Makoto Shing

DiffusionBlocks. DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation

arxiv-latex-cleaner. arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

TAID. Official implementation of "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models"

Score-Entropy-Discrete-Diffusion. [ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

hugo-PaperMod. A fast, clean, responsive Hugo theme.

Bayesian-Flow-Networks. A simple implimentation of Bayesian Flow Networks (BFN)

evolutionary-model-merge. Official repository of Evolutionary Optimization of Model Merging Recipes

LWM. Large World Model -- Modeling Text and Video with Millions Context

surya. OCR, layout analysis, reading order, table recognition in 90+ languages

star-vector. StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

style-aligned. Official code for "Style Aligned Image Generation via Shared Attention"

DiffiT. [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

data-juicer. Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

tokenization. A comprehensive deep dive into the world of tokens

cross-image-attention. Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

PixArt-alpha. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

InstaFlow. :zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

ncsnv2. The official PyTorch implementation for NCSNv2 (NeurIPS 2020)

ml-fastvit. This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

epochraft. Checkpointable dataset utilities for foundation model training

hyperdreambooth. Implementation of HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

text2cinemagraph. Text2Cinemagraph: Text-Guided Synthesis of Eulerian Cinemagraphs [SIGGRAPH ASIA 2023]

JourneyDB.

translate_dataset. Python

taesd. Tiny AutoEncoder for Stable Diffusion (and other image models)

generative-models. Generative Models by Stability AI

MaskDiT. Code for Fast Training of Diffusion Models with Masked Transformers

OMS-DPM. The official code of paper "OMS-DPM: Optimizing Model Schedule for Diffusion Probabilistic Model" accepted by ICML 2023

oft. Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".

Asymmetric_VQGAN. Jupyter Notebook

Awesome-Controllable-T2I-Diffusion-Models. A collection of resources on controllable generation with text-to-image diffusion models.

instruction-tuned-sd. Code for instruction-tuning Stable Diffusion.

ProFusion. Code for Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach

deepface. A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

classifier-free-guidance-pytorch. Implementation of Classifier Free Guidance in Pytorch, with emphasis on text conditioning, and flexibility to include multiple text embedding models

open-diffusion. Simple large-scale training of stable diffusion with multi-node support.

open-muse. Open reproduction of MUSE for fast text2image generation.

mup. maximal update parametrization (µP)

lm_perplexity. Python

mmc4. MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

consistency_models. Official repo for consistency models.

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

torch-batch-svd. A 100x faster SVD for PyTorch⚡️

LVDM. LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation

VideoCrafter. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

Kandinsky-2. Kandinsky 2 — multilingual text2image latent diffusion model

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

alpaca_ja. alpacaデータセットを日本語化したものです

tomesd. Speed up Stable Diffusion with this one simple trick!

open_flamingo. An open-source framework for training large multimodal models.

Text2Video-Zero. [ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

Text-To-Video-Finetuning. Finetune ModelScope's Text To Video model using Diffusers 🧨

polyglot. Polyglot: Large Language Models of Well-balanced Competence in Multi-languages

oslo. OSLO: Open Source for Large-scale Optimization

zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

gigagan-pytorch. Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

ControlNet. Let us control diffusion models!

python-package-template. A template repo for Python packages

RL4LMs. A modular RL library to fine-tune language models to human preferences

AdvancedML. Reading list for the Advanced Machine Learning Course

trl. Train transformer language models with reinforcement learning.

style2paints. sketch + style = paints :art: (TOG2018/SIGGRAPH2018ASIA)

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

stable-diffusion-deploy. Learn to serve Stable Diffusion models on cloud infrastructure at scale. This Lightning App shows load-balancing, orchestrating, pre-provisioning, dynamic batching, GPU-inference, micro-services working together via the Lightning Apps framework.

clipseg. This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

face_recognition. The world's simplest facial recognition api for Python and the command line

CrossAttentionControl. Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion

make-a-video-pytorch. Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

blended-diffusion. Official implementation for "Blended Diffusion for Text-driven Editing of Natural Images" [CVPR 2022]

stablediffusion-infinity. Outpainting with Stable Diffusion on an infinite canvas

coyo-dataset. COYO-700M: Large-scale Image-Text Pair Dataset

k-diffusion. Karras et al. (2022) diffusion models for PyTorch

.tmux. Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍

AudioCLIP. Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

cloob-training. CLOOB training (JAX) and inference (JAX and PyTorch)

CLIP-Image-Captioning. [WIP] Using CLIP and GPT2-XL to generate captions from images.

glide-finetune. Finetune glide-text2im from openai on your own data.

clip-retrieval. Easily compute clip embeddings and build a clip retrieval system with them

CLIP-Guided-Diffusion. Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.

guided-diffusion. Python

AwesomeAnimeResearch. Papers, repository and other data about anime or manga research. Please let me know if you have information that the list does not include.

pixray. Python

xmanager. A platform for managing machine learning experiments

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

PromptPapers. Must-read papers on prompt-based tuning for pre-trained language models.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

