← 返回 Skills 市场
AI Media Generation
作者
bowen-dotcom
· GitHub ↗
· v1.0.1
· MIT-0
965
总下载
4
收藏
3
当前安装
2
版本数
在 OpenClaw 中安装
/install aisa-media-gen-skill
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 to be what it claims: a client for AIsa image/video generation that needs only your AISA_API_KEY. Before installing or running it: 1) Confirm you trust the AIsa service and that the API key you provide is intended for this use (don’t reuse high-privilege or unrelated keys). 2) Review the included script if you have concerns — it makes HTTPS calls to api.aisa.one, decodes inline base64 images, and writes files to disk. 3) Be mindful when supplying img_url values or allowing automatic downloads: the client will fetch/download URLs returned by the API (and will accept user-provided image URLs), so avoid passing local/internal URLs or sensitive endpoints. 4) Run it in a controlled environment first (not on sensitive hosts) and inspect outputs/paths it writes to. If you don’t trust the upstream API (api.aisa.one) or the key, don’t install/use the skill.
功能分析
Type: OpenClaw Skill
Name: aisa-media-gen-skill
Version: 1.0.1
The skill bundle provides a Python client and instructions for generating images and videos via the AIsa API (api.aisa.one). The script `scripts/media_gen_client.py` uses standard Python libraries to handle API requests and download generated media files to the local system. The behavior is entirely consistent with the stated purpose of the skill, and no evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description (image + video generation via AIsa) matches the requested binary dependencies (python3, curl), the single environment variable (AISA_API_KEY), and the code which calls api.aisa.one endpoints. Nothing requested appears unrelated to media generation.
Instruction Scope
SKILL.md instructs use of curl and the provided Python client to call AIsa endpoints, create video tasks, poll status, and save results. The instructions do not attempt to read unrelated local files or extra environment variables. Note: the client will download external URLs returned by the API (signed media URLs) and will accept user-supplied img_url values, which means it may read or fetch arbitrary external hosts as part of normal operation — this is expected for a media downloader but worth user awareness.
Install Mechanism
There is no install spec; this is instruction-only plus a Python script. No packages or downloads are installed by the skill itself.
Credentials
Only a single API credential (AISA_API_KEY) is required and declared as the primary credential. The script reads that env var or accepts an explicit CLI argument. No other secrets or unrelated credentials are requested.
Persistence & Privilege
Skill does not request permanent inclusion (always is false), does not modify other skills or system-wide settings, and does not ask to store tokens in unrelated locations. It runs as an on-demand client script.
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 aisa-media-gen-skill - 安装完成后,直接呼叫该 Skill 的名称或使用
/aisa-media-gen-skill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
openclaw-media-gen 1.0.1
- Updated all AIsa API documentation links from aisa.mintlify.app to docs.aisa.one.
- Adjusted references to API documentation pages and index accordingly (including llms.txt location).
- No functional or code changes; documentation only.
v1.0.0
AI Image & Video Generation: Create images with Gemini and videos with Qwen Wan 2.6 via single API key. Async video processing, automatic file saving, parameter control for resolution, duration, and artistic styles.
元数据
常见问题
AI Media 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 965 次。
如何安装 AI Media Generation?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install aisa-media-gen-skill」即可一键安装,无需额外配置。
AI Media Generation 是免费的吗?
是的,AI Media Generation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
AI Media Generation 支持哪些平台?
AI Media 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 AI Media Generation?
由 bowen-dotcom(@bowen-dotcom)开发并维护,当前版本 v1.0.1。
推荐 Skills