ViGen

ViGen is a unified platform that provides access to multiple AI generative models in one place. Users can generate images from text prompts, create short video clips, convert text to natural speech, and transform songs into MIDI notation using a lightweight 0.9B model. The platform features a simple interface where users describe what they want and the AI generates it.

Key features include image generation with various aspect ratios (3:4, 1:1, 4:3, 16:9, 9:16), video generation from prompts or still images, text-to-speech conversion, and Songscription for audio-to-MIDI conversion. ViGen integrates multiple model options and showcases recent creations to inspire users. Some features are currently in beta (Video Generation and Text to Speech marked as "Coming soon").

ViGen is designed for creators, designers, musicians, and anyone looking to generate multimedia content quickly without requiring technical expertise. It's ideal for rapid prototyping, content creation, and exploring AI-generated media.