• Stars
    star
    18
  • Rank 1,208,065 (Top 24 %)
  • Language
    Python
  • License
    MIT License
  • Created over 2 years ago
  • Updated over 1 year ago

Reviews

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

Repository Details

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

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
37,011
star
2

audio-dataset

Audio Dataset for training CLAP and other models
Python
616
star
3

CLIP_benchmark

CLIP-like model evaluation
Jupyter Notebook
601
star
4

dalle2-laion

Pretrained Dalle2 from laion
Python
499
star
5

CLAP

Contrastive Language-Audio Pretraining
Python
479
star
6

natural_voice_assistant

Python
439
star
7

laion-3d

Collect large 3d dataset and build models
253
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

scaling-laws-openclip

Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
Jupyter Notebook
152
star
13

CLIP-based-NSFW-Detector

Python
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
110
star
17

AIW

Alice in Wonderland code base for experiments and raw experiments data
Python
108
star
18

LAION-5B-WatermarkDetection

Python
102
star
19

video-clip

Let's make a video clip
92
star
20

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.
91
star
21

General-GPT

Jupyter Notebook
64
star
22

Discord-Scrapers

Implementation of a discord channel scraper to generate datasets.
Python
60
star
23

Text-to-speech

Python
58
star
24

Big-Interleaved-Dataset

Big-Interleaved-Dataset
Python
57
star
25

riverbed

Tools for content datamining and NLP at scale
Python
41
star
26

OCR-ensemble

Jupyter Notebook
38
star
27

Conditional-Pretraining-of-Large-Language-Models

Python
37
star
28

interesting-text-datasets

33
star
29

blade2blade

Adversarial Training and SFT for Bot Safety Models
Python
32
star
30

temporal-embedding-aggregation

Aggregating embeddings over time
Python
31
star
31

deep-image-diffusion-prior

Inverts CLIP text embeds to image embeds and visualizes with deep-image-prior.
Jupyter Notebook
31
star
32

watermark-detection

A repository containing datasets and tools to train a watermark classifier.
Python
31
star
33

medical

This repository will be a summary and outlook on all our open, medical, AI advancements.
Jupyter Notebook
28
star
34

Anh

Anh - LAION's multilingual assistant datasets and models
Python
27
star
35

laion50BU

Un-*** 50 billions multimodality dataset
24
star
36

LAION-SAFETY

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

opendream

Frontend (and soon also midleware and backend) for a new, opensource image generation platform.
TypeScript
14
star
38

laion5B-paper

Building the laion5B paper
13
star
39

laion-dedup

Python
13
star
40

notebooks

A collection of generative and training notebooks getting mirrored to google colab.
Jupyter Notebook
12
star
41

laionide

This repository contains training code and checkpoitns for finetuning glide.
Python
12
star
42

super-resolution

This is the LAION repository for creating open super-resolution models with the help of LAION-5B subsets.
11
star
43

dataset-spec

Describe the format of image/text datasets
Python
10
star
44

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
45

image-deduplication-testset

HTML
8
star
46

project-menu

Projects at LAION
8
star
47

laion-ai.github.io

laion github website
Svelte
6
star
48

dataset-usage

This repository is a summary of all systems and scientific papers that use LAION datasets.
6
star
49

repository-overview

This repository will give a quick overview of all projects and repositories from LAION.
5
star
50

LionizeR

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

KAISER

Knowledge Acquisition and Interlinking via Semantic Embeddings and Reasoning
4
star
52

lucidrains-projects

A summary of all lucidrains repositores and links to training / research approaches by LAION or other communities.
Jupyter Notebook
3
star
53

decentralized-learning

A basic setup for decentralized-learning that can be used for training future DALLE/CLIP/CLAP models.
3
star
54

diffusion-prior

DALL-E2 diffusion prior
Python
3
star
55

GIF

General / Global Inference Framework
Python
3
star
56

website

This is the development repository of the LAION-AI website.
HTML
3
star
57

safety-pipeline

A collection of safety classifiers and models to process image and texts.
Python
3
star
58

NeoGen

3
star
59

laion5b-subsets

Creating subsets from laion5b via embeddings search
Jupyter Notebook
2
star
60

human_artifacts

A repo containing images for artifact annotation.
2
star
61

public-relations

All media / publicity on LAION and related stuff!
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

dataset-inference

The new repository for the genral inference pipeline.
Python
2
star
66

introduction-resources

Recommended intro resources
2
star
67

balanced-laion5b

This repository shall help finding a good distribution for huge datasets like LAION-5B for more efficient training.
2
star
68

hand-inference

A model to run hand inference on a cluster.
Jupyter Notebook
2
star
69

BUD-E_V1.0

BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the creation and integration of diverse skills for educational and research applications.
1
star
70

laion5b-bias

This repository is a collection of found biases in the LAION-5B dataset.
1
star
71

dataset-tasks

datasets that should be downloaded & converted to our standard training formart.
1
star
72

LAION-AUDIO

This repository contains prompts & best practices to annotate audio clips with a very high degree of details using Audio-Language-Models
1
star
73

AIW_webpage

Alice in Wonderland project and initiative webpage
1
star