Video
Cosmos Predict 2.5
Create text-guided video scenes with Cosmos Predict 2.5.
- Text to video
- Image to video
- Video editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Cosmos Predict 2.5. Review your own result before publishing.
A starting point.
Explore movement and object interactions from a written scene or supplied visual source.
Before you publish.
Check spatial continuity and contact between objects across frames; simulated motion is not a validated physics 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
Text mode requires prompt. Image mode adds image_url; video mode adds video_url. Match your source to the operation.
Adjust guidance_scale from 1–20, optionally add negative_prompt and retain seed. Review video_output_type; Raywake exposes no duration or frame-count controls.
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/text-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 20 |
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.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
Image to videocosmos-predict-2.5/image-to-video
Supported inputs
These fields come from the current studio form for cosmos-predict-2.5/image-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
image_url | Text | Required | — |
prompt | Text | Required | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 20 |
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.
Video editingcosmos-predict-2.5/video-to-video
Supported inputs
These fields come from the current studio form for cosmos-predict-2.5/video-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
video_url | Text | Required | — |
guidance_scale | Number | Optional | ≥ 1 · ≤ 20 |
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 through the API.
Start with this model ID for the endpoint featured on this page:
cosmos-predict-2.5/text-to-video
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-video ·
cosmos-predict-2.5/text-to-video - image-to-video ·
cosmos-predict-2.5/image-to-video - video-to-video ·
cosmos-predict-2.5/video-to-video
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.