Midjourney Video is Coming! V8 Model is Ready to Launch, A New Era of AI Creativity is Around the Corner!

AIbase基地

Published inAI News · 8 min read · Jun 5, 2025

According to the latest news, Midjourney's video feature is expected to launch this month, and the development of V7.1 and V8 models is also accelerating. This article will provide you with a detailed analysis of Midjourney's latest developments, including breakthroughs in video features, server upgrades, style reference (sref) optimization, and future model plans, giving you an overview of the cutting-edge progress in AI image generation.

Video function on the verge of launch, rating party next week

According to AIbase, Midjourney's video generation function has entered its final sprint stage and is expected to be officially released this month. A new batch of servers will go online within the next one to two weeks, followed closely by the launch of the video feature. To ensure model quality, Midjourney plans to hold a video rating party next week, inviting users to participate in evaluations to optimize the final model.

The new video feature will focus on image-to-video conversion as its core functionality, without support for text-to-video or external image input. Initially, it will offer two basic resolutions, with no upscaling function available. The Midjourney team emphasizes that video generation will focus on dynamic effects and visual aesthetics while ensuring affordability, making it accessible even for monthly subscription users paying $10.

Notably, the video feature will initially only be available to annual subscribers to assess server performance. This feature will only be available on the Midjourney website and there are currently no plans to support Discord platforms.

Server expansion to support video and model upgrades

To support the video feature and the growing user demand, Midjourney is accelerating its server expansion. AIbase understands that new servers will go online within the next one to two weeks, with more servers planned for deployment next month. These hardware upgrades will provide strong support for video generation and subsequent model optimizations, ensuring smooth user experiences.

Major updates to style references (sref)

Midjourney's style reference (sref) feature will also undergo significant upgrades. The new version of sref is expected to be released next week, significantly improving the accuracy of style references and better aligning with the performance of reference images. Additionally, the new version will support random style generation, providing users with more creative possibilities. This update will further solidify Midjourney's leading position in the field of image style control.

V7.1 and V8: Accelerating model upgrades

Midjourney's V7 model is expected to become the default model next week, with V7.1 development already underway. AIbase learned that V7.1 will focus on optimizing hand and body coherence, with training work to start one to two weeks after the completion of the video model.

More excitingly, Midjourney is fully accelerating the research and development of the V8 model. The team stated that V7 failed to fully achieve its expected functions, so V8 will bring "significant differences," integrating more innovative features. V8 is expected to be released within the next few months, marking another leap forward for Midjourney in the field of AI image generation.

Style explorer and website function optimization

In addition to core model upgrades, Midjourney is also developing a brand-new style explorer (Style Explorer), which is planned to be launched after the sref update. This tool will help users explore and apply diverse artistic styles more conveniently. Moreover, AIbase noticed that Midjourney may close some "rooms" on the website due to low usage rates, as the team focuses resources on developing more popular features.

Midjourney leads the new era of AI creativity

Midjourney's latest developments demonstrate its ambition in the fields of AI image and video generation. From the imminent launch of the video feature to the accelerated development of the V8 model, Midjourney is pushing technological innovation at an impressive pace. AIbase believes that with the launch of new servers and the optimization of style reference functions, Midjourney will continue to provide global creators with more powerful and flexible tools, driving the AI-driven creative revolution.

For users eager to try the video feature, AIbase recommends closely following Midjourney's official website announcements, participating in next week's rating party, and experiencing this groundbreaking feature ahead of time.

Undoubtedly, Midjourney's video feature and model upgrades will inject new vitality into the AI creative domain. Whether professional designers or AI art enthusiasts, everyone should look forward to Midjourney's latest developments.

Aibidia Raises $28 Million in Series B Funding to Expand AI-Driven Tax Technology into the US Market

Finnish fintech company Aibidia has recently secured $28 million in Series B funding. This capital will be used to expand its AI-driven tax technology platform into the US market. The round was led by Activant, with participation from existing investors DN Capital, FPV, and Icebreaker.vc, marking an important step for Aibidia as it extends advanced tax compliance and transfer pricing solutions to global businesses.

BAAI Launches Emu3 and Other WuJie Series Large Models

At the recently concluded 7th Beijing BDA Conference, BAAI released a series of large models named 'WuJie'. The release of these models marks another technological leap in the field of artificial intelligence, drawing the attention of many tech enthusiasts. The models released this time include the native multimodal world model Emu3, brain science multimodal universal foundational model JianWei Brainμ, and the ontology-crossing embodied brain-cerebellum collaboration framework RoboOS2.0 as well as the embodied brain RoboBrain2.0. Additionally, there are full...

Manus Launches Text-to-Video Function Aiming to Rival OpenAI's Sora

AI startup Manus recently announced the launch of its new Text-to-Video function, aiming to provide users with a convenient experience to generate videos through simple text commands. The function is now available for抢先 trial to Basic, Plus, and Pro members. Manus stated on social media platform X that users just need to enter text commands, and their intelligent system can convert these instructions into structured and coherent videos within minutes, demonstrating its strong capabilities in AI video generation.

AI Gradually Replacing Entry-level Employees, Significant Decrease in Junior Recruitment at Tech Companies

During the keynote speech at Snowflake Summit 2025, OpenAI CEO Sam Altman pointed out that more and more companies are beginning to view AI agents as entry-level employees. Altman stated that the focus of many employees' work has shifted to assigning tasks to AI agents, evaluating the quality of their results, integrating work content, and providing feedback. This working model is very similar to managing entry-level employees. Image source note: The image was generated by AI.

Future five years: Half of entry-level white-collar jobs may be replaced by AI

In a recent interview, Dario Amodei, CEO of Anthropic, issued an eye-catching warning. He stated that with the rapid development of artificial intelligence (AI) technology, within the next five years, half of the entry-level white-collar jobs may be replaced, and the unemployment rate could soar to 10% to 20%. Amodei emphasized that many workers are not aware that this change is coming, and many people find it hard to believe. Image source notes: The image was generated by AI.

Meta Team Research Finds: Simplifying Reasoning Chains Can Significantly Enhance AI Accuracy

Recently, Meta's FAIR team and researchers from the Hebrew University of Jerusalem jointly released a new study indicating that reducing the reasoning time of large language models can significantly improve their performance in complex reasoning tasks. The research findings show that using shorter reasoning chains, the accuracy of AI models has increased by 34.5%, which challenges some assumptions in the current AI industry. Image source notes: The image was generated by AI and is licensed by Midjourney in this study, the authors point out that prolonged deliberation

DeepSeek Quietly Releases R1 Latest Version, Performance Close to OpenAI 03 Shocks the Industry

The open-source large model field has received another major message. DeepSeek recently released the latest 0528 version of the R1 model quietly. This move has attracted widespread attention in the AI developer community. Notably, DeepSeek adopted a very low-key release strategy this time, neither releasing detailed technical specification documents nor holding any form of release event, but instead chose to quietly open model downloads. As usual, the official is expected to release a full model card in the near future, where more information about the new version's features will be published.

OpenAI CFO Reveals: Restructuring New Structure Paves the Way for a Possible IPO

Sarah Frueh, CFO of OpenAI, recently revealed at the Dublin Tech Summit that the company's ongoing organizational restructuring is paving the way for a possible initial public offering (IPO). Although OpenAI is actively preparing, whether it can successfully go public depends on both the company's own preparation and the overall atmosphere of the capital market. Image source note: Images generated by AI, images authorized service provider Midjourney. Frueh mentioned Microsoft's investment in OpenAI.