Remove/Change background of video.

diffusion-based Image Restoration model

Upscale images for better quality

Generate high-quality predictions from images

A gradio demo for Posterior-Mean Rectified Flow (PMRF)

Face Recognition

3D Passive Face Liveness Detection (Face Anti-Spoofing)

ML-powered speech recognition directly in your browser

Realtime implementation of Whisper large turbo

Transcribe audio from files, microphone, or YouTube

Detect objects in images and videos

Quickly edit the expression of a face

Generate a video from a prompt and an image

Generate captions for images in various styles

Swap faces in images and enhance them if desired

Create a large, deduplicated dataset for LLM pre-training

Generate detailed image captions

VLMEvalKit Eval Results in video understanding benchmark

Enlarge images with control