aliyun-qwen-image
This skill provides standardized image generation using Alibaba's Qwen models through the DashScope SDK. It normalizes requests across qwen-image variants with support for prompts, negative prompts, dimensions, seeds, and reference images, while handling authentication via environment variables or credential files.
aliyun-qwen-image generates images using Qwen models through DashScope SDK with a normalized interface.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-18
aliyun-qwen-image generates images using Qwen models through DashScope SDK with a normalized interface. This skill provides standardized image generation using Alibaba's Qwen models through the DashScope SDK. It normalizes requests across qwen-image variants with support for prompts, negative prompts, dimensions, seeds, and reference images, while handling authentication via environment variables or credential files.
Use it when
- aliyun-qwen-image supports multiple Qwen image model variants, including qwen-image-plus and qwen-image-max.
- Yes, aliyun-qwen-image is designed for integration into video-agent pipelines.
Verify before relying
Read SKILL.md below before installing (6 files). Open directory: indexed for reading, not audited.
Install
cinience/alicloud-skills/aliyun-qwen-image · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I generate images with the Qwen AI model using aliyun-qwen-image?
aliyun-qwen-image provides standardized image generation using Alibaba's Qwen models through the DashScope SDK. You pass a prompt, optional negative prompt, dimensions, and seed to the skill, which normalizes your request and calls the appropriate qwen-image variant (like qwen-image-max or qwen-image-plus). Authentication uses environment variables or credential files automatically.
What is the difference between qwen-image-plus vs qwen-image-max?
aliyun-qwen-image supports multiple Qwen image model variants, including qwen-image-plus and qwen-image-max, each with different capabilities and performance characteristics. The skill abstracts these differences by normalizing your image.generate requests and routing them to the correct model endpoint via DashScope API, so you can switch models without changing your integration code.
Can aliyun-qwen-image be integrated into a video-agent pipeline?
Yes, aliyun-qwen-image is designed for integration into video-agent pipelines. It maps normalized image.generate requests to the DashScope API, allowing you to generate images on-demand as part of a larger video workflow. The skill handles authentication, error handling, and API response parsing transparently.
How do I set up API key authentication for aliyun-qwen-image?
aliyun-qwen-image handles authentication via environment variables or credential files—no manual setup required. Set your DashScope API key in your environment, and the skill automatically uses it. The skill also includes error handling for authentication failures and rate-limit responses (like 429 errors).
Does aliyun-qwen-image support reproducible image generation with seeds?
Yes, aliyun-qwen-image supports reproducible image generation by accepting a seed parameter. You can also enable caching of results to optimize repeated requests. These features help ensure consistent outputs and reduce API calls when generating similar images.
What parameters does aliyun-qwen-image accept for image generation?
aliyun-qwen-image accepts prompts, negative prompts, image dimensions, seeds for reproducibility, and reference images. It normalizes these parameters across Qwen model variants and handles the DashScope SDK integration, returning structured JSON responses with generated image URLs and metadata.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Category: provider
Model Studio Qwen Image
Validation
mkdir -p output/aliyun-qwen-image
python -m py_compile skills/ai/image/aliyun-qwen-image/scripts/generate_image.py && echo "py_compile_ok" > output/aliyun-qwen-image/validate.txt
Pass criteria: command exits 0 and output/aliyun-qwen-image/validate.txt is generated.
Output And Evidence
- Write generated image URLs, prompts, and metadata to
output/aliyun-qwen-image/. - Keep at least one sample JSON response per run.
Build consistent image generation behavior for the video-agent pipeline by standardizing image.generate inputs/outputs and using DashScope SDK (Python) with the exact model name.
Prerequisites
- Install SDK (recommended in a venv to avoid PEP 668
(truncated - see the full file via the links below)
File tree — 6 files
skills/ai/image/aliyun-qwen-image/SKILL.md
skills/ai/image/aliyun-qwen-image/agents/openai.yaml
skills/ai/image/aliyun-qwen-image/references/api_reference.md
skills/ai/image/aliyun-qwen-image/references/prompt-guide.md
skills/ai/image/aliyun-qwen-image/references/sources.md
skills/ai/image/aliyun-qwen-image/scripts/generate_image.py
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate images using Qwen models via DashScope SDK”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
This skill wraps Aliyun's Wan video generation models through the DashScope SDK, enabling both text-to-video and image-to-video workflows. It standardizes video.generate requests with support for prompt control, duration, frame rate, resolution, seed, and motion parameters across multiple Wan model variants.
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.
Z-Image Turbo enables fast text-to-image generation through Alibaba Cloud's DashScope multimodal API. Control output dimensions, randomization seed, and optional prompt enhancement while managing costs based on your feature selection.
This skill harnesses Alibaba's Wan 2.7 video editing model to transform video appearance through style transfer (clay, anime, etc.) or content-aware edits guided by text prompts and optional reference images. It handles async task creation, polling, and media validation across multiple aspect ratios and resolutions.
Create images from text descriptions or edit existing ones using Wan and Qwen Image models. Supports style transfer, subject consistency across multiple reference images, text rendering in images, and interleaved text-image output for tutorials and guides. Choose from multiple models optimized for different tasks—from fast drafts to high-resolution 4K generation.
Create images from text descriptions or edit existing ones with Wan and Qwen Image models. This skill handles text-to-image generation, style transfer, subject consistency across reference images, and interleaved text-image output for tutorials and guides.
More skills aliyun-solution-article-illustrator (MIT) · Dashscope (AGPL-3.0) · aliyun-wan-i2v (MIT) · aliyun-happyhorse-r2v (MIT) · aliyun-modelstudio-entry (MIT) · aliyun-modelstudio-entry-test (MIT)