# Send Generate product photos for ecommerce to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "productai-skill", "name": "Generate product photos for ecommerce", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Shapes/productai-skill", "canonicalUrl": "https://clawhub.ai/Shapes/productai-skill", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/productai-skill", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=productai-skill", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CHANGELOG.md", "QUICKSTART.md", "SETUP-GUIDE.md", "README.md", "config.example.json", "package.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "productai-skill", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T17:11:13.667Z", "expiresAt": "2026-05-08T17:11:13.667Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=productai-skill", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=productai-skill", "contentDisposition": "attachment; filename=\"productai-skill-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "productai-skill" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/productai-skill" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/productai-skill", "downloadUrl": "https://openagent3.xyz/downloads/productai-skill", "agentUrl": "https://openagent3.xyz/skills/productai-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/productai-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/productai-skill/agent.md" } } ``` ## Documentation ### ProductAI Integration ProductAI.photo is an AI-powered service that generates professional product photos from existing images. It enables e-commerce businesses, marketers, and designers to create studio-quality product photography without hiring photographers. ### Quick Start 1. Get Your API Key Visit ProductAI Studio → API Access → Copy your API key 2. Run Setup cd ~/.openclaw/workspace/productai scripts/setup.py # Paste your API key when prompted 3. Generate Images # Generate product photo with custom background scripts/generate_photo.py \\ --image https://example.com/product.jpg \\ --prompt "modern living room with natural lighting" \\ --output result.png # Use multiple reference images (nanobanana/seedream support 2 images) scripts/generate_photo.py \\ --image https://example.com/product1.jpg https://example.com/product2.jpg \\ --prompt "Put the first image on top of the second image" \\ --output result.png # High quality with Nano Banana Pro scripts/generate_photo.py \\ --image https://example.com/product.jpg \\ --prompt "white studio background" \\ --model nanobananapro \\ --output hq.png # Upscale an image (20 tokens) scripts/upscale_image.py \\ --image https://example.com/photo.jpg \\ --output upscaled.png ### Core Capabilities Photo Generation (/api/generate) Background replacement with AI-generated scenes Product placement in realistic environments Multi-image compositing (up to 2 reference images with certain models) Custom prompts for full creative control Image Upscaling (/api/upscale) Professional AI upscaling (Magnific Precision Upscale) Preserves image details without distortion 20 tokens per upscale Models Available gpt-low — GPT Low Quality (2 tokens) gpt-medium — GPT Medium Quality (3 tokens) gpt-high — GPT High Quality (8 tokens) kontext-pro — Kontext Pro (3 tokens) nanobanana — Nano Banana (3 tokens) — DEFAULT nanobananapro — Nano Banana Pro (8 tokens) seedream — Seedream (3 tokens) Multi-Image Support: nanobanana, nanobananapro, and seedream support up to 2 reference images for advanced compositing. ### API Setup Step 1: Get Your API Key Visit ProductAI Studio Navigate to API Access section Click Generate API Key or copy existing key Step 2: Run Setup Script cd ~/.openclaw/workspace/productai scripts/setup.py This will interactively create config.json with your credentials: { "api_key": "your-api-key-here", "api_endpoint": "https://api.productai.photo/v1", "default_model": "nanobanana", "default_resolution": "1024x1024", "plan": "standard" } The config file is automatically secured with 600 permissions. ### Installation The integration scripts require Python 3.7+ with these dependencies: pip install requests pillow All dependencies are handled automatically by the scripts. ### E-commerce Product Photos Generate clean product shots for online stores: scripts/generate_photo.py \\ --image https://example.com/raw-product.jpg \\ --prompt "white studio background with soft shadows" \\ --output store-listing.png ### Marketing Campaign Visuals Create lifestyle shots for advertising: scripts/generate_photo.py \\ --image https://example.com/bottle.jpg \\ --prompt "outdoor picnic scene with blanket and basket, golden hour lighting" \\ --output campaign-hero.png \\ --model kontext-pro ### Multi-Image Compositing Combine multiple products into one scene: scripts/generate_photo.py \\ --image https://example.com/product1.jpg https://example.com/product2.jpg \\ --prompt "Place the lipstick on top of the cosmetics box" \\ --model nanobanana \\ --output composite.png ### High-Quality Output Use Nano Banana Pro for premium results: scripts/generate_photo.py \\ --image https://example.com/product.jpg \\ --prompt "luxury marble countertop setting with morning light" \\ --model nanobananapro \\ --output premium.png ### Image Upscaling Upscale images for print or high-res displays: scripts/upscale_image.py \\ --image https://example.com/product.jpg \\ --output upscaled.png ### Async Workflow (No Wait) Start generation and check later: # Start job (prints job ID) scripts/generate_photo.py \\ --image https://example.com/product.jpg \\ --prompt "studio background" \\ --no-wait # Output: Job created: 12345 # Later, resume and download scripts/generate_photo.py \\ --job-id 12345 \\ --output result.png ### API Reference See API.md for complete endpoint documentation, request/response formats, and authentication details. ### Pricing & Token Costs ProductAI uses a token-based pricing system: OperationToken CostGPT Low Quality Generation2 tokensGPT Medium Quality Generation3 tokensGPT High Quality Generation8 tokensKontext Pro3 tokensNano Banana Pro8 tokensNano Banana3 tokensSeedream3 tokensMagnific Precision Upscale20 tokens Subscription Plans: Visit ProductAI.photo for current plans and token packages. Rate Limits: 15 requests per minute Daily limits based on subscription plan Note: Tokens are deducted when each operation starts (not on completion). ### Troubleshooting API Key Issues Verify config.json exists: cat ~/.openclaw/workspace/productai/config.json Check API key in ProductAI Studio → API Access Regenerate key if needed OUT_OF_TOKENS Error Check your token balance in ProductAI Studio Purchase more tokens or upgrade plan Remember: tokens are deducted when jobs start, not on completion Rate Limit (429) Maximum 15 requests per minute Wait before retrying Use --no-wait for batch jobs and check status later Job Failed (ERROR status) Check image URL is accessible and under 10MB Verify image format (PNG, JPG, or WebP only) Check prompt length and content Try a different model Multi-Image Not Working Only nanobanana, nanobananapro, and seedream support multiple images Maximum 2 reference images Use array format: --image url1 url2 ### Support Website: https://www.productai.photo Documentation: See references/API.md Contact: support@productai.photo (or team contact when available) ### Advanced Topics For detailed API specifications, authentication flows, webhook integration, and batch processing patterns, see API.md. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Shapes - Version: 1.0.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T17:11:13.667Z - Expires at: 2026-05-08T17:11:13.667Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/productai-skill) - [Send to Agent page](https://openagent3.xyz/skills/productai-skill/agent) - [JSON manifest](https://openagent3.xyz/skills/productai-skill/agent.json) - [Markdown brief](https://openagent3.xyz/skills/productai-skill/agent.md) - [Download page](https://openagent3.xyz/downloads/productai-skill)