od Kling Direct
Kling V3 Standard via direct API — 720p text-to-video (5/10/15s)
Szczegółowa treść dla tego modelu pojawi się wkrótce.
Kling Direct
Kling V3 native 4K text-to-video via direct API (3-15s)
Kling Direct
Kling V3 Pro via direct API — 1080p image-to-video (5/10s)
FAL AI (ByteDance)
ByteDance motion transfer — full body, expressions, lip movement from driving video to any character (humans, animals, cartoons)
FAL AI (Seedance)
ByteDance Seedance 2.0 via FAL — multimodal ref system: up to 9 images + 3 videos + 3 audio, native audio