A comprehensive AI image processing toolset for automated background removal, facial clarity enhancement, and AI-generated background replacement.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tukeli-visual-api
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 tukeli-visual-api 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 Tukeli Visual API?
The Tukeli Visual API skill provides advanced computer vision capabilities directly to your AI agent environment. By leveraging the Tukeli REST API, this skill enables seamless image matting (removing backgrounds from portraits or objects), face enhancement for restoring low-quality photos, and sophisticated AI-driven background generation based on text prompts. As part of the broader ecosystem of Openclaw Skills, it empowers developers to build complex visual workflows without needing deep expertise in neural networks or GPU management.
This skill supports both local file uploads and image URLs, returning results as binary streams or Base64 encoded strings. It is designed for high-precision tasks such as hair-level portrait segmentation and professional-grade image restoration, making it an essential tool for automated media production.
Tukeli Visual API Use Cases
- Removing backgrounds from product photos for e-commerce listings.
- Enhancing blurry or low-resolution portraits into high-definition images.
- Generating professional AI backgrounds for transparent PNGs using text descriptions.
- Automating batch image processing workflows for media and marketing teams.
- Extracting high-precision hair-level masks for professional portrait editing.
How Tukeli Visual API Works
- The user provides an image via a local file path or a public URL and specifies the desired API action.
- The skill authenticates with the Tukeli cloud servers using a configured API key from the environment variables.
- For matting or face clearing, the API processes the request synchronously and returns the processed image data.
- For AI Background replacement, the skill submits an asynchronous task and retrieves a task ID.
- The skill then queries the task status until the AI-generated background is ready for download.
- Processed files are saved to the local directory with accompanying metadata for further integration into Openclaw Skills workflows.
Tukeli Visual API Setup
To get started with this skill, follow these installation steps:
- Sign up for an account at the Tukeli official website to obtain your API key.
- Add your key to your project environment configuration:
TUKELI_API_KEY=your_secret_api_key
- Install the required Python dependencies:
pip install -r scripts/requirements.txt
- Execute the processing script using the CLI:
python scripts/tukeli.py --api matting --image your_photo.jpg --output result.png
Tukeli Visual API Data Schema & Taxonomy
The skill organizes processed assets and tracking information as follows:
| Data Type | Specification |
|---|---|
| Supported Inputs | PNG, JPG, JPEG, BMP, GIF, WEBP |
| Output Directory | data/outputs/ |
| File Naming | {api_type}_{timestamp}.png |
| Metadata Storage | .meta.json file for every processed image |
The metadata includes critical taxonomy such as API endpoint used, processing duration, original file size, and the specific parameters applied during the transformation.
Tukeli Visual API Advanced Features
- Multi-mode Matting: Optimized algorithms for humans, objects, or specific head-area extraction.
- Asynchronous AI Generation: Support for complex text-to-image background generation with task polling.
- Image Refinement: Automated cropping of transparent whitespace and custom hex-code background filling.
- High-Resolution Support: Processes images up to 4096 x 4096 pixels and 25MB in size.
- Seamless Orchestration: Designed to work in tandem with other Openclaw Skills for end-to-end automated image editing pipelines.
SKILL.md
Loading
Related Openclaw Skills
Baidu Qianfan Search
A professional-grade integration for the Baidu Qianfan Enterprise Search API, enabling AI agents to perform advanced web, image, and video searches in Chinese.
Dependency Map Builder
A specialized skill for mapping cross-team dependencies and identifying project bottlenecks and risk chains.
Multi-Model Response Comparator
A benchmarking tool that executes prompts across multiple AI models to compare output quality, style, and cost-effectiveness.
Paper Review
Automate multi-stage academic paper reviews, checking for technical correctness, novelty, and citation accuracy across multiple disciplines.
Dependency Upgrade Briefing
A specialized AI agent skill designed to analyze and explain the benefits, risks, and rollback strategies of software dependency updates.
CPA Calculator Ecommerce
A powerful financial modeling tool to determine acquisition cost guardrails for ecommerce brands before scaling ad spend.
Featured*
