Resources for developers and teams
Explore tutorials on agentic desktop automation, PixLab APIs and developer tools, alongside guides to AI, computer vision and vision language models (VLMs). Find code examples, setup instructions and practical advice for your projects.
Find code examples, integration walkthroughs and practical guides, organized by topic.
Python and JavaScript guides to ID document scanning and image processing, from your first request to bulk workflows.
ID document scanning
Python + JavaScript
Scan passports and ID cards with the DOCSCAN API. Follow the request from image input to extracted fields your application can use.
Background removal
High-volume image processing
Use the background removal API to prepare product images and catalog assets. Start with one image, then build a bulk processing workflow.
Text and watermark removal
Python + JavaScript
Clean captions, labels and watermarks you have permission to remove with the text and watermark removal API. Save the finished images for your website or store.
Step-by-step guides to desktop automation, facial authentication and browser video editing.
Desktop automation
Windows + macOS
Use the Think-Act Desktop Agent for writing, OCR, document work and screen recording. Start with a defined task and add tools when the workflow needs them.
Facial authentication
fio.js + backend integration
Add FACEIO facial authentication to an existing website or web app. Connect face enrollment and returning-user login to the accounts and sessions your backend manages.
Browser video editing
MP4 + WebM export
Work through a video project in the PixLab Video Editor, from your first clip to a finished export. Prepare videos for your website, social channels or marketing campaigns.
Keep the reference close
Use these references alongside the tutorials to check authentication, request parameters, model options and response formats.
Understand API keys, HTTP requests and JSON responses before writing your first integration.
Read the REST API GuideCheck model options and request formats for document questions, OCR and structured extraction.
Read the VLM API ReferenceFind language-specific examples you can adapt to your application and compare with the endpoint documentation.
Browse Code ExamplesBuild with PixLab
Working through a PixLab API tutorial? Get your API key and start a 7-day free trial in the Console. Test the examples with your own files and review the plan limits before running a larger workload.