Mage-VL
Codec-native video & image understanding with Mage-VL 4B
Create multiple diagram types instantly from JSON!
A Step Towards Music Generation Foundation Model
Extract and visualize knowledge graphs from text in multiple languages
Fast image relighting using Latent Bridge Matching
Convert document images into structured text and markdown
Refine your prompts
Generate customized images from text and reference photo
Generate voice-cloned audio from your text and voice sample
Create a 3D model from an image in 10 seconds!
In-browser background removal
Generate images from text or image-derived prompts
Generate images in the style of a reference image
Generate images from text prompts
Generate captions, detections, and OCR from an image
Apply the motion of a video on a portrait