---
title: "Stability AI models: release history and timeline"
description: "Generative AI company behind Stable Diffusion, Stable Video and Stable Audio, releasing many of its image, video, audio and language models with open weights."
type: "release-archive"
canonical_url: "https://theaiengineering.com/releases/stability-ai"
markdown_url: "https://theaiengineering.com/releases/stability-ai.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-05-20"
citation: "The AI Engineering Editors. \"Stability AI models: release history and timeline.\" The AI Engineering, updated May 20, 2026. https://theaiengineering.com/releases/stability-ai"
license: "CC BY 4.0"
license_url: "https://creativecommons.org/licenses/by/4.0/"
data_csv: "https://theaiengineering.com/releases.csv"
data_json: "https://theaiengineering.com/releases.json"
---

# Stability AI models: release history and timeline

Generative AI company behind Stable Diffusion, Stable Video and Stable Audio, releasing many of its image, video, audio and language models with open weights.

- Headquarters: London, United Kingdom
- Founded: 2019
- Website: https://stability.ai

28 releases from 1 lab, 23 with open weights. Dates are the labs' official announcement dates.

## May 2026

### Stable Audio 3.0 Large

Largest Stable Audio 3.0 model with the family's most advanced musicality, built for music platforms and creative applications that need low-latency, high-volume generation.

- Date: 2026-05-20
- Lab: Stability AI
- Type: Music
- Weights: Proprietary
- Modalities: text, audio → audio
- Available at launch: API, Enterprise
- Permalink: https://theaiengineering.com/releases/2026/05#stable-audio-3-large

Highlights:

- Generates tracks of more than six minutes
- Supports single and multi-segment audio inpainting and continuation
- Available via the Stability AI API and enterprise self-hosting

Source: [Meet Stable Audio 3.0, the model family built for artistic experimentation with open-weight models](https://stability.ai/news-updates/meet-stable-audio-3-the-model-family-built-for-artistic-experimentation-with-open-weight-models)

### Stable Audio 3.0 Small, Small SFX and Medium

Open-weight members of the Stable Audio 3.0 family, trained on fully licensed data with a semantic-acoustic autoencoder; Small runs full music composition on-device and Medium generates tracks over six minutes.

- Date: 2026-05-20
- Lab: Stability AI
- Type: Music
- Weights: Open weights
- Modalities: text, audio → audio
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/05#stable-audio-3-open

Highlights:

- 3.0 Small generates up to two minutes; Medium more than six minutes
- Small SFX targets on-device sound effects
- LoRA training documentation published with the weights

Source: [Meet Stable Audio 3.0, the model family built for artistic experimentation with open-weight models](https://stability.ai/news-updates/meet-stable-audio-3-the-model-family-built-for-artistic-experimentation-with-open-weight-models)

## September 2025

### Stable Audio 2.5

Enterprise-focused audio model with improved musical composition that generates tracks up to three minutes long in under two seconds on a GPU and supports audio inpainting.

- Date: 2025-09-10
- Lab: Stability AI
- Type: Music
- Weights: Proprietary
- Modalities: text, audio → audio
- Available at launch: API, Consumer app, Cloud platforms, Enterprise
- Permalink: https://theaiengineering.com/releases/2025/09#stable-audio-2-5

Highlights:

- Post-trained with the Adversarial Relativistic-Contrastive method
- Trained on a fully licensed dataset
- Available via the Stability API, fal, Replicate, ComfyUI and on-premises licensing

Source: [Stability AI Introduces Stable Audio 2.5, the First Audio Model Built for Enterprise Sound Production at Scale](https://stability.ai/news-updates/stability-ai-introduces-stable-audio-25-the-first-audio-model-built-for-enterprise-sound-production-at-scale)

## May 2025

### Stable Audio Open Small

341M-parameter text-to-audio model developed with Arm and optimized to run entirely on Arm CPUs, generating up to 11 seconds of audio on a smartphone in under 8 seconds.

- Date: 2025-05-14
- Lab: Stability AI
- Type: Music
- Weights: Open weights
- Modalities: text → audio
- Parameters: 341M
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/05#stable-audio-open-small

Highlights:

- 341M parameters versus 1.1B for Stable Audio Open
- Optimized with Arm KleidiAI
- Free for commercial use under the Stability AI Community License

Source: [Stability AI and Arm Collaborate to Release Stable Audio Open Small, Enabling Real-World Deployment for On-Device Audio Generation](https://stability.ai/news-updates/stability-ai-and-arm-release-stable-audio-open-small-enabling-real-world-deployment-for-on-device-audio-control)

## March 2025

### Stable Virtual Camera

Multi-view video generation model that turns 2D images into immersive videos with 3D camera control, keeping 3D consistency across sequences up to 1,000 frames.

