技能详情(站内镜像,无评论)
许可证:MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本:v1.0.0
统计:⭐ 2 · 893 · 0 current installs · 0 all-time installs
⭐ 2
安装量(当前) 0
🛡 VirusTotal :良性 · OpenClaw :良性
Package:aisadocs/openclaw-aisa-llm-image-video-qwen-wan26-gemini-3-pro-image
安全扫描(ClawHub)
- VirusTotal :良性
- OpenClaw :良性
OpenClaw 评估
The skill's code, instructions, and required AISA_API_KEY are coherent with its stated purpose (image + video generation via the AIsa API); nothing in the package requests unrelated credentials or performs unexpected actions.
目的
Name/description claim image+video generation via AIsa; required binary (python3, curl) and single env var AISA_API_KEY match that purpose. The included client code calls the documented AIsa endpoints (api.aisa.one) and implements Gemini image and Wan video flows described in SKILL.md.
说明范围
SKILL.md and the Python client only instruct calls to AIsa endpoints, create/poll async video tasks, parse inline image base64, and save/download media to local disk. This is within scope. Note: the client will download arbitrary URLs returned by the service or provided as --img-url, so downloaded content may be large or come from external storage (signed URLs).
安装机制
No install spec (instruction-only with a bundled Python script). No remote archives or opaque installers are fetched by the skill itself, so install risk is low.
证书
Only AISA_API_KEY is required and used (explicit or from env). No additional secrets, unrelated credentials, or config paths are requested. The API key is proportional to the claimed functionality.
持久
Skill is not always-enabled and does not request elevated/system-wide persistence or modify other skills. disable-model-invocation is false (agent may invoke autonomously) which is the platform default and not problematic here.
综合结论
This package appears to do what it says: it uses your AISA_API_KEY to call AIsa endpoints to generate images/videos and saves downloaded media locally. Before installing, consider: (1) only provide a dedicated AISA API key you trust and monitor its usage/billing (video generation can incur continuous costs), (2) review/inspect the included media_gen_client.py if you plan to run it locally, (3) be aware the client will download URLs returned by…
安装(复制给龙虾 AI)
将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「Generate images & videos with: Gemini 3 Pro Image + Qwen Wan 2.6 (video) via one API key」。简介:Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/aisadocs/openclaw-aisa-llm-image-video-qwen-wan26-gemini-3-pro-image/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
---
name: openclaw-media-gen
description: "Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key."
homepage: https://openclaw.ai
metadata: {"openclaw":{"emoji":"🎬","requires":{"bins":["python3","curl"],"env":["AISA_API_KEY"]},"primaryEnv":"AISA_API_KEY"}}
---
# OpenClaw Media Gen 🎬
Generate **images** and **videos** with one AIsa API key:
- **Image**: `gemini-3-pro-image-preview` (Gemini GenerateContent)
- **Video**: `wan2.6-t2v` (Qwen Wan 2.6 / Tongyi Wanxiang, async task)
API Reference: [AIsa API Reference](https://aisa.mintlify.app/api-reference/introduction) (all pages available at `https://aisa.mintlify.app/llms.txt`)
## 🎯 Pricing Advantage
### Video Generation (WAN) - Cost Comparison
| Resolution | AIsa (Contract) | AIsa (Official) | Bailian (Official) | OpenRouter |
|------------|-----------------|-----------------|-------------------|------------|
| 720P | **$0.06/sec** | ~$0.08 | ~$0.10 | ❌ |
| 1080P | **$0.09/sec** | ~$0.12 | ~$0.15 | ❌ |
| Pro/Animate | **$0.108–0.156** | ~$0.18 | ~$0.25 | ❌ |
**Key Benefits**:
- **25-40% cheaper** than Bailian official pricing
- **OpenRouter doesn't support video** - AIsa is the only unified API with video generation
- Contract pricing available for production workloads
- Single API key for both image and video generation
## 🔥 What You Can Do
### Image Generation (Gemini)
```
"Generate a cyberpunk cityscape at night, neon lights, rainy, cinematic"
```
### Video Generation (Wan 2.6)
```
"Use a reference image to generate a 5-second shot: slow camera push-in, wind blowing hair, cinematic, shallow depth of field"
```
## Quick Start
```bash
export AISA_API_KEY="your-key"
```
---
## 🖼️ Image Generation (Gemini)
### Endpoint
- Base URL: `https://api.aisa.one/v1`
- `POST /models/{model}:generateContent`
Documentation: `google-gemini-chat` (GenerateContent) at `https://aisa.mintlify.app/api-reference/chat/chat-api/google-gemini-chat.md`
### curl Example (returns inline_data for images)
```bash
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"}]}
]
}'
```
> Note: Response may contain `candidates[].parts[].inline_data` (typically with base64 data and mime type); client script automatically parses and saves the file.
---
## 🎞️ 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` (required for async)
Documentation: `video-generation` at `https://aisa.mintlify.app/api-reference/aliyun/video/video-generation.md`
```bash
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 Status
- `GET /services/aigc/tasks?task_id=...`
Documentation: `task` at `https://aisa.mintlify.app/api-reference/aliyun/video/task.md`
```bash
curl "https://api.aisa.one/apis/v1/services/aigc/tasks?task_id=YOUR_TASK_ID"
-H "Authorization: Bearer $AISA_API_KEY"
```
---
## Python Client
```bash
# Generate image (save to local file)
python3 {baseDir}/scripts/media_gen_client.py image
--prompt "A cute red panda, cinematic lighting"
--out "out.png"
# Create video task (requires 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
# Poll task status
python3 {baseDir}/scripts/media_gen_client.py video-status --task-id YOUR_TASK_ID
# Wait until success (optional: print video_url on success)
python3 {baseDir}/scripts/media_gen_client.py video-wait --task-id YOUR_TASK_ID --poll 10 --timeout 600
# Wait until success and auto-download mp4
python3 {baseDir}/scripts/media_gen_client.py video-wait --task-id YOUR_TASK_ID --download --out out.mp4
```
## 💡 Use Cases
- **AI Agents**: Automate visual content generation for social media, marketing materials
- **Content Creators**: Generate custom images and videos programmatically
- **Developers**: Build apps with multimodal generation capabilities
- **Businesses**: Cost-effective alternative to Bailian with better pricing
## 🚀 Why AIsa for Media Generation?
1. **Unified API**: Single key for both images (Gemini) and videos (WAN)
2. **Best Pricing**: 25-40% cheaper than alternatives
3. **Production Ready**: Contract pricing and enterprise support available
4. **No Competition**: OpenRouter doesn't support video generation
5. **Simple Integration**: Python client with async task management built-in