What’s New in v5.5 / v5.6

This release introduces major improvements in audio realism and cinematic camera control, making generated videos feel more complete and production-ready.

✨ Highlights

1) Audio-Visual Synchronization (Full Sound Field)

v5.5 / v5.6 now supports a complete sound field, including:

• BGM (Background Music)
• SFX (Sound Effects)
• Character Dialogues / Voice Lines

Result: videos are richer, more immersive, and audio matches visuals more naturally.

2) Multi-Shot Camera Control (Cinematic Cuts)

You can now generate multi-shot sequences with stronger control over lens language.

Input format:

1 image + 1 description + Multi-shot enabled

What improves: - More abundant lens language design - Better camera movement - Clear shot switching / scene transitions - More flexible shot scale changes (wide → close-up → aerial, etc.)

Examples of supported camera language: - Push-in / pull-out - Cut to next shot - Switching perspectives - Shot scale changes

🎬 Example: Multi-Shot Prompting

Prompt

The video shows A close-up shot shows a man with reddish-brown hair and a beard, wearing a black shirt and a red earpiece in his left ear. He looks slightly off-camera to the right. He says, “i didn’t have any choices.”. Cut to the next scene, a close-up shot of a blonde woman looking directly ahead. The back of the man’s head is visible in the foreground on the left. The woman says angrily, “Sorry, you gotta tell the judge.” Cut to the next scene, a close-up shot of the man with reddish-brown hair and a beard. The back of the woman’s head is visible in the foreground on the left. The man says sadly, “you are my sunshine”. Cut to the next scene, a close-up shot of the blonde woman looking directly ahead. The back of the man’s head is visible in the foreground on the left. The woman says calmly,”fine”.

Example Output (Multi-Shot Structure)

• Shot 1: Wide shot of the predator sprinting.
• Shot 2: Close-up of the prey darting across the grass.
• Shot 3: Aerial shot of the chase.
  Audio: rapid footsteps, predator growling, prey’s frantic breathing.

🧠 Prompt Idea

She can not stand her work and she is going to quit and yell in the office.

With multi-shot enabled, this can become a cinematic sequence like: - Shot 1: Wide shot of a busy office with tense ambient noise. - Shot 2: Medium shot of her clenching her fists at her desk. - Shot 3: Close-up as she stands up and yells. - Shot 4: Reaction shots of coworkers turning around in shock. - Audio: office ambience + footsteps + chair scrape + angry dialogue + tense BGM