- Date: 2025-03-18
- Lab: Stability AI
- Type: Video
- Weights: Open weights
- Modalities: image → video
- License: Stability AI Non-Commercial Research Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/03#stable-virtual-camera

Highlights:

- Research release under a non-commercial license
- Weights on Hugging Face and code on GitHub
- Supports seamless loops and revisiting viewpoints

Source: [Introducing Stable Virtual Camera: Multi-View Video Generation with 3D Camera Control](https://stability.ai/news-updates/introducing-stable-virtual-camera-multi-view-video-generation-with-3d-camera-control)

## November 2024

### Stable Diffusion 3.5 Large ControlNets

Blur, Canny and Depth ControlNet models for Stable Diffusion 3.5 Large that add structural control to generations, including tiled upscaling to 8K and 16K resolution.

- Date: 2024-11-26
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text, image → image
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/11#sd-3-5-large-controlnets

Highlights:

- Three control types: Blur, Canny and Depth
- Weights on Hugging Face with ComfyUI support
- Stability AI Community License

Source: [ControlNets for Stable Diffusion 3.5 Large](https://stability.ai/news-updates/sd3-5-large-controlnets)

## October 2024

### Stable Diffusion 3.5 Medium

2.5B-parameter Stable Diffusion 3.5 model with an improved MMDiT-X architecture, designed to run on standard consumer hardware and generate images between 0.25 and 2 megapixels.

- Date: 2024-10-29
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text → image
- Parameters: 2.5B
- License: Stability AI Community License
- Available at launch: Open weights, API
- Permalink: https://theaiengineering.com/releases/2024/10#stable-diffusion-3-5-medium

Highlights:

- 2.5B parameters
- Requires about 9.9 GB of VRAM excluding text encoders
- Released one week after SD 3.5 Large

Source: [Introducing Stable Diffusion 3.5](https://stability.ai/news-updates/introducing-stable-diffusion-3-5)

### Stable Diffusion 3.5 Large and Large Turbo

Open Stable Diffusion 3.5 release led by the 8.1B-parameter Large base model for professional 1MP work and a distilled Large Turbo variant that generates images in four steps.

- Date: 2024-10-22
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text → image
- Parameters: 8.1B
- License: Stability AI Community License
- Available at launch: Open weights, API, Cloud platforms
- Permalink: https://theaiengineering.com/releases/2024/10#stable-diffusion-3-5-large

Highlights:

- Stable Diffusion 3.5 Large has 8.1B parameters
- Large Turbo generates in 4 steps
- Free commercial use for smaller organizations under the Stability AI Community License

Source: [Introducing Stable Diffusion 3.5](https://stability.ai/news-updates/introducing-stable-diffusion-3-5)

## June 2024

### Stable Diffusion 3 Medium

First open-weight release from the Stable Diffusion 3 series, a 2B-parameter text-to-image model, also offered through the Stability API with TensorRT and AMD-optimized versions.

- Date: 2024-06-12
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text → image
- Parameters: 2B
- License: Stability AI Community License
- Available at launch: Open weights, API
- Permalink: https://theaiengineering.com/releases/2024/06#stable-diffusion-3-medium

Highlights:

- 2B parameters
- TensorRT-optimized version developed with NVIDIA
- Available on the Stability API powered by Fireworks AI

Source: [Announcing the Open Release of Stable Diffusion 3 Medium, Our Most Sophisticated Image Generation Model to Date](https://stability.ai/news-updates/stable-diffusion-3-medium)

### Stable Audio Open

Open text-to-audio model for generating up to 47 seconds of samples and sound effects such as drum beats, instrument riffs, ambience and foley for music production and sound design.

- Date: 2024-06-05
- Lab: Stability AI
- Type: Music
- Weights: Open weights
- Modalities: text → audio
- Parameters: 1.1B
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/06#stable-audio-open

Highlights:

- Up to 47 seconds of audio per generation
- Weights on Hugging Face
- 1.1B parameters, per Stability AI's later Stable Audio Open Small announcement

Source: [Introducing Stable Audio Open - An Open Source Model for Audio Samples and Sound Design](https://stability.ai/news-updates/introducing-stable-audio-open)

## April 2024

### Stable LM 2 12B

12B-parameter base and instruction-tuned language models trained on 2 trillion tokens in seven languages, released alongside an updated Stable LM 2 1.6B with tool use and function calling.

