Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

Concept Sliders for Precise Control of Diffusion Models

A comprehensive deep dive into the world of tokens

1-shot image segmentation using Stable Diffusion

[ICCV 2023] Iterative Prompt Learning for Unsupervised Backlit Image Enhancement

MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications

Zero-shot Image-to-Image Translation [SIGGRAPH 2023]

Important concepts in numerical linear algebra and related areas

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

TMLR2023

Implementation of "DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning"

Using Low-rank adaptation to quickly fine-tune diffusion models.

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

GLIDE: a diffusion-based text-conditional image synthesis model

Official code for "Top-Down Visual Attention from Analysis by Synthesis" (CVPR 2023 highlight)

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

Diagrams for visualizing neural network architecture (Created with diagrams.net)

Repo for the paper "Extrapolating from a Single Image to a Thousand Classes using Distillation"

pix2pix3D: Generating 3D Objects from 2D User Inputs

An unnecessarily tiny implementation of GPT-2 in NumPy.

Using pre-trained Diffusion models as priors for inference tasks

Extended LaTeX template for CVPR/ICCV papers

Implementation of "Denoising Diffusion Probabilistic Models", Ho et al., 2020

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

Personal implementations of Machine Learning papers

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Examples for classification, object detection, segmentation, embedding networks and more. Including Grad-C…