This is the repo of LAION, a non-profit organization to liberate machine learning research, models and datasets.
126
Public repositories
47,159
Total stars
4,257
Followers
LAION-AI maintains a significant public GitHub presence, focusing on machine learning research, models, and datasets. Their repositories primarily utilize languages like Python and Jupyter Notebook, featuring notable projects such as Open-Assistant and CLAP, which contribute to advancing AI capabilities and dataset accessibility.
Top languages
Public repositories
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
CLAP
Contrastive Language-Audio Pretraining
CLIP_benchmark
CLIP-like model evaluation
audio-dataset
Audio Dataset for training CLAP and other models
aesthetic-predictor
A linear estimator on top of clip to predict the aesthetic quality of pictures
dalle2-laion
Pretrained Dalle2 from laion
natural_voice_assistant
No description provided for this repository.
CLIP-based-NSFW-Detector
No description provided for this repository.
lucidrains-projects
A summary of all lucidrains repositores and links to training / research approaches by LAION or other communities.
laion-3d
Collect large 3d dataset and build models
laion-datasets
Description and pointers of laion datasets
phenaki
A phenaki reproduction using pytorch.
Open-Instruction-Generalist
Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks
scaling-laws-openclip
Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
ldm-finetune
Home of `erlich` and `ongo`. Finetune latent-diffusion/glid-3-xl text2image on your own data.
laion-dreams
Aim for the moon. If you miss, you may hit a star.
LAION-5B-WatermarkDetection
No description provided for this repository.
AIW
Alice in Wonderland code base for experiments and raw experiments data
laion.ai
No description provided for this repository.
emotion-annotations
No description provided for this repository.
Discord-Scrapers
Implementation of a discord channel scraper to generate datasets.
video-clip
Let's make a video clip
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.
watermark-detection
A repository containing datasets and tools to train a watermark classifier.
LAION-SAFETY
An open toolbox for NSFW & toxicity detection
General-GPT
No description provided for this repository.
Text-to-speech
No description provided for this repository.
Big-Interleaved-Dataset
Big-Interleaved-Dataset
interesting-text-datasets
No description provided for this repository.
riverbed
Tools for content datamining and NLP at scale
Desktop_BUD-E
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.
OCR-ensemble
No description provided for this repository.
blade2blade
Adversarial Training and SFT for Bot Safety Models
Conditional-Pretraining-of-Large-Language-Models
No description provided for this repository.
deep-image-diffusion-prior
Inverts CLIP text embeds to image embeds and visualizes with deep-image-prior.
laion5B-paper
Building the laion5B paper
emotional-speech-annotations
This repository contains prompts & best practices to annotate audio clips with a very high degree of details using Audio-Language-Models
temporal-embedding-aggregation
Aggregating embeddings over time
medical
This repository will be a summary and outlook on all our open, medical, AI advancements.
conditioned-prior
(wip) Use LAION-AI's CLIP "conditoned prior" to generate CLIP image embeds from CLIP text embeds.
Anh
Anh - LAION's multilingual assistant datasets and models
scaled-echo-tts
Scaled diffusion transformer for text-to-speech synthesis (DiT + T5Gemma2 conditioning, TorchTitan & Megatron backends, tested up to 1024 GPUs)
Desktop-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.
laion50BU
Un-*** 50 billions multimodality dataset
scaling-laws-for-comparison
No description provided for this repository.
school-bud-e-frontend-old
A frontend that is compatible to the school-bud-e-backend.
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
laion-dedup
No description provided for this repository.
bud-e
A general human-ai interaction platform.
univeral-audio-annotation-pipeline
No description provided for this repository.
Vocalino-V0.1-Voice-Acting-Pipeline
Open-weights voice acting pipeline combining zero-shot voice cloning with natural-language direction. Provide a reference voice (or generate one) and describe how the line should be performed. Produces speech that keeps the voice identity while following emotional and stylistic prompts—no training required.
opendream
Frontend (and soon also midleware and backend) for a new, opensource image generation platform.
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.
worldsim
No description provided for this repository.
super-resolution
This is the LAION repository for creating open super-resolution models with the help of LAION-5B subsets.
laionide
This repository contains training code and checkpoitns for finetuning glide.
project-menu
Projects at LAION
model-retrieval
Easily compute model embeddings and save the embeddings.
project-alexandria
Official repo for Project Alexandria
open-sci-ref-0.01
No description provided for this repository.
image-deduplication-testset
No description provided for this repository.
