Ad-Ready: AI Advertising Image Generator

Generate professional advertising images from product URLs using a 4-phase AI pipeline on ComfyDeploy.

⚠️ CRITICAL: Required Inputs Checklist

Before running ANY ad generation, the agent MUST ensure ALL of these are provided:

🚨 NEVER Skip These Steps:

1. 1. Product image — Download the main product photo from the product URL. The scraper is fragile; always provide a product image explicitly.
2. Brand logo — Download the logo from the brand's official website or search for "{brand name} logo" online. Must be a clean logo image (PNG preferred).
3. Brand profile — If the brand doesn't exist in the catalog, run brand-analyzer skill FIRST to generate one. Never submit with "No Brand" when a brand is known.
4. Reference image — Search for an existing ad or visual with a style that matches what we're generating. Can be from previously generated images, the brand's campaigns, or found online. This dramatically improves output quality.

Auto-Preparation Workflow

When the user asks to generate an ad, follow this workflow:

CODEBLOCK0

Usage

Full command (recommended):

Auto-fetch mode (downloads product image and logo automatically):

The --auto-fetch flag will:

• - Download the main product image from the product URL
• Search and download the brand logo
• Both get uploaded to ComfyDeploy automatically

API Details

Endpoint: https://api.comfydeploy.com/api/run/deployment/queue
Deployment ID: INLINECODE11

ComfyDeploy Input Variables

These are the exact variable names the ComfyDeploy deployment expects:

4-Phase Pipeline (How It Works Internally)

Phase 1: Product Scraping

• - Gemini Flash visits the product URL
• Extracts: title, description, features, price, images
• ⚠️ Image scraping is the most fragile part — always provide product images manually

Phase 2: Campaign Brief Generation (CRITICAL)

• - Uses Brand Identity JSON + Product Data → 10-point brief
• Everything downstream depends on brief quality
• Brief covers: strategic objective, central message, visual tone, product role, photographer, art direction, environment, textures, signature

Phase 3: Blueprint Generation

• - Master Prompt (per funnel stage) + Brief + Product JSON + Keyword Bank + Format
• Gemini Flash generates complete Blueprint JSON
• Covers: scene, production, graphic design, lighting, composition, materials, CTA

Phase 4: Image Generation

• - Nano Banana Pro (Imagen 3.0) generates the final image
• Uses Blueprint JSON + all reference images (product, talent, logo, style ref)

Supporting Reference Nodes

• - pose_ref → enforce a specific pose (replicated exactly)
• INLINECODE21 → replicate photographic style (⚠️ can be too literal, being optimized)
• INLINECODE22 → replicate location and color palette

Brand Profiles

Existing catalog (70+ brands):

Creating new brand profiles:

This generates a full Brand Identity JSON and saves it to the catalog automatically.

Prompt Profiles (Funnel Stages)

How to choose:

• - Most ads → Conversion (purchase intent)
• New product launches → Awareness
• Retargeting → Consideration or Evaluation
• Existing customers → Retention or Loyalty

Aspect Ratios

Model Catalog

Models for talent/face reference: INLINECODE37

Priority: User-provided model > Catalog selection > No model (product-only ad)

Known Limitations

1. 1. Product image scraping is fragile — always provide product images manually when possible
2. photostyleref can be too literal — the style reference may be replicated too closely
3. Some websites block scraping — Armani works well, others may return incorrect data
4. Auto 4-Format is alpha — bugs and edge cases exist
5. Gemini hallucinations — occasional issues in complex reasoning steps

Ad-Ready vs Morpheus

Source Repository

• - GitHub: https://github.com/PauldeLavallaz/ads_SV
• Local clone: ~/clawd/ad-ready/
• Patreon docs: https://www.patreon.com/posts/from-product-to-149933468

API Key

Uses ComfyDeploy API key. Set via COMFY_DEPLOY_API_KEY environment variable.