• Stars
    star
    11
  • Rank 1,644,434 (Top 34 %)
  • Language
  • License
    MIT License
  • Created about 2 years ago
  • Updated about 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

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

More Repositories

1

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Python
36,706
star
2

audio-dataset

Audio Dataset for training CLAP and other models
Python
575
star
3

CLIP_benchmark

CLIP-like model evaluation
Jupyter Notebook
497
star
4

dalle2-laion

Pretrained Dalle2 from laion
Python
489
star
5

CLAP

Contrastive Language-Audio Pretraining
Python
479
star
6

natural_voice_assistant

Python
349
star
7

laion-3d

Collect large 3d dataset and build models
238
star
8

phenaki

A phenaki reproduction using pytorch.
Python
218
star
9

aesthetic-predictor

A linear estimator on top of clip to predict the aesthetic quality of pictures
Jupyter Notebook
199
star
10

Open-Instruction-Generalist

Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks
Python
195
star
11

ldm-finetune

Home of `erlich` and `ongo`. Finetune latent-diffusion/glid-3-xl text2image on your own data.
Python
169
star
12

CLIP-based-NSFW-Detector

Python
135
star
13

scaling-laws-openclip

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
Jupyter Notebook
135
star
14

laion-datasets

Description and pointers of laion datasets
HTML
131
star
15

laion-dreams

Aim for the moon. If you miss, you may hit a star.
121
star
16

laion.ai

HTML
99
star
17

Open-GIA

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.
88
star
18

video-clip

Let's make a video clip
85
star
19

LAION-5B-WatermarkDetection

Python
85
star
20

General-GPT

Jupyter Notebook
64
star
21

Text-to-speech

Python
60
star
22

Big-Interleaved-Dataset

Big-Interleaved-Dataset
Python
56
star
23

riverbed

Tools for content datamining and NLP at scale
Python
40
star
24

Discord-Scrapers

Implementation of a discord channel scraper to generate datasets.
Python
40
star
25

OCR-ensemble

Jupyter Notebook
37
star
26

Conditional-Pretraining-of-Large-Language-Models

Python
36
star
27

interesting-text-datasets

33
star
28

blade2blade

Adversarial Training and SFT for Bot Safety Models
Python
32
star
29

deep-image-diffusion-prior

Inverts CLIP text embeds to image embeds and visualizes with deep-image-prior.
Jupyter Notebook
31
star
30

watermark-detection

A repository containing datasets and tools to train a watermark classifier.
Python
31
star
31

temporal-embedding-aggregation

Aggregating embeddings over time
Python
30
star
32

medical

This repository will be a summary and outlook on all our open, medical, AI advancements.
Jupyter Notebook
28
star
33

Anh

Anh - LAION's multilingual assistant datasets and models
Python
27
star
34

laion50BU

Un-*** 50 billions multimodality dataset
24
star
35

conditioned-prior

(wip) Use LAION-AI's CLIP "conditoned prior" to generate CLIP image embeds from CLIP text embeds.
Python
18
star
36

LAION-SAFETY

An open toolbox for NSFW & toxicity detection
Jupyter Notebook
16
star
37

laion5B-paper

Building the laion5B paper
13
star
38

opendream

Frontend (and soon also midleware and backend) for a new, opensource image generation platform.
TypeScript
13
star
39

notebooks

A collection of generative and training notebooks getting mirrored to google colab.
Jupyter Notebook
12
star
40

laionide

This repository contains training code and checkpoitns for finetuning glide.
Python
12
star
41

laion-dedup

Python
12
star
42

dataset-spec

Describe the format of image/text datasets
Python
10
star
43

LAION-PEOPLE

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.
10
star
44

image-deduplication-testset

HTML
8
star
45

project-menu

Projects at LAION
8
star
46

laion-ai.github.io

laion github website
Svelte
6
star
47

dataset-usage

This repository is a summary of all systems and scientific papers that use LAION datasets.
6
star
48

repository-overview

This repository will give a quick overview of all projects and repositories from LAION.
5
star
49

KAISER

Knowledge Acquisition and Interlinking via Semantic Embeddings and Reasoning
4
star
50

LionizeR

Experiments with Summarization, Long Context and Retrieval
Python
4
star
51

safety-pipeline

A collection of safety classifiers and models to process image and texts.
Python
3
star
52

decentralized-learning

A basic setup for decentralized-learning that can be used for training future DALLE/CLIP/CLAP models.
3
star
53

diffusion-prior

DALL-E2 diffusion prior
Python
3
star
54

GIF

General / Global Inference Framework
Python
3
star
55

website

This is the development repository of the LAION-AI website.
HTML
3
star
56

lucidrains-projects

A summary of all lucidrains repositores and links to training / research approaches by LAION or other communities.
Jupyter Notebook
3
star
57

NeoGen

3
star
58

laion5b-subsets

Creating subsets from laion5b via embeddings search
Jupyter Notebook
2
star
59

human_artifacts

A repo containing images for artifact annotation.
2
star
60

public-relations

All media / publicity on LAION and related stuff!
2
star
61

dataset-inference

The new repository for the genral inference pipeline.
Python
2
star
62

public-domain-images

A collection of public domain images donated for ML training.
2
star
63

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
Python
2
star
64

language-models

2
star
65

introduction-resources

Recommended intro resources
2
star
66

balanced-laion5b

This repository shall help finding a good distribution for huge datasets like LAION-5B for more efficient training.
2
star
67

hand-inference

A model to run hand inference on a cluster.
Jupyter Notebook
2
star
68

laion5b-bias

This repository is a collection of found biases in the LAION-5B dataset.
1
star
69

dataset-tasks

datasets that should be downloaded & converted to our standard training formart.
1
star