Kling AI officially launches Kling 4.0: 15 references per task, 30s clips, 10 keyframes
testingcatalog · x · 2026-10-23
Kling AI has officially released Kling 4.0, its next-gen video model focused on control and consistency:
- Omni Reference combines up to 15 images, videos, subjects, or voices in a single task.
- Each generation runs up to 30 seconds and supports up to 10 keyframes for controlled scene progression.
The launch page also showcases Kling Image 3.0 (native 4K, series generation), an agentic Canvas creation workflow, and MCP/CLI for batch automated generation.
More from Multimodal
- Blender 5.2's new SDF Grid makes volumetric slicing trivial, in both directions — 5agado · 2026-10-23
- MOSS Image base model showcase: photoreal outputs, full reproducible settings — COMPLOGICGADH · 2026-10-23
- Pruna's P-Video-2-Pro-Avatar ships on MiniMax H3 — and the docs' 4K is an upscale of 768p — neurocartel · 2026-10-23
- Kling 4.0 hands-on: multi-shot cyberpunk robot demo shows strong character consistency — testingcatalog · 2026-10-23
- Run Lola Run director Tom Tykwer uses Seedance in hybrid AI filmmaking experiment — Uncanny_Harry · 2026-10-23
- "Still Worth Something" S01E01: a Pixar-style fully AI-animated comedy short — LPGroves · 2026-10-23