Video
Cosmos Predict 2.5 Distilled
Generate text-guided video with the distilled Cosmos Predict 2.5 model.
- Text to video
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Cosmos Predict 2.5 Distilled. Review your own result before publishing.
A starting point.
Describe one physical scene with a clear action to explore motion and spatial continuity.
Before you publish.
Watch for impossible interactions, disappearing objects and flicker; generated footage is not physical evidence.
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
Provide prompt and optionally negative_prompt to steer away from unwanted content. Retain seed when comparing the scene.
Review video_output_type for export. Raywake exposes no duration, frame-count, sampling-step or guidance controls for this distilled operation.
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 cosmos-predict-2.5/distilled/text-to-video. Other modes may require different inputs.
| Input | Type | Requirement |
|---|---|---|
prompt | Text | Required |
negative_prompt | Text | Optional |
seed | Whole number | Optional |
video_output_type | Text | Optional |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Cosmos Predict 2.5 Distilled through the API.
Start with this model ID for the endpoint featured on this page:
cosmos-predict-2.5/distilled/text-to-video
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.