This is a submission for the DEV's Worldwide Show and Tell Challenge Presented by Mux
What I Built
AdForge AI is an enterprise visual production platform that transforms brand guidelines and campaign briefs into production-ready marketing assets using an automated multi-agent AI pipeline.
Key Capabilities:
My Pitch Video
Demo
🔗 Live Demo: https://ad-forge-ai.vercel.app
🔗 Backend API: https://adforge-ai.onrender.com
🔗 GitHub: https://github.com/omkardongre/AdForge-AI
No login required - fully accessible for testing.
The Story Behind It
As a developer working with marketing teams, I watched them spend weeks creating campaign visuals - coordinating between designers, waiting for revisions, and losing brand consistency across platforms. It's slow, expensive, and broken.
Most AI tools just generate random outputs. Marketing teams need deterministic, controllable, and reproducible visual generation. That's why I built AdForge AI.
What Makes It Special
1. Multi-Agent Pipeline
Instead of a single AI call, AdForge uses specialized agents working together:
2. JSON-Native Visual Controls
Unlike traditional AI tools that regenerate everything from scratch, AdForge gives you direct control over generation parameters:
3. Deterministic Reproducibility
Every generated image has a reproducibility seed. Same seed + same JSON = identical output. Enterprises can recreate approved assets months later with pixel-perfect accuracy.
4. Three Generation Modes
Generate: Text-to-image with structured prompts
Refine: Natural language modifications ("make lighting warmer") that update only specific parameters
Inspire: Upload reference images - AI extracts visual DNA and generates new assets in that style
5. AI-Powered Campaign Analysis
Select any two assets, click Compare - Gemini AI analyzes both with full campaign context and provides:
Technical Highlights
Backend (Python/FastAPI)
Frontend (React/Vite/TypeScript)
Key Features Implemented
What I Learned
What's Next
More...
What I Built
AdForge AI is an enterprise visual production platform that transforms brand guidelines and campaign briefs into production-ready marketing assets using an automated multi-agent AI pipeline.
Key Capabilities:
- 🎨 AI-powered brand DNA extraction from minimal input
- 🚀 Automated multi-agent pipeline for asset generation
- 🎛️ JSON-native visual controls (camera, lighting, composition)
- 🔄 Natural language refinement without full regeneration
- 🛡️ Deterministic reproducibility with seeds
- 📤 Multi-destination export (PDF, Slack, HDR)
My Pitch Video
Demo
🔗 Live Demo: https://ad-forge-ai.vercel.app
🔗 Backend API: https://adforge-ai.onrender.com
🔗 GitHub: https://github.com/omkardongre/AdForge-AI
No login required - fully accessible for testing.
The Story Behind It
As a developer working with marketing teams, I watched them spend weeks creating campaign visuals - coordinating between designers, waiting for revisions, and losing brand consistency across platforms. It's slow, expensive, and broken.
Most AI tools just generate random outputs. Marketing teams need deterministic, controllable, and reproducible visual generation. That's why I built AdForge AI.
What Makes It Special
1. Multi-Agent Pipeline
Instead of a single AI call, AdForge uses specialized agents working together:
- Brand DNA Extractor: Analyzes minimal input to create complete brand guidelines
- Scene Composer: Creates visual concepts from campaign briefs
- JSON Generator: Builds structured prompts with camera/lighting/composition parameters
- Variation Generator: Creates multiple versions with parameter variations
- Quality Assurance: Validates brand compliance
2. JSON-Native Visual Controls
Unlike traditional AI tools that regenerate everything from scratch, AdForge gives you direct control over generation parameters:
- Camera angle (eye-level, low, high, bird's eye)
- Lighting setup (studio soft, dramatic, golden hour, natural)
- Light direction, saturation, contrast
- All mapped to structured JSON sent to the generation API
3. Deterministic Reproducibility
Every generated image has a reproducibility seed. Same seed + same JSON = identical output. Enterprises can recreate approved assets months later with pixel-perfect accuracy.
4. Three Generation Modes
Generate: Text-to-image with structured prompts
Refine: Natural language modifications ("make lighting warmer") that update only specific parameters
Inspire: Upload reference images - AI extracts visual DNA and generates new assets in that style
5. AI-Powered Campaign Analysis
Select any two assets, click Compare - Gemini AI analyzes both with full campaign context and provides:
- Brand alignment assessment
- Campaign fit analysis
- Data-driven recommendation
Technical Highlights
Backend (Python/FastAPI)
- Multi-agent architecture with async/await
- Structured image generation via Bria API
- Vision AI integration using Google Gemini
- SQLite database with async support
Frontend (React/Vite/TypeScript)
- 4-step Brand Wizard with color pickers
- Campaign creation with multi-platform selection
- Refine Modal, Visual Controls, Inspire Modal
- AI Compare page
- Export Panel with PDF/Slack/HDR options
Key Features Implemented
- 12 UI Pages/Modals: Dashboard, Brands (list/detail/wizard), Campaigns (list/detail/create), Gallery, Export, Settings, Compare, plus 4 modals (Refine, Inspire, Visual Controls, Reproducibility Proof)
- Multi-Platform Generation: Automatically generates assets at correct dimensions (Instagram 1080×1080, LinkedIn 1200×627, Facebook 1200×630)
- Export Capabilities: PDF storyboard generation, Slack notifications, HDR formats (TIFF 300 DPI, PNG, JPEG)
What I Learned
- Determinism is critical for enterprise AI: Random outputs don't work in professional workflows. Reproducible generation with seeds is essential.
- Multi-agent systems work: Breaking complex creative workflows into specialized agents produces better results than monolithic AI calls.
- Vision AI enables new workflows: Gemini's image analysis unlocks reference-based generation and intelligent asset comparison.
What's Next
- Real-time collaboration with live preview
- A/B test analytics on generated variations
- Digital Asset Management (DAM) integration
- Batch processing for large-scale campaigns
- Enhanced semantic search using vector embeddings
More...