← 返回 Skills 市场
cinience

Alicloud Ai Image Qwen Image Edit

作者 cinience · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
1081
总下载
0
收藏
6
当前安装
2
版本数
在 OpenClaw 中安装
/install alicloud-ai-image-qwen-image-edit
功能描述
Edit images with Alibaba Cloud Model Studio Qwen Image Edit models (qwen-image-edit, qwen-image-edit-plus, qwen-image-edit-max and snapshots). Use when modif...
使用说明 (SKILL.md)

Category: provider

Model Studio Qwen Image Edit

Validation

mkdir -p output/alicloud-ai-image-qwen-image-edit
python -m py_compile skills/ai/image/alicloud-ai-image-qwen-image-edit/scripts/prepare_edit_request.py && echo "py_compile_ok" > output/alicloud-ai-image-qwen-image-edit/validate.txt

Pass criteria: command exits 0 and output/alicloud-ai-image-qwen-image-edit/validate.txt is generated.

Output And Evidence

  • Save edit request payloads, result URLs, and model parameters under output/alicloud-ai-image-qwen-image-edit/.
  • Keep one sample request/response pair for reproducibility.

Use Qwen Image Edit models for instruction-based image editing instead of text-to-image generation.

Critical model names

Use one of these exact model strings:

  • qwen-image-edit
  • qwen-image-edit-plus
  • qwen-image-edit-max
  • qwen-image-2.0
  • qwen-image-2.0-pro
  • qwen-image-edit-plus-2025-12-15
  • qwen-image-edit-max-2026-01-16

Prerequisites

  • Install SDK in a virtual environment:
python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope
  • Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials.

Normalized interface (image.edit)

Request

  • prompt (string, required)
  • image (string | bytes, required) source image URL/path/bytes
  • mask (string | bytes, optional) inpaint region mask
  • size (string, optional) e.g. 1024*1024
  • seed (int, optional)

Response

  • image_url (string)
  • seed (int)
  • request_id (string)

Operational guidance

  • Keep prompts task-oriented: describe what to change and what to preserve.
  • Use masks for deterministic local edits.
  • Save output assets to object storage and persist only URLs.
  • For subject consistency, provide explicit constraints in prompt.

Local helper script

Prepare a normalized request JSON and validate response schema:

.venv/bin/python skills/ai/image/alicloud-ai-image-qwen-image-edit/scripts/prepare_edit_request.py \
  --prompt "Replace the sky with sunset, keep buildings unchanged" \
  --image "https://example.com/input.png"

Output location

  • Default output: output/alicloud-ai-image-qwen-image-edit/images/
  • Override base dir with OUTPUT_DIR.

Workflow

  1. Confirm user intent, region, identifiers, and whether the operation is read-only or mutating.
  2. Run one minimal read-only query first to verify connectivity and permissions.
  3. Execute the target operation with explicit parameters and bounded scope.
  4. Verify results and save output/evidence files.

References

  • references/sources.md
安全使用建议
This skill looks like a legitimate wrapper for Alibaba Cloud Qwen image-edit models, but before installing: (1) note that SKILL.md requires a DASHSCOPE_API_KEY or credentials in ~/.alibabacloud/credentials even though the registry metadata omitted any required env — ask the publisher to correct the metadata or document why creds are optional; (2) inspect the 'dashscope' pip package provenance (PyPI name, source repo) before installing and prefer creating a disposable venv; (3) provide least-privilege cloud credentials (a key scoped only to the necessary Model Studio operations) and avoid using broad account keys; (4) confirm where outputs are stored (default output/ path and any object storage) and whether those artifacts may contain sensitive data; and (5) if you need higher assurance, request the publisher to declare the required environment variables in the registry metadata and to provide a checksum/source for the dashscope package. Overall the skill is coherent with its purpose but the missing credential declaration is a notable inconsistency.
功能分析
Type: OpenClaw Skill Name: alicloud-ai-image-qwen-image-edit Version: 1.0.1 The skill bundle provides a legitimate interface for Alibaba Cloud's Qwen Image Edit models. It includes a helper script (scripts/prepare_edit_request.py) for JSON request formatting and response validation, and standard instructions in SKILL.md for environment setup using the official 'dashscope' SDK. No indicators of data exfiltration, malicious execution, or prompt injection were found.
能力评估
Purpose & Capability
The name and description (Qwen Image Edit on Alibaba Cloud) match the included instructions and the helper script: they prepare a normalized image.edit request and validate responses. However, the metadata declares no required env vars or credentials while the SKILL.md explicitly requires DASHSCOPE_API_KEY or an Alibaba Cloud creds entry, which is inconsistent.
Instruction Scope
SKILL.md instructions stay within the skill's stated purpose: preparing requests, validating responses, running a small py_compile validation, guiding prompt/mask usage, and asking to perform a minimal read-only connectivity check. The helper script only reads/writes JSON request/response files and does not attempt to access unrelated system paths or exfiltrate data by itself.
Install Mechanism
There is no install spec; the SKILL.md recommends creating a Python venv and pip installing the 'dashscope' package. This is a typical approach for an SDK-based integration. The only risk is the external pip package — verify the package's provenance (dashscope) before installing.
Credentials
The runtime docs require DASHSCOPE_API_KEY or adding dashscope_api_key to ~/.alibabacloud/credentials (cloud credentials). The skill metadata, however, lists no required env vars or primary credential. That mismatch is concerning: the skill will need cloud credentials to operate, but the registry metadata does not declare them, which could lead to unexpected credential requests at runtime.
Persistence & Privilege
The skill is not always-enabled and does not request persistent privileges. It writes output under an output/ directory and suggests using object storage for assets. There is no evidence it modifies other skills or system-wide config.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install alicloud-ai-image-qwen-image-edit
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /alicloud-ai-image-qwen-image-edit 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
batch publish from alicloud-skills on 2026-03-11
v1.0.0
alicloud-ai-image-qwen-image-edit v1.0.0 – Initial Release - Introduces Alibaba Cloud’s Qwen Image Edit Max for instruction-based image editing (inpainting, style transfer, local edits). - Supports task-oriented prompts, subject consistency, and region masking. - Standardized request/response interface for image editing tasks. - Includes setup instructions using the dashscope SDK and API key configuration. - Provides operational guidance and example script for preparing edit requests. - Defines default and customizable output locations for edited images.
元数据
Slug alicloud-ai-image-qwen-image-edit
版本 1.0.1
许可证 MIT-0
累计安装 7
当前安装数 6
历史版本数 2
常见问题

Alicloud Ai Image Qwen Image Edit 是什么?

Edit images with Alibaba Cloud Model Studio Qwen Image Edit models (qwen-image-edit, qwen-image-edit-plus, qwen-image-edit-max and snapshots). Use when modif... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1081 次。

如何安装 Alicloud Ai Image Qwen Image Edit?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install alicloud-ai-image-qwen-image-edit」即可一键安装,无需额外配置。

Alicloud Ai Image Qwen Image Edit 是免费的吗?

是的,Alicloud Ai Image Qwen Image Edit 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Alicloud Ai Image Qwen Image Edit 支持哪些平台?

Alicloud Ai Image Qwen Image Edit 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Alicloud Ai Image Qwen Image Edit?

由 cinience(@cinience)开发并维护,当前版本 v1.0.1。

💬 留言讨论