AdForge AI

AI-powered enterprise campaign platform with 6-agent pipeline, multi-platform asset generation, brand consistency scoring, and production-ready exports for marketing teams.

Comment

Project Story

Inspiration

The advertising industry faces a $13.5B+ content production problem. Brands now produce 2,000+ visual assets per year, but existing AI tools lack fine-grained control, require regenerating everything for small changes, and produce inconsistent outputs. We built AdForge AI to solve this by enabling precise, reproducible, enterprise-grade visual production with a multi-agent AI pipeline.

What it does

AdForge AI is a complete enterprise campaign visual production platform that transforms brand guidelines and campaign briefs into production-ready visual assets at scale.

Core Features

  • Dashboard: Real-time stats (Brands, Campaigns, Assets counts) with Quick Actions to create brands, campaigns, or view assets
  • 4-Step Brand Wizard: Guided workflow (Brand Info → Colors → Visual Style → Review) with AI-powered DNA extraction. Enter minimal info and our LLM expands it into complete brand guidelines
  • AI Color Palette Expansion: Pick 3 brand colors and AI expands into a complete palette with primary, secondary, background, and text colors
  • Campaign Creation: Select brand, set name, objective (awareness/conversion), key message, call-to-action, and target platforms (Instagram Feed/Story, Facebook Feed, LinkedIn Post, Google Display)
  • Multi-Platform Generation: Automatically generates assets at correct dimensions for each platform (e.g., 1080×1080 for Instagram, 1200×627 for LinkedIn)
  • Asset Gallery: Browse all generated assets with quality scores (100% = brand compliant) and platform dimensions
  • Generation Settings: Configure number of scenes and variations per scene in Settings page

Image Generation Features

1. Generate Mode

  • Text-to-image generation with structured JSON prompts containing:
    • CameraSettings: angle (eye_level, low, high), FOV, focal_length, distance
    • LightingSettings: setup (studio_soft, dramatic, golden_hour, natural), direction, intensity, color_temperature
    • ColorSettings: brand color palette, temperature, saturation, contrast
    • CompositionSettings: rule_of_thirds, depth_of_field, framing
  • 5 camera presets and 5 lighting presets automatically applied based on scene analysis

2. Refine Mode

  • Iterative asset modification via UI modal
  • Enter instructions like "make the lighting warmer" or "change camera angle to low"
  • Updates only specified attributes while preserving everything else

3. Inspire Mode (with Vision AI)

  • Upload reference image OR enter creative direction OR both
  • Gemini Vision AI analyzes reference images to extract visual characteristics
  • Generates new images inspired by reference style

Visual Controls

  • Direct parameter editing with visual sliders for camera angle, lighting setup, light direction, saturation, and contrast
  • Advanced Options: Enter reproducibility seed to regenerate identical images

AI Compare (Campaign-Aware Asset Comparison)

  • Select any 2 campaign assets for side-by-side comparison
  • Gemini AI analyzes both images with campaign context and provides recommendations

Determinism Proof (Reproducibility)

  • Every asset has a Shield icon showing seed value used for generation
  • Copy seed → paste in Visual Controls → Regenerate = identical image

Export Panel

  • PDF Storyboard: Professional PDF with all campaign assets
  • Slack Notifications: Team alerts when campaigns are ready
  • Print-Ready Formats: TIFF (300 DPI), PNG, JPEG for print campaigns

How we built it

Backend (Python/FastAPI):

  • Multi-agent pipeline with 6 specialized AI agents:
    1. Brand DNA Extractor: Extracts complete brand identity from minimal input
    2. Scene Composer: Creates visual scene descriptions from campaign briefs
    3. JSON Generator: Builds structured prompts with camera, lighting, color, composition parameters
    4. Variation Generator: Creates multiple versions with parameter variations
    5. Quality Assurance: Validates brand compliance (shows quality % in Gallery)
    6. Format Exporter: Multi-format delivery (PDF, Slack, HDR)
  • Image generation via Bria API with structured JSON prompts
  • Vision AI integration using Google Gemini for Inspire mode and AI Compare
  • LLM orchestration using Google Gemini for prompt translation
  • SQLite database with async support

Frontend (React/Vite/TailwindCSS):

  • Dashboard with stats and Quick Actions
  • 4-step Brand Setup Wizard with color pickers
  • Campaign creation with brand selection and platform checkboxes
  • Refine Modal, Visual Controls, and Inspire Modal
  • AI Compare page with campaign-aware analysis
  • ConsistencyBadge for reproducibility proof
  • Asset Gallery with quality scores
  • Export Panel with PDF, Slack, HDR options
  • Settings page for generation defaults

Challenges we ran into

  1. JSON Schema Design: Designing the precise JSON structure for structured image generation required careful experimentation
  2. Multi-Platform Aspect Ratios: Generating consistent brand visuals across 3+ platform dimensions while maintaining composition quality. Solved with platform-specific camera presets
  3. Vision-Based Inspire Mode: Integrated Gemini Vision AI to analyze reference images and build structured prompts from the analysis
  4. Reproducibility: Implemented seed-based deterministic generation with UI for copying and reusing seeds

Accomplishments that we're proud of

  • All 3 Generation Modes: Generate, Refine, and Inspire fully integrated
  • Structured JSON Control: Visual sliders for camera angle, lighting, saturation, contrast—directly mapped to generation parameters
  • Vision-Powered Inspire Mode: Gemini analyzes reference images to build generation prompts
  • Campaign-Aware AI Compare: Gemini compares assets with brand/campaign context
  • Reproducibility Proof: Every asset has verifiable seed for exact recreation
  • 6-Agent Architecture: Automated pipeline from brief to production assets
  • 12 UI Pages/Modals: Dashboard, Brands (list/detail/wizard), Campaigns (list/detail/create), Gallery, Export, Settings, Compare, Refine Modal, Inspire Modal, Visual Controls, Determinism Proof
  • Deployed and Working: Live on Vercel (frontend) and Render (backend)

What we learned

  • Structured JSON-based image generation is a game-changer for enterprise workflows—deterministic control is essential for brand consistency
  • Multi-agent systems are highly effective for complex, multi-step creative workflows
  • Vision AI integration enables true "Inspire mode" by extracting visual DNA from reference images
  • Real-world production tools need export capabilities (PDF, Slack, print formats) to be truly useful

What's next for AdForge AI

  • Real-time Collaboration: Multi-user editing with live preview
  • A/B Test Insights: Analytics on generated variations
  • DAM Integration: Connect with existing Digital Asset Management systems
  • Batch Processing: Generate hundreds of variations in parallel for large campaigns
  • Enhanced Semantic Search: Natural language asset search using vector embeddings

Try It Out

Built With

  • bria-api
  • fastapi
  • google-gemini
  • pydantic
  • python
  • react
  • render
  • reportlab
  • shadcn-ui
  • slack-sdk
  • sqlite
  • tailwindcss
  • vite
Share this project:

Updates

Submission history