Video Effects Balloon Flyaway
Playground
Try it on WavespeedAI!Transform your photos into playful balloon videos where subjects float away with a whimsical spin.
Features
Balloon Flyaway Effect
Requirements
Number of Images
- Mandatory
- Only supports uploading one image
Number of People
- Supports single-subject, dual-subject, and multi-subject in realistic style characters and animals
Image Requirements
- When the person/animal in the photo is a single subject and fully visible, the effect is better
Prompt
- Mandatory
- The format should remain largely unchanged, for details please refer to the “prompt” parameter in the request example
- If there are personalized requirements, the prompt words can be modified without altering the structure and majority of the content
Effect Boundaries
- When the number of subjects in the photo is three or more, or the subjects are close to each other, there may be missing subjects when they turn into balloons and fly away
Best Practices
- Use clear, well-lit photos
- Ensure all subjects are fully visible
- Maintain appropriate spacing between subjects
- Keep the default prompt structure
- Avoid complex backgrounds
- Use photos with good contrast between subjects and background
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/video-effects/balloon-flyaway" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"image": "https://image01.cf.vidu.studio/vidu-maas/Tempmates_material/Funny/Funny/0317/bianqiqiufeizou_upload.png"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| image | string | Yes | - | An image to be used as the start frame of the generated video. Requirements: 1. Only accepts 1 image; 2. Supports single-subject, dual-subject, and multi-subject in realistic style characters and animals; 3. Best results achieved when subjects are fully visible and not too close to each other; 4. Images can be provided via URLs or Base64 encode; 5. Supported codecs: PNG, JPEG, JPG, WebP; 6. Image aspect ratio must be less than 1:4 or 4:1; 7. Maximum file size: 50MB; 8. Base64 decode length must be under 50MB with appropriate content type string. |
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 Query Parameters
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 | 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 |