aliyun-qwen-image-edit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: provider

分类：provider

Model Studio Qwen Image Edit

Model Studio Qwen 图像编辑

Validation

验证

bash

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.

bash

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

通过标准：命令退出码为0，且生成

output/aliyun-qwen-image-edit/validate.txt

文件。

Output And Evidence

输出与凭证

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.

将编辑请求载荷、结果URL和模型参数保存在
```
output/aliyun-qwen-image-edit/
```
目录下。
留存一组请求/响应样本用于复现。

请使用Qwen图像编辑模型完成指令驱动的图像编辑任务，而非文生图生成。

Critical model names

核心模型名称

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
```

请使用以下准确的模型字符串之一：

```
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

前置条件

Install SDK in a virtual environment:

bash

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

Set

DASHSCOPE_API_KEY

in your environment, or add

dashscope_api_key

~/.alibabacloud/credentials

在虚拟环境中安装SDK：

bash

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

在环境变量中设置

DASHSCOPE_API_KEY

，或者将

dashscope_api_key

添加到

~/.alibabacloud/credentials

文件中。

Normalized interface (image.edit)

标准化接口（image.edit）

Request

请求参数

```
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)

```
prompt
```
（字符串，必填）
```
image
```
（字符串 | 字节流，必填）源图像URL/路径/字节流
```
mask
```
（字符串 | 字节流，可选）图像修复区域掩码
```
size
```
（字符串，可选）例如
```
1024*1024
```
```
seed
```
（整数，可选）

Response

返回参数

```
image_url
```
(string)
```
seed
```
(int)
```
request_id
```
(string)

```
image_url
```
（字符串）
```
seed
```
（整数）
```
request_id
```
（字符串）

Operational guidance

操作指引

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.

提示词需面向任务：明确描述需要修改的内容和需要保留的内容。
进行确定性局部编辑时使用掩码。
将输出资源保存到对象存储中，仅持久化存储URL。
如需保持主体一致性，请在提示词中添加明确约束。

Local helper script

本地辅助脚本

Prepare a normalized request JSON and validate response schema:

bash

.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"

生成标准化请求JSON并验证响应格式：

bash

.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

输出路径

Default output:
```
output/aliyun-qwen-image-edit/images/
```
Override base dir with
```
OUTPUT_DIR
```
.

默认输出路径：
```
output/aliyun-qwen-image-edit/images/
```
可通过
```
OUTPUT_DIR
```
环境变量覆盖基础目录。

Workflow

工作流程

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.

确认用户意图、区域、标识，以及操作是只读还是修改性质。
先运行一个最简只读查询验证连通性和权限。
使用明确参数和有限范围执行目标操作。
验证结果并保存输出/凭证文件。

References

参考文档

```
references/sources.md
```

```
references/sources.md
```