Kreative Core | Vision

AI-powered visual search that turns hours of footage scrubbing into seconds of natural language queries. "Find person smiling" - done.

Coming to Adobe Exchange

Features That Feel Like Magic

πŸ”

Semantic Search

Search with natural language: "beach sunset", "person running", "product close-up". Vision understands context, not just keywords.

πŸ‘₯

Face Recognition

Automatically cluster faces into "Person 1", "Person 2". Rename once, and Vision updates all clips featuring that person.

πŸ“

Location Detection

Visual landmark recognition identifies locations. Tag once, search forever. "Show me all Bosphorus Bridge shots".

🎬

Shot Classification

Automatically categorizes shots: Wide, Medium, Close-Up, Steadycam, Handheld. Perfect for finding coverage.

⚑

The Lifesaver

Search results auto-generate a new sequence with In/Out points set. One click from search to stringout.

πŸ”’

100% Offline

All AI runs on your machine. No cloud uploads, no credits, no internet required. Your NDA-protected footage stays private.

How It Works

1

Analyze Footage

Select clip, sequence, or entire project. Vision analyzes with CLIP AI and InsightFace models - running locally on your GPU.

2

Search Naturally

Type what you're looking for: "happy crowd", "interior office", "sunset timelapse". Vision searches semantically, not just tags.

3

Review & Refine

Click any result to preview in Source Monitor. Double-click to load with In/Out points. Refine face/location tags as you work.

4

Generate Sequence

Hit "Create Sequence" (The Lifesaver). Vision generates a stringout with all search results, perfectly timed. Edit from there.

Powered by State-of-the-Art AI

We leverage the same models used by OpenAI, Google, and Meta - optimized for local deployment. No compromises on accuracy, no cloud dependency.

OpenAI CLIP InsightFace ONNX Runtime GPU Accelerated Node.js Backend