Loading...
Loading...
Compare original and translation side by side
Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code), see agent-compatibility.md once per session.
Agent设置: 如果你的Agent不会自动加载技能(例如Claude Code), 每个会话首次使用时请查看 agent-compatibility.md。
| Location | Purpose |
|---|---|
| Default execution — sync/async, upload, download |
| Fallback: curl (sync/async), code generation |
| Prompt formulas, style keywords, negative_prompt, prompt_extend decision |
| API supplement |
| Official documentation URLs |
| Agent self-check: register skills in project config for agents that don't auto-load |
| 位置 | 用途 |
|---|---|
| 默认执行入口 — 同步/异步、上传、下载 |
| 备用方案:curl(同步/异步)、代码生成 |
| Prompt编写公式、风格关键词、negative_prompt、prompt_extend决策说明 |
| API补充说明 |
| 官方文档链接 |
| Agent自检:为不会自动加载技能的Agent在项目配置中注册技能 |
$DASHSCOPE_API_KEYos.environ["DASHSCOPE_API_KEY"].env.envDASHSCOPE_API_KEY=sk-your-key-here$DASHSCOPE_API_KEYos.environ["DASHSCOPE_API_KEY"].env.envDASHSCOPE_API_KEY=sk-your-key-heresk-...sk-sp-...sk-sp-references/codingplan.mdsk-...sk-sp-...sk-sp-references/codingplan.md| User Want | Mode | Model |
|---|---|---|
| Generate image from text only | t2i | |
| Edit image / apply style transfer based on 1–4 reference images | image-edit | |
| Subject consistency: generate new images maintaining subject from references | image-edit | |
| Multi-image composition: combine style from one image, background from another | image-edit | |
| Single-image editing preserving subject consistency | i2i | |
| Multi-image fusion: place object from one image into another scene | i2i | |
| Interleaved text-image output (e.g., tutorials, step-by-step guides) | interleave | |
| Fast text-to-image drafts | t2i | |
| Edit text within images, precise element manipulation | image-edit | |
| Multi-image fusion with realistic textures | image-edit | |
| Posters / complex Chinese+English text rendering | t2i | |
| Text-to-image with fixed aspect ratios (batch) | t2i | |
| 用户需求 | 模式 | 模型 |
|---|---|---|
| 仅通过文本生成图像 | t2i | |
| 基于1-4张参考图编辑图像/应用风格迁移 | image-edit | |
| 主体一致性:保留参考图主体特征生成新图像 | image-edit | |
| 多图合成:结合一张图的风格和另一张图的背景 | image-edit | |
| 单图编辑并保留主体一致性 | i2i | |
| 多图融合:将一张图中的物体放到另一个场景中 | i2i | |
| 图文混排输出(例如教程、分步指南) | interleave | |
| 快速文生图草稿 | t2i | |
| 编辑图像内的文字、精准操作元素 | image-edit | |
| 真实质感的多图融合 | image-edit | |
| 海报/复杂中英文字渲染 | t2i | |
| 固定宽高比的批量文生图 | t2i | |
| Model | Use Case |
|---|---|
| wan2.6-t2i | Recommended for text-to-image — sync + async, best quality |
| wan2.6-image | Image editing ONLY (NOT for pure text-to-image) — requires |
| wan2.5-i2i-preview | Image editing — single-image editing with subject consistency, multi-image fusion (up to 3 images), async-only |
| wan2.5-t2i-preview | Preview — free size within constraints |
| wan2.2-t2i-flash | Fast — lower latency |
| wan2.2-t2i-plus | Professional — improved stability |
| 模型 | 适用场景 |
|---|---|
| wan2.6-t2i | 文生图推荐首选 — 支持同步+异步,画质最优 |
| wan2.6-image | 仅用于图像编辑(不可用于纯文生图) — 需要传入 |
| wan2.5-i2i-preview | 图像编辑 — 支持保留主体一致性的单图编辑、多图融合(最多3张图),仅支持异步 |
| wan2.5-t2i-preview | 预览版 — 支持约束范围内的自由尺寸 |
| wan2.2-t2i-flash | 快速版 — 延迟更低 |
| wan2.2-t2i-plus | 专业版 — 稳定性更高 |
| Model | Use Case |
|---|---|
| qwen-image-2.0-pro | Fused generation + editing — text rendering, realistic textures, multi-image (1–3 input, 1–6 output) |
| qwen-image-2.0 | Accelerated generation + editing |
| qwen-image-edit-max | Image editing — 1–6 output images |
| qwen-image-edit-plus | Image editing — 1–6 output images |
| qwen-image-edit | Image editing — 1 output image only |
| qwen-image-plus | Text-to-image — fixed resolutions only (async) |
| qwen-image-max | Text-to-image — fixed resolutions only |
qwen-image-2.0-proqwen-image-2.0qwen-image-edit-max/plus/editwan2.6-image/multimodal-generation/generationmessagesqwen-image-2.0-proqwen-image-2.0qwen-image-plusqwen-image-max/text2image/image-synthesisinput.promptwan2.6-imagewan2.5-i2i-previewwan2.6-imagewan2.5-i2i-previewwan2.6-t2iwan2.6-imageenable_interleave: truewan2.6-imagewan2.5-i2i-preview⚠️ Important: The model list above is a point-in-time snapshot and may be outdated. Model availability changes frequently. Always check the official model list for the authoritative, up-to-date catalog before making model decisions.
