Kling 4.0 launches: 30-second shots, 10 keyframes, and 15 references in one scene
miilesus · x · 2026-10-24
Kling AI has broken its long silence and released Kling 4.0, with support for 30-second clips, high speed, and strong motion consistency. The video platform each::labs went live with it day one, highlighting the key capabilities:
- Mix up to 15 references in a single scene — cast, props, and voices generated together
- Call every beat with up to 10 keyframes
- Go up to 30 seconds in one shot
One prompt now brings your whole cast, props, and voices into a single generation — a step change toward long-form narrative video generation.
Related event: Kling 4.0 Launched: 30-Second Clips, 10 Keyframes, 15 References(2 posts)→
More from Multimodal
- Character LoRA trained on 21 images fails across models—training setup questioned — IntrovertedOtaku03 · 2026-10-24
- Tencent's Hy-Nomas video world model runs natively in ComfyUI on 12GB VRAM — LatentSpacer · 2026-10-24
- Video models replace NeRF/3DGS pipelines: single-frame novel view synthesis, open-source soon — jonstephens85 · 2026-10-24
- MOSS-Image LoRA flood: photography sliders, art styles, and Edit capability merged into ComfyUI — optimisticalish · 2026-10-24
- Recreating PS2-Era Harry Potter With FastH3-V2 in 4 Steps — aziib · 2026-10-24
- A Full AI Music Video Made Locally on DGX Spark With MiniMax H3 — Ornery-Block-3522 · 2026-10-24