What Is Stable Diffusion 3 Medium?
Stable Diffusion 3 Medium is Stability AI’s two-billion-parameter MMDiT checkpoint. It is an important compact member of the SD3 family and exposes the controls many open-model users expect: steps, guidance, a negative prompt, prompt expansion and a deterministic seed.
Stable Diffusion Model Versions
Stable Diffusion 3 Medium
Open weights · 1K
From 3 Credits
Stable Diffusion 3.5 Large
The full 8B SD 3.5 model with negative prompts, CFG and sampling-step control.
- Resolutions: 1K / 2K
- Reference images: not supported
- Modes: Text to Image
- Speed: Balanced
Stable Diffusion 3.5 Large Turbo
The four-step distilled SD 3.5 Large for fast, controllable open-model drafts.
- Resolutions: 1K / 2K
- Reference images: not supported
- Modes: Text to Image
- Speed: Fastest
Stable Diffusion 3.5 Medium
The resource-efficient SD3.5 tier with classic CFG, steps and negative-prompt controls.
- Resolutions: 1K / 2K
- Reference images: not supported
- Modes: Text to Image, Typography
- Speed: Balanced
Stable Diffusion 3 Medium
Stability AI’s two-billion-parameter SD3 checkpoint with typography, negative prompts and familiar diffusion controls.
- Resolutions: 1K
- Reference images: not supported
- Modes: Text to Image, Typography
- Speed: Balanced
Stable Image Ultra
The full classic parameter set: Negative Prompt, Steps, Guidance, Strength.
- Resolutions: 1K / 2K
- Reference images: up to 1
- Modes: Text to Image, Image to Image, Edit Image
- Speed: Balanced
What Is Stable Diffusion 3 Medium Best For?
- Open-weight evaluation
- Typography experiments
- Controlled illustration
- Classic negative-prompt workflows
How to Use Stable Diffusion 3 Medium
- Start with 28 steps and guidance 5.
- Name only concrete exclusions.
- Fix a seed for comparisons.
- Use SD 3.5 when the newer family is more important than checkpoint fidelity.
Stable Diffusion 3 Medium Settings Explained
Guidance
Five is the documented default; extreme values can reduce natural texture.
Prompt Expansion
Disabled by default so the compact checkpoint follows your literal prompt.
The panel above shows only the parameters Stable Diffusion 3 Medium actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.
Stable Diffusion 3 Medium Prompt Examples
Typography portrait
Expressive tiger warrior in full armour before a fabric banner reading “OPEN / SOURCE”, dramatic painterly battlefield light
Graphic still life
Four geometric glass vessels on cobalt plinths, precise studio reflections, modern design magazine cover, clean negative space
Stable Diffusion 3 Medium Test Results
Testing in progress
Every model runs the same eight-category prompt set — portrait, product, poster text, anime character, interior, multi-reference, image editing and character consistency — recording generation time, success rate, text accuracy and identity retention. That run has not finished for Stable Diffusion 3 Medium, so this page shows no scores. We do not publish numbers we have not measured.
Stable Diffusion 3 Medium Limitations
- Older than SD 3.5
- Text-to-image only here
- Small exact lettering still needs review
Stable Diffusion 3 Medium Pricing and Credits
Credits scale with resolution and image count. The Generate button always shows what this run costs.
1K
3 credits / image
Failed generations cost 0 credits.
Commercial Use and Image Rights
Open weights are governed by the Stability AI Community License; hosted use also follows the selected service terms.
- Model used: Stable Diffusion 3 Medium
- Model developer: Stability AI
- The inference route is managed internally and may change without changing the selected model
- Uploads are sent only to the configured inference service needed to complete the generation
- You can delete any generation from your history at any time
Frequently Asked Questions
Is this Stable Diffusion 3.5?+
No. This page preserves the exact earlier SD3 Medium checkpoint rather than substituting SD 3.5.
Why include an older checkpoint?+
Named open checkpoints remain useful for reproducibility, comparison and workflows built around their visual character.
Release History and Sources
June 12, 2024 · Open weights released
This date applies to the event shown. Later API access, weights and availability on All Image AI may have different dates.
Explore this event on the image model timeline →
Related Models and Tools
AI Image Generator
Create an image, try a new look or transform a photo. Start with the result you want.
Image to Image
Start from an image. You decide how much of it survives.
Image Upscaler
Scale up to print size and rebuild texture on the way.
FLUX.2 Max
Black Forest Labs
The highest-fidelity FLUX.2 tier for final-publish generation and demanding prompt adherence.
FLUX.2 Flex
Black Forest Labs
FLUX.2 with explicit guidance and step controls for typography-heavy final renders.
FLUX.2 Flash
Black Forest Labs
A low-cost FLUX.2 route for rapid generation and exact multi-reference edits.
FLUX.2 Turbo
Black Forest Labs
A fast FLUX.2 draft model with prompt expansion and unusually low megapixel cost.