Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates images using Seedream4.5 and videos using Kling models through LiblibAI's API. Supports text-to-image, text-to-video, and image-to-video workflows via a CLI script. Tasks run asynchronously with automatic polling until results are ready.
Combines image and video generation in a single CLI with automatic async polling, eliminating the need to manually check task status or use separate tools for each modality.
When to use it
- Generating concept art from a text description
- Animating a static photo into a short video clip
- Creating illustrations for a blog post or slide deck
- Producing a promotional video clip from a written prompt
- Batch generating multiple image variations for a design review
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate a 5-second video of a rocket launching into space
- 1Run the text2video command with the prompt and --duration 5 flag
- 2Receive a generateUuid from the API submission response
- 3Poll /api/generate/status automatically until the task completes
- 4Extract the videoUrl from the completed task result
A URL to the generated 5-second video file, valid for 7 days
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.