Stability AI ORG

Generative models for conditional audio generation

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

No description.

No description.

Generative Models by Stability AI

AI models from Stability AI that generate 3D videos and multi-view imagery from single images or videos using diffusion techniques.

StableLM: Stability AI Language Models

StableLM is a collection of open-source language models from Stability AI, available at multiple sizes, for researchers and developers who want to run, fine-tune, or study AI text models locally as an alternative to commercial APIs.

Community interface for generative AI

The open-source version of DreamStudio, a browser-based app for generating and editing AI images using Stable Diffusion, that you run locally and can connect to any image generation back-end via a TypeScript plugin system.

Official Code for Stable Cascade

StableSwarmUI, A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.

SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

No description.

Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.

No description.

No description.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

A framework for few-shot evaluation of autoregressive language models.

No description.

Interface definitions for API interactions between components

Code Assistance/ Developer Productivity suite of Models

Awesome Stability List

Stability REST API examples, issues, and discussions | https://api.stability.ai

Iterable datapipelines for pytorch training.

python library for invisible image watermark (blind image watermark)

Stability.AI Model Metadata Standard Specification

Relightable multi-view 3D reconstruction with disentangled illumination and spatially varying PBR materials

No description.

Deploy your HPC Cluster on AWS in 20min. with just 1-Click.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

No description.

Golang functions for interacting with Stability API

Official implementation of AnimateDiff.

No description.

A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion.

No description.

Karras et al. (2022) diffusion models for PyTorch

External project in GitHub for marketing purposes. This repo will be used for code samples that accompany blog posts on https://stability.ai/learning-hub

A library for training and deploying machine learning models on Amazon SageMaker

Using Low-rank adaptation to quickly fine-tune diffusion models + HF Accelerate

Notebooks for Stability AI models

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

No description.

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

Variance reduction for Sliced Wasserstein Distance using Reservoir Sampling.

No description.

AWS Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in TensorFlow, TensorFlow 2, PyTorch, and MXNet.

Fast and memory-efficient exact attention

No description.

Code for building and running containers available on AWS marketplace

FaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.

Model API for GALACTICA

No description.

An open source implementation of CLIP.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

No description.

No description.

No description.

Collection of best practices, reference architectures, model training examples and utilities to train large models on AWS.

A high-throughput and memory-efficient inference and serving engine for LLMs

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

A Python-CUDA implementation of the Wavelet Transform

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

GH app to listen for actions build requests and submit

A tool for comparing large S3 buckets

Use Hugging Face with JavaScript

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

No description.

ComfyUI's ControlNet Auxiliary Preprocessors

No description.

A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！

No description.

Serve any model without boilerplate code

Module, Model, and Tensor Serialization/Deserialization

Contrib repository for the OpenTelemetry Collector

A set of tools that gives agents powerful capabilities.

No description.

Official Implementation of "Splat the Net: Radiance Fields with Splattable Neural Primitives"

A model-driven approach to building AI agents in just a few lines of code.

Rembg is a tool to remove images background

Webapp to live inside of the Munge auth domain, run as the SlurmUser, and launch GitHub Actions runners based on build requests

Fork of Qwen Image Bench for Stable Tribunal

SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

Measures and metrics for image2image tasks. PyTorch.

Examples for Stability AI Deep Learning Containers on AWS SageMaker

Scripts for interacting with Stability AI's inference server containers.

Interactive 3D connectivity editor and rendering pipeline with ECR deployment

No description.

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

Documentation for the Strands Agents SDK. A model-driven approach to building AI agents in just a few lines of code.

Project of llm evaluation to Japanese tasks

Robust recipes for to align language models with human and AI preferences

Slurm on Google Cloud Platform

No description.

Checkpointable dataset utilities for foundation model training

Example of using Epochraft to train HuggingFace transformers models with PyTorch FSDP

maximal update parametrization (µP)

Custom features shared by Stability AI devcontainers

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

The most powerful and modular stable diffusion GUI with a graph/nodes interface.

Localhost proxy for IAM Credentials API project

ControlNet scheduling and masking nodes with sliding context support

Resources for demos and training

Simple slurm tracking bot to check usage