Kling: Kling O1 Image API

Kling Image O1 (Omni Image 1.0) is a groundbreaking, unified multimodal foundation model built on the Multimodal Visual Language (MVL) framework. Unlike traditional models that separate text-to-image from image editing, O1 integrates generation, transformation, and semantic understanding into a single neural architecture. It treats text, multiple reference images, and even hand-drawn doodles as simultaneous inputs, allowing for "Director-level" control. O1 is specifically designed for complex "Contextual Transplantation"—for example, taking a specific character from @Image1, changing their outfit to match @Image2, and placing them in the environment of @Image3—all while maintaining pixel-perfect lighting and structural consistency.

• Input: text, image
• Output: image
• File input: Supported
• Released: 2025-11-30
• Knowledge cutoff: 2026-02-28