Stable Diffusion
Open-source image generation you can run locally
Stable Diffusion is the most popular open-source image generation model, running on local GPUs or cloud services. SDXL and SD3 produce high-quality images with full creative control and no content restrictions.
Editor rating is our overall editorial judgment of the tool, out of 5. It is not a test score and not a user-review average. Ratings have not been re-scored since the tool was listed here. The reasons are in Best for and Pros & cons below.
Requires some technical comfort with API keys, command line, or coding. If you're new to AI, start with a chat-based tool first.
Best for
Pros & cons
✓ Pros
✗ What this won't do
Use cases
Generating product images at scale
Training custom style models
Running offline image generation
Creating game assets
Create an account
Sign up on the Stability AI Developer Platform. Signing in with Google gives you 25 free credits to try it.
Get your API key
Open the API Keys page in your account and copy the key. Your code sends it with each request in the Authorization header.
Generate your first image
Send a text prompt to Stable Image Core, the fast, low-cost model, for example "a cozy reading corner, watercolor style". Each image uses 3 credits.
Watch your credits
Each model uses a different number of credits per request. When the free credits run out, buy more on the Pricing page.
Compare alternatives
| Tool | Category | Editor rating | Pricing |
|---|---|---|---|
| Stable Diffusion (current) | Design | 4.5 | Free (open-source) / hosted from $10 mo |
| Midjourney | Design | 4.8 | From $10 mo |
| Figma AI | Design | 4.4 | Included with Figma / from $15 mo |