Stability AI
Stability AI develops the Stable Diffusion image models and Stable Audio, offered through an API, open weights and enterprise solutions.
About this tool
Stability AI is the company behind Stable Diffusion, one of the best-known families of image generation models, many of which are released with open weights. Its Stable Diffusion 3.5 models come in several sizes, from a large flagship model for professional quality to smaller and faster variants designed to run on consumer hardware.
The company also develops Stable Audio for generating music and sound from text or audio samples, and 3D and video models for creative production. Its models are available through an API that uses prepaid credits, through downloadable weights for self-hosting, and through enterprise partnerships aimed at studios and brands that want production-ready generative tools.
What you can do
Stable Diffusion 3.5
Image models in several sizes, with versions focused on quality, speed or running on consumer GPUs.
Stable Audio
Create music and sound effects from a text description or an audio sample, with a plugin for digital audio workstations.
3D and video models
Models for volumetric and video generation support storyboarding, world building and visual effects.
API and open weights
Use the hosted API with credits, or download open models and run them on your own infrastructure.
Who is it for?
- A developer integrates image generation into an app through the Stability API.
- A music producer sketches ideas with Stable Audio inside a DAW.
- A studio fine-tunes an open Stable Diffusion model on its own visual style.
Before you choose
Open model licences differ, some with conditions for commercial use above a revenue threshold; check the licence for each model.
Self-hosting requires capable GPUs and maintenance; compare that cost with the hosted API for your volume.
Frequently asked questions
Is Stable Diffusion free to use?
Many Stable Diffusion models are released with open weights you can download, under licences that set conditions on use.
How does the Stability AI API charge?
The API uses credits worth US$0.01 each, with 25 free credits to start; each model has its own credit cost.
Does Stability AI make audio models?
Yes, Stable Audio generates music and sound effects from text prompts or audio samples.
Check the official website for current features, pricing, and terms.
Similar tools
Stable Audio
AudioStable Audio is Stability AI’s music and sound effect generator, built on the Stable Audio 3.0 model family trained on licensed data, with DAW integration.
FLUX by Black Forest Labs
Image & DesignFLUX is a family of image and video generation models from Black Forest Labs, available through an API, a playground and open weights for self-hosting.
Tensor.Art
Image & DesignTensor.Art is an AI model sharing and image generation platform where users run, train, upload and download community models such as Stable Diffusion variants.
Prodia
CodingProdia provides a JavaScript‑driven interface that connects to a Stable Diffusion API, enabling developers to generate high‑quality images and AI‑created music.
DeepSeek
CodingDeepSeek develops large language models, including open-weight reasoning models, offered through a chat app and an OpenAI-compatible developer API.
Wan
VideoWan is a family of video generation models from Alibaba’s Wan team, with open-source releases on GitHub and a hosted creative platform now on Wan 3.0.