being refined for quality and accessibility. Multiple quality and pricing tiers are in the works, ensuring even entry-level ($10/month) subscribers can access these features. Early feedback points to videos with a unique Midjourney aesthetic and smooth motion. However, a full public rollout is dependent on necessary server upgrades, expected within the next 45 days. If infrastructure delays occur, early access may be limited to higher-tier subscribers.

🖥️ Infrastructure and Release Strategy

The team highlighted the critical role of upcoming server infrastructure deployments, particularly for the video feature. In the event of launch delays, there may be a temporary restriction on who can access new features, favoring higher subscription levels until capacity scales.

🗳️ Feature Feedback and Prioritization

Midjourney is launching another round of user feature and image ranking sessions in the next two weeks. These are designed to better capture and respond to user preferences around personalization and future development. Dedicated ranking for video features is likely to occur before the broader video rollout.

🖌️ UI and Pro User Experience

Plans are underway to enhance the user interface, especially for professional users with high-resolution (4K) displays. Batch processing, due to its resource intensity, may be rolled out first to premium tiers, aligning with their commitment to offering advanced features for power users.

🏢 Enterprise and API Roadmap

On the business front, Midjourney may soon survey users about enterprise-specific needs and API access. They’re exploring specialized moderation and management features, possibly restricting certain API and moderation tools to enterprise clients.

🚫 NSFW Policy

Midjourney reaffirmed its current NSFW stance, stating clearly that there are no plans to introduce nudity, with all policies and systems remaining unchanged.

🔮 Looking Ahead

Immediate priorities include rolling out the faster Version 7, the new Sref, and features for referencing multiple subjects. This will be followed by the video model release and server upgrades, with continued focus on deepening user personalization. Longer-term ambitions involve experimenting with voice-based creative tools and expanding advanced UI features for broader creative possibilities.

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!

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!

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!

Midjourney’s latest Office Hours provided a packed agenda, highlighting a series of significant updates and ongoing experiments aimed at evolving the platform’s creative capabilities. As a third party following these developments, here’s an objective recap of what’s changing, why it matters, and what’s next for the Midjourney community.

🚀 Big Release Day: Too Much at Once?

The team rolled out a substantial number of new features and improvements, sparking internal debate about whether the release cadence is too ambitious. Updates include a refreshed editor design, aesthetic tuning, the new Omni Reference tool, an experimental parameter, and changes to fast mode. Users can expect noticeable changes in how they interact with Midjourney starting today.

🖌️ Editor Design Overhaul

Responding directly to user feedback, the editor interface has been refined for both looks and usability. The improved design not only feels more modern but also enhances image editing functionality, aiming to streamline the creative workflow for artists and casual users alike.

🎨 Aesthetic Upgrades: Subtle but Important

A small, targeted update is now live to boost prompt accuracy and overall output consistency. While this change is only expected to impact about 1% of existing prompts, it’s a meaningful step toward making Midjourney’s results more reliable and predictable for all users.

🤖 Omni Reference Feature: A Step Forward in Customization

Perhaps the most anticipated release is the Omni Reference feature. This tool allows users to input a single reference image but manipulate it in new ways—combining people, objects, and various style changes. A weight parameter lets users fine-tune how closely results match the original reference. Notably, Omni Reference is versatile enough to handle both Midjourney-generated images and real-world photos (though it doesn’t work in conversation mode yet). For those exploring fashionable avatars or imaginative scenes, it opens up new creative territory.

📝 Tips for Using Omni Reference

Users are advised to be specific with prompts when using this tool. For example, referencing an image of a sword and a chipmunk requires explicit instructions, such as “chipmunk holding a sword,” to achieve desired results. Omni Reference works especially well for styling and setting-based images and can be further enhanced when paired with editor refinements. Still, some experimentation may be necessary to fine-tune outputs.

🧪 New Experimental Parameter: “–exp”

Another major addition is the experimental parameter, a new option that boosts image detail and creativity at the cost of prompt precision. It’s especially effective with shorter prompts and may interact with existing personalization features. The parameter is still evolving and could be renamed or further integrated in the future.

