# Stable Diffusion 3.5 Large AI Image Generator

> The full 8B SD 3.5 model with negative prompts, CFG and sampling-step control.

Canonical URL: https://allimageai.com/models/stable-diffusion-3-5-large/

Website: All Image AI

Language: English

Stable Diffusion 3.5 Large is Stability AI’s 8B open-weight base model. This hosted route exposes the familiar negative prompt, guidance, step and seed controls without requiring a local GPU.

## Model details

- Developer: Stability AI
- Status on All Image AI: Active
- Last verified: 2026-08-25
- Maximum output: 2K
- Modes: Text to Image
- Reference images: not supported
- Resolutions: 1K, 2K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3

## Best for

- Open-weight workflows
- Negative-prompt control
- Fine-tuned sampling
- Illustration and concept art

## How to use

1. Write the positive prompt.
2. Add only concrete exclusions to Negative Prompt.
3. Fix the seed before tuning.
4. Generate at 1K first and use 2K selectively.

## Settings explained

### Negative Prompt

Explicitly lists defects, objects or styles that should not appear.

### Steps

Twenty-eight is the balanced default; use more only for difficult compositions.

## Prompt examples

### Controlled illustration

> Ancient observatory above a cloud sea, midnight blue and brass, detailed storybook illustration, dramatic moonlight

Negative: watermark, blurry, duplicate objects.

### Product concept

> Minimal ceramic desk lamp, warm white glaze, pale grey studio sweep, soft directional shadow

## Limitations

- Slower and more expensive than Turbo
- Text-to-image only here
- Best quality is around its native 1MP range

## 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 | 5 |
| 2K | 19 |

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 under the Stability AI Community License; service use also follows the selected provider terms.

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

## Frequently asked questions

### Can I download the model weights here?

No. This is a hosted inference route; Stability AI distributes the open weights separately.

### Which SD 3.5 variant should I choose?

Choose Large for control and final quality; Turbo is the faster draft tier.

## Release history and sources

October 22, 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/introducing-stable-diffusion-3-5)

[Event evidence on the timeline](https://allimageai.com/timeline/#event-stable-diffusion-3-5-large)

## Other versions

- [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 Diffusion 3 Medium](https://allimageai.com/models/stable-diffusion-3-medium.md): Open weights · 1K
- [Stable Image Ultra](https://allimageai.com/models/stable-image-ultra.md): Recommended · 2K