[NeurIPS 2024] Boosting the performance of consistency models with PCM!

[CVPR2024] Official PyTorch implementation of "Contrastive Denoising Score(CDS) for Text-guided Latent Diffusion Image Editing"

My take on E(n) Equivariant Graph Neural Networks

Exploration into the Scaling Value Iteration Networks paper, from Schmidhuber's group

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

[CVPR'23] MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation

KandinskyVideo — multilingual end-to-end text2video latent diffusion model

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Official PyTorch implementation for the paper Minimizing Trajectory Curvature of ODE-based Generative Models, ICML 2023

The codebase of our paper "Improving the Training of Rectified Flows"

Light and Optimal Schrödinger Bridge Matching (ICML 2024) official PyTorch implementation=

PyTorch Implementation of Diffusion Schrodinger Bridge Matching

Text-to-Music Generation with Rectified Flow Transformers

PyTorch implementation of Real-ESRGAN model

Model for watermark classification implemented with PyTorch

Code for "Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation" @ NeurIPS 2023

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

[IJCAI-24] Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting

Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)

Scaling Diffusion Transformers with Mixture of Experts

[CVPR2024] Official implementation of High-fidelity Person-centric Subject-to-Image Synthesis.

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Official Github Repo for Neurips 2024 Paper Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment

Audio Prompt Adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning [ISMIR 2024]

VoiceLDM: Text-to-Speech with Environmental Context

FMBoost: Boosting Latent Diffusion with Flow Matching (ECCV 2024 Oral)

Zero-shot Image-to-Image Translation [SIGGRAPH 2023]