Nvidia Cosmos 3 Super Image-to-Video

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

modellane/nvidia-cosmos-3-super-image-to-video-df7a7734 · Image to video · NVIDIA

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

Vendor
NVIDIA
Task
Image to video
Output
Video
Price
$0 · per run
Longest run
7 seconds

Input parameters

  • Prompt prompt — required, at most 2500 characters Describe what you want produced as concretely as you can.
  • Source image image_url — required The frame the generation starts from.
  • Negative prompt negative_prompt — optional Things you don't want to see in the output.
  • Image size image_size — optional
  • Duration duration — optional, default: 5, options: 1, 2, 3, 4, 5, 6, 7 A longer duration raises the price directly.
  • 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: 6, range: 1–20 A high value stays close to the prompt, a low value leaves the model more room.
  • 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

        Waves reaching the shore in soft daylight; slow camera movement, calm atmosphere.

        Example request

        POST /v1/queue/modellane/nvidia-cosmos-3-super-image-to-video-df7a7734

        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.