Qwen-Image Tool
Generate and edit images using Alibaba Qwen-Image models
pinned to #d0b9194updated 2 weeks ago
Ask your AI client: “install plugins/qwen-image-tool”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install plugins/qwen-image-toolmetahub onboarded this repo on the author's behalf.
If you own github.com/agentscope-ai/QwenPaw on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
21,840
Last commit
2 weeks ago
Latest release
published
- #agent
- #agent-harness
- #agentscope
- #harness-engineering
- #llm-tools
- #llms
- #loop-engineering
- #skills
- #super-agent
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.d0b9194· 2 weeks ago
Kind-specific
31Plugin: manifest fields complete
Plugin: bundled artifacts presentwarn
Couldn't find a skills/ subdir or an MCP server config inside the plugin
A plugin is most useful when it bundles ≥ 1 skill or an MCP server.
Plugin: bundle shape
empty bundle
Plugin: manifest location
manifest at plugin.json
Release history
1- releasecurrentd0b9194warn2 weeks ago
Contents
Generate and edit images using Alibaba Cloud's Qwen-Image models via DashScope SDK.
Tools
generate_image_qwen - 文生图
Generate high-quality images from text prompts. Supports complex text rendering, multi-style artwork, and fine-grained detail control.
Parameters:
prompt(required): Image description (Chinese/English)size: Image size in "width*height" format (default:"2048*2048")n: Number of images to generate, 1–6 (default: 1)negative_prompt: What to exclude from the imageprompt_extend: Enable prompt auto-optimization (default: true)
Available models:
| Model | Description |
|---|---|
qwen-image-2.0-pro ⭐ | Best text rendering, semantic adherence |
qwen-image-2.0 | Balanced speed and quality |
qwen-image-max | Highest realism |
qwen-image-plus | Diverse art styles |
Recommended sizes for qwen-image-2.0 series:
2048*2048(1:1, default)2688*1536(16:9)1536*2688(9:16)2368*1728(4:3)
edit_image_qwen - 图像编辑
Edit images or fuse multiple images using text instructions.
Parameters:
prompt(required): Edit instruction. Use "图一"/"图二" (or "image 1"/"image 2") to refer to reference imagesreference_images(required): List of image URLs or local file paths (at least 1)size: Output image size (leave empty to auto-detect from input)n: Number of output images (default: 1)negative_prompt: What to excludeprompt_extend: Enable prompt auto-optimization (default: true)
Supported models:
| Model | Best for |
|---|---|
qwen-image-2.0-pro ⭐ | General editing, text rendering |
qwen-image-2.0 | Fast editing |
qwen-image-edit-max | Industrial design, geometry |
qwen-image-edit-plus | Multi-image output |
qwen-image-edit | Basic single-image editing |
Image input support:
- HTTP/HTTPS URLs (used directly)
- Local file paths:
.png,.jpg,.jpeg,.webp(auto-converted to base64)
Example prompts:
- Single image edit:
"将图片风格改为水墨画风格" - Multi-image fusion:
"以图一的城市照片为底图,将图二中的卡通角色放置在建筑物周围" - Text rendering:
"在右下角添加印章,内容为'2025'"
Configuration
Each tool has independent configuration fields:
| Field | Description | Default |
|---|---|---|
api_key | DashScope API key (required) | — |
endpoint | Regional API endpoint | https://dashscope.aliyuncs.com/api/v1 |
timeout | Request timeout in seconds | 120 |
model | Model name for image generation/editing | qwen-image-2.0-pro |
Endpoints:
- Beijing:
https://dashscope.aliyuncs.com/api/v1 - Singapore:
https://dashscope-intl.aliyuncs.com/api/v1
Note: API key and endpoint must be from the same region.
Get your API key at: https://bailian.console.aliyun.com/
Output
Generated images are saved to {DEFAULT_MEDIA_DIR}/qwen_image/ as PNG files. Image URLs from the API are valid for 24 hours.
Reviews
No reviews yet. Be the first.
Related
cc10x
The Loop Engine — harness and loop engineering plugin for Claude Code. Router-kernel orchestration, workflow artifacts, sub-agent delegation, hook enforcement, Test Honesty Gates, fresh-context verification, and memory that persists. 73% leaner than v11, zero quality regression.
explanatory-output-style
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
serena
Semantic code analysis MCP server providing intelligent code understanding, refactoring suggestions, and codebase navigation through language server protocol integration.
mh install plugins/qwen-image-tool