← 返回 Skills 市场
aisadocs

Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key

作者 AIsa · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
1740
总下载
3
收藏
10
当前安装
1
版本数
在 OpenClaw 中安装
/install openclaw-aisa-llm-image-video
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 to do exactly what it claims: call AIsa's image and video endpoints using AISA_API_KEY and save the returned media. Before installing, confirm you trust the AIsa service (api.aisa.one) and are willing to send prompts and any image URLs you provide to that provider. Treat AISA_API_KEY like a secret: only use a key with appropriate scope and avoid pasting highly sensitive prompts or private images unless you trust the service's privacy policy. Note the client may download remote URLs (the video output URL or any URL you pass as img_url), so avoid providing untrusted URLs you don't want fetched. If you want further assurance, review the full included Python script (scripts/media_gen_client.py) to verify no additional network calls or logging of secrets occur in the truncated portion.
功能分析
Type: OpenClaw Skill Name: openclaw-aisa-llm-image-video Version: 1.0.0 The skill bundle is benign. It provides a client for the AIsa API to generate images and videos. The `SKILL.md` and `README.md` files contain clear instructions and examples for using the API and the provided Python script, with no evidence of prompt injection or malicious intent. The `scripts/media_gen_client.py` script securely retrieves the `AISA_API_KEY` from environment variables, makes legitimate API calls to `https://api.aisa.one`, and saves generated media (images, videos) to local files. There is no evidence of data exfiltration, malicious execution, persistence, or obfuscation beyond the stated purpose of media generation.
能力评估
Purpose & Capability
Name/description ask for image+video generation via AIsa and the skill requires only python3/curl and AISA_API_KEY. The provided Python client and curl examples call api.aisa.one endpoints for Gemini image generation and Wan video tasks, which is coherent with the stated purpose.
Instruction Scope
SKILL.md and the included script only instruct calls to the documented AIsa endpoints, polling for task status, saving returned inline images, and optionally downloading a video URL returned by the API. The instructions do not request unrelated files, credentials, or system state beyond the declared AISA_API_KEY. The script writes files only when saving generated media.
Install Mechanism
No install spec; this is instruction-only with a bundled Python script. No external installers or archive downloads are invoked by the skill itself, so there is no suspicious install-time network activity or arbitrary code fetch.
Credentials
Only AISA_API_KEY is required and declared as the primary credential. That is proportional: the API key is necessary to authenticate to api.aisa.one. No additional keys, secrets, or unrelated environment variables are requested.
Persistence & Privilege
always is false and the skill does not request system-wide persistence or modify other skills' configuration. It runs as an instruction-only client and does not claim elevated platform privileges.
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 openclaw-aisa-llm-image-video
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /openclaw-aisa-llm-image-video 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. - Generate both images (via Gemini 3 Pro Image) and videos (via Qwen Wan 2.6) with a single API key. - Added image generation with Gemini 3 Pro endpoint and video generation via Qwen Wan 2.6 (asynchronous tasks). - Included curl examples and Python client scripts for quick start. - Provided full API references and usage instructions. - Requires only python3, curl, and an AISA_API_KEY environment variable.
元数据
Slug openclaw-aisa-llm-image-video
版本 1.0.0
许可证
累计安装 10
当前安装数 10
历史版本数 1
常见问题

Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key 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 1740 次。

如何安装 Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key?

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

Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key 是免费的吗?

是的,Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key 完全免费(开源免费),可自由下载、安装和使用。

Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key 支持哪些平台?

Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key 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 Images & videos generation with Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key?

由 AIsa(@aisadocs)开发并维护,当前版本 v1.0.0。

💬 留言讨论