Kling has launched the multimodal video generator Kling O1 as part of its announced omni-week initiative for creators worldwide users.

Overview

Kling O1 is described as a multimodal generative model able to combine diverse reference materials to synthesize video outputs matching provided prompts.

Users can supply text, images, and existing video clips as references, and the model interprets those inputs jointly to generate coherent new video sequences.

Input formats and capabilities

The system accepts multiple reference formats, including textual prompts, static images, and short video clips, allowing cross-modal alignment during synthesis.

• Text prompts to define narrative, style, or motion guidance for the generated video.
• Images used as visual references for style, color palettes, or subject appearance.
• Video clips provided to convey movement, timing, or scene continuity for synthesis.

Pricing and access

One generated video is priced at 40 credits, according to Kling’s announcement; the platform uses a credit-based billing model for content creation.

The company announced Kling O1 during the omni-week showcase and indicated availability through its official web interface without publishing further distribution specifics.

Documentation and usage

Kling recommends consulting the technical documentation and usage policies for guidance on content restrictions, format specifications, and expected credit consumption.