← 返回 Skills 市场
aisapay

AIsa Media Gen

作者 AIsaPay · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
1622
总下载
1
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install 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)

OpenClaw Media Gen 🎬

用 AIsa API 一把钥匙生成图片视频

  • 图片gemini-3-pro-image-preview(Gemini GenerateContent)
  • 视频wan2.6-t2v(通义万相 / Qwen Wan 2.6,异步任务)

API 文档索引见 AIsa API Reference(可从 https://aisa.mintlify.app/llms.txt 找到所有页面)。

🔥 你可以做什么

图片生成(Gemini)

"生成一张赛博朋克风格的城市夜景,霓虹灯,雨夜,电影感"

视频生成(Wan 2.6)

"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"

Quick Start

export AISA_API_KEY="your-key"

🖼️ Image Generation (Gemini)

Endpoint

  • Base URL: https://api.aisa.one/v1
  • POST /models/{model}:generateContent

文档:google-gemini-chat(GenerateContent)见 https://aisa.mintlify.app/api-reference/chat/chat-api/google-gemini-chat.md

curl 示例(返回 inline_data 时为图片)

curl -X POST "https://api.aisa.one/v1/models/gemini-3-pro-image-preview:generateContent" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents":[
      {"role":"user","parts":[{"text":"A cute red panda, ultra-detailed, cinematic lighting"}]}
    ]
  }'

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。


🎞️ Video Generation (Qwen Wan 2.6 / Tongyi Wanxiang)

Create task

  • Base URL: https://api.aisa.one/apis/v1
  • POST /services/aigc/video-generation/video-synthesis
  • Header:X-DashScope-Async: enable(必填,异步)

文档:video-generationhttps://aisa.mintlify.app/api-reference/aliyun/video/video-generation.md

curl -X POST "https://api.aisa.one/apis/v1/services/aigc/video-generation/video-synthesis" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-DashScope-Async: enable" \
  -d '{
    "model":"wan2.6-t2v",
    "input":{
      "prompt":"cinematic close-up, slow push-in, shallow depth of field",
      "img_url":"https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/320px-Cat03.jpg"
    },
    "parameters":{
      "resolution":"720P",
      "duration":5,
      "shot_type":"single",
      "watermark":false
    }
  }'

Poll task

  • GET /services/aigc/tasks?task_id=...

文档:taskhttps://aisa.mintlify.app/api-reference/aliyun/video/task.md

curl "https://api.aisa.one/apis/v1/services/aigc/tasks?task_id=YOUR_TASK_ID" \
  -H "Authorization: Bearer $AISA_API_KEY"

Python Client

# 生成图片(保存到本地文件)
python3 {baseDir}/scripts/media_gen_client.py image \
  --prompt "A cute red panda, cinematic lighting" \
  --out "out.png"

# 创建视频任务(需要 img_url)
python3 {baseDir}/scripts/media_gen_client.py video-create \
  --prompt "cinematic close-up, slow push-in" \
  --img-url "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/320px-Cat03.jpg" \
  --duration 5

# 轮询任务状态
python3 {baseDir}/scripts/media_gen_client.py video-status --task-id YOUR_TASK_ID

# 等待直到成功(可选:成功后打印 video_url)
python3 {baseDir}/scripts/media_gen_client.py video-wait --task-id YOUR_TASK_ID --poll 10 --timeout 600

# 等待直到成功并自动下载 mp4
python3 {baseDir}/scripts/media_gen_client.py video-wait --task-id YOUR_TASK_ID --download --out out.mp4
安全使用建议
This skill appears coherent for generating images and videos through AIsa using a single AISA_API_KEY. Before installing: (1) only provide an API key scoped appropriately (least privilege) and avoid sharing other secrets; (2) be aware the client will fetch user-provided img_url values and will download returned video URLs to disk — do not pass internal or sensitive endpoints (risk of SSRF or data leakage if an attacker can control URLs); (3) verify you trust the api.aisa.one domain and the AIsa service terms; (4) run the skill in a sandbox or with limited filesystem/network permissions if you want extra safety. If you need more assurance, request the full (untruncated) Python script and verify there are no hidden network calls to unexpected domains.
功能分析
Type: OpenClaw Skill Name: aisa-media-gen Version: 1.0.0 The skill bundle is a client for the AIsa media generation API. It requires `python3`, `curl`, and an `AISA_API_KEY` environment variable, all explicitly declared in `SKILL.md`. The `scripts/media_gen_client.py` script performs HTTP requests to `https://api.aisa.one` for image and video generation, and downloads generated media files (images, videos) to local storage. All network interactions and file operations are directly aligned with the stated purpose of generating and retrieving media, with no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the agent beyond the skill's intended functionality.
能力评估
Purpose & Capability
Name/description, SKILL.md, and the included Python client all target AIsa image/video generation. Requiring AISA_API_KEY and python3 is appropriate; curl is requested because the README shows curl examples (but the runtime client is Python).
Instruction Scope
The instructions and script stay within the stated purpose (call AIsa endpoints, poll tasks, save returned media). One behavioral note: the client will download arbitrary URLs supplied as img_url and will fetch signed video URLs returned by the API — this is expected for media download but means a user-supplied or agent-supplied URL could cause the client to make network requests to arbitrary hosts (possible SSRF/internal requests) or to write files to disk.
Install Mechanism
No install spec (instruction-only) and the code is bundled as a single Python script. Nothing is downloaded or extracted at install time.
Credentials
Only AISA_API_KEY is required and declared as the primary credential, which is proportionate for an API client that authenticates to AIsa. The SKILL.md and script do not read other environment variables or unrelated credentials.
Persistence & Privilege
The skill is not set always:true and does not request system-wide configuration changes. Model invocation is allowed (default) which is normal for skills; no excessive persistence or cross-skill config writes are present.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install aisa-media-gen
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /aisa-media-gen 触发
  4. 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
v1.0.0
Initial release of openclaw-media-gen (aisa-media-gen): - Generate images with Gemini 3 Pro Image and videos with Qwen Wan 2.6 using a single API key. - Provides API and curl examples for image and video generation. - Includes guidance for Python client usage for both image and video workflows. - Requires only Python3, curl, and your AISA_API_KEY environment variable. - Full API documentation references included for quick integration.
元数据
Slug aisa-media-gen
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

AIsa Media Gen 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 1622 次。

如何安装 AIsa Media Gen?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install aisa-media-gen」即可一键安装,无需额外配置。

AIsa Media Gen 是免费的吗?

是的,AIsa Media Gen 完全免费(开源免费),可自由下载、安装和使用。

AIsa Media Gen 支持哪些平台?

AIsa Media Gen 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 AIsa Media Gen?

由 AIsaPay(@aisapay)开发并维护,当前版本 v1.0.0。

💬 留言讨论