Compute normals for images and videos
Find similar images from a collection
Recognize micro-expressions in images
Visual Retrieval with ColPali and Vespa
Identify characters from Peaky Blinders
Use hand gestures to type on a virtual keyboard
Generate mask from image
Enhance and upscale images, especially faces
Apply artistic style to your photos
Extract text from images using OCR
Complete depth for images using sparse depth maps
Swap faces in images
Find images matching a text query
StableNormal is a powerful AI tool designed to compute normals for images and videos. It provides a robust solution for generating high-quality normal maps, which are essential for various applications in computer vision, graphics, and image processing. Normal maps are used to add detail to surfaces or to simulate complex lighting effects, making StableNormal a versatile tool for both professionals and enthusiasts.
• High-Quality Normal Maps: Generates precise and detailed normal maps from images and video frames.
• Support for Multiple Formats: Works seamlessly with popular image and video formats.
• User-Friendly Interface: Intuitive design for easy navigation and customization.
• Batch Processing: Process multiple files simultaneously to save time.
• Real-Time Preview: Preview normal maps before exporting.
• Customizable Settings: Adjust parameters to achieve desired results.
• Cross-Platform Compatibility: Available on Windows, macOS, and Linux.
What file formats does StableNormal support?
StableNormal supports common image formats like PNG, JPG, and BMP, as well as video formats such as MP4, AVI, and MOV.
Can I process multiple files at once?
Yes, StableNormal offers batch processing, allowing you to compute normals for multiple files simultaneously.
How do I customize the output settings?
You can adjust settings like resolution, smoothing, and detail levels in the "Settings" menu before computing the normal maps.