The creative and AI community is eagerly awaiting the latest announcements from Midjourney, as the platform prepares to launch its anticipated video generation feature this month. This move coincides with the accelerated development of the Midjourney V8 model, heralding a new era of innovation in the world of AI-powered design.
Midjourney Video Feature: Transforming Still Images into Motion
According to well-informed sources, Midjourney's video generation feature has entered its final development stages, with expectations for it to be available to users soon.
To support this significant addition, the company is expanding its server infrastructure.
A new batch of servers is scheduled to go live within the next two weeks, followed by further enhancements in the subsequent month.
Initially, the new feature will focus on converting still images into video clips. In its first phase, it will not support direct text-to-video conversion or the use of external images.
The platform will offer two basic rendering resolutions, with no upscaling capabilities in the initial release.
The Midjourney team emphasizes that the essence of video generation will be its motion effects and visual aesthetics, while maintaining a reasonable cost. This will ensure it is accessible even to subscribers of the basic $10 monthly plan.
Notably, access to this feature will initially be limited to annual subscribers. This strategy aims to evaluate server performance under heavy load.
The feature will debut exclusively on the official Midjourney website, with no current plans for integration with Discord. To ensure the quality of the final model, the company intends to host a "video rating party" next week, inviting users to help evaluate and refine the product.
Midjourney Updates: V7.1 and V8 Aim for Greater Precision and Innovation
Alongside the video feature, Midjourney's core models are undergoing significant advancements.
The V7 model is expected to become the default option within the next week, while the V7.1 model has already entered development.
Midjourney V7.1 will specifically focus on improving the consistency of hands and bodies in generated images, with its training scheduled to begin one to two weeks after the video model is finalized.
Even more exciting is the full-scale acceleration of research and development for the Midjourney V8 model. The team acknowledged that V7 did not fully meet expectations.
Therefore, V8 is set to be a "massive leap forward," incorporating new and innovative capabilities.
Many anticipate the release of V8 within the next few months, marking another significant milestone for Midjourney in the field of AI image generation.
Improvements in Style Control and Exploration
The enhancements don't stop there. Midjourney's Style Reference (SREF) feature is also set to receive a major update.
Expected next week, the new version of SREF will improve the accuracy of style matching, making the results more faithful to the reference images used.
Additionally, the new version will support the generation of random styles, granting users greater creative flexibility. Such update further solidifies Midjourney's leading position in AI-driven stylistic control.
Beyond the core model updates, Midjourney is developing a "Style Explorer," planned for launch after the SREF update. This tool will help users discover and apply different artistic styles more easily.
In a related move, Midjourney may discontinue some of the less-used "Rooms" features on its website to reallocate resources toward more popular and in-demand developments.
Finally, Midjourney's latest updates reflect its grand ambitions in both AI image and video generation. From the imminent launch of the video feature to the accelerated development of the V8 model, the platform is pushing the boundaries of innovation at an unprecedented pace.
