⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

Text-to-Audio/Music Generation

WavJourney: Compositional Audio Creation with LLMs

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

A family of diffusion models for text-to-audio generation.

🔊 Text-Prompted Generative Audio Model

[CVPRW 2023] SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing

Code Release for DiffusionRig (CVPR 2023)

so-vits-svc fork with realtime support, improved interface and more features.

SoftVC VITS Singing Voice Conversion

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

Generative Diffusion Prior for Unified Image Restoration and Enhancement (CVPR2023)

Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training (ICMR 2023)

Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution

[SIGGRAPH Asia 2024] ReVersion: Diffusion-Based Relation Inversion from Images

PrefGen: Preference Guided Image Generation with Relative Attributes

[AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

Suggestions for those interested in developing audio applications of machine learning

Stable diffusion for real-time music generation

Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

Revisiting Image Deblurring with an Efficient ConvNet - An efficient CNN performs better than Transformer

Official Code for our CVPR2023 paper "Human Guided Ground-truth Generation for Realistic Image Super-resolution"

Official code for "SRFormer: Permuted Self-Attention for Single Image Super-Resolution" (ICCV 2023) and SRFormerV2

[ICCV 2023] Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution; runner-up method for the model complexity track in NTIRE2023 Efficient SR challenge