aliyun-wan-image

Aliyun Wan Image lets you create and modify images using DashScope's Wan 2.7 models via text prompts, image editing, interactive region selection, or multi-image sequences. Supports output up to 4K on the professional model and includes color palette customization.

Aliyun Wan Image generates images from text prompts using Alibaba's Wan 2.7 DashScope models.

AI-generated summary based on this skill's SKILL.md

★ 397 ⁮ 34 MIT updated 2026-07-18 by cinience

Install

cinience/alicloud-skills/aliyun-wan-image · repository language: Python

Manual (git clone) CLI (skillfed)

git clone https://github.com/cinience/alicloud-skills
cp -r alicloud-skills/skills/ai/image/aliyun-wan-image ~/.claude/skills/aliyun-wan-image

npx skillfed install cinience/alicloud-skills/aliyun-wan-image

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate image from text with Aliyun Wan 2.7?

Aliyun Wan Image uses DashScope's Wan 2.7 models to generate images directly from text prompts. You provide a text description of what you want to create, and the model synthesizes a corresponding image. The professional wan2.7-image-pro variant supports output up to 4K resolution, making it suitable for high-quality image creation tasks.

Can Aliyun Wan Image edit existing images with AI prompts?

Yes, Aliyun Wan Image supports AI-powered image editing. You can modify existing images by providing text instructions that describe the changes you want. The tool also enables interactive region-based editing through bounding boxes, allowing you to target specific areas of an image for precise modifications.

What's the DashScope image generation API and how does it work?

Aliyun Wan Image leverages the DashScope image generation API, which provides access to Aliyun's Wan 2.7 models. This API enables text-to-image synthesis, image editing, and batch operations. It's designed for multimodal generation tasks and integrates seamlessly with applications needing AI-powered image creation and manipulation capabilities.

Can I batch generate multiple images sequentially with consistent style?

Aliyun Wan Image supports creating multiple consistent images in sequence with style control. You can generate batches of images while maintaining visual coherence across the set. This feature is useful for creating image series, variations, or collections where stylistic consistency matters.

Does Aliyun Wan Image support color palette customization?

Yes, Aliyun Wan Image includes color palette customization and parameter control. You can define custom color schemes and adjust generation parameters to influence the visual output, giving you fine-grained control over the appearance and mood of generated or edited images.

What license does Aliyun Wan Image use?

Aliyun Wan Image is released under the MIT license, which permits free use, modification, and distribution for both commercial and private purposes, subject to the license terms.

SKILL.md

rendered from the published skill — quoted content, verbatim

Wan 2.7 Image Generation & Editing

Validation

mkdir -p output/aliyun-wan-image
python -m py_compile skills/ai/image/aliyun-wan-image/scripts/generate_image.py &amp;&amp; echo "py_compile_ok" &gt; output/aliyun-wan-image/validate.txt

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

Output And Evidence

Write generated image URLs, prompts, and metadata to output/aliyun-wan-image/.
Keep at least one sample JSON response per run.

Prerequisites

Install SDK (recommended in a venv):

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.

Critical model names

wan2.7-image-pro — professional version, supports 4K output
wan2.7-image — faster

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 4 files

skills/ai/image/aliyun-wan-image/SKILL.md
skills/ai/image/aliyun-wan-image/references/api_reference.md
skills/ai/image/aliyun-wan-image/references/sources.md
skills/ai/image/aliyun-wan-image/scripts/generate_image.py

All skills by cinience → Best document-to-slide-deck skills for AI agents - SkillFed →