- Date: 2024-04-08
- Lab: Stability AI
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 12B
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/04#stable-lm-2-12b

Highlights:

- Seven languages including English, Spanish, German and French
- Commercial use through a Stability AI Membership
- Base and chat models on Hugging Face

Source: [Introducing Stable LM 2 12B](https://stability.ai/news-updates/introducing-stable-lm-2-12b)

### Stable Audio 2.0

Second-generation Stable Audio model producing full tracks with coherent structure up to three minutes long at 44.1 kHz stereo from a single prompt, and adding audio-to-audio generation.

- Date: 2024-04-03
- Lab: Stability AI
- Type: Music
- Weights: Proprietary
- Modalities: text, audio → audio
- Available at launch: Consumer app, API
- Permalink: https://theaiengineering.com/releases/2024/04#stable-audio-2

Highlights:

- Trained exclusively on licensed data from the AudioSparx library
- Free to use on the Stable Audio website at launch
- API availability followed later

Source: [Introducing Stable Audio 2.0](https://stability.ai/news-updates/stable-audio-2-0)

## March 2024

### Stable Code Instruct 3B

Instruction-tuned version of Stable Code 3B that adds natural language interaction for code generation and software development tasks, focusing on Python, JavaScript, Java, C, C++ and Go.

- Date: 2024-03-25
- Lab: Stability AI
- Type: Coding
- Weights: Open weights
- Modalities: text → text
- Parameters: 3B
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/03#stable-code-instruct-3b

Highlights:

- Built on Stable Code 3B
- Weights and code on Hugging Face
- Commercial use through a Stability AI Membership

Source: [Introducing Stable Code Instruct 3B](https://stability.ai/news-updates/introducing-stable-code-instruct-3b)

## February 2024

### Stable Diffusion 3

Stable Diffusion 3 suite combining a diffusion transformer architecture with flow matching, ranging from 800M to 8B parameters, announced in early preview with improved multi-subject prompts and spelling.

- Date: 2024-02-22
- Lab: Stability AI
- Type: Image
- Weights: Proprietary
- Modalities: text → image
- Parameters: 800M to 8B
- Available at launch: API
- Permalink: https://theaiengineering.com/releases/2024/02#stable-diffusion-3

Highlights:

- Announced with a waitlist for an early preview
- Stable Diffusion 3 and SD3 Turbo became available in the Stability API on April 17, 2024
- Multimodal Diffusion Transformer uses separate weights for image and language

Source: [Stable Diffusion 3](https://stability.ai/news-updates/stable-diffusion-3)

### Stable Cascade

Research-preview text-to-image model built on the Würstchen architecture, using a three-stage design that decouples text-conditional generation from decoding to make fine-tuning more efficient.

- Date: 2024-02-12
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text → image
- Parameters: Stage C: 1B or 3.6B
- License: Stability AI Non-Commercial Research Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/02#stable-cascade

Highlights:

- Stage C released in 1B and 3.6B parameter versions
- Non-commercial license
- Training and inference code on GitHub

Source: [Introducing Stable Cascade](https://stability.ai/news-updates/introducing-stable-cascade)

## January 2024

### Stable LM 2 1.6B

First model of the Stable LM 2 series, a 1.6B-parameter small language model with base and instruction-tuned versions trained on about 2 trillion tokens in seven languages.

- Date: 2024-01-19
- Lab: Stability AI
- Type: Small model
- Weights: Open weights
- Modalities: text → text
- Parameters: 1.6B
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/01#stable-lm-2-1-6b

Highlights:

- Languages: English, Spanish, German, Italian, French, Portuguese and Dutch
- Commercial use through a Stability AI Membership
- Updated version with tool use released April 8, 2024

Source: [Introducing Stable LM 2 1.6B](https://stability.ai/news-updates/introducing-stable-lm-2)

### Stable Code 3B

3B-parameter code completion model built on Stable LM 3B and trained on 18 programming languages, adding fill-in-the-middle support and training on sequences up to 16,384 tokens.

- Date: 2024-01-16
- Lab: Stability AI
- Type: Coding
- Weights: Open weights
- Modalities: text → text
- Context window: 16,384 tokens
- Parameters: 3B
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/01#stable-code-3b

Highlights:

- Fill-in-the-middle code completion
- Trained on 18 programming languages
- Included in the Stability AI Membership for commercial use

Source: [Stable Code 3B: Coding on the Edge](https://stability.ai/news-updates/stable-code-2024-llm-code-completion-release)

## December 2023

### StableLM Zephyr 3B

3B-parameter chat model extending Stable LM 3B-4e1t, preference-tuned with a Zephyr-style pipeline for instruction following and question answering on edge devices.