| 模型 | 适用场景 |
|---|---|
| qwen-image-2.0-pro | 融合生成+编辑 — 支持文字渲染、真实质感、多图处理(1-3张输入,1-6张输出) |
| qwen-image-2.0 | 加速版生成+编辑 |
| qwen-image-edit-max | 图像编辑 — 1-6张输出图像 |
| qwen-image-edit-plus | 图像编辑 — 1-6张输出图像 |
| qwen-image-edit | 图像编辑 — 仅输出1张图像 |
| qwen-image-plus | 文生图 — 仅支持固定分辨率(异步) |
| qwen-image-max | 文生图 — 仅支持固定分辨率 |
qwen-image-2.0-proqwen-image-2.0qwen-image-edit-max/plus/editwan2.6-image/multimodal-generation/generationmessagesqwen-image-2.0-proqwen-image-2.0qwen-image-plusqwen-image-max/text2image/image-synthesisinput.promptwan2.6-imagewan2.5-i2i-previewwan2.6-imagewan2.5-i2i-previewwan2.6-t2iwan2.6-imageenable_interleave: truewan2.6-imagewan2.5-i2i-preview⚠️ 重要提示: 上述模型列表是当前时间点的快照,可能会过时。模型可用性会频繁更新。在选择模型前,请务必查看官方模型列表获取权威、最新的目录信息。
⚠️ Multiple artifacts: When generating multiple files in a single session, you MUST append a numeric suffix to each filename (e.g.,out_1.png) to prevent overwrites.out_2.png
⚠️ 多文件生成: 单个会话中生成多个文件时,必须为每个文件名添加数字后缀(例如、out_1.png)以防止覆盖。out_2.png
DASHSCOPE_API_KEYQWEN_API_KEY[ -n "$DASHSCOPE_API_KEY" ].envecho 'DASHSCOPE_API_KEY=sk-your-key-here' >> .env.envDASHSCOPE_API_KEYQWEN_API_KEY[ -n "$DASHSCOPE_API_KEY" ].envecho 'DASHSCOPE_API_KEY=sk-your-key-here' >> .env.envpython3 --version # must be 3.9+python3python --versionpy -3 --versionpython3 --version # 必须为3.9+python3python --versionpy -3 --versionscripts/cdpython3 <this-skill-dir>/scripts/image.py --helpundefinedscripts/cdpython3 <本技能目录>/scripts/image.py --helpundefined
**More examples** (interleaved output, wan2.5-i2i, qwen-image-2.0-pro, qwen-image-plus): See [execution-guide.md](references/execution-guide.md)
| Argument | Description |
|----------|-------------|
| `--request '{...}'` | JSON request body |
| `--file path.json` | Load request from file |
| `--async` | Force async mode (required for wan2.5 and older; auto-enabled for qwen-image-plus/max and interleaved output) |
| `--model ID` | Override model (`wan2.6-t2i` default; see model list in help) |
| `--output path` | Save image to path (or directory for multi-image output) |
| `--print-response` | Print response JSON to stdout |
**更多示例**(图文混排输出、wan2.5-i2i、qwen-image-2.0-pro、qwen-image-plus):请查看[execution-guide.md](references/execution-guide.md)
| 参数 | 说明 |
|----------|-------------|
| `--request '{...}'` | JSON请求体 |
| `--file path.json` | 从文件加载请求体 |
| `--async` | 强制异步模式(wan2.5及更早版本需要;qwen-image-plus/max和图文混排输出会自动启用) |
| `--model ID` | 覆盖默认模型(默认是`wan2.6-t2i`;可查看帮助中的模型列表) |
| `--output path` | 将图像保存到指定路径(多图输出时指定目录) |
| `--print-response` | 将响应JSON打印到标准输出 |0output.resultsoutput.task_idoutput.task_idtask_status: SUCCEEDEDls -la <output_path>[ACTION_REQUIRED][UPDATE_AVAILABLE]0output.resultsoutput.task_idoutput.task_idtask_status: SUCCEEDEDls -la <输出路径>[ACTION_REQUIRED][UPDATE_AVAILABLE]| Error Pattern | Diagnosis | Resolution |
|---|---|---|
| Python not on PATH | Try |
| Script version check failed | Upgrade Python to 3.9+ |
| Python < 3.9 | Upgrade Python to 3.9+ |
| Missing API key | Obtain key from QwenCloud Console; add to |
