Discover LAION-AI/project-menu Open Source project

Audio Dataset for training CLAP and other models

37,011

audio-dataset

CLIP-like model evaluation

616

CLIP_benchmark

Pretrained Dalle2 from laion

601

dalle2-laion

Contrastive Language-Audio Pretraining

499

CLAP

479

natural_voice_assistant

Collect large 3d dataset and build models

439

laion-3d

253

phenaki

A phenaki reproduction using pytorch.

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

218

aesthetic-predictor

Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks

199

Open-Instruction-Generalist

Home of `erlich` and `ongo`. Finetune latent-diffusion/glid-3-xl text2image on your own data.

195

ldm-finetune

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

169

scaling-laws-openclip

152

CLIP-based-NSFW-Detector

Description and pointers of laion datasets

135

laion-datasets

Aim for the moon. If you miss, you may hit a star.

131

laion-dreams

121

laion.ai

Alice in Wonderland code base for experiments and raw experiments data

110

AIW

108

LAION-5B-WatermarkDetection

O-GIA is an umbrella for research, infrastructure and projects ecosystem that should provide open source, reproducible datasets, models, applications & safety tools for Open Generalist Interactive Agents (O-GIA). O-GIA systems will act in collaboration with human or autonomously, supporting various kind of validated decision making and assistance.

102

video-clip

Let's make a video clip

Open-GIA

General-GPT

Implementation of a discord channel scraper to generate datasets.

Discord-Scrapers

Text-to-speech

Big-Interleaved-Dataset

Tools for content datamining and NLP at scale

riverbed

OCR-ensemble

Conditional-Pretraining-of-Large-Language-Models

Adversarial Training and SFT for Bot Safety Models

interesting-text-datasets

blade2blade

Aggregating embeddings over time

temporal-embedding-aggregation

Inverts CLIP text embeds to image embeds and visualizes with deep-image-prior.

deep-image-diffusion-prior

A repository containing datasets and tools to train a watermark classifier.

watermark-detection

This repository will be a summary and outlook on all our open, medical, AI advancements.

medical

Anh - LAION's multilingual assistant datasets and models

Anh

Un-*** 50 billions multimodality dataset

laion50BU

conditioned-prior

(wip) Use LAION-AI's CLIP "conditoned prior" to generate CLIP image embeds from CLIP text embeds.

An open toolbox for NSFW & toxicity detection

LAION-SAFETY

Frontend (and soon also midleware and backend) for a new, opensource image generation platform.

opendream

TypeScript

laion5B-paper

Building the laion5B paper

laion-dedup

A collection of generative and training notebooks getting mirrored to google colab.

notebooks

This repository contains training code and checkpoitns for finetuning glide.

laionide

This is the LAION repository for creating open super-resolution models with the help of LAION-5B subsets.

super-resolution

dataset-spec

Describe the format of image/text datasets

This project provides a data set with bounding boxes, body poses, 3D face meshes & captions of people from our LAION-2.2B. Additionally it provides clusters based on the poses and face meshes and pose-related captions based on these cluster assignments.

LAION-PEOPLE

image-deduplication-testset

This repository is a summary of all systems and scientific papers that use LAION datasets.

laion-ai.github.io

laion github website

Svelte

dataset-usage

repository-overview

This repository will give a quick overview of all projects and repositories from LAION.

LionizeR

Experiments with Summarization, Long Context and Retrieval

Knowledge Acquisition and Interlinking via Semantic Embeddings and Reasoning

KAISER

lucidrains-projects

A summary of all lucidrains repositores and links to training / research approaches by LAION or other communities.

A basic setup for decentralized-learning that can be used for training future DALLE/CLIP/CLAP models.

decentralized-learning

diffusion-prior

DALL-E2 diffusion prior

General / Global Inference Framework

GIF

This is the development repository of the LAION-AI website.

website

A collection of safety classifiers and models to process image and texts.

safety-pipeline

Creating subsets from laion5b via embeddings search

NeoGen

laion5b-subsets

A repo containing images for artifact annotation.

human_artifacts

public-relations

All media / publicity on LAION and related stuff!

public-domain-images

A collection of public domain images donated for ML training.

math_problems-step-by-step_solutions

Here we provide and collect many functions to generate math problem and step by step solutions for LLM training

The new repository for the genral inference pipeline.

language-models

dataset-inference

Recommended intro resources

introduction-resources

balanced-laion5b

This repository shall help finding a good distribution for huge datasets like LAION-5B for more efficient training.

hand-inference

A model to run hand inference on a cluster.