The V5.5 model comes with 2 major highlights, upgrading AI videos from "moving images" to storytelling content:
<aside> 💡
1. Audio-Visual Synchronization
</aside>
1 image + 1 description + Auto-Sound enabled = ?
💬 V5
Visuals Clips with music that barely matches the Clips.
✅ V5.5
A complete sound field including BGM, SFX, and character dialogues, making the video richer and more comprehensive in terms of audio.
<aside> 💡
2. Multi-Shot Camera Control
</aside>
💬 V5
1 image + 1 description + No Multi-shot function
= Single-shot visuals
✅ V5.5
1 image + 1 description + Multi-shot enabled
= More abundant lens language design, including push-in, switching, and shot scale changes.
PixVerse Website → Video → Model Select V5.5
Enable Audio or Multi-Shot to maximize your experience.
A girl stands at the airport exit where people come and go, she is holding a piece of paper with "Jimmy" written in lipstick on it, she is waiting and ready to pick Jimmy up and suddenly a wind blows the paper away.
V5 model, image2video
single shot, no sound
PixVerse_V5_Image_Text_540P_A_girl_stands_at_t.mp4
V5.5, image2video
enabled Audio and Multi-shot