qwen-imageGenerate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.
Install via ClawdBot CLI:
clawdbot install Robin797860/qwen-imageGenerate high-quality images using Alibaba Cloud's Qwen Image API (通义万相).
Generate an image (returns URL only):
uv run {baseDir}/scripts/generate_image.py --prompt "一副典雅庄重的对联悬挂于厅堂之中" --size "1664*928" --api-key sk-xxx
Generate and save locally:
uv run {baseDir}/scripts/generate_image.py --prompt "一副典雅庄重的对联悬挂于厅堂之中" --size "1664*928" --api-key sk-xxx
With custom model:
Support qwen-image-max-2025-12-30 qwen-image-plus-2026-01-09 qwen-image-plus
uv run {baseDir}/scripts/generate_image.py --prompt "a beautiful sunset over mountains" --model qwen-image-plus-2026-01-09 --api-key sk-xxx
You can obtain the API key and run the image generation command in the following order.
models.providers.bailian.apiKey in ~/.openclaw/openclaw.jsonskills."qwen-image".apiKey in ~/.openclaw/openclaw.jsonDASHSCOPE_API_KEY environment variableSizes:
1664*928 (default) - 16:9 landscape1024*1024 - Square format720*1280 - 9:16 portrait1280*720 - 16:9 landscape (smaller)Additional flags:
--negative-prompt "unwanted elements" - Specify what to avoid--no-prompt-extend - Disable automatic prompt enhancement--watermark - Add watermark to generated image--no-verify-ssl - Disable SSL certificate verification (use when behind corporate proxy)MEDIA_URL:MEDIA_URL: https://...)!Generated ImageMEDIA_URL: in the output - extract this URL and display it using markdown image syntax: !generated imageMEDIA_URL: in the script output and render the image for the userGenerated Mar 1, 2026
Marketing teams can generate high-quality visual content for social media, ads, and websites using text prompts, especially effective for campaigns targeting Chinese-speaking audiences with culturally relevant imagery. It streamlines creative workflows by producing images on-demand without manual design work.
Online retailers can create product mockups, lifestyle images, or promotional graphics based on descriptions, helping showcase items in various settings without costly photoshoots. Supports multiple aspect ratios like square or landscape for different platform requirements.
Educators and content creators can generate illustrations, diagrams, or scene depictions for textbooks, presentations, or online courses, enhancing learning materials with custom visuals tailored to specific topics or languages.
Artists, writers, and game developers can use this skill to brainstorm concepts, create storyboard images, or generate assets for projects, leveraging its support for detailed prompts and negative prompts to refine outputs.
Businesses can produce branded imagery for reports, internal communications, or client presentations, using custom sizes and models to maintain consistency and professionalism across visual assets.
Offer the image generation capability as a paid API service to developers or businesses, charging per request or through subscription tiers based on usage volume and features like custom models or sizes. Revenue comes from transaction fees or monthly plans.
Integrate this skill into a larger platform where users pay for access to AI-generated images, with premium features such as high-resolution outputs, watermark removal, or batch processing. Monetize through freemium models or one-time purchases.
License the technology to other companies for embedding into their own products, such as design tools or marketing software, generating revenue through licensing fees or revenue-sharing agreements based on client usage.
💬 Integration Tip
Ensure API keys are securely managed via environment variables or configuration files, and test the script output parsing for reliable URL extraction before deployment.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.