Midjourney, a prominent name in the AI image creation industry, has unveiled its debut AI-powered video generation model called V1. This new model specializes in converting static images into short video clips, enabling users to animate either their own uploaded photos or visuals generated within the Midjourney platform into dynamic five-second videos. The feature is currently only accessible via the web and is free for all users on the platform.
V1 functions as an image-to-video tool, allowing users to either upload their own images or use ones created by other Midjourney models. From a single image, V1 generates four unique video clips, each lasting five seconds. Similar to Midjourney’s image-generation tools, V1 is exclusively accessible via Discord and is currently limited to web-based use during its initial rollout.
midjourney introduces video generation and it’s surpassing all my expectations. pic.twitter.com/lWqakbSTVV
— Phi Hoang (@apostraphi) June 18, 2025
Following the release of its AI video tools, Midjourney has announced future plans to work on AI models capable of generating 3D visualizations, along with real-time AI systems that can deliver instant results.
To access V1 at launch, the most affordable option is Midjourney’s Basic subscription, priced at $10 per month. Users subscribed to the $60 Pro tier or the $120 Mega tier can generate unlimited videos using the platform’s slower “Relax Mode.” Midjourney has also stated that it plans to reevaluate the pricing structure for its video generation models over the coming month.
Introducing our V1 Video Model. It's fun, easy, and beautiful. Available at 10$/month, it's the first video model for *everyone* and it's available now. pic.twitter.com/iBm0KAN8uy
— Midjourney (@midjourney) June 18, 2025
How to use the new V1 model:
The V1 model offers various customizable options, allowing users to fine-tune their video outputs to their preferences.
You can opt for an automatic mode that animates images with random motion, or switch to manual mode, where you can input detailed text instructions to define the exact type of animation you’d like to apply to your video.
Users have two video creation modes to choose from: Fast Mode and Relax Mode.
Fast Mode operates on a monthly GPU time allocation, where each image consumes one minute of GPU time, and generating a video takes about eight minutes. Once this GPU time limit is reached, users must wait until the next cycle to resume creating content.
In contrast, Relax Mode—exclusively accessible to Pro-tier members and higher—offers unlimited video generation without consuming GPU minutes. However, this comes with increased processing times, and it may take up to 10 minutes to complete a single video prompt.