| Invalid or mismatched key | Run qwencloud-ops-auth (non-plaintext check only); verify key is valid |
| SSL cert issue (proxy/corporate) | macOS: run |
| Network unreachable | Check internet; set |
| Rate limited | Wait and retry with backoff |
| Server error | Retry with backoff |
| Can't write output | Use |
| 错误特征 | 诊断 | 解决方案 |
|---|---|---|
| Python不在PATH中 | 尝试 |
| 脚本版本检查不通过 | 将Python升级到3.9+ |
类型提示附近的 | Python版本低于3.9 | 将Python升级到3.9+ |
| 缺失API密钥 | 从QwenCloud控制台获取密钥;添加到 |
| 密钥无效或不匹配 | 运行qwencloud-ops-auth(仅做非明文检查);验证密钥有效性 |
| SSL证书问题(代理/企业网络) | macOS:运行 |
| 网络不可达 | 检查网络连接;如果使用代理则设置 |
| 触发速率限制 | 等待后按指数退避策略重试 |
| 服务端错误 | 等待后按指数退避策略重试 |
| 无法写入输出路径 | 使用 |
| Field | Type | Description |
|---|---|---|
| string | Text description of the image to generate (required) |
| string | Content to avoid in the image (max 500 chars) |
| string | Resolution — |
| int | Random seed for reproducibility [0, 2147483647] |
| string | |
| bool | Enable prompt rewriting (default: true; image editing mode only) |
| 字段 | 类型 | 说明 |
|---|---|---|
| string | 待生成图像的文本描述(必填) |
| string | 图像中要避免的内容(最多500字符) |
| string | 分辨率 — |
| int | 用于复现结果的随机种子,范围[0, 2147483647] |
| string | |
| bool | 启用prompt重写(默认:true;仅图像编辑模式可用) |
| Field | Type | Description |
|---|---|---|
| string[] | 1–4 image URLs or local paths for editing mode; 0–1 for interleave mode |
| string | Single image URL/path (shorthand; |
| bool | |
| int | Number of images to generate in editing mode (1–4, default: 1). Billed per image. |
| int | Max images in interleave mode (1–5, default: 5). Billed per image. |
| bool | Add "AI Generated" watermark (default: false) |
| 字段 | 类型 | 说明 |
|---|---|---|
| string[] | 编辑模式下1-4张图像的URL或本地路径;混排模式下0-1张 |
| string | 单张图像URL/路径(简写形式; |
| bool | |
| int | 编辑模式下生成的图像数量(1-4,默认:1)。按生成张数计费。 |
| int | 混排模式下最多生成的图像数量(1-5,默认:5)。按生成张数计费。 |
| bool | 添加“AI Generated”水印(默认:false) |
| Model | Key Differences |
|---|---|
| async-only, 1–3 images, |
| 1–3 images, n=1–6 (except |
| async-only, n fixed at 1, 5 fixed resolutions only |
| 模型 | 核心差异 |
|---|---|
| 仅支持异步、1-3张图、 |
| 1-3张图、n=1-6(除了 |
| 仅支持异步、n固定为1、仅支持5种固定分辨率 |
1K2K1280*1280960*12801280*960720*12801280*7201K2K1280*1280960*12801280*960720*12801280*720| Field | Description |
|---|---|
| URL of generated image (24h validity). Use this when chaining to another skill. |
| Array of all image URLs (multi-image output, wan2.6-image, qwen-image-edit) |
| Number of generated images |
| Local file path of the downloaded image. Use this for user preview or non-API operations. |
| Array of local file paths (multi-image output) |
| Array of |
| Image dimensions |
| Seed used |
| 字段 | 说明 |
|---|---|
| 生成图像的URL(有效期24小时)。串联其他技能时使用该字段。 |
| 所有图像URL的数组(多图输出、wan2.6-image、qwen-image-edit场景) |
| 生成的图像数量 |
| 下载的图像本地文件路径。用户预览或非API操作时使用该字段。 |
| 本地文件路径的数组(多图输出场景) |
| |
| 图像尺寸 |
| 生成使用的种子 |
