TRStart creating
Menu

Stable Diffusion 3.5 Medium

Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Input

Fields marked * are required. Review the price before generating.

The prompt to generate an image from.

The size of the generated image.

The number of images to generate.

Additional settings
Tips and requirements

The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).

The number of inference steps to perform.

The same seed and the same prompt given to the same version of the model will output the same image every time.

Tips and requirements

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

The format of the generated image.

Tips and requirements

If true (default), the requested image_size is silently rounded to the nearest compatible value for this model. If false, the request returns a 422 error when the requested image_size is not directly compatible.

Price$0.04 / megapixel

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use Stable Diffusion 3.5 Medium

Getting started

Specify subject relationships and lighting for a concept illustration or scene.

Review your result

Inspect perspective, facial details and requested text at the actual output size.

Inputs and settings

Write prompt; use negative_prompt for exclusions. The provider begins at 40 steps and guidance_scale 4.5; compare adjustments with the same seed.

Choose 1–4 images with num_images and JPEG or PNG with output_format. auto_fix concerns compatible image sizing; it does not repair visual mistakes in the generated content.

We use analytics cookies. Privacy policy