Studio Ghibli Image Filter
/install mediaio-ghibli-image-filter
\r \r
Media.io Ghibli Image Filter Skill\r
\r
Overview\r
This skill calls Media.io OpenAPI to run Ghibli-style conversion using model code effects-ghibli.\r
The API is asynchronous:\r
- Submit generation request and get
task_id.\r - Poll task result endpoint until the task is finished.\r \r
When To Use\r
- The user wants to convert an image to Ghibli-like style.\r
- The user can provide an image URL reachable by Media.io servers.\r
- The user wants task-based generation with polling.\r \r
When Not To Use\r
- The user asks for local file upload only (this API expects image URL input).\r
- The user asks for non-Media.io providers.\r
- The user asks for real-time synchronous image output in one call.\r \r
Requirements\r
\r
Environment Variables\r
| Variable | Required | Description |\r
|---|---|---|\r
| MEDIAIO_API_KEY | Yes | Media.io OpenAPI key, used in header X-API-KEY. |\r
\r
Base Headers\r
Content-Type: application/json\rX-API-KEY: $MEDIAIO_API_KEY\r \r
Supported Endpoints\r
\r
1) Query Credits\r
- Method:
POST\r - Endpoint:
https://openapi.media.io/user/credits\r - Body:
{}\r - Purpose: check available credits before generation.\r \r
2) Create Ghibli Task\r
- Method:
POST\r - Endpoint:
https://openapi.media.io/generation/effects/effects-ghibli\r - Body:\r
{\r
"data": {\r
"images": "https://example.com/input.jpg",\r
"ratio": "9:16",\r
"batch": "1"\r
}\r
}\r
```\r
- Required fields:\r
- `data.images` (string URL)\r
- Optional fields:\r
- `data.ratio` (string): `9:16`, `16:9`, `1:1`, `4:3`, `3:4`, `3:2`, `2:3`\r
- `data.batch` (string): `1`, `2`, `3`, `4`\r
\r
### 3) Query Task Result\r
- Method: `POST`\r
- Endpoint: `https://openapi.media.io/generation/result/{task_id}`\r
- Body: `{}`\r
- Path parameter:\r
- `task_id` (string, required)\r
\r
## Request and Response Contract\r
\r
### Common Success Envelope\r
```json\r
{\r
"code": 0,\r
"msg": "",\r
"data": {},\r
"trace_id": "..."\r
}\r
```\r
\r
### Create Task Response\r
- On success, `data.task_id` is returned.\r
\r
### Task Result Response\r
- `data.status` can be one of the following values:\r
- `waiting`: queued\r
- `processing`: running\r
- `completed`: completed successfully\r
- `failed`: failed\r
- `timeout`: timed out\r
- `data.reason`: provides additional context (e.g., `success` or error message)\r
- When status is `completed`:\r
- `data.result` is an array of output objects with generated URLs\r
- Each result object contains `val` (internal path), `preview` (public HTTPS URL), and `status` (completion status)\r
\r
## Standard Invocation Flow\r
1. Call `user/credits` to verify balance.\r
2. Call `effects-ghibli` with `data.images` and optional `data.ratio`, `data.batch`.\r
3. Extract `task_id`.\r
4. Poll `generation/result/{task_id}` every 3 to 5 seconds.\r
5. Stop when status is `completed` or `failed`.\r
6. Return output URLs from `data.result` when `completed`.\r
\r
## cURL Examples\r
\r
### Query Credits\r
```bash\r
curl --request POST \\r
--url https://openapi.media.io/user/credits \\r
--header 'Content-Type: application/json' \\r
--header "X-API-KEY: $MEDIAIO_API_KEY" \\r
--data '{}'\r
```\r
\r
### Create Ghibli Task\r
```bash\r
curl --request POST \\r
--url https://openapi.media.io/generation/effects/effects-ghibli \\r
--header 'Content-Type: application/json' \\r
--header "X-API-KEY: $MEDIAIO_API_KEY" \\r
--data '{\r
"data": {\r
"images": "https://example.com/input.jpg",\r
"ratio": "9:16",\r
"batch": "1"\r
}\r
}'\r
```\r
\r
### Query Task Result\r
```bash\r
curl --request POST \\r
--url https://openapi.media.io/generation/result/\x3Ctask_id> \\r
--header 'Content-Type: application/json' \\r
--header "X-API-KEY: $MEDIAIO_API_KEY" \\r
--data '{}'\r
```\r
\r
#### Successful Response Example\r
```json\r
{\r
"code": 0,\r
"msg": "",\r
"data": {\r
"task_id": "effect-86f0f82a-36dc-4a7c-928a-721a18ef482f",\r
"status": "completed",\r
"reason": "success",\r
"result": [\r
{\r
"val": "aicloudtmp/550160908/3/202603/1/combo_tm_alg-20260317165022-802800-60eb3-dwt.png",\r
"preview": "https://url_to_generated_image.png",\r
"status": "completed"\r
}\r
]\r
},\r
"trace_id": "a18315ba568b5c34407808d12cbc8457"\r
}\r
```\r
\r
Response fields when status is `completed`:\r
- `data.task_id`: unique task identifier\r
- `data.status`: `completed` indicates successful completion\r
- `data.reason`: `success` indicates no error occurred\r
- `data.result`: array of output objects, each containing:\r
- `val`: internal file path of the generated asset\r
- `preview`: publicly accessible HTTPS URL for the generated asset\r
- `status`: `completed` for each result item\r
\r
## Error Handling Guidance\r
- Treat `code != 0` as failure.\r
- Typical authentication errors:\r
- `374004`: not authenticated. Apply for an APP KEY at https://developer.media.io/.\r
- Typical request validation error:\r
- `490000`: params error\r
- Typical billing/credits error:\r
- `490505`: insufficient credits. Recharge before invoking generation APIs.\r
- Always include `trace_id` in logs for troubleshooting.\r
\r
## Agent Behavior Requirements\r
- Validate that input contains a non-empty image URL before calling the create endpoint.\r
- Do not claim immediate output after task creation; always poll by `task_id`.\r
- If credits are insufficient, return a clear message and stop instead of retry loops.\r
- Avoid exposing raw API keys in logs or responses.\r
\r
## Safety and Compliance Notes\r
- Only process user-provided or user-authorized images.\r
- Do not imply identity verification or biometric certainty from generated images.\r
- Generated output is synthetic media and should be presented as edited content.\r
\r
## References\r
- Media.io platform: https://developer.media.io/\r
- API documentation: https://platform.media.io/docs/\r
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install mediaio-ghibli-image-filter - 安装完成后,直接呼叫该 Skill 的名称或使用
/mediaio-ghibli-image-filter触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Studio Ghibli Image Filter 是什么?
Transform photos and images into Studio Ghibli-style artwork using AI via Media.io OpenAPI. Applies the iconic hand-drawn, painterly aesthetic of Ghibli film... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 186 次。
如何安装 Studio Ghibli Image Filter?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mediaio-ghibli-image-filter」即可一键安装,无需额外配置。
Studio Ghibli Image Filter 是免费的吗?
是的,Studio Ghibli Image Filter 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Studio Ghibli Image Filter 支持哪些平台?
Studio Ghibli Image Filter 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Studio Ghibli Image Filter?
由 wondershare-boop(@wondershare-boop)开发并维护,当前版本 v1.0.3。