nosaydomore

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

IOPaint

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.

flash-attention

Fast and memory-efficient exact attention

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

StreamDiffusion

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

lama

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

sd-scripts

ControlNet-v1-1-nightly

Nightly release of ControlNet 1.1

notebooks

Notebooks using the Hugging Face libraries 🤗

lectures

Material for cuda-mode lectures

Stable-Diffusion-WebUI-TensorRT

TensorRT Extension for Stable Diffusion Web UI

IQA-PyTorch

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

FreeU

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

how-to-optim-algorithm-in-cuda

how to optimize some algorithm in cuda.

torchdistill

A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆25 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

CUDA-Learn-Notes

🎉 Modern CUDA Learn Notes with PyTorch: fp32、fp16/bf16、fp8/int8、flash_attn、sgemm、sgemv、warp/block reduce、dot prod、elementwise、softmax、layernorm、rmsnorm、hist etc.

BiRefNet

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

MAT

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

Loser-HomeWork

卢瑟们的作业展示，答案讲解，以及一些C++知识

MI-GAN

[ICCV 2023] MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

aesthetic-predictor

A linear estimator on top of clip to predict the aesthetic quality of pictures

CM-GAN-Inpainting

CM-GAN for Image Inpainting

CapDec

CapDec: SOTA Zero Shot Image Captioning Using CLIP and GPT2, EMNLP 2022 (findings)

ViECap

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning, ICCV 2023

DeCap

ICLR 2023 DeCap: Decoding CLIP Latents for Zero-shot Captioning

ReIQA

Official implementation for CVPR2023 Paper "Re-IQA : Unsupervised Learning for Image Quality Assessment in the Wild"

ghjson