Shared Middle-Layer for Triton Compilation

Official inference repo for FLUX.1 models

assembles images in a grid

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

CoreNet: A library for training deep neural networks

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

Implementation of UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

unoffical implement for upsample guidance

Some useful tips for faiss

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) on multi-GPU Clusters

Microsoft Automatic Mixed Precision Library

A native PyTorch Library for large model training

Code for QuaRot, an end-to-end 4-bit inference of large language models.

A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust

real time face swap and one-click video deepfake with only a single image

Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

Segment Anything in High Quality [NeurIPS 2023]

Official PyTorch implementation of "Multi-modal Queried Object Detection in the Wild" (accepted by NeurIPS 2023)

[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

Open-MAGVIT2: Democratizing Autoregressive Visual Generation

[ICLR 2024 Spotlight] This is the official PyTorch implementation of "EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models"

TerDiT: Ternary Diffusion Models with Transformers

Official implementation of Half-Quadratic Quantization (HQQ)

DREAM: Diffusion Rectification and Estimation-Adaptive Models (CVPR 2024)

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

[CVPR 2024] SinSR: Diffusion-Based Image Super-Resolution in a Single Step