Kling AI 4.0 debuts with 30-second clips, stereo audio, but doesn't outpace Wan 3.0 and Seedance 2.5
The Decoder · rss · 2026-10-20
Kuaishou's Kling AI released version 4.0 of its video generator, adding clips up to 30 seconds, 10-keyframe image input, 8,000-token prompt comprehension, stereo audio, multilingual lip sync, and a lighter Flash variant.
In comparisons against Wan 3.0 and Seedance 2.5, Kling 4.0 holds its own but doesn't pull ahead — an early sign the breakneck pace of AI video model progress may be leveling off.
More from Multimodal
- Gojo project generates 108 ornament designs from 36 skeletons with hierarchical pattern-aware coloring — debreuil · 2026-10-20
- HF co-founder: Most-derived model on the Hub isn't Llama—it's Germany's FLUX.1-dev — robrombach · 2026-10-20
- FLUX 3 Max image-to-video: writing prompts as shot lists works best — OdinLovis · 2026-10-20
- Three practical rules for AI video generation: one line per character, never cut to new faces — OdinLovis · 2026-10-20
- Wabi launch video frames revealed: mini-apps, session UI and Y2K visuals — joonasvirtanen · 2026-10-20
- fal and BFL launch FLUX 3 Max: tied #1 in image-to-video quality, ~12s generation, 75% off — gorkem · 2026-10-20