Image
Cosmos 3 Super Image
Create still images from text with Cosmos 3 Super Image.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Cosmos 3 Super Image. Review your own result before publishing.
A starting point.
Describe spatial relationships and materials for a scene concept.
Before you publish.
Inspect object contact, reflections and any requested lettering.
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
This operation requires prompt and returns images. The wider Cosmos family supports other media, but this Raywake endpoint takes no source video or image.
negative_prompt names unwanted features; guidance_scale controls prompt guidance. Set num_images and JPEG or PNG output_format, and record seed for comparisons.
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 nvidia/cosmos-3-super/text-to-image. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 · Max. characters: 4096 |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
negative_prompt | Text | Optional | Max. characters: 1024 |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
output_format | Text | Optional | jpeg, png |
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 Cosmos 3 Super Image through the API.
Start with this model ID for the endpoint featured on this page:
nvidia/cosmos-3-super/text-to-image
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.