- Date: 2023-12-07
- Lab: Stability AI
- Type: Small model
- Weights: Open weights
- Modalities: text → text
- Parameters: 3B
- License: Stability AI Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/12#stablelm-zephyr-3b

Highlights:

- Supervised fine-tuning followed by preference tuning
- Launched under a non-commercial license
- Built on Stable LM 3B-4e1t

Source: [Introducing Stable LM Zephyr 3B: A New Addition to Stable LM, Bringing Powerful LLM Assistants to Edge Devices](https://stability.ai/news-updates/stablelm-zephyr-3b-stability-llm)

## November 2023

### SDXL Turbo

Real-time text-to-image model distilled from SDXL 1.0 with Adversarial Diffusion Distillation, cutting the required sampling steps from 50 to one while keeping high fidelity.

- Date: 2023-11-28
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text → image
- License: Stability AI Community License
- Available at launch: Open weights, Consumer app
- Permalink: https://theaiengineering.com/releases/2023/11#sdxl-turbo

Highlights:

- Single-step image generation
- Initially released under a non-commercial research license
- Beta real-time demo on Clipdrop

Source: [Introducing SDXL Turbo: A Real-Time Text-to-Image Generation Model](https://stability.ai/news-updates/stability-ai-sdxl-turbo)

### Stable Video Diffusion

Stability AI's first open video model, released in research preview as two image-to-video models generating 14 and 25 frames at customizable frame rates between 3 and 30 frames per second.

- Date: 2023-11-21
- Lab: Stability AI
- Type: Video
- Weights: Open weights
- Modalities: image → video
- License: Stability AI Community License
- Available at launch: Open weights, API
- Permalink: https://theaiengineering.com/releases/2023/11#stable-video-diffusion

Highlights:

- Code on GitHub and weights on Hugging Face
- API access added on December 20, 2023
- Current Hugging Face license is the Stability AI Community License

Source: [Introducing Stable Video Diffusion](https://stability.ai/news-updates/stable-video-diffusion-open-ai-video-model)

## October 2023

### Stable LM 3B

Experimental 3B-parameter compact language model designed to run on portable devices, intended as an intermediate release in the Stable LM line.

- Date: 2023-10-02
- Lab: Stability AI
- Type: Small model
- Weights: Open weights
- Modalities: text → text
- Parameters: 3B
- License: CC-BY-SA-4.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/10#stable-lm-3b

Highlights:

- 3B parameters, aimed at smart devices and laptops
- Released on Hugging Face as stablelm-3b-4e1t
- Base for later models such as Stable Code 3B

Source: [Introducing Stable LM 3B: Bringing Sustainable, High-Performance Language Models to Smart Devices](https://stability.ai/news-updates/stable-lm-3b-sustainable-high-performance-language-models-smart-devices)

## September 2023

### Stable Audio

Stability AI's first music and sound generation product, generating tracks from text prompts and a requested duration through a web interface with free and Pro tiers.

- Date: 2023-09-13
- Lab: Stability AI
- Type: Music
- Weights: Proprietary
- Modalities: text → audio
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2023/09#stable-audio

Highlights:

- Free tier generates tracks up to 45 seconds
- Pro subscription produces 90-second tracks for commercial use
- Users set a desired track length along with the text prompt

Source: [Announcing Stable Audio, a product for music & sound generation](https://stability.ai/news-updates/stable-audio-using-ai-to-generate-music)

## August 2023

### StableCode (Alpha)

Stability AI's first code models: a base model trained on BigCode's The Stack, an instruction-tuned model and a long-context completion model aimed at single and multi-line autocomplete.

- Date: 2023-08-08
- Lab: Stability AI
- Type: Coding
- Weights: Open weights
- Modalities: text → text
- Parameters: 3B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/08#stablecode-alpha

Highlights:

- Three models: base, instruction-tuned and long-context completion
- Completion model released under Apache 2.0
- 3B parameters

Source: [Announcing Stable Code Alpha](https://stability.ai/news-updates/stablecode-llm-generative-ai-coding)

## July 2023

### SDXL 1.0

Open release of Stable Diffusion XL, Stability AI's flagship image model at the time, with a 3.5B-parameter base model and a refiner forming a 6.6B-parameter pipeline at native 1024x1024.

