🚀 Midjourney Office Hours Highlights: June 18th

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!