MOVA: Towards Scalable and Synchronized Video–Audio Generation

Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

A lightning fast audio upsampler.

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

DigThatData's Public Brainstorming space

System which logs and analyzes academic reading habits

contains many of my preliminary research ideas

Converting text-LMs into Visual Language Models

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

The most powerful local music generation model that outperforms most commercial alternatives

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

A template for research projects in computer science/machine learning using python and julia

A curated list of engineering blogs

The best ChatGPT that $100 can buy.

Wan: Open and Advanced Large-Scale Video Generative Models

Contexts Optical Compression

[CVPR 2024] Official repo for "InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model".

🚀 Efficient implementations of state-of-the-art linear attention models

SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）

My dotfiles, managed by stow

Train transformer language models with reinforcement learning.

Run SD1.x/2.x/3.x, SDXL, and FLUX.1 on your phone device

Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU/GPU inference.

Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis

[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official Implementation)