Text and image to video
Generate video in different ratios and styles from prompts or a starting image.
Tool profile · Video
Kuaishou's multimodal visual-generation platform for text-to-video, image-to-video, reference control, and image creation.
01 / Overview
02 / Core features
Generate video in different ratios and styles from prompts or a starting image.
Use people, objects, scenes, or multiple reference images to guide results.
Structure connected clips around scenes, actions, and camera relationships.
Create images in the same platform before moving into video generation.
03 / Use cases
Generate shot candidates from scripts or key visuals.
Use references to keep people and scenes more consistent.
Turn posters, illustrations, or product images into moving clips.
04 / Platforms and languages
Capabilities and credit rules may differ by region, model version, and account plan.
06 / Common questions
No. It also includes text-to-video, reference controls, and image-creation entry points.
Model, resolution, duration, campaigns, and account plans affect consumption; check the current generation panel.
It is better suited to generating and organizing shots; complete long-form work still needs scripting, editing, sound, and consistency management.
07 / Sources
Current generation entry points, models, and account features.
2026-08-08↗SourceKuaishou official Kling AI 3.0 announcementMultimodal video, image, and narrative-control capabilities.
2026-08-08↗SourceKuaishou investor-relations newsOfficial announcements for Kling product and model updates.
2026-08-08↗