Dashscope Image Gen

该 Skill 提供一个 Python 命令行脚本，读取提示词后调用 DashScope 的 OpenAI 兼容模式图片生成接口（qwen-image-max），将返回的图片保存到指定输出文件；附带一个说明接口与鉴权方式的参考文档。可选支持尺寸和数量参数。

热度 83.07

最近更新 2026-05-11 17:33:09

分类：创作依赖：代码执行 / 读写文件 / 第三方 API应用场景：图像生成

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add dashscope-image-gen

Metadata

name: dashscope-image-gen
description: Generate images via Alibaba DashScope OpenAI-compatible endpoint (compatible-mode) using qwen-image-max. Use when the user asks for 文生图/图片生成/image generation, wants to call /images/generations, or needs a scriptable CLI tool to create images from prompts.

Use this skill to generate an image from a text prompt through DashScope compatible-mode.

Preferred (no secrets in shell history):

export DASHSCOPE_API_KEY="..."
./scripts/dashscope_image_gen.py --prompt "a cute robot, watercolor" --out robot.png

Optional params (best-effort; support depends on DashScope):

./scripts/dashscope_image_gen.py --prompt "industrial factory at night" --size 1024x1024 --n 1 --out factory.png

Re-run with the same command and copy the HTTP error body.
If the error indicates a different route/payload than OpenAI Images API:
- Update scripts/dashscope_image_gen.py accordingly.
- Update references/dashscope-openai-compatible.md with the correct details.

scripts/dashscope_image_gen.py: main CLI (calls POST {baseUrl}/images/generations)
references/dashscope-openai-compatible.md: endpoint/auth notes