qwen-image-plus-sophnetGenerate images via Sophnet Qwen-Image-Plus and poll for task completion. Use when the user asks for Sophnet image generation, Qwen-Image-Plus, or requests an image from the Sophnet API.
Install via ClawdBot CLI:
clawdbot install DuffyCoder/qwen-image-plus-sophnetUse the Sophnet image generator API to create an image task, poll until it
finishes, then return the image URL.
Set the API key (preferred):
export SOPHNET_API_KEY="YOUR_API_KEY"Run the script with an absolute path (do NOT cd to the skill directory):
bash /home/shutongshan/.openclaw/workspace/skills/qwen-image-plus-sophnet/scripts/generate_image.sh --prompt "your prompt"--prompt (required): user prompt--negative-prompt (optional)--size (optional, default 1024*1024)--n (optional, default 1)--watermark (optional, default false)--prompt-extend (optional, default true)--api-key (optional, overrides SOPHNET_API_KEY)--poll-interval (optional, default 2)--max-wait (optional, default 300)The script prints:
TASK_ID=...STATUS=succeededIMAGE_URL=... (one or more lines)Use the IMAGE_URL value to respond to the user.
model=Qwen-Image-Plus and user promptSUCCEEDEDurl and return to the userPrompt:
A scenic mountain landscape in ink wash styleCommand:
bash /home/shutongshan/.openclaw/workspace/skills/qwen-image-plus-sophnet/scripts/generate_image.sh \
--prompt "A scenic mountain landscape in ink wash style" \
--negative-prompt "blurry, low quality" \
--size "1024*1024" \
--n 1 \
--watermark false \
--prompt-extend trueOutput:
TASK_ID=7BWFICt0zgLvuaTKg8ZoDg
STATUS=succeeded
IMAGE_URL=https://dashscope-result-wlcb-acdr-1.oss-cn-wulanchabu-acdr-1.aliyuncs.com/7d/d5/20260203/cfc32567/f0e3ac18-31f6-4a1a-b680-a71d3e6bcbe03032414431.png?Expires=1770714400&OSSAccessKeyId=LTAI5tKPD3TMqf2Lna1fASuh&Signature=fF12GZ7RgGsC7OpEkGCapkBUXws%3DError: No API key provided. -> set SOPHNET_API_KEY or pass --api-keySTATUS=failed -> check key permissions/quota or prompt parametersError: url not found in response -> inspect API response manuallyGenerated Mar 1, 2026
Artists and designers can generate custom images for projects like book covers, album art, or concept sketches. This skill enables rapid prototyping of visual ideas based on textual prompts, saving time in the creative workflow.
Marketing teams can produce unique images for social media posts, advertisements, or blog illustrations. By specifying styles like ink wash or adjusting parameters, it helps create branded visuals without extensive graphic design resources.
Educators and content creators can generate illustrative images for textbooks, presentations, or online courses. This supports visual learning by creating custom diagrams or scenes tailored to specific topics, such as historical landscapes.
E-commerce businesses can create product mockups or lifestyle images for catalogs and websites. It allows for generating images of items in various settings, enhancing online listings and reducing the need for physical photoshoots.
Game developers can quickly generate concept art or background images for video games. This skill aids in visualizing characters, environments, or items during early design phases, streamlining the asset production pipeline.
Offer tiered subscription plans for businesses to access the Sophnet API, providing different usage limits and features. This generates recurring revenue while catering to varying needs from small teams to large enterprises.
Sell credits that users purchase to generate images, with pricing based on image size or quantity. This model appeals to occasional users or those with fluctuating demands, ensuring they only pay for what they use.
Provide custom integration of the image generation skill into third-party platforms or applications for a fee. This includes technical support and branding options, targeting companies looking to enhance their own products with AI capabilities.
đŹ Integration Tip
Ensure the SOPHNET_API_KEY is set as an environment variable for security, and use the provided script with absolute paths to avoid directory issues.
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.
äœżçšć çœź image_generate.py èæŹçæćŸç, ćć€æž æ°ć ·äœç `prompt`ă
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.