Video Generation node

The Video Generation node produces a video clip from a text prompt using a dedicated video model.

Handles

Handle	Purpose
prompt	The text prompt describing the clip
first	The starting frame (image)
last	The ending frame (image)
references	Reference images or clips (reference-to-video)

Configuration

• Model — the video model.
• Aspect ratio — e.g. 16:9, 9:16.
• Resolution — e.g. 1280x720.
• Duration — clip length in seconds.
• FPS — frames per second.
• Seed — deterministic output.
• Generate audio — whether to synthesize audio with the clip.

Important: model capabilities

Video models differ in what inputs they accept:

• Veo 3.0/3.1 — text + first/last frame. It does not accept arbitrary reference images.
• Kling t2v — text only. Kling i2v — a single starting image.
• MiniMax H3 — image-to-video (a single starting image), no references.
• Wan 3.0 Video — the reference-to-video model: accepts images and clips.

The node warns — and the engine fails fast with an actionable message — when you wire references into a model that cannot consume them.

Example — text + first frame

prompt: "A drone flyover of the coastline at golden hour"
first: <generated or uploaded image>
model: alibaba/wan-v3.0-video

Story continuation

The node also emits the clip’s first and last frame as images, so a second Video node can start where the first ended (wire First frame / Last frame source handles into the next node’s first/last targets).

Notes

• Video generation is premium — a single clip can cost over €1, and the node card shows a badge to warn you.
• Generated clips are saved to the node’s artifact history.

Related

• Merge Videos — concatenate clips.
• Image Generation — producing start/end frames.