🛡️ Moderation: Stricter Safeguards for Reference Features

With the launch of Omni Reference, Midjourney is increasing its moderation efforts, particularly for images referencing real people. The platform maintains zero tolerance for misuse and will adjust safeguards in response to community feedback. This is a clear signal that user safety and ethical image generation remain priorities.

🔮 What’s Next: Upcoming Features and Improvements

Looking forward, the team hinted at several features on the horizon. Next week should see improvements to the Q4 parameter, and a new S-REF feature is also in the pipeline, aimed at improving mood board creation. An upscaler upgrade is in development, and the community will be involved in voting to help prioritize additional style and aesthetic changes. There’s also ongoing discussion about the future direction for V8 and video features.

🎥 Video Capabilities: Progress and Challenges

On the video front, the team is still deciding whether to retrain models or continue optimizing the current pipeline. Data contamination from AI-generated clips remains a concern, and significant effort is being made to clean up datasets and boost video quality.

🤝 Community Collaboration: The Heart of Midjourney’s Progress

Throughout the session, the team reinforced their commitment to collaborative feature development. User feedback remains essential in steering future updates, and the community is encouraged to experiment with new features and share both successes and challenges.

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!

🚀 Features & Testing: Major Experiments in the Works

The latest Office Hours saw Midjourney’s team testing new default image settings, with internal guides and moderators reporting a clear preference over prior versions. A new experimental “less-conservative” tuning mode is also being trialed, significantly boosting visual quality, but at the expense of precise prompt adherence. The team is undecided on when, or if, this mode will see a public release.

🖼️ Omni-Reference & Personalization: Progress and Roadblocks

Omni-Reference—the system enabling image-based prompts—has proven solid for single-image input but stumbles with scenes involving multiple subjects, such as two faces or unconventional object arrangements. Meanwhile, prototypes for personalization around aesthetics and style are advancing, though not yet ready for public trials due to the effort needed for thorough evaluation.

🛠️ Release Strategy & Quality Balance: Speed Versus Polish

There’s an internal push to ship updates more quickly, even if they aren’t perfect, to keep user creativity at the forefront. This has sparked ongoing debate about finding the right balance between rapid releases and product polish, particularly after last week’s swift rollout met with mixed community reactions. A recent holiday weekend also caused a two-day slip in the release schedule.

🎨 Image Settings & Personalization Roadmap: Quality and the Future

The conservative image quality update is considered “good enough” and poised for immediate launch, although a short delay is being considered to test a more ambitious variant. In the longer run, Midjourney plans regular, community-driven personalization updates, with new rating tools to help steer improvements. Ambitiously, the V7 release could deliver up to a tenfold leap in output quality, but robust tools are needed to reliably measure such jumps.

🖼️ Omni-Reference Status: Almost Ready, With Fixes Pending

Omni-Reference is now delivering around 80–90% successful results, but about 10% of outputs still show unwanted “burnt” artifacts. Engineering work is underway to address these, and the team is developing a more nuanced moderation framework to balance creative freedom with safety. If all goes well, Omni-Reference could see public release within the next week.

⚡ Fast Mode & “q 4” Engine: Speed with Minor Tradeoffs

The fast-render “q 4” engine is showing only a slight (about 2%) dip in image quality for some edge cases. The team aims to launch it alongside the Omni-Reference feature, possibly as soon as next week.

📹 Video Model Progress: Early Wins and Next Steps

Midjourney’s video model has produced its first viable results, impressing with unexpectedly high quality for the cost. The plan is to make this feature affordable for existing subscribers, with aesthetic consistency that outpaces current market options, though a few quirks remain. More training and optimization are needed, so the earliest possible public preview would be next month.

🛤️ Upcoming Milestones: What’s Next on the Roadmap

The V7 update, integrating Omni-Reference, refreshed aesthetics, and Fast Mode, is on track for release in the coming weeks. After that, attention will likely turn to V8 rather than 3-D generation, as the latter doesn’t offer as much near-term potential. Two competing designs for an enhanced style-reference system are also under consideration, part of a broader push toward “aesthetic singularity”—the ambition to massively expand creative style options within a year.

