Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →openakita/tongyi-image
通过阿里云百炼 DashScope 生成 AI 图片 — 文生图、图像编辑、风格重绘、背景生成、画面扩展、涂鸦作画、电商套图。任务异步执行+轮询，成功后可自动下载到本地。
Passed 13 of 21 test cases with the skill, and 7 of 21 without it.
and 4 more in the full report
7 fixed7 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Here is a reference image of my living room photo. Please modify it by adding a modern floor lamp next to the sofa and changing the wall color to warm beige, keeping the overall room layout.
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the wan27-edit model for reference-based image editing. | Missed | Passed |
The instructions your model reads when the skill loads.
输入一句中文/英文描述（可选参考图、风格、尺寸），输出一张或多张高清图片。
所有调用都是 DashScope 异步任务：先 POST 拿 task_id，再轮询 GET task_status，
就绪后下载图片 URL（24h 过期，自动落盘到 data_dir/images/）。
seedance-video skill）；需要精确蒙版的局部修图（用 image-edit 插件）tongyi_image_create({prompt, model?, size?, negative_prompt?, n?})tongyi_image_status({task_id})tongyi_image_list({limit?})| mode | 描述 | 主流模型 |
|---|---|---|
| text2img | 纯文本生图 | wan27-pro, qwen-pro |
| img_edit | 参考图改写（无蒙版） | wan27-edit |
| style_repaint | 把一张人像换成预设风格 | wanx-style-repaint |
| bg_generation | 给商品/前景图生成新背景 | wanx-background-generation |
| outpainting | 画面外扩 / 改变长宽比 | wanx-outpainting |
| sketch2img | 涂鸦/线稿成图 | wanx-sketch-to-image |
| ecommerce | 电商套图（一组商品场景图） | wanx-ecommerce |
prompt + (可选 ref image) → DashScope POST → task_id →
poll loop（默认 10s）→ status==SUCCEEDED →
extract image URLs → (可选 auto_download) → 落盘 + 广播 task_update
test cases passed, vs 7 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.