Generative AI · Creative AI · production
AI Compare Hub
Unified multi-model generative media platform.
Production multimodal generation platform giving users unified access to a large ecosystem of image, video, and audio models—with side-by-side comparison from a single prompt.
Unified multimodal generation workspace
My role
Applied AI / Platform Engineering
- AI Architecture
- Backend Engineering
- Integration
- Productionization
Period / 2024–Present
Overview
Production multimodal generation platform giving users unified access to a large ecosystem of image, video, and audio models—with side-by-side comparison from a single prompt.
Problem
Teams evaluating generative media models face fragmented provider UIs, inconsistent parameters, and no reliable way to compare outputs under identical prompts.
System
A normalized multi-provider orchestration layer with asynchronous job execution, status tracking, and a shared generation history across staging and production.
System anatomy
Architecture
Multi-provider fan-out with async job orchestration.
- Model router
- Parallel provider execution
- Normalized result schema
- Generation history
Architecture
Prompt intake fans out through a model router into parallel provider executions, then converges through async orchestration into a normalized asset pipeline.
- Prompt → Model Router
- Model Router → Flux
- Model Router → Kling
- Model Router → Veo
- Model Router → OpenAI
- Flux → Async Orchestration
- Kling → Async Orchestration
- Veo → Async Orchestration
Engineering decisions
Asynchronous generation architecture
Multimodal jobs are long-running and provider-specific. Queue-based processing with webhook/polling status tracking keeps the API responsive while preserving model-specific parameters.
Normalized result pipeline
Providers return incompatible payloads. A normalization layer enables comparison UI, history, and asset handling without coupling the product to any single vendor.
Staging and production workflow parity
Generation history and parameter preservation across environments reduce regression risk when adding or updating models.
Reliability / production
- Queue-based processing
- Webhook and polling status tracking
- Retries on provider failures
- Cloud asset handling
- Model-specific parameter preservation
Stack
Outcomes
- Unified access across Flux, Kling, Veo, Seedream/Seedance, Runway, Luma, Ideogram, Stable Diffusion, MiniMax, and OpenAI.
- Side-by-side comparison of up to four models from one prompt.
- Async generation with queues, webhooks/polling, retries, and cloud asset handling across staging and production.
Links
Product visuals
