netflix/void-model
Video-to-Video • Updated • 951
Load and run a web-based application
Analyze video virality potential and receive feedback
Extract text from images with bounding boxes
Count people entering and exiting using video
Detect and count boxes in images and videos
Search images using text or upload an image to find similar ones
Predict depth map from a single image
Kontext image editing on FLUX[dev]
Find similar images by selecting regions