aisa-media-gen-skillGenerate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key.
Install via ClawdBot CLI:
clawdbot install bowen-dotcom/aisa-media-gen-skill用 AIsa API 一把钥匙生成图片与视频:
gemini-3-pro-image-preview(Gemini GenerateContent)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)。
"生成一张赛博朋克风格的城市夜景,霓虹灯,雨夜,电影感"
"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"
export AISA_API_KEY="your-key"
https://api.aisa.one/v1POST /models/{model}:generateContent文档:google-gemini-chat(GenerateContent)见 https://aisa.mintlify.app/api-reference/chat/chat-api/google-gemini-chat.md。
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。
https://api.aisa.one/apis/v1POST /services/aigc/video-generation/video-synthesisX-DashScope-Async: enable(必填,异步)文档:video-generation 见 https://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
}
}'
GET /services/aigc/tasks?task_id=...文档:task 见 https://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"
# 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
Generated Mar 1, 2026
Create custom visuals for social media ads and promotional content, such as generating vibrant images of products in cinematic settings or short videos showcasing brand stories. This reduces reliance on stock media and accelerates campaign deployment.
Generate high-quality images and videos for online listings, like showcasing items in lifestyle contexts or creating dynamic video previews. This enhances product appeal and can increase conversion rates by providing engaging media without extensive photoshoots.
Produce visuals for blogs, news articles, or educational materials, such as creating illustrative images for topics or short explainer videos. This supports content teams in quickly generating relevant media to complement written work.
Use image and video generation to mock up concepts for films, games, or design projects, like visualizing scenes or character designs. This aids in pre-production by allowing rapid iteration and feedback before final production.
Offer the skill as a paid API service to developers and businesses, charging per request or through subscription tiers for media generation. This model leverages the underlying AIsa API to provide scalable access to AI media tools.
Integrate the skill into a custom platform for agencies or enterprises, allowing them to generate branded media internally. Revenue comes from licensing fees or setup costs for tailored deployments.
Market the skill to freelancers and small studios as a tool to enhance their workflow, offering it as part of a software suite with tutorials and support. Revenue is generated through one-time purchases or add-on subscriptions.
💬 Integration Tip
Ensure the AISA_API_KEY is securely stored and manage asynchronous video tasks with proper polling to handle delays in generation.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.