AI Agent Skills

A unified inference and post-training framework for accelerated video generation.

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.