KAISER
Knowledge Acquisition and Interlinking via Semantic Embeddings and Reasoning
Megatron-LM-Open-Sci
MegaTron open-sci fork
voice-taxonomies
Collection of three complementary voice taxonomies: VoiceNet (59 speech dimensions), EmoNet (40 emotion categories), VocalBurst (82 non-speech sounds)
Retrieval-Augmented-Voice-Cloning
Retrieval-augmented voice cloning and emotion conditioning data generation pipeline. Combines Echo TTS, ChatterboxVC, and Empathic Insight Voice+ to generate large-scale datasets of emotionally conditioned speech with disentangled speaker identity and emotional prosody.
open_clip_mammut
OpenCLIP fork with MaMMUT support
safety-pipeline
A collection of safety classifiers and models to process image and texts.
Dream-E
No description provided for this repository.
emonet-face
Official repository for the NeurIPS 2025 paper “EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition.” Includes a 40-category emotion taxonomy, balanced synthetic datasets, expert annotations, and baseline models for fair and reproducible evaluation.
annotate-collection
A repository with data for annotation.
decentralized-learning
A basic setup for decentralized-learning that can be used for training future DALLE/CLIP/CLAP models.
chatterbox-voice-conversion
High-level Python library for zero-shot voice conversion using Resemble AI's Chatterbox S3Gen model
BVD
No description provided for this repository.
agent-bud-e
Building an agentic voice assistant for mobile & desktop devices with episodic, semantic & procedural memories
llm-template
A template for procedural template generation using JSON outputs form LLMs.
AIW_webpage
Alice in Wonderland project and initiative webpage
laion5b-subsets
Creating subsets from laion5b via embeddings search
Open-Sci-hf
No description provided for this repository.
curiosit-e
File server for curiosit-e content.
images-for-slideshows
No description provided for this repository.
django-htmx-llm-streaming
A prototype showing how to stream using Django x htmx.
crawlingathome
A client library for Crawling@Home's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.
school-bud-e-frontend
School Bud-E is an intelligent and empathetic learning assistant designed to revolutionize the educational experience.
Admin_Bud-E
Admin Bud-E is a lightweight, privacy-first control center for AI chat, speech-to-text, and text-to-speech. Manage providers, routing, and costs with a simple Admin Console. Give users per-period credits, prices per model, and a shared Common Pool. EU-friendly via OpenAI-Format endpoints or our optional Google Cloud Vertex proxy.
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.
snac-to-llama3
No description provided for this repository.
bud-e-mobile
Mobile app development of all bud-e derivatives.
laionbox
LaionBox: Fine-tuned DramaBox TTS with Multi-Auxiliary Differentiable Losses
open-sci-ref
No description provided for this repository.
Voice-Acting-Pipeline
Self-contained DramaBox voice acting pipeline: VoiceNet taxonomy, multi-GPU prompt generation, TTS synthesis, and audio refinement
emolia-bench
Benchmark analysis
jax-dacvae-echotts
JAX/TPU training code for EchoTTS with DACVAE latent codec
tunes
No description provided for this repository.
scientific-summaries
No description provided for this repository.
open-clap-scaling
Multi-node scaling benchmarks for CLAP contrastive audio-language models on HPC clusters
vocolino
No description provided for this repository.
helden-bud-e-frontend
No description provided for this repository.
DSA-Wissen-BM25-Server
No description provided for this repository.
StoryBuddy-frontend
No description provided for this repository.
Open-Sci-moe-hf
No description provided for this repository.
Frequently asked questions
What does LAION-AI build on GitHub?
LAION-AI develops various machine learning tools and datasets on GitHub. Their projects include Open-Assistant, which is a chat-based assistant, and CLAP, which focuses on language-audio pretraining.
Which programming languages does LAION-AI use?
LAION-AI primarily uses Python and Jupyter Notebook for their projects, along with other languages such as TypeScript, HTML, Dart, and JavaScript, allowing for diverse development approaches.
Are LAION-AI's repositories public?
Yes, all of LAION-AI's repositories are public. This transparency enables collaboration and allows the research community to access their machine learning models and datasets freely.
Is this exposure intended?
Monitor LAION AI with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account