Ai Ghibli Filter Video
Playground
Try it on WavespeedAI!AI Ghibli Filter Video transforms a photo into a Studio Ghibli anime style video with customizable duration. Ready-to-use REST inference API, no coldstarts, affordable pricing.
Features
AI Ghibli Filter Video
Transform any video clip into a hand-painted Studio Ghibli-style animated scene. AI Ghibli Filter Video reimagines your real-world footage with the soft watercolor textures, warm color palettes, and dreamlike atmosphere that define Ghibli’s iconic visual style — no animation skills required.
Upload a video, set your duration, and watch your everyday moments become scenes straight out of a Miyazaki film.
Why You’ll Love It
-
Authentic Ghibli aesthetics Captures the signature soft brushwork, painterly backgrounds, and warm, luminous color grading of classic Studio Ghibli films.
-
Works on any scene Landscapes, street scenes, people in motion — the filter adapts beautifully to a wide range of real-world footage.
-
Adjustable duration Process between 5 and 15 seconds of video to get the perfect stylized clip.
-
Instant, shareable results Ready to post, share, or use as creative content in seconds.
How to Use
- Upload your video — a clear clip with good lighting and stable framing works best.
- Set duration — drag the slider to choose between 5 and 15 seconds.
- Hit Run — AI transforms your footage into Ghibli-style animation.
- Download and share your stylized video.
Pricing
| Duration | Cost |
|---|---|
| 5s | $0.30 |
| 10s | $0.60 |
| 15s | $0.90 |
Rate: $0.06 per second.
Best Use Cases
- Social media content — Turn travel clips, nature footage, or everyday moments into viral Ghibli-style videos.
- Creative projects — Add a hand-painted animated feel to short films, intros, or mood reels.
- Gifts and keepsakes — Reimagine memorable moments as something magical and artistic.
- Fan art & tributes — Celebrate your love of Studio Ghibli with your own footage as the canvas.
Pro Tips
- Outdoor scenes with natural light, greenery, and movement produce the most Ghibli-like results.
- Smooth, stable footage transforms more cleanly than shaky or heavily compressed clips.
- Try running the same clip at different durations to find the most visually striking segment.
- Scenes with a clear subject and open background tend to look most cinematic after transformation.
Notes
- Image (video) is the only required field.
- Duration range is 5 to 15 seconds.
- Ensure video URLs are publicly accessible if using a link rather than a direct upload.
- Please ensure your content complies with WaveSpeed AI’s usage policies.
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/ai-ghibli-filter-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"duration": 5
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| image | string | Yes | - | The URL of the input image. | |
| duration | integer | No | 5 | 5 ~ 15 | Video duration in seconds (5-15). |
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 |