A local image generation workflow supporting Stable Diffusion 1.5 and SDXL models integrated with non-blocking subagent execution.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-generator
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 image-generator 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 Image Generator Skill?
The Image Generator Skill enables your AI agent to produce visual content directly on local hardware using industry-standard Stable Diffusion models. By leveraging the diffusers library, this skill allows for the creation of diverse artistic styles—ranging from Pixar-inspired 3D renders to traditional Ukiyo-e—without the need for external cloud subscriptions. As a native extension for Openclaw Skills, it provides a privacy-focused solution for teams needing on-demand graphics.
This skill is built for efficiency and responsiveness. It utilizes a subagent architecture to ensure that the primary agent remains available for conversation while the computationally intensive image generation process runs in the background. Whether you are using the lightweight SD 1.5 for speed or the high-fidelity SDXL for detail, this skill handles model loading, inference, and image delivery seamlessly.
Image Generator Skill Use Cases
- Creating custom illustrations or concept art during live chat sessions.
- Automating the generation of social media assets or marketing imagery.
- Developing a private, local alternative to paid AI image generation services.
- Sending AI-generated visual reports or diagrams to enterprise collaboration tools like Feishu.
How Image Generator Skill Works
- The agent detects an image generation request such as "draw a cat" or "generate a 3D character."
- It optionally retrieves style templates from a local markdown file to enhance the user's prompt.
- A dedicated subagent is spawned using the sessions_spawn function to prevent blocking the main chat interface.
- The subagent loads the specified model (defaulting to SD 1.5) and optimizes it for the local CPU environment.
- The image is synthesized, saved to a temporary directory, and then uploaded to the Feishu platform.
- Finally, the skill sends the generated image directly to a designated group chat via the Feishu API.
Image Generator Skill Setup
To use this skill within your Openclaw Skills environment, ensure you have the necessary Python dependencies installed:
pip install torch diffusers transformers accelerate requests
You must also configure your Feishu App ID and App Secret within the skill script to enable image delivery to your team channels. For optimal performance on standard hardware, the skill is pre-configured to utilize 8 CPU cores.
Image Generator Skill Data Schema & Taxonomy
The skill manages prompt templates and temporary assets according to the following structure:
| Data Type | Path / Identifier | Description |
|---|---|---|
| Prompt Templates | ~/.openclaw/workspace/skills/image-prompts/SKILL.md |
Contains style presets like 'Plushie' or 'Crystal' |
| Temporary Images | /tmp/xxx.png |
Local storage path for generated files before upload |
| Feishu Integration | chat_id |
The destination group chat ID for the final image delivery |
Image Generator Skill Advanced Features
- Subagent Multi-tasking: Uses non-blocking runtimes so the agent can handle other tasks while generating images.
- Dual Model Support: Toggle between SD 1.5 (fast, ~4GB RAM) and SDXL (high quality, ~13GB RAM) based on hardware availability.
- CPU Thread Optimization: Specifically tuned for local execution using
torch.set_num_threads(8)to maximize performance on multi-core processors. - Styled Prompting: Automatic integration of style-specific keywords to improve visual output quality without user input.
SKILL.md
Loading
Related Openclaw Skills
Exa Search & Research MCP
A powerful neural search integration that enables AI agents to perform advanced web crawling and deep research using the Exa protocol.
OpenProse AI Virtual Machine
OpenProse is a specialized programming language that transforms LLMs into high-fidelity virtual machines capable of orchestrating complex multi-agent sessions.
Tunneling (TinyFish)
A seamless SSH-based tunneling skill to create public HTTPS URLs for local applications without any signup or software installation.
Manifold Markets Prediction Trading
A comprehensive interface for searching, analyzing, and executing trades on Manifold Markets prediction platforms.
River Memory
A local semantic memory system utilizing Ollama to provide vector-based search and storage capabilities for AI agents.
Gradient Inference for DigitalOcean
Integrate DigitalOcean's Gradient Serverless Inference into your AI agent workflows for high-performance LLM chat and image generation.
Featured*
