In a major leap forward for generative AI, San Francisco-based research lab Midjourney has launched its first-ever text-to-video generation model, dubbed V1. The tool enables users to animate static images into short video clips with the help of AI, marking a significant expansion of Midjourney’s creative toolkit.
Introducing our V1 Video Model. It’s fun, easy, and beautiful. Available at 10$/month, it’s the first video model for *everyone* and it’s available now. pic.twitter.com/iBm0KAN8uy
— Midjourney (@midjourney) June 18, 2025
With V1, users can transform either uploaded images or AI-generated visuals from Midjourney into dynamic five-second video animations. Upon clicking “animate,” the system generates four short clips, each of which can be extended up to 20 seconds. However, it remains unclear whether these animations include sound.
Smart Motion Control
V1 supports both Automatic and Manual animation modes. In Automatic mode, the AI proposes motion directions to bring images to life, while Manual mode offers more control, allowing users to type in custom prompts to guide the animation’s movement and narrative flow.
In addition, users can select between two camera styles:
- Low Motion – Features a fixed camera setup with subtle movements.
- High Motion – Offers dynamic camera and subject motion throughout the video.
Accessible to All
In a move that democratizes access, Midjourney has made V1 available across all subscription tiers, including free accounts. Still, users should be aware that creating videos consumes significantly more computational resources than generating images. Midjourney noted that each video clip requires eight times more GPU time than a still image.
V1 operates in two performance modes:
- Fast Mode: Provides a fixed GPU time quota every month for image and video generation. A single image consumes one minute of GPU time, while a video eats up eight minutes. Once this limit is exhausted, users can’t create more content until the next cycle.
- Relax Mode: Currently being tested with Pro-tier subscribers and above, this mode offers unlimited GPU time, albeit with longer wait periods. Video prompts may take up to 10 minutes to complete in this queue-based system.
The launch of V1 positions Midjourney to compete directly with other major players in the AI video space, offering a powerful and cost-effective way to animate still imagery. As video generation becomes a cornerstone of creative expression and content marketing, tools like V1 are poised to reshape the landscape of digital storytelling.
