Nvidia Cosmos 3 Super Text-to-Image

Use Nvidia Cosmos 3 Super Text-to-Image for image; see supported inputs and option-based pricing on this page.

modellane/nvidia-cosmos-3-super-text-to-image-a679cec1 · Text to image · NVIDIA

Nvidia Cosmos 3 Super Text-to-Image supports text to image. Its documented input fields are listed below; the request price is calculated from the selected options.

Vendor
NVIDIA
Task
Text to image
Output
Image
Price
$0 · per run

Input parameters

  • Prompt prompt — required, at most 2500 characters Describe what you want produced as concretely as you can.
  • Negative prompt negative_prompt — optional Things you don't want to see in the output.
  • Image size image_size — optional
  • Steps num_inference_steps — optional, default: 28, range: 1–50 More steps usually give a cleaner result and take longer.
  • Prompt adherence guidance_scale — optional, default: 4, range: 1–20 A high value stays close to the prompt, a low value leaves the model more room.
  • Output format output_format — optional, options: jpeg, png
  • Seed seed — optional The same seed and the same settings produce a similar result; leave it empty and one is picked at random.
  • Safety checker enable_safety_checker — optional, default: false

Recommended use cases

    Where it is strong

      Limits

        Example prompt

        A red bicycle against a stone wall at sunset, in natural light.

        Example request

        POST /v1/queue/modellane/nvidia-cosmos-3-super-text-to-image-a679cec1

        Playground

        The identifier, price, parameters, and example requests on this page can be read without signing in. Running the model from the panel sends a real generation request and charges the project balance; the playground therefore requires an account.