Image
Sana v1.5 1.6B
Generate images from text with the Sana v1.5 1.6B variant.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Sana v1.5 1.6B. Review your own result before publishing.
A starting point.
Explore a scene’s subject, lighting and style using a written brief.
Before you publish.
Review small objects and background details before selecting a 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
Describe the scene in prompt and exclusions in negative_prompt. style_name lets you specify a visual treatment; this operation does not edit a source photo.
Use num_images for 1–4 outputs. The API starts at 18 steps and guidance_scale 5; record seed and change one setting at a time. Select JPEG or PNG with 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/v1.5/1.6b. 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 1.6B through the API.
Start with this model ID for the endpoint featured on this page:
sana/v1.5/1.6b
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.