mirror of
https://github.com/openclaw/openclaw.git
synced 2026-04-19 05:01:15 +00:00
1.7 KiB
1.7 KiB
title, summary, read_when
| title | summary | read_when | |||
|---|---|---|---|---|---|
| Runway | Runway video generation setup in OpenClaw |
|
Runway
OpenClaw ships a bundled runway provider for hosted video generation.
- Provider:
runway - Auth:
RUNWAYML_API_SECRET(canonical;RUNWAY_API_KEYalso works) - API: Runway task-based video generation API
Quick start
- Set the API key:
openclaw onboard --auth-choice runway-api-key
- Set a default video model:
{
agents: {
defaults: {
videoGenerationModel: {
primary: "runway/gen4.5",
},
},
},
}
Video generation
The bundled runway video-generation provider defaults to runway/gen4.5.
- Modes: text-to-video, single-image image-to-video, and single-video video-to-video
- Runtime: async task submit + poll via
GET /v1/tasks/{id} - Agent sessions:
video_generatestarts a background task, and later calls in the same session now return active-task status instead of spawning a duplicate run - Status lookup:
video_generate action=status - Local image/video references: supported via data URIs
- Current video-to-video caveat: OpenClaw currently requires
runway/gen4_alephfor video inputs - Current text-to-video caveat: OpenClaw currently exposes
16:9and9:16for text-only runs
To use Runway as the default video provider:
{
agents: {
defaults: {
videoGenerationModel: {
primary: "runway/gen4.5",
},
},
},
}