Cosmos Predict 2.5 Image To Video
Playground
Try it on WavespeedAI!Cosmos Predict 2.5 Image-to-Video generates video from an image and text prompt using NVIDIA’s 2B Cosmos Post-Trained Model. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Features
Cosmos Predict 2.5 Image-to-Video
Cosmos Predict 2.5 Image-to-Video generates video from an image and text prompt using NVIDIA’s 2B Cosmos Post-Trained Model. Upload a reference image and describe the motion — the model creates smooth, natural 5-second video clips with high fidelity to the source image.
Why Choose This?
-
NVIDIA Cosmos architecture Powered by NVIDIA’s 2B parameter Cosmos Post-Trained Model for high-quality video generation.
-
Natural motion Generates smooth, realistic movement based on your text description.
-
High fidelity Preserves the visual details, style, and composition of your source image.
-
Prompt Enhancer Built-in tool to automatically improve your motion descriptions.
-
Simple pricing Flat $0.25 per video, no complex calculations.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired motion and action |
| image | Yes | Reference image to animate (URL or upload) |
How to Use
- Upload your image — provide the reference image to animate.
- Write your prompt — describe the motion, camera movement, and scene dynamics in detail.
- Use Prompt Enhancer (optional) — click to automatically refine your description.
- Run — submit and download your 5-second video.
Pricing
| Output | Cost |
|---|---|
| Per video | $0.25 |
Best Use Cases
- Nature Scenes — Animate landscapes, gardens, and natural environments with gentle motion.
- Product Visualization — Bring product images to life with subtle movement.
- Social Media Content — Create engaging short-form videos from still images.
- Artistic Animation — Transform illustrations and artwork into dynamic videos.
- Marketing & Ads — Animate hero images and promotional visuals.
Pro Tips
- Use detailed, descriptive prompts for best results — include specific motion, camera movement, and environmental effects.
- Describe natural, physically plausible motion for more realistic output (e.g., “gentle breeze,” “slowly moves forward”).
- Include atmospheric details like lighting, weather, and mood in your prompts.
- Clear, high-quality source images produce better animations.
- Try the Prompt Enhancer to automatically improve your descriptions.
Notes
- Both prompt and image are required fields.
- Output duration is fixed at 5 seconds.
- Ensure uploaded image URLs are publicly accessible.
Related Models
- Cosmos Predict 2.5 Video-to-Video — Transform existing videos with text prompts.
- Wan 2.6 Image-to-Video — Multi-resolution image-to-video with flexible duration.
- Vidu Q3 Image-to-Video — High-quality image animation with audio support.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/cosmos-predict-2.5/image-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text prompt describing the motion, action, and style you want in the generated video | |
| image | string | Yes | - | URL of the input image to use as the first frame of the video |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |