Midjourney has officially entered the AI video race with the launch of its first video generation model, V1. Announced on Wednesday, the new tool can transform static images into dynamic five-second clips.
V1 is an image-to-video model that produces four short five-second clips from a single input image. The feature is currently limited to Midjourney’s Discord server and is accessible via the web only. Users can upload their image or use one created with Midjourney’s earlier models to start generating videos.
Custom Animation Controls
There are two animation options with V1: an automatic mode that animates the image at random, and a manual mode that allows input-specific animation directions. There are also motion settings that can control both camera and subject movement by toggling between “low” and “high” motion. Each clip starts at five seconds and can be extended in four-second increments, up to 21 seconds in total.
You can watch some of V1’s creations here.
Pricing and Access
V1 is significantly more resource-intensive than image generation. Midjourney claims that each video generation costs about 8x more than a standard image. Basic plan subscribers ($10/month) have limited access, while Pro ($60/month) and Mega ($120/month) subscribers can generate unlimited videos in the slower “Relax” mode. The company plans to review and possibly adjust pricing over the next month.
Already has Positive Feedback
Initial feedback on V1 has been largely positive, with users praising the creativity of the clips. However, as with Midjourney’s image models, the output tends to lean toward the surreal and artistic rather than photorealistic. Whether V1 can compete on a technical level with more established video models remains to be seen.
Stay Connected with ProPakistani
Get the latest tech news, telecom insights, and product launches wherever you prefer.
Add ProPakistani to Preferred Sources and see more of our stories in Google Search and Top Stories.
