0
Image generationMITPython

Stability AI Generative Models

Stability AI’s reference code for SDXL and Stable Video Diffusion.

GitHub
Stars
27.3K
Forks
3.1K
Open issues
338
Last commit
2025-12-16

Live from the GitHub API · updated 2026-10-15

What is Stability AI Generative Models?

Stability AI’s generative-models repository contains the official sampling and training code for SDXL, SDXL-Turbo, Stable Video Diffusion and related models, with Streamlit demos for local testing.

Key features

  • Reference implementations for SDXL and SVD
  • Streamlit sampling demos
  • Config-driven training code

System requirements

Platforms
Linux
GPU
NVIDIA
VRAM
16 GB+ (more for video)

How to install Stability AI Generative Models

Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.

Linux

  1. 1
    Clone and install.
    git clone https://github.com/Stability-AI/generative-models.git
cd generative-models
python3 -m venv .pt2
source .pt2/bin/activate
pip install -r requirements/pt2.txt
pip install .
  2. 2
    Run the sampling demo described in the README.
    streamlit run scripts/demo/sampling.py --server.port <port>

Strengths

  • Official reference code
  • Includes video diffusion

Limitations

  • Developer-oriented
  • Linux-focused

Stability AI Generative Models alternatives compared

SoftwareStarsLicensePlatformsVRAM
Stability AI Generative Models

Stability AI’s reference code for SDXL and Stable Video Diffusion.

27.3KMIT16 GB+ (more for video)
Diffusers

Hugging Face’s Python library for diffusion models.

34.7KApache-2.0—
ComfyUI

Node-based interface for diffusion models — images, video and audio.

137.6KGPL-3.04 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models
Stable Diffusion WebUI (AUTOMATIC1111)

The classic browser UI for Stable Diffusion with a massive extension ecosystem.

165.1KAGPL-3.04 GB minimum (with --medvram/--lowvram), 8 GB+ recommended
Stable Diffusion WebUI Forge

A faster, leaner fork of the A1111 WebUI with FLUX support.

13.1KAGPL-3.06 GB+ (FLUX NF4/GGUF variants run on 6–8 GB)
Fooocus

Midjourney-like simplicity for SDXL: type a prompt and press Generate.

53.4KGPL-3.04 GB minimum, 6 GB+ recommended

Related models

Stable DiffusionThe open-source image model with the largest ecosystem.

FAQ

Is Stability AI Generative Models free?

Yes — Stability AI Generative Models is open-source software released under the MIT license. Check the license (and any model weight licenses) before commercial use.

Does Stability AI Generative Models run on Windows, Mac and Linux?

Stability AI Generative Models supports: Linux.

What hardware do I need for Stability AI Generative Models?

NVIDIA. VRAM: 16 GB+ (more for video)

How do I install Stability AI Generative Models?

1. Clone and install. 2. Run the sampling demo described in the README.

What are the best Stability AI Generative Models alternatives?

Popular alternatives include Diffusers, ComfyUI, Stable Diffusion WebUI (AUTOMATIC1111), Stable Diffusion WebUI Forge. See the comparison table on this page.

Can I use Stability AI Generative Models online without installing it?

If you just want results, AiLoft runs top image models such as GPT Image 2.5 and Nano Banana Pro in the browser — no GPU or setup required.

Skip the install — generate images in your browser

No GPU, drivers or Python needed. Use GPT Image 2.5 and Nano Banana Pro online and compare them side by side.

AI Image Generator
Open-source AI image generators