- Date: 2023-07-26
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text, image → image
- Parameters: 3.5B base, 6.6B ensemble
- License: CreativeML OpenRAIL++-M
- Available at launch: Open weights, API, Consumer app, Cloud platforms
- Permalink: https://theaiengineering.com/releases/2023/07#sdxl-1-0

Highlights:

- Released under the CreativeML OpenRAIL++-M License
- Runs on consumer GPUs with 8GB VRAM
- Available on Amazon SageMaker, Amazon Bedrock and DreamStudio

Source: [Announcing SDXL 1.0](https://stability.ai/news-updates/stable-diffusion-sdxl-1-announcement)

### Stable Beluga 1 and Stable Beluga 2

Instruction fine-tuned language models from Stability AI and its CarperAI lab, built on the LLaMA 65B and Llama 2 70B foundation models and trained on a synthetic Orca-style dataset.

- Date: 2023-07-21
- Lab: Stability AI
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Parameters: 65B and 70B
- License: Stable Beluga Non-Commercial Community License
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/07#stable-beluga

Highlights:

- Released for non-commercial research use
- Formerly codenamed FreeWilly
- Trained on 600,000 synthetic instruction examples

Source: [Meet Stable Beluga 1 and Stable Beluga 2, Our Large and Mighty Instruction Fine-Tuned Language Models](https://stability.ai/news-updates/stable-beluga-large-instruction-fine-tuned-models)

## June 2023

### SDXL 0.9

Research release of Stable Diffusion XL with a 3.5B-parameter base model in a 6.6B-parameter two-model ensemble, offered on Clipdrop and the Stability API ahead of the open SDXL 1.0 release.

- Date: 2023-06-22
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text, image → image
- Parameters: 3.5B base, 6.6B ensemble
- License: SDXL 0.9 Research License
- Available at launch: Open weights, API, Consumer app
- Permalink: https://theaiengineering.com/releases/2023/06#sdxl-0-9

Highlights:

- Research weights available on application under a non-commercial, research-only license
- Uses two CLIP models including OpenCLIP ViT-G/14
- Native 1024x1024 resolution

Source: [Stability AI launches SDXL 0.9: A Leap Forward in AI Image Generation](https://stability.ai/news-updates/sdxl-09-stable-diffusion)

## April 2023

### DeepFloyd IF

Cascaded pixel diffusion text-to-image model from Stability AI's DeepFloyd research lab, using a T5-XXL text encoder to render coherent text in images, released under a non-commercial research license.

- Date: 2023-04-28
- Lab: Stability AI
- Type: Image
- Weights: Open weights
- Modalities: text → image
- License: DeepFloyd IF License Agreement
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/04#deepfloyd-if

Highlights:

- Research release on a non-commercial, research-permissible license
- Uses T5-XXL-1.1 as the text encoder
- Supports zero-shot image-to-image translation

Source: [Stability AI releases DeepFloyd IF, a powerful text-to-image model that can smartly integrate text into images](https://stability.ai/news-updates/deepfloyd-if-text-to-image-model)

### StableLM (Alpha)

First Stable LM release, 3B and 7B base language models trained on an experimental dataset built on The Pile with 1.5 trillion tokens, plus research-only instruction-tuned variants.

- Date: 2023-04-19
- Lab: Stability AI
- Type: LLM
- Weights: Open weights
- Modalities: text → text
- Context window: 4,096 tokens
- Parameters: 3B and 7B
- License: CC-BY-SA-4.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2023/04#stablelm-alpha

Highlights:

- Base models usable commercially under CC BY-SA 4.0
- Trained with a 4,096-token sequence length
- Instruction-tuned research models released alongside

Source: [Stability AI Launches the First of its Stable LM Suite of Language Models](https://stability.ai/news-updates/stability-ai-launches-the-first-of-its-stablelm-suite-of-language-models)

## Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL. Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

The AI Engineering Editors. "Stability AI models: release history and timeline." The AI Engineering, updated May 20, 2026. https://theaiengineering.com/releases/stability-ai

HTML link:

```html
<a href="https://theaiengineering.com/releases/stability-ai">Stability AI models: release history and timeline</a> (The AI Engineering)
```

- Title: Stability AI models: release history and timeline
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-05-20
- URL: https://theaiengineering.com/releases/stability-ai
- Markdown: https://theaiengineering.com/releases/stability-ai.md
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- Full dataset as CSV: https://theaiengineering.com/releases.csv
- Full dataset as JSON: https://theaiengineering.com/releases.json
