Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

dParallel: Learnable Parallel Decoding for dLLMs

Official repo for AMD hybrid models training and inference workflow

Code for BLT research paper

Code for paper 'OFDM-guided Deep Joint Source Channel Coding for Wireless Multipath Fading Channels', IEEE TCCN

[NeurlPS2024] One-Step Effective Diffusion Network for Real-World Image Super-Resolution

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

[CVPR 2025] Official implementation of the paper "TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution".

Efficient vision foundation models for high-resolution generation and perception.

[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation (CVPR 2024)

[NeurIPS 2024]Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs

Generative Models by Stability AI

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

[ECCV2024] This is the official implementation of GraphBEV, a BEV multi-modal framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

This repo provides a working re-implementation of Latent Adversarial Diffusion Distillation by AMD

Inference-only implementation of "One-Step Diffusion Distillation through Score Implicit Matching" [NIPS 2024]

[NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

[NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Fast and memory-efficient exact attention

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

[ICCV 2025] QuEST: Efficient Finetuning for Low-bit Diffusion Models

This repository contains the PyTorch implementation of the CVPR'2024 paper (Highlight), IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection.

[ICCV2023] Official Implementation of "UniTR: A Unified and Efficient Multi-Modal Transformer for Bird’s-Eye-View Representation"