Image
Stable Diffusion 3 Medium
Create images from text using Stable Diffusion 3 Medium.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Stable Diffusion 3 Medium. Review your own result before publishing.
A starting point.
Describe a clear scene and include exact lettering when it is needed.
Before you publish.
Check spelling, object count and relationships between subjects before publishing.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Use prompt for the scene and negative_prompt for exclusions. prompt_expansion adds detail; leave it off when comparing your original wording.
num_images supports 1–4 outputs. The provider starts at 28 steps and guidance_scale 5; change one setting at a time with a recorded seed. No source-image input is exposed here.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for stable-diffusion-v3-medium. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 50 |
prompt_expansion | On/off | Optional | — |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Stable Diffusion 3 Medium through the API.
Start with this model ID for the endpoint featured on this page:
stable-diffusion-v3-medium
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.