KlingAI
#17 in Text-to-Videokling · since 2024-06-06 · 2× · last seen Jun 29, 2026
17
Momentum
KlingAI is a text-to-video generator by Chinese company Kuaishou Technology, available globally since June 2024. The model is based on a diffusion-transformer architecture (DiT) with a proprietary 3D variational autoencoder (VAE) for spatiotemporal compression. The platform uses a credit-based subscription model and supports text-to-video, image-to-video, and (since version 2.6) native single-pass audio generation. Since Kling 3.0 (February 2026), native 4K at 60 fps is available; earlier versions (up to 2.6) produce videos at up to 1080p and 30 fps.
Momentum trend
04.04.03.07.
Features
| Resolution | Up to 1080p (480p/720p/1080p) for models v1–v2.6; from Kling 3.0 (Feb. 2026), native 4K (3840×2160). Free tier is limited to max. 360p–720p. |
| Video Quality/Frame Rate | Up to Kling 2.6: 1080p at 30 fps (Standard and Professional mode). From Kling 3.0: up to 4K (3840×2160) at 30–60 fps. Aspect ratios: 16:9, 9:16, 1:1. |