← 返回 Skills 市场
Unified API for powerful image and video generation
作者
chaimengphp
· GitHub ↗
· v1.0.1
· MIT-0
1195
总下载
1
收藏
6
当前安装
2
版本数
在 OpenClaw 中安装
/install openclaw-aisa-media-gen
功能描述
Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.
使用说明 (SKILL.md)
\r \r
OpenClaw Media Gen 🎬\r
\r 用 AIsa API 一把钥匙生成图片与视频:\r \r
- 图片:
gemini-3-pro-image-preview(Gemini GenerateContent)\r - 视频:
wan2.6-t2v(通义万相 / Qwen Wan 2.6,异步任务)\r \r API 文档索引见 AIsa API Reference(可从https://docs.aisa.one/llms.txt找到所有页面)。\r \r
🔥 你可以做什么\r
\r
图片生成(Gemini)\r
"生成一张赛博朋克风格的城市夜景,霓虹灯,雨夜,电影感"\r
```\r
\r
### 视频生成(Wan 2.6)\r
```\r
"用一张参考图生成 5 秒镜头:镜头缓慢推进,风吹动头发,电影感,浅景深"\r
```\r
\r
## Quick Start\r
\r
```bash\r
export AISA_API_KEY="your-key"\r
```\r
\r
---\r
\r
## 🖼️ Image Generation (Gemini)\r
\r
### Endpoint\r
\r
- Base URL: `https://api.aisa.one/v1`\r
- `POST /models/{model}:generateContent`\r
\r
文档:`google-gemini-chat`(GenerateContent)见 `https://docs.aisa.one/reference/generatecontent`。\r
\r
### curl 示例(返回 inline_data 时为图片)\r
\r
```bash\r
curl -X POST "https://api.aisa.one/v1/models/gemini-3-pro-image-preview:generateContent" \\r
-H "Authorization: Bearer $AISA_API_KEY" \\r
-H "Content-Type: application/json" \\r
-d '{\r
"contents":[\r
{"role":"user","parts":[{"text":"A cute red panda, ultra-detailed, cinematic lighting"}]}\r
]\r
}'\r
```\r
\r
> 说明:该接口的响应中可能出现 `candidates[].parts[].inline_data`(通常包含 base64 数据与 mime 类型);客户端脚本会自动解析并保存文件。\r
\r
---\r
\r
## 🎞️ Video Generation (Qwen Wan 2.6 / Tongyi Wanxiang)\r
\r
### Create task\r
\r
- Base URL: `https://api.aisa.one/apis/v1`\r
- `POST /services/aigc/video-generation/video-synthesis`\r
- Header:`X-DashScope-Async: enable`(必填,异步)\r
\r
文档:`video-generation` 见 `https://docs.aisa.one/reference/post_services-aigc-video-generation-video-synthesis`。\r
\r
```bash\r
curl -X POST "https://api.aisa.one/apis/v1/services/aigc/video-generation/video-synthesis" \\r
-H "Authorization: Bearer $AISA_API_KEY" \\r
-H "Content-Type: application/json" \\r
-H "X-DashScope-Async: enable" \\r
-d '{\r
"model":"wan2.6-t2v",\r
"input":{\r
"prompt":"cinematic close-up, slow push-in, shallow depth of field",\r
"img_url":"https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/320px-Cat03.jpg"\r
},\r
"parameters":{\r
"resolution":"720P",\r
"duration":5,\r
"shot_type":"single",\r
"watermark":false\r
}\r
}'\r
```\r
\r
### Poll task\r
\r
- `GET /services/aigc/tasks?task_id=...`\r
\r
文档:`task` 见 `https://docs.aisa.one/reference/get_services-aigc-tasks`。\r
\r
```bash\r
curl "https://api.aisa.one/apis/v1/services/aigc/tasks?task_id=YOUR_TASK_ID" \\r
-H "Authorization: Bearer $AISA_API_KEY"\r
```\r
\r
---\r
\r
## Python Client\r
\r
```bash\r
# 生成图片(保存到本地文件)\r
python3 {baseDir}/scripts/media_gen_client.py image \\r
--prompt "A cute red panda, cinematic lighting" \\r
--out "out.png"\r
\r
# 创建视频任务(需要 img_url)\r
python3 {baseDir}/scripts/media_gen_client.py video-create \\r
--prompt "cinematic close-up, slow push-in" \\r
--img-url "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/320px-Cat03.jpg" \\r
--duration 5\r
\r
# 轮询任务状态\r
python3 {baseDir}/scripts/media_gen_client.py video-status --task-id YOUR_TASK_ID\r
\r
# 等待直到成功(可选:成功后打印 video_url)\r
python3 {baseDir}/scripts/media_gen_client.py video-wait --task-id YOUR_TASK_ID --poll 10 --timeout 600\r
\r
# 等待直到成功并自动下载 mp4\r
python3 {baseDir}/scripts/media_gen_client.py video-wait --task-id YOUR_TASK_ID --download --out out.mp4\r
```\r
\r
安全使用建议
This skill appears internally consistent, but before installing consider: (1) You must trust the external AIsa service because your AISA_API_KEY and requests will be sent to api.aisa.one; keys may be billed or grant broad access—do not reuse sensitive keys. (2) The client will download generated media and any user-supplied image URLs to local disk—avoid passing untrusted URLs and run the tool in an environment where large downloads and file writes are acceptable. (3) Examples use curl while the client is Python-based; curl is not harmful but is only needed for example CLI snippets. (4) Review the provided scripts if you have stricter security requirements, and consider running them in an isolated container or VM if you want to limit network/file-system exposure.
