OmniGen2: Unified Image Understanding and Generation.
Hand-controlled arpeggiator, drum machine, and visualizer
Audio Conditioned LipSync with Latent Diffusion Models
NotebookLM conversational speech model
Voice Clone AI Podcast Generator with Chatterbox
Segment and extract objects from images
Fast image relighting using Latent Bridge Matching
A Unified Framework for Image Customization
Generate images and visualize concepts within them
Generate realistic talking video from an image and audio
Generate images and process numbers visually
Demo for Aero-1-Audio
Generate high-quality images from text descriptions