Stability AI Open Models: Model List and Licenses
About Stability AI
Stability AI is the AI company that has released the Stable Diffusion image models. It publishes image, audio and other generation models on its stabilityai organization on Hugging Face, and it is the publisher that made local image generation widespread.
What It Releases
- Stable Diffusion: SDXL, Stable Diffusion 3 and 3.5 and more. In 2025 and 2026 it released many versions optimized for AMD GPUs and NPUs and for NVIDIA TensorRT.
- Stable Audio 3 (May 2026): according to its model page, a family of fast latent diffusion models (small, medium, large) for variable-length audio generation and editing. It can generate several minutes of audio, avoids the cost of full-length generation for short sounds, and supports inpainting. There are also small versions for music and sound effects.
- There are also research models.
Licenses
Most recent models use the Stability AI Community License. Research, non-commercial use and commercial use by individuals or organizations with annual revenue below US$1 million are free. Commercial use requires registering with Stability AI, and above US$1 million in revenue an enterprise license is required. Some SDXL models use the CreativeML Open RAIL++-M license. This summary is not legal advice; read each model’s license text before use.
Running Them Locally
- Official GGUF builds exist only for some older language models (StableLM 2) (as of 2026-09-26). The image and audio models are used through diffusers, ComfyUI and similar tools.
- Its range of builds for AMD GPUs and NPUs is rare among publishers.
- Many models are gated, so accept the license on Hugging Face before downloading.
Sources: the model page of stabilityai/stable-audio-3-medium; the Stability AI Community License in stabilityai/stable-audio-3-optimized; the model list of the stabilityai organization on Hugging Face (all as of 2026-09-26).
Our Coverage and Data
Local Model Watch has not published an article on Stability AI’s models yet. The model list below is collected by code from Hugging Face every day. Part of our publisher index; model families link to their family pages.
At a Glance
| Item | Value |
|---|---|
| Hugging Face organization | stabilityai |
| Models on Hugging Face | 117 |
| Articles on its own models | 0 |
| Articles on derived models | 0 |
Recent Models on Hugging Face
The publisher lists 117 models in total on Hugging Face. Below are up to 15 of the most recent generative models (text, image, video, audio and so on), the scope of this site, per organization. Classifiers, feature extractors, research components and repositories without a model card are omitted, and the publisher’s own quantized builds and helper variants are folded into the row of the original model. Parameter counts are left blank for repositories that pack weights into integer types, where Hugging Face’s count is not the real parameter count.
→ Scroll horizontally to see all columns
| Released | Model | Task | Parameters | License | Official variants |
|---|---|---|---|---|---|
| 2026-05-19 | stabilityai/stable-audio-3-optimized | audio | — | stable-audio-community |
— |
| 2026-05-17 | stabilityai/SAME-L | — | 852M | stable-audio-community |
— |
| 2026-05-17 | stabilityai/SAME-S | — | 108M | stable-audio-community |
— |
| 2026-05-17 | stabilityai/stable-audio-3-small-music | audio | 568M | stable-audio-community |
base |
| 2026-05-17 | stabilityai/stable-audio-3-small-sfx | audio | 568M | stable-audio-community |
base |
| 2026-05-17 | stabilityai/stable-audio-3-medium | audio | 2.3B | stable-audio-community |
base |
| 2026-05-02 | stabilityai/stable-diffusion-3.5-medium-amdnpu | image generation | — | stabilityai-ai-community |
— |
| 2026-05-02 | stabilityai/stable-diffusion-3-medium-amdnpu | image generation | — | stabilityai-ai-community |
— |
| 2026-02-26 | stabilityai/sdxl-base-amdnpu | image generation | — | openrail++ |
— |
| 2026-02-26 | stabilityai/sdxl-turbo-amdnpu | image generation | — | stabilityai-ai-community |
— |
| 2026-02-26 | stabilityai/sd-turbo-amdnpu | image generation | — | stabilityai-ai-community |
— |
| 2025-11-04 | stabilityai/sp4d | — | — | stabilityai-ai-community |
— |
| 2025-08-08 | stabilityai/stable-diffusion-3.5-controlnets-tensorrt | image generation | — | stabilityai-ai-community |
— |
| 2025-08-08 | stabilityai/stable-diffusion-3.5-medium-tensorrt | image generation | — | stabilityai-ai-community |
— |
| 2025-05-16 | stabilityai/stable-diffusion-3.5-large-tensorrt | image generation | — | stabilityai-ai-community |
— |
From the Hugging Face API. Last changed 2026-09-27 (JST). Collected by code.
Last updated 2026-09-27 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under “Our Coverage and Data" are assembled by code from our article log and the Hugging Face API.