🏗️ Tooling, UI, & Infrastructure: Under-the-Hood Improvements

Continued improvements are being made to the in-app editor to ensure a smoother experience for all images. New website workflows are being explored to collect user feedback faster, outpacing traditional guide/mod review cycles. Behind the scenes, “collective intelligence” projects and hardware upgrades are progressing, with the first public details expected in about six months.

🌏 Community & Commercial Considerations: Keeping Users at the Core

Midjourney remains committed to prioritizing fun and creative freedom for its users, even as some subscribers push for more commercial-grade results. There’s an active effort to broaden the testing pool, allowing everyday users to influence image quality alongside internal guides and moderators.

TL;DR

🚀 Testing: New default image settings and experimental tuning modes; Omni-Reference strong on singles, tricky on complex scenes.

🛠️ Release: Faster updates prioritized, but debate on polish; schedule delayed slightly by holiday.

🎨 Personalization: Style & aesthetic personalization in the works; V7 could be a huge quality leap.

🖼️ Image: Conservative quality update nearly ready; Omni-Reference aiming for next week after artifact fixes.

📹 Video: Early video model promising, public preview possibly next month.

🏗️ Infrastructure: Editor and feedback tools improving; hardware and “collective intelligence” upgrades coming.

🌏 Community: User creativity prioritized; plans to expand test pools for more inclusive quality input.

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!

Welcome to Issue 39 of Imagine Weekly 👋

People are creating incredible things with Midjourney V7. Alongside this new major version, Midjourney has also released an updated version of their editor. We now have layers and many more options to generate stunning images.

How do you like Imagine Weekly? Is there anything I can do differently? Anything you want to see more or less of? Just shoot me an email hello@imagine-weekly.com ✉️

In this issue you’ll find:

• 📖 Office Hours TL;DR

• 🛠️ Tools to explore

• 🎨 Some new srefs to tinker with and other sources of inspiration

Twitter tweet

Twitter tweet

📖 TL;DR

🚀 Releases & Improvements: Weekly updates, editor enhancements, fast mode, and aesthetic updates.

🎨 Q4 Mode & Tuning: Higher-quality renders, community feedback for aesthetic balance.

🖼️ Reference Systems: Omniref and S-Ref improvements for better referencing.

⚡ Draft Mode & UI: Ultra-fast generation, real-time interfaces, maintaining aesthetics.

🎥 Video Features: Video model training, balancing cost and quality, community input.

🔧 Infrastructure Upgrades: New servers for V8 model, experimental V7.1/7.2 runs.

📱 User Experience: Explore page updates, mobile improvements, secret hardware projects.

🌈 Related & Tools

Twitter tweet

Twitter tweet

🛠️ Tools

Twitter tweet

🎨 Inspiration, Prompts and Srefs

Twitter tweet

Twitter tweet

Twitter tweet

Twitter tweet

Midjourney V.7 Getting there. Was never easy to make a lot of people at… | Didier Quarroz 郭荻 | 15 comments

Midjourney V.7 Getting there. Was never easy to make a lot of people at once but it works quite well now. | 15 comments on LinkedIn

www.linkedin.com/posts/guodi_midjourney-v7-getting-there-was-never-activity-7316121066895020032-Ye3f

#midjourney #srefcode | Olga Volosin

--chaos 25 --ar 2:3 --sref 583730153 --profile n2adpdu --sv 4 --sw 1000 --stylize 1000 --v 7 #midjourney #srefcode

www.linkedin.com/posts/olga-voloshin_midjourney-srefcode-activity-7318301971059281922-yzxb

See you next week 👋🤖

I hope you enjoyed this issue of Imagine Weekly. If you found it helpful, we'd be thrilled if you could share it with your colleagues and friends. Please feel free to reach out with any suggestions or feedback.

To support me:

☕️  I’d be happy about a coffee

😘 Recommend the newsletter to your friends: it really helps!

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