P-tuning-v2. An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

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

dialogue-generation. Generating responses with pretrained XLNet and GPT-2 in PyTorch.

jrte-corpus. Japanese Realistic Textual Entailment Corpus (NLP 2020, LREC 2020)

transformers-interpret. Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

causal-text. Package for computing causal effects of text (as treatment)

KeyBERT. Minimal keyword extraction with BERT

chatux. Chat Bot UI / Conversational UI library for Java Script

ML-From-Scratch. Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

algorithms. A collection of algorithms and data structures

electra. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

DialoGPT. Large-scale pretraining for dialogue

awesome-dl4nlp. A curated list of awesome Deep Learning (DL) for Natural Language Processing (NLP) resources

hessian_penalty. Official Implementation of "The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement" (ECCV 2020 Spotlight)

bert-japanese. BERT models for Japanese text.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

glcic. Globally and Locally Consistent Image Completion with TensorFlow

dataset-shift-osdc16. Support material for my OSDC London 2016 talk on Dataset Shift in Machine Learning

lda2vec. Python

clinicalBERT. repository for Publicly Available Clinical BERT Embeddings

SequentialPhenotypePredictor. Early diagnosis predictor using contextual representation of medical events

causal-text-embeddings. Software and data for "Using Text Embeddings for Causal Inference"

denoiseHSR-AAAI. Causally Denoise Word Embeddings Using Half-Sibling Regression

mat2vec. Supplementary Materials for Tshitoyan et al. "Unsupervised word embeddings capture latent knowledge from materials science literature", Nature (2019).

BioSentVec. BioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences

lit. The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

dash. Data Apps & Dashboards for Python. No JavaScript Required.

fastText. Library for fast text representation and classification.

awesome-embedding-models. A curated list of awesome embedding models tutorials, projects and communities.

HRNet-Facial-Landmark-Detection. This is an official implementation of facial landmark detection for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919

sentimentr. Dictionary based sentiment analysis that considers valence shifters

Data-Visualizations-Medium. Understanding Data and Machine Learning Models with Visualizations

MLT-contributions. Jupyter Notebook

decision-tree-splits-continuous-variables. A simple example to answer - how is a splitting point chosen for continuous variables in decision trees?

covid-chestxray-dataset. We are building an open database of COVID-19 cases with chest X-ray or CT images.

Messenger. Messenger

InputBarAccessoryView. A simple and easily customizable InputAccessoryView for making powerful input bars with autocomplete and attachments

messenger-iOS-chat-swift-firestore. Messenger Clone - Real-time iOS Chat with Firebase Firestore written in Swift

awesome-machine-learning. A curated list of awesome Machine Learning frameworks, libraries and software.

AutoViz. Automatically Visualize any dataset, any size with a single line of code. Created by Ram Seshadri. Collaborators Welcome. Permission Granted upon Request.

Material. A UI/UX framework for creating beautiful applications.

LTMorphingLabel. [EXPERIMENTAL] Graceful morphing effects for UILabel written in Swift.

KYNavigationProgress. Simple extension of UINavigationController to display progress on the UINavigationBar.

activity-bar. iOS 7 style progress bar for showing ogoing activity

Spring. A library to simplify iOS animations in Swift.

MapSnap. Easily create, cache, and access map snapshots on iOS

folding-cell. :octocat: 📃 FoldingCell is an expanding content cell with animation made by @Ramotion

weWrk_ios. weWrk is a work related social networking platform for construction workers and companies, using the Firebase API and infrastructure.

Voluny. Voluny is a quick, easy and simple volunteering app that is tailored specifically for volunteers who love to help out their community as well as to recruiters, who are seeking for volunteers for their organizations.

awesome-ios-animation. :umbrella: A collection of iOS animation repos

Hero. Elegant transition library for iOS & tvOS

LFLoginController. Customizable login screen, written in Swift 🔶

ESTabBarController. :octocat: ESTabBarController is a Swift model for customize UI, badge and adding animation to tabbar items. Support lottie!

SwipeableTabBarController. UITabBarController with swipe interaction between its tabs.

awesome-ios. A curated list of awesome iOS ecosystem, including Objective-C and Swift Projects

awesome-swift. A collaborative list of awesome Swift libraries and resources. Feel free to contribute!

Graphite. Simple force directed graph drawing for iOS

Chameleon. Color framework for Swift & Objective-C (Gradient colors, hexcode support, colors from images & more).

chameleon. Color framework for Swift & Objective-C (Gradient colors, hexcode support, colors from images & more).

simplenote-ios. Simplenote for iOS

gitignore. A collection of useful .gitignore templates

IQKeyboardManager. Codeless drop-in universal library allows to prevent issues of keyboard sliding up and cover UITextField/UITextView. Neither need to write any code nor any setup required and much more.

Alamofire. Elegant HTTP Networking in Swift

CLTypingLabel. iOS UILabel with character by character typing /typewriter animation

open-source-ios-apps. :iphone: Collaborative List of Open-Source iOS Apps

ProgressHUD. ProgressHUD is a lightweight and easy-to-use HUD for iOS. Over 5000+ animations.