← 返回 Skills 市场

Aliyun Qwen Image Edit

Name: Aliyun Qwen Image Edit
Author: cinience

作者 cinience · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

127

总下载

当前安装

版本数

在 OpenClaw 中安装

/install aliyun-qwen-image-edit

功能描述

Use when editing images with Alibaba Cloud Model Studio Qwen Image Edit models (qwen-image-edit, qwen-image-edit-plus, qwen-image-edit-max, qwen-image-2.0 se...

使用说明 (SKILL.md)

Category: provider

Model Studio Qwen Image Edit

Validation

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

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

Output And Evidence

Save edit request payloads, result URLs, and model parameters under output/aliyun-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-2.0-2026-03-03
qwen-image-2.0-pro-2026-03-03
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/aliyun-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/aliyun-qwen-image-edit/images/
Override base dir with OUTPUT_DIR.

Workflow

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

References

references/sources.md

安全使用建议

Do not install or run this skill until the author clears up the mismatches. Specifically: (1) The SKILL.md requires DASHSCOPE_API_KEY or ~/.alibabacloud/credentials, but the registry metadata declares no required env vars or config paths — ask the publisher to update metadata to declare these credentials and explain required IAM permissions. (2) Verify the 'dashscope' package origin (PyPI vs. other) and review it before pip installing in a sandboxed venv. (3) Provide only a least-privilege API key for testing, preferably a temporary/service account key restricted to the minimal Model Studio actions needed. (4) Run the validation command (py_compile and the prepare script) in an isolated environment and inspect network calls while exercising the skill to confirm it only talks to Alibaba Cloud endpoints. (5) If you intend to allow autonomous agent invocation, ensure the agent's policies and credential scopes prevent data exfiltration and limit modifications. If the publisher cannot justify the missing metadata or provide a trustworthy homepage/source, treat the skill as untrusted.

功能分析

Type: OpenClaw Skill Name: aliyun-qwen-image-edit Version: 1.0.0 The skill bundle is a legitimate integration for Alibaba Cloud's Qwen Image Edit models. The provided Python script (scripts/prepare_edit_request.py) safely handles JSON request preparation and response validation without any risky execution or network calls. The instructions in SKILL.md correctly guide the agent to use the official 'dashscope' SDK and follow standard Alibaba Cloud credential practices.

能力评估

⚠ Purpose & Capability

The skill's name, description, and code (prepare_edit_request.py) match an image-edit helper for Alibaba Cloud Qwen models. However, the SKILL.md explicitly instructs the user to set DASHSCOPE_API_KEY or add an entry to ~/.alibabacloud/credentials so the SDK can authenticate. The registry metadata declares no required env vars or config paths. That mismatch between claimed requirements and actual instructions is unexpected and concerning.

⚠ Instruction Scope

SKILL.md instructs creating a virtualenv and installing the 'dashscope' SDK and to provide DASHSCOPE_API_KEY or credentials in ~/.alibabacloud/credentials. The included script itself only prepares JSON and does not read environment variables, but the runtime workflow clearly expects the agent or operator to supply cloud credentials and call cloud APIs. The instructions also direct saving request/response artifacts to output/..., and suggest storing assets in object storage. The skill's instructions therefore access credentials and filesystem locations that are not declared in metadata — scope creep and a documentation/metadata coherence issue.

ℹ Install Mechanism

There is no formal install spec in the registry (instruction-only). The SKILL.md tells operators to pip install 'dashscope' in a venv. This is a normal approach for Python helpers but is not enforced by the registry metadata; the package origin (dashscope on PyPI or elsewhere) should be verified before installation. No downloads from arbitrary URLs or extract/install steps are present.

⚠ Credentials

The runtime docs require DASHSCOPE_API_KEY or entries in ~/.alibabacloud/credentials, yet the skill metadata lists no required environment variables or config paths and has no primary credential declared. Requesting cloud API keys is reasonable for an Alibaba Cloud integration, but the omission from the metadata is a significant inconsistency. Users need explicit, minimal credential requirements declared (and guidance about required IAM permissions).

ℹ Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. Autonomous invocation is allowed by default (disable-model-invocation is false), which is normal. Combined with the credential requirement (from SKILL.md), autonomous invocation increases potential blast radius, so confirm the agent's allowed behaviors and credential scope before enabling autonomous runs.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install aliyun-qwen-image-edit
安装完成后，直接呼叫该 Skill 的名称或使用 /aliyun-qwen-image-edit 触发
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

v1.0.0

Initial release of aliyun-qwen-image-edit skill for image editing with Alibaba Cloud Qwen models. - Supports instruction-based editing with inpainting, style transfer, and local modifications. - Compatible with multiple Qwen Image Edit model versions; model name must match exactly. - Provides a normalized request/response interface for prompts, images, masks, and parameters. - Outputs request payloads and results under standardized output directory. - Includes setup steps, operational guidance, and a validation script for reproducibility.

元数据

Slug aliyun-qwen-image-edit

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题