Kuaishou's Kling released Kling 3.0 Turbo, the next generation of its video generation model. The biggest innovation: a "two-stage workflow" — first generate a fast preview, then refine to cinema-quality — that decouples iteration speed from final quality.
The two-stage workflow:
- Stage 1: "Fast preview" — a 4-step distilled model that generates a 1080p video in 1 second. Quality is "rough but coherent," suitable for rapid iteration and idea validation.
- Stage 2: "Cinema final" — a 32-step full model that takes the preview and refines it to 4K cinema quality. The refinement is "preview-conditioned" — it preserves the structure of the preview but adds fine details, lighting, and motion smoothness.
The benchmark: on the internal "production quality" benchmark, Kling 3.0 Turbo's "Cinema final" output scores 84.7, on par with Sora 2 and Veo 2. The "Fast preview" scores 71.3, sufficient for idea validation.
The commercial angle: Kling 3.0 Turbo is available via Kuaishou's API at $0.04 per second of preview + $0.12 per second of final. The pricing model encourages iteration — users can generate many previews cheaply, then commit to the more expensive final only when satisfied.
The bigger takeaway: "two-stage video generation" is the right architecture for creative workflows. Traditional single-stage generation forces users to "commit" to a 30-second video before seeing it, leading to wasted compute and time. The preview-final split decouples iteration from finalization, and the "preview-conditioned refinement" preserves the user's creative intent. For the industry, this is the workflow that creative professionals will demand.