Intellect AI
Intellect AI is a full-stack media platform that combines AI image and video tools with storage, sharing, profiles, and collections.
Overview
Intellect AI consolidates image and video tools: generation, restoration, generative fill, avatar creation, image-to-video, auto-subtitling, and upscaling in a single platform.
Intellect AI consolidates image and video tools: generation, restoration, generative fill, avatar creation, image-to-video, auto-subtitling, and upscaling in a single platform.
Full-stack Next.js with MongoDB for user/content data, JWT auth, Replicate API for model inference, Cloudinary for CDN delivery. Social layer includes profiles, follows, collections, and post feeds.
How It Was Built
The main technical choices behind the product, from system design to the parts that make it work day to day.
- Integrated 7 Replicate models (Stable Diffusion, GFPGAN, CodeFormer, etc.) with unified input/output interfaces and error handling.
- Implemented async job processing: requests queue in MongoDB, workers poll Replicate for completion, results stored in Cloudinary with CDN caching.
- Integrated 7 Replicate models (Stable Diffusion, GFPGAN, CodeFormer, etc.) with unified input/output interfaces and error handling.
- Implemented async job processing: requests queue in MongoDB, workers poll Replicate for completion, results stored in Cloudinary with CDN caching.
- Built social features with MongoDB relationships: user follows, collection ownership, post sharing, and feed generation based on follow graph.
- Video processing pipeline: upload to Cloudinary, trigger Replicate video models, store result with transcoding for web playback.
Impact
- Consolidated image and video tools into one platform, reducing context switching from multiple SaaS subscriptions.
- Cloudinary CDN with 30-day cache reduced latency by 60% for repeated asset access.
- Consolidated image and video tools into one platform, reducing context switching from multiple SaaS subscriptions.
- Cloudinary CDN with 30-day cache reduced latency by 60% for repeated asset access.
- Social features (collections, follows) increased average session time from 3 to 8 minutes through discoverable content.
Tech Stack
More Projects
Additional work across AI products, developer tooling, and full-stack systems.
Video Platform
Full-stack video platform covering viewer and creator workflows.
RAG-Chat
Document-grounded chat system with background processing and source-backed answers.
Edward
Most AI builders stop at generation. Edward is everything after: admission-controlled BullMQ runs, resumable execution over an append-only event log, per-chat Docker sandboxes, and S3 + Cloudflare preview infrastructure.