Image
Sana v1.5 4.8B
Create images from a written brief with Sana v1.5 4.8B.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Sana v1.5 4.8B. Review your own result before publishing.
A starting point.
Test a detailed material or environment description with a defined focal point.
Before you publish.
Inspect perspective, fine textures and secondary objects in the result.
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 subject and setting, then negative_prompt for exclusions. Choose style_name deliberately rather than mixing several conflicting styles.
The API starts at 18 steps and guidance_scale 5. Raywake allows 1–50 steps and 1–4 images; compare settings with a fixed seed and export JPEG or PNG through output_format.
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 sana/v1.5/4.8b. 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 |
output_format | Text | Optional | jpeg, png |
seed | Whole number | Optional | — |
style_name | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Sana v1.5 4.8B through the API.
Start with this model ID for the endpoint featured on this page:
sana/v1.5/4.8b
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.