Skip to main content

Midjourney Prepares to Launch Video Feature and V8 Model

Midjourney, the leading AI image generation platform, is gearing up for a major update with the imminent launch of its video feature and accelerated development of its V8 model. These advancements signal a new phase in AI-powered creativity.

Image

Video Feature Nears Release The video generation function has entered its final testing phase and could debut as early as this month. Midjourney plans a "rating party" next week where users can evaluate the feature before its official rollout. The initial version will focus solely on image-to-video conversion, offering two basic resolutions without upscaling capabilities.

To manage server load, the feature will initially be available only to annual subscribers through Midjourney's website, with no immediate plans for Discord integration. Despite these limitations, the team emphasizes affordability, ensuring even $10/month subscribers can access the tool.

Infrastructure Upgrades Underway New servers are scheduled to launch within weeks to support both the video feature and growing user demand. Additional hardware deployments next month will further bolster system capacity. These upgrades aim to maintain performance standards as Midjourney expands its capabilities.

Style Reference Improvements A significant update to the style reference (sref) feature arrives next week. The enhanced version promises better accuracy in replicating artistic styles from reference images and introduces random style generation for increased creative flexibility. This refinement strengthens Midjourney's position in precise image style control.

Next-Generation Models in Development While V7 becomes the default model next week, development continues on V7.1 with specific improvements to hand and body rendering coherence. More substantially, work accelerates on V8 - described by developers as containing "significant differences" from previous versions due to unrealized potential in V7's architecture.

New Tools Coming Soon Beyond core model updates, Midjourney plans to introduce a Style Explorer tool following the sref update. This will help users navigate diverse artistic styles more effectively. Some lesser-used website features may be retired as resources concentrate on more popular tools.

These developments demonstrate Midjourney's commitment to pushing boundaries in AI-assisted creativity. From visual storytelling through video generation to refined artistic control in still images, these updates offer creators powerful new possibilities.

For those eager to try these features early, watching for official announcements about next week's rating party provides the best opportunity. As AI transforms creative workflows globally, Midjourney continues positioning itself at the forefront of this revolution.

Key Points

  1. Video generation launches this month with image-to-video conversion as core functionality
  2. Server expansions begin within weeks to support new features and growing demand
  3. Style reference tools receive major accuracy improvements and random style generation
  4. V8 model development accelerates with promised "significant differences" from previous versions
  5. New Style Explorer tool coming soon after sref updates complete

Enjoyed this article?

Subscribe to our newsletter for the latest AI news, product reviews, and project recommendations delivered to your inbox weekly.

Weekly digestFree foreverUnsubscribe anytime

Related Articles

India's Alpie AI Model Makes Waves - But Is It Truly Homegrown?
News

India's Alpie AI Model Makes Waves - But Is It Truly Homegrown?

A new AI contender from India called Alpie is turning heads with performance that rivals giants like GPT-4o and Claude3.5 in math and coding tests. However, technical analysis reveals it's actually built on a Chinese open-source model, raising questions about innovation versus optimization. What makes Alpie special is its ability to run efficiently on consumer hardware, potentially democratizing AI access for smaller developers.

January 15, 2026
AIMachine LearningIndia Tech
AI Cracks Erdős' Toughest Puzzles: Mathematicians Stunned by GPT5.2's Breakthroughs
News

AI Cracks Erdős' Toughest Puzzles: Mathematicians Stunned by GPT5.2's Breakthroughs

In an unprecedented feat, GPT5.2 has solved 11 of Paul Erdős' legendary unsolved mathematical problems in just two weeks, verified by formal proof tools. The breakthrough has top mathematicians like Terry Tao taking notice, with Harvard's Noam Elkies building on AI-generated solutions. This marks a turning point where artificial intelligence isn't just assisting human researchers - it's making autonomous discoveries at the frontiers of pure mathematics.

January 15, 2026
Artificial IntelligenceMathematicsGPT5
DeepSeek-V4 Set to Revolutionize Code Generation This February
News

DeepSeek-V4 Set to Revolutionize Code Generation This February

DeepSeek is gearing up to launch its powerful new AI model, DeepSeek-V4, around Chinese New Year. The update promises major leaps in code generation and handling complex programming tasks, potentially outperforming competitors like Claude and GPT series. Developers can expect more organized responses and better reasoning capabilities from this innovative tool.

January 12, 2026
AI DevelopmentProgramming ToolsMachine Learning
Midjourney's Niji 7 Upgrade Brings Anime Characters to Life
News

Midjourney's Niji 7 Upgrade Brings Anime Characters to Life

Midjourney's specialized anime model Niji・Journey has leveled up with version 7, delivering stunning improvements in character consistency and detail. The update particularly shines in rendering expressive eyes and facial features that finally look natural together. Beyond visual polish, Niji 7 understands complex prompts better than ever - even handling wild requests like four-armed ice cream enthusiasts without breaking a sweat. For anime creators and fans alike, this might be the most exciting AI art upgrade of the year.

January 12, 2026
AI ArtAnime GenerationMidjourney
Mugen3D Turns Single Photos Into Stunning 3D Worlds
News

Mugen3D Turns Single Photos Into Stunning 3D Worlds

A groundbreaking AI tool called Mugen3D is transforming how we create 3D content. Using advanced 3D Gaussian Splatting technology, it can generate remarkably realistic models from just one image - capturing textures, lighting, and materials with astonishing accuracy. This innovation promises to democratize 3D creation across industries from gaming to e-commerce.

January 12, 2026
AIComputerGraphicsDigitalCreation
News

Qualcomm and Google Join Forces to Revolutionize Car Tech with AI

Qualcomm and Google are teaming up to tackle one of the automotive industry's biggest headaches: fragmented in-car systems. Their new 'Automotive AI Agent' combines Qualcomm's Snapdragon Digital Chassis with Google's Android Automotive OS, promising smoother development and smarter features like facial recognition. The partnership also introduces cloud-based development tools that could cut R&D time significantly. This collaboration marks a major step toward more unified, intelligent vehicle systems.

January 9, 2026
automotive-techAIsmart-cars