
Stable Diffusion
Editors' choice
37 0Open-weights text-to-image model by Stability AI: runs locally on a GPU, LoRA and ControlNet, versions 1.5 to 3.5. Free under $1M annual revenue.
- Category
- Image & Design
- Pricing
- Free
- Free plan
- Yes
- Access
- Open source, API
- Use case
- Image generation
Stable Diffusion is an open text-to-image generation model developed by Stability AI. Unlike closed services, it can be downloaded and run on your own computer with a GPU—without a subscription or the limitations of a third-party service. A large community has grown around the model, with thousands of fine-tuned models and interfaces such as ComfyUI and Automatic1111.
A model with open weights: available for download from Hugging Face. Stable Diffusion is free for organizations with revenue of up to $1 million.
Versions
- 1.5 (2022) — lightweight and reliable, serving as the foundation for numerous community models.
- 2.1 (2022) — negative prompts and 768×768 resolution.
- SDXL (2023) — significantly higher quality; SDXL Turbo enables fast generation.
- 3.5 (2024) — models with up to 8 billion parameters, better at understanding long descriptions and text in images.
Capabilities
- Images from descriptions and reference images (img2img), inpainting, and fragment replacement.
- Fine-tuning. LoRA, ControlNet, and additional training for your own style.
- Local deployment — data does not leave your environment for the cloud.
- API — through the Stability AI platform.
Pricing
The models are free for personal use and for companies with annual revenue of up to $1 million (Community License). Large companies require an Enterprise License. The Stability AI API is paid for with credits. Local deployment requires a GPU; newer versions need more VRAM.
Articles about this tool
- The 5 best AI image generators for commercial use
- The best Stable Diffusion prompts: 46 ready-to-use examples
- How to download and install Stable Diffusion models
- Stable Diffusion prompt generators
- How to speed up image generation in Stable Diffusion
- How to install and use LoRA models in Stable Diffusion
- ControlNet for Stable Diffusion: what it is and how to install it
- How to install Stable Diffusion on your computer
FAQ
Do I need a VPN or proxy to use the service?
It depends on your region. If the service is not available in your country, its site says so; a VPN or proxy is a way around regional limits, but follow the rules of the service and the laws of your country. How to choose a proxy is covered in our guide to proxies for Claude. The easiest check is to open the service site.
Is it safe to share my data with an AI tool?
Do not enter passwords, payment details, personal data or trade secrets. Many services store requests and may use them to train models, especially on free plans. Check the privacy policy and the settings of the service, where training can often be switched off.
Similar tools
-
30 0
OpenArt is an AI image generator with a graphics editor: text prompts, sketch-to-image and QR codes. 100 free credits, plans from $7.99 a month.
- Image & Design
- Paid
- Image generation
- Photo editing
-
28 0
Green Screen AI is an interactive, easy-to-use platform for transforming your photos into generative art with artificial intelligence.
- Image & Design
- Photo editing
-
28 0
MakeLogo AI is a powerful AI-powered tool for creating unique logos.
- Image & Design
- Paid
- Logos & branding
-
28 0
An AI tool for planning residential spaces. Access is completely free for regular users.
- Image & Design
- Free
- Architecture
-
27 0
Rostrio (formerly Passphoto) is an AI-powered service for processing personal photos.
- Image & Design
- Photo editing
-
27 0
Freemium AI headshot generator: studio-quality photos for LinkedIn, actor headshots, marketing and social media profiles from your selfies.
- Image & Design
- Paid
- Photo editing