Skip to main content
Video nodes generate video from text and images and transform existing clips — editing, merging, subtitling, removing backgrounds, upscaling, extracting frames, and lipsync. Most run on a model you select in the node’s config and consume credits per run. Connect a video source (a generator, an upload, or an upstream node) into a transform node, then chain transforms to build a pipeline.

Generate video

Create video from a text prompt and/or a first-frame image, with brand context.

Edit video

Modify an existing video based on text instructions.

Merge videos

Combine multiple clips into one video with configurable transitions.

Add video subtitles

Add subtitles or captions with optional styling and burn-in.

Remove video background

Strip the background from a video for compositing and overlays.

Upscale video

Increase the resolution of a video with an AI upscaler.

Extract video frame

Pull a single frame from a video as an image.

Generate lipsync

Drive a face from an image or video with an audio track.