cromin

docling

Get your documents ready for gen AI

How2TrainUrVAE

How To Train Your VAE CODE

depthsplat

DepthSplat: Connecting Gaussian Splatting and Depth

BitNet

Official inference framework for 1-bit LLMs

Allegro

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

generative-ai-for-beginners

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

Pyramid-Flow

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

PMRF

Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

ml-depth-pro

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

JDM-HDRNet

Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography (ECCV2024)

UnSAM

[NeurIPS 2024] Code release for "Segment Anything without Supervision"

StoryMaker

StoryMaker: Towards consistent characters in text-to-image generation

Retinexformer

"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023) & (NTIRE 2024 Challenge)

Efficient-MIF

Train your fusion model and test downstream tasks in one repo.

Show-o

Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

DualResidualNetworks

Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration

MIRNetv2

[TPAMI 2022] Learning Enriched Features for Fast Image Restoration and Enhancement. Results on Defocus Deblurring, Denoising, Super-resolution, and image enhancement

Image-Adaptive-3DLUT

Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time

Unique3D

[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

NAFNet

The state-of-the-art image restoration model without nonlinear activation functions.

LlamaGen

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

SCI

[CVPR 2022] This is the official code for the paper "Toward Fast, Flexible, and Robust Low-Light Image Enhancement".

multi_illumination

schedule_free

Schedule-Free Optimization in PyTorch

vision-lstm

xLSTM as Generic Vision Backbone

UHDformer

[AAAI-24] Correlation Matching Transformation Transformers for UHD Image Restoration

Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

T-GATE

T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!

MLLA

Official repository of MLLA (NeurIPS 2024)