Phosor AI for Openclaw

Phosor AI is a versatile video generation skill that enables text-to-video and image-to-video workflows with support for custom LoRA styles.

jasonstarlight
v1.0.2
Mar 23, 2026
0
1.3k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install phosor-ai

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install phosor-ai using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Phosor AI?

Phosor AI is a professional-grade video generation tool designed to integrate seamlessly into AI workflows. It leverages advanced models like Wan 2.2 14B to transform text prompts and static images into dynamic, high-quality video content. By utilizing Openclaw Skills, developers can programmatically control video parameters including resolution, frame rates, and guidance scales.

What sets this skill apart is its deep support for custom LoRA (Low-Rank Adaptation) models. Users can upload their own style weights or import them from external URLs to ensure their generated videos maintain a consistent aesthetic or brand identity. With a robust CLI client and comprehensive job management features, it is built for both rapid prototyping and automated media production pipelines.

Phosor AI Use Cases

  • Creating high-quality marketing videos from text descriptions using Openclaw Skills.
  • Animating static product photos into cinematic video clips for ecommerce.
  • Applying specialized artistic styles to AI-generated video via custom LoRA models.
  • Automating bulk video production tasks through scheduled CLI commands.
  • Integrating AI video generation into existing creative dashboards or automated pipelines.

How Phosor AI Works

  1. The user authenticates with the Phosor platform using a secure API key.
  2. For image-to-video tasks, the user first uploads a source image to receive a specific S3 key.
  3. A video generation job is submitted via the CLI, specifying parameters like prompt, resolution, and optional LoRA IDs.
  4. The system tracks the job through a PENDING and PROCESSING lifecycle, storing state in a local JSON file.
  5. The user polls for job completion or fetches the final video URL once the state transitions to COMPLETED.

Phosor AI Setup

To get started with this skill, follow these steps:

  1. Sign up at phosor.ai and generate your API key in Settings → API Keys.
  2. Configure your environment variables:
export PHOSOR_API_KEY="your-api-key-here"
  1. Ensure you have python3 installed to run the client script located at scripts/phosor_client.py.
  2. Verify your connection:
python3 scripts/phosor_client.py check-key

Phosor AI Data Schema & Taxonomy

The skill manages job states and assets using a structured local and remote approach:

Data Type Description
phosor-pending.json Local file tracking IDs of active generation jobs.
request_id Unique identifier for tracking T2V or I2V job status.
s3_key Returned after upload-image; used as the source for video animation.
lora_id Reference ID for uploaded or imported LoRA style models.
JSON stdout All CLI commands return parseable JSON for easy integration with other Openclaw Skills.

Phosor AI Advanced Features

  • Custom LoRA Management: Upload dual .safetensors (high/low noise) or import directly from external URLs.
  • Precise Frame Alignment: Supports specific frame intervals (1 + 4*k) for optimized playback and server processing.
  • Multi-Resolution Support: Native handling of landscape and portrait orientations from 480p up to 1080p.
  • Local State Tracking: Automated polling and cleanup of job history via the poll and history commands.
  • Quota Monitoring: Built-in commands to check real-time credit usage and API limits.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*