High order Moment Models

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

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

Intrinsic Image Diffusion for Single-view Material Estimation

Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful Diffuse Intrinsic Image Decomposition in the Wild" (TOG 2024)

Implementation of Agent Attention in Pytorch

Official repository of Agent Attention (ECCV2024)

A concise but complete full-attention transformer with a set of promising experimental features from various papers

IQA: Deep Image Structure and Texture Similarity Metric

Implementation of Axial attention - attending to multi-dimensional data efficiently

A data logger to intercept analog images from a Game Boy Camera

Documentation and Generation of GB Camera dither Patterns

Google Drive Public File Downloader when Curl/Wget Fails

🗺 OpenStreetMap 3D renderer powered by WebGL2

Godot Jolt is a Godot extension that integrates the Jolt physics engine

[NeurIPS 2023] Customize spatial layouts for conditional image synthesis models, e.g., ControlNet, using GPT

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

This repo accompanies the research paper, ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data and contains the data, scripts to visualize and proces…

PyTorch code and models for the DINOv2 self-supervised learning method.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Nightly release of ControlNet 1.1

Parallel processing with progress bars

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Supercharge Your Model Training

This is PyTorch implementation of our paper "LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network".(CVPR'22)

Let us control diffusion models!

📷 The toolkit of HDR synthesis approaches based on alignment methods

A Python library for alpha matting