功能分析
Type: OpenClaw Skill
Name: openclaw-aisa-media-gen
Version: 1.0.1
The skill bundle is a legitimate tool for generating images and videos using the AIsa API (Gemini and Wan 2.6 models). The Python client (scripts/media_gen_client.py) uses the standard library to interact with official endpoints at api.aisa.one and includes standard functionality for downloading generated media. No suspicious behaviors, data exfiltration, or prompt injection risks were identified.
能力评估
Purpose & Capability
Name/description ask for one API key for AIsa image/video generation; the skill requires AISA_API_KEY and binaries python3 and curl, and the included Python client calls only api.aisa.one endpoints. All requested capabilities are consistent with generating media from AIsa.
Instruction Scope
SKILL.md describes calling AIsa endpoints, creating/polling async video tasks, extracting inline image data, and saving files locally. Instructions do not ask the agent to read unrelated files, other credentials, or exfiltrate data to unexpected endpoints; all network calls target api.aisa.one or user-supplied media URLs.
Install Mechanism
No install spec (instruction-only plus an included Python script). That is low-risk; nothing is fetched from arbitrary third-party URLs during install. The provided Python script uses only the stdlib (urllib) and writes outputs to local files.
Credentials
Only AISA_API_KEY is declared and used (also exposed via an optional --api-key flag). This is proportionate for a client that authenticates to AIsa. No unrelated secrets or configuration paths are requested.
Persistence & Privilege
Skill is not always-enabled and does not request elevated platform privileges. It writes downloaded media to local files (expected behavior) but does not attempt to modify other skills or global agent configs.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install openclaw-aisa-media-gen - 安装完成后,直接呼叫该 Skill 的名称或使用
/openclaw-aisa-media-gen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
版本历史
v1.0.1
Version 1.0.1
- SKILL.md revised with concise bilingual (Chinese & English) instructions and usage examples.
- Documentation links updated to new domain: docs.aisa.one.
- Removed extensive pricing tables and "Why AIsa" sections for brevity.
- Streamlined quick start, API curl examples, and Python client instructions.
- Focused content on core use cases and minimal setup.
v1.0.0
**Major update: Adds powerful media generation (images & videos) via unified API.**
- New capability: Generate images with Gemini 3 Pro Image; generate videos with Qwen Wan 2.6 (Tongyi Wanxiang) using a single AIsa API key.
- Replaces all previous search-related functions and documentation with detailed guides and pricing for media generation.
- Includes new Python and curl examples for image/video creation, status polling, and file download.
- Highlights exclusive support for video generation (not available on OpenRouter) and significantly lower pricing versus competitors.
- Updates use cases, feature summary, and quick start instructions for visual content workflows.
元数据
常见问题
Unified API for powerful image and video generation 是什么?
Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1195 次。
如何安装 Unified API for powerful image and video generation?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-aisa-media-gen」即可一键安装,无需额外配置。
Unified API for powerful image and video generation 是免费的吗?
是的,Unified API for powerful image and video generation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Unified API for powerful image and video generation 支持哪些平台?
Unified API for powerful image and video generation 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 Unified API for powerful image and video generation?
由 chaimengphp(@chaimengphp)开发并维护,当前版本 v1.0.1。
推荐 Skills