# Stable Diffusion 3 Medium AI Image Generator

> Stability AI’s two-billion-parameter SD3 checkpoint with typography, negative prompts and familiar diffusion controls.

Canonical URL: https://allimageai.com/models/stable-diffusion-3-medium/

Website: All Image AI

Language: English

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.

## Model details

- Developer: Stability AI
- Status on All Image AI: Active
- Last verified: 2026-08-25
- Maximum output: 1K
- Modes: Text to Image, Typography
- Reference images: not supported
- Resolutions: 1K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4

## Best for

- Open-weight evaluation
- Typography experiments
- Controlled illustration
- Classic negative-prompt workflows

## How to use

1. Start with 28 steps and guidance 5.
2. Name only concrete exclusions.
3. Fix a seed for comparisons.
4. Use SD 3.5 when the newer family is more important than checkpoint fidelity.

## 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.

## 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

## Limitations

- Older than SD 3.5
- Text-to-image only here
- Small exact lettering still needs review

## Pricing and credits

Credits for one image at default quality and mode. Resolution, quality, reference inputs, edit mode and output count can change the total. Check the Generate button before submitting.

| Resolution | Credits / image |
| --- | --- |
| 1K | 3 |

Failed generations cost 0 credits. Catalog availability does not guarantee runtime availability; the workspace reports whether the selected model can run.

[Credit plans](https://allimageai.com/pricing.md)

## Test results

Testing in progress. No verified benchmark scores have been published for this model.

## Commercial use and image handling

Open weights are governed by the Stability AI Community License; hosted use also follows the selected service terms.

Uploads are processed by the configured inference service. You can delete a generation from your history.

## 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.

- [stability.ai](https://stability.ai/news-updates/stable-diffusion-3-medium)

[Event evidence on the timeline](https://allimageai.com/timeline/#event-stable-diffusion-3-medium)

## Other versions

- [Stable Diffusion 3.5 Large](https://allimageai.com/models/stable-diffusion-3-5-large.md): Full quality · 2K
- [Stable Diffusion 3.5 Large Turbo](https://allimageai.com/models/stable-diffusion-3-5-large-turbo.md): Fast draft · 2K
- [Stable Diffusion 3.5 Medium](https://allimageai.com/models/stable-diffusion-3-5-medium.md): Negative prompt · 2K
- [Stable Image Ultra](https://allimageai.com/models/stable-image-ultra.md): Recommended · 2K