A powerful CLI tool for generating decentralized AI images and videos through the Openclaw Skills framework.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install sogni-gen
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install sogni-gen 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 Sogni Image & Video Generation?
Sogni Image & Video Generation is a professional-grade skill that leverages Sogni AI's decentralized GPU network to produce high-fidelity media content. By integrating this tool into your Openclaw Skills workflow, you gain access to a wide array of state-of-the-art models for text-to-image, text-to-video, and advanced image editing. This skill is designed for both human developers and AI agents, providing a robust interface for media creation without the need for local high-end hardware.
The utility goes beyond simple generation, offering specialized workflows for face transfer, photo restoration, and complex video manipulations. As a core component of the Openclaw Skills library, it provides a seamless bridge between local file management and decentralized AI compute, ensuring that generated assets are organized and easily accessible for downstream applications.
Sogni Image & Video Generation Use Cases
- Creating cinematic video sequences from simple text prompts or static reference images.
- Generating consistent subject portraits across multiple camera angles using the 360-degree sweep mode.
- Transforming user photos into stylized avatars through the photobooth face-transfer functionality.
- Restoring vintage and damaged photographs by leveraging advanced image-to-image editing models.
- Producing audio-driven animations using sound-to-video (s2v) workflows for realistic lip-syncing.
How Sogni Image & Video Generation Works
- The user or agent initiates a request via the CLI, specifying prompts, models, and reference files.
- The skill retrieves authentication tokens from the local Sogni credentials file to authorize the request.
- The command is transmitted to Sogni AI's decentralized network, where a specialized worker node processes the generation.
- Real-time progress is monitored, and the final media asset is generated as a URL or downloaded to a specified local path.
- Metadata regarding the render, including seeds and model parameters, is stored locally to allow for iterative editing or continuation.
Sogni Image & Video Generation Setup
To start using this skill within your Openclaw Skills environment, follow these steps:
- Obtain your credentials from the Sogni AI dashboard.
- Create a secure credentials file:
mkdir -p ~/.config/sogni
cat > ~/.config/sogni/credentials << 'EOF'
SOGNI_USERNAME=your_username
SOGNI_PASSWORD=your_password
EOF
chmod 600 ~/.config/sogni/credentials
- Install the skill via npm:
mkdir -p ~/.clawdbot/skills
cd ~/.clawdbot/skills
npm i sogni-gen
ln -sfn node_modules/sogni-gen sogni-gen
Sogni Image & Video Generation Data Schema & Taxonomy
The skill manages its operations through a structured set of files and directories within the Openclaw Skills ecosystem:
| Path | Purpose |
|---|---|
~/.config/sogni/credentials |
Stores encrypted username and password for API access. |
~/.config/sogni/last-render.json |
Persists metadata from the most recent generation for easy retrieval. |
~/.openclaw/openclaw.json |
Stores default plugin configurations such as model IDs and dimensions. |
~/.clawdbot/media/inbound |
Acts as the primary directory for locating user-provided images and audio. |
~/Downloads/sogni |
Default destination for assets generated via Model Context Protocol (MCP). |
Sogni Image & Video Generation Advanced Features
- Video-to-Video (V2V) transformation using ControlNet guidance for Canny, Pose, and Depth mapping.
- Automated scene continuation through built-in last-frame extraction and video concatenation wrappers.
- Deterministic seed strategies (prompt-hash) to ensure consistent results across repeated Openclaw Skills requests.
- LoRA support for fine-tuned style control and multiple-angle subject consistency.
- Smart video resizing that automatically adjusts dimensions to meet model-specific requirements while maintaining aspect ratios.
SKILL.md
Loading
Related Openclaw Skills
sogni-gen
A versatile AI skill for generating decentralized images, videos, and 360-degree turnarounds using Sogni AI's high-performance network.
LinkedIn Poster
A specialized skill for programmatically sharing text updates to LinkedIn personal profiles and company pages via OAuth 2.0.
Antigravity Sync
Automatically synchronize and configure Google Antigravity models and API quotas for your AI agent environment.
Bailian Web Search
A high-performance web search integration for AI agents powered by Alibaba's Bailian API.
Dify AI Application Development Skill
Dify is an open-source LLM application development platform designed to orchestrate AI workflows, agents, and RAG-based knowledge bases.
Warden Agent Builder
A comprehensive toolkit for developing, testing, and deploying original LangGraph-based AI agents within the Warden Protocol ecosystem.
METADATA
Featured*
