Model index
Kuaishou·Kling

Kling AI 3.0

The native multimodal 3.0 line unifies image, video, and audio understanding, generation, and editing in narratives up to 15 seconds.

CurrentVideo generationImage generationMultimodalWeights not released
MODEL NUMBER178
Release date
2026-02-05
Organization
Kuaishou
Family
Kling
01

Specifications

Only published specifications are shown.

Input modalities
Text · Image · Audio · Video
Output modalities
Video · Audio · Image
Open weights
No
Status
Current
02

Overview

Overview

The native multimodal 3.0 line unifies image, video, and audio understanding, generation, and editing in narratives up to 15 seconds.

03

Changes from predecessor

Compared with Kling 2.6

PreviousKling 2.6 · ctx
CurrentKling AI 3.0 · ctx
New capabilities Multi-shot narrative Character consistency
04

Architecture & capabilities

Key capabilities

Multi-shot narrativeNative audioVideo editingCharacter consistency
05

Release history

General release

Kuaishou launched the Kling AI 3.0 multimodal line.

View source
06

Related models

Select a card to view the related model.

07

Sources