# Stable Diffusion 3.5

Make images from a text prompt with Stable Diffusion 3.5 by Stability, at 126 credits per image. See its settings, limits and exact prices.

Stable Diffusion 3.5 is Stability's image model, tagged Fast and Open Source in the Studio picker. It makes images from a text prompt only. The price is flat at 126 credits per image at every aspect ratio.

## At a glance

- **Maker:** Stability
- **Type:** Image model
- **Modes:** Text to image
- **Aspect ratios:** 16:9, 4:3, 1:1, 3:4, 9:16. The Studio starts on 4:3.
- **Outputs per run:** 1 to 4, set with **Count**
- **Reference image:** Not accepted. This model works from a text prompt only.
- **Resolution:** No resolution choice

## What it costs

These are credits per image, as of 2026-10-10. The Studio shows the live quote for your settings before you generate, and the total it charges is that quote multiplied by **Count**.

| Setting | Credits per image |
| --- | --- |
| Any aspect ratio | 126 |

The price is the same at every aspect ratio.

## Use it in Studio

1. **Open Create Image** In Studio, open **Create Image**. Sign in when the Studio asks, because every generation needs an account.
2. **Choose Stable Diffusion 3.5** Open the model picker, which groups models by maker, and choose Stable Diffusion 3.5.
3. **Write your prompt** Describe the image. Stable Diffusion 3.5 works from text only, so there is no reference image to attach.
4. **Set the output** Choose an aspect ratio and **Count** from 1 to 4.
5. **Check the price and generate** The Studio shows the credit price for your settings. It is the same price the server charges. Results appear as cards and are saved to your **Library**.

## Limits

- You need to be signed in to generate. Stable Diffusion 3.5 is available on every plan, including Free; credits are the limit.
- No reference image. If you attach one, the Studio says "Stable Diffusion 3.5 can't use a reference image — remove it or pick another model".
- If a generation fails, the credits are refunded. The Studio does not run a different model in its place.

## Common questions

**Does Stable Diffusion 3.5 accept a reference image?**

No. It works from a text prompt only. For image-to-image, pick a model that lists a reference image, such as [GPT Image 2.5](https://www.uova.com/help/models/image/gpt-image-2-5) at 37 credits.

**Can I use my own image with Stable Diffusion 3.5?**

No. Stable Diffusion 3.5 works from a text prompt only. The models that accept a reference image are listed on [Image models](https://www.uova.com/help/models/image).

**Similar models**

- [FLUX 2 Pro](https://www.uova.com/help/models/image/flux-2-pro): Photorealism. Default credits: 56.
- [GPT Image 2.5](https://www.uova.com/help/models/image/gpt-image-2-5): Realistic images, typography. Default credits: 37.

Source: https://www.uova.com/help/models/image/stable-diffusion-3-5