OneFormer
Segment images into objects, instances, or scenes
Match images to find similar pictures
4k Image from text in 5 second
Transcribe or translate audio from microphone, file, or YouTube
Convert audio to subtitles
Transcribe audio to text from microphone, file, or YouTube video
Transcribe and translate YouTube video audio
Video Dubbing with Open Source Projects
Transcribe or translate audio and YouTube videos to text
Predict depth map from a single image
Transcribe audio files into written text
Create lineβart from photos with artistic filters
Generate 3D room layout from an RGB panorama image
Generate interactive 3D depth view from a photo