sogni-gen
Generate images **and videos** using Sogni AI's decentralized network, with local credential/config files and optional local media inputs. Ask the agent to "draw", "generate", "create an image", or "make a video/animate" from a prompt or reference image.
Why use this skill?
Integrate Sogni AI into OpenClaw to generate images and videos via decentralized GPUs. Fast, programmable, and easy to configure for your creative workflow.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/krunkosaurus/sogni-genWhat This Skill Does
The sogni-gen skill integrates your OpenClaw agent directly with the Sogni AI decentralized GPU network. This powerful capability allows you to generate high-quality images and videos without leaving your command-line workflow. By utilizing a distributed compute architecture, it provides a cost-effective and efficient way to turn text prompts into visual media. Whether you are generating creative assets, visualizing concepts, or producing short video animations, this skill handles the heavy lifting of credential management, model selection, and local file storage automatically.
Installation
To integrate this skill, ensure you have the OpenClaw CLI installed, then run the installation command:
clawhub install openclaw/skills/skills/krunkosaurus/sogni-gen
Post-installation, you must authenticate by visiting https://app.sogni.ai/. Create your credentials file at ~/.config/sogni/credentials with your SOGNI_USERNAME and SOGNI_PASSWORD, ensuring you set the file permissions to chmod 600 for security. If you are using an npm-based environment, you can alternatively install via npm i sogni-gen inside your .clawdbot/skills directory.
Use Cases
This skill is perfect for developers, designers, and creative professionals who need programmatic access to generative AI. Use it to generate consistent assets for UI prototypes, create training imagery for machine learning models, or produce 360-degree product views. The integration with local file paths makes it easy to pipe outputs directly into your project directories or build pipelines.
Example Prompts
- "Generate a 512x512 image of a futuristic cyberpunk city skyline with neon lights in a rainstorm."
- "Make a short video animation of a golden retriever running through a sunny meadow, use the turbo model."
- "Create a 360-degree rotation render of a minimalist ceramic vase, saving the output to my local downloads folder."
Tips & Limitations
- Efficiency: Always use the
--jsonflag when scripting to parse output URLs programmatically. - Storage: Monitor the
~/Downloads/sognidirectory if you are running frequent batch generations. - FFmpeg: If using
--angles-360-video, ensureffmpegis installed on your system path to assemble the frames into an MP4. - Costs: Keep an eye on your token balance by running
node sogni-gen.mjs --balanceto avoid unexpected interruptions during large batch operations. - Precision: Utilize the
--seedand--last-seedoptions to ensure consistency across multiple variations of the same image prompt.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-krunkosaurus-sogni-gen": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api