POST /api/v1/services/aigc/multimodal-generation/generationPOST /api/v1/services/aigc/image-generation/generationX-DashScope-Async: enablePOST /api/v1/services/aigc/image2image/image-synthesisX-DashScope-Async: enablePOST /api/v1/services/aigc/text2image/image-synthesisX-DashScope-Async: enableoss://QWEN_TMP_OSS_BUCKETQWEN_TMP_OSS_REGION.envpip install alibabacloud-oss-v2QWEN_TMP_OSS_AK_IDQWEN_TMP_OSS_AK_SECRETOSS_ACCESS_KEY_IDOSS_ACCESS_KEY_SECREToss:PutObjectoss:GetObjectreferences/custom-oss.mdX-DashScope-Sse: enablestream: truePOST /api/v1/services/aigc/multimodal-generation/generationPOST /api/v1/services/aigc/image-generation/generationX-DashScope-Async: enablePOST /api/v1/services/aigc/image2image/image-synthesisX-DashScope-Async: enablePOST /api/v1/services/aigc/text2image/image-synthesisX-DashScope-Async: enableoss://.envQWEN_TMP_OSS_BUCKETQWEN_TMP_OSS_REGIONpip install alibabacloud-oss-v2QWEN_TMP_OSS_AK_IDQWEN_TMP_OSS_AK_SECRETOSS_ACCESS_KEY_IDOSS_ACCESS_KEY_SECREToss:PutObjectoss:GetObjectreferences/custom-oss.mdX-DashScope-Sse: enablestream: trueimage_urlhttps://oss://local_path| Scenario | Use |
|---|---|
| Feed to another skill (video-gen, vision, image-edit) | |
| Show to user / open in editor | |
image_urlhttps://oss://local_path| 场景 | 使用字段 |
|---|---|
| 输入到其他技能(视频生成、视觉分析、图像编辑) | |
| 展示给用户 / 在编辑器中打开 | |
| HTTP | Meaning | Action |
|---|---|---|
| 401 | Invalid or missing API key | Run qwencloud-ops-auth if available; else prompt user to set key (non-plaintext check only) |
| 400 | Bad request (invalid prompt, size) | Verify parameters and constraints |
| 429 | Rate limited | Retry with exponential backoff |
| 5xx | Server error | Retry with exponential backoff |
| HTTP状态码 | 含义 | 处理方式 |
|---|---|---|
| 401 | API密钥无效或缺失 | 如果有qwencloud-ops-auth则运行该技能;否则提示用户设置密钥(仅做非明文检查) |
| 400 | 请求错误(prompt无效、尺寸无效) | 验证参数和约束是否符合要求 |
| 429 | 触发速率限制 | 按指数退避策略重试 |
| 5xx | 服务端错误 | 按指数退避策略重试 |
./output/qwencloud-image-generation/skills/output/./output/qwencloud-image-generation/skills/output/[ACTION_REQUIRED] qwencloud-update-check skill is not installed[ACTION_REQUIRED] qwencloud-update-check skill is not installedThe update-check skill is not installed. It keeps you informed about new qwencloud/qwencloud-ai features and bug fixes.
- Install now — I'll run the install command for you
- Skip for now — do nothing this time
- Never remind me — permanently suppress this prompt
npx skills add QwenCloud/qwencloud-ai --skill qwencloud-update-check -ypython3 <this-skill-scripts-dir>/gossamer.py --dismisspython3 <this-skill-scripts-dir>/gossamer.py --dismisspython3 <this-skill-scripts-dir>/gossamer.py --never-install更新检查技能未安装,该技能会通知你qwencloud/qwencloud-ai的新功能和bug修复信息。
- 立即安装 — 我会为你运行安装命令
- 暂时跳过 — 本次不做任何操作
- 不再提醒 — 永久屏蔽该提示
npx skills add QwenCloud/qwencloud-ai --skill qwencloud-update-check -ypython3 <本技能脚本目录>/gossamer.py --dismisspython3 <本技能脚本目录>/gossamer.py --dismisspython3 <本技能脚本目录>/gossamer.py --never-install[UPDATE_AVAILABLE][UPDATE_AVAILABLE][ACTION_REQUIRED][UPDATE_AVAILABLE][ACTION_REQUIRED][UPDATE_AVAILABLE]qwencloud-update-check/SKILL.mdpython3 <qwencloud-update-check-dir>/scripts/check_update.py --print-responseqwencloud-update-check/SKILL.mdpython3 <qwencloud-update-check目录>/scripts/check_update.py --print-response