Change Log

Music Video Sequence creates music videos with unique moments and settings. It analyzes the structure and content of your sound to map the visuals to your song.

• Access: Open Music Video Sequence in the Dashboard Workflows.

• Modes: choose Generate to create from audio and description alone, Reference to guide each clip with a reference image, or Restyle to restyle your image using your aesthetic prompt and sound.

• Length and quality: generate videos from 30 seconds up to 4 minutes, with a choice of aspect ratios and resolutions, with Refined or Fast quality.

• Description: describe your subject, action, setting and aesthetic. Or create without a prompt and let the sound control the video. 

Example prompt:
Subject:  “A woman with close-cropped silver hair in a weathered leather jacket, walking through rain-slicked city streets at night, standing on a rooftop at dawn with the wind pulling at her jacket, catching a train in a crowded subway station.”
Aesthetic: Neo-noir R&B visual. Teal-and-amber grade, anamorphic bloom, 35mm grain.

Read the guide → Music Video Sequence: Create music videos shaped by your sound

Lyric Video is a new Kaiber-developed workflow It analyses your song and creates a music video with timed lyrics built right into the shots.

Access: Open Lyric Video in the Dashboard Workflows.

Lyrics: automatically transcribed from your audio. Check them over and make any edits before you generate.

Trim your track: select just the section you want to use.

Reference image: add an optional image to guide the content and style of your video.

Description: describe what you want to see and how your lyrics should appear in the scene. Your words become part of the world of the video, painted on walls, formed in the sky, and more.

Sample prompts:
"A station departure board flips through the lyrics in long continuous shots."
"A man walks through city streets, the lyrics are spray-painted in graffiti on the walls of buildings."

Guide How to Create Lyric Videos in Kaiber

OpenAI's newest image model, now available in Kaiber.

GPT Image 2.5 upgrades GPT Image 2 for text to image and precise image editing with strong preservation of faces, products, details and style from your reference images.

Two versions to choose from:

• Flare: the fast option. Great for quick iterations, everyday generations, and testing ideas.

• Sunburst: the precision option. Slower, but built for polished, detailed work where every edit needs to land exactly.

Access: Add a Create Image Flow to the Canvas and choose GPT Image from the menu. Open Advanced Features at the bottom of the flow to toggle between Flare or Sunburst