Skip to main content

SceneMakerAIAbout Architecture Install PoC Docs Blog Release Notes Open Source Ecosystem Contributions

한국어
English

All posts

2026

Launching a Tech Blog
Project Introduction and Qwen 3.6 Application in the Broadcasting Domain
Sharing My Experience with Optimizing "faster-whisper" for Korean Speech Recognition
Voice Analysis Process and Results
Building a RAG Pipeline
Designing a Langgraph-Based Broadcast Workflow
Explanation of the Short-Form Video Auto-Generation Pipeline_1
Explanation of the Short-Form Video Auto-Generation Pipeline_2
Implementation of the "View All" Service
09_Best Practices for Optimizing Basic Inference in vLLMs
09_An Explanation of Context-Based Ad Optimization Technology
DB Schema Release
10_Sharing SBSi Pilot Test Case Studies
10_Analysis of Broadcast AI Service Performance Benchmark Results
Comprehensive Guide to Contributing to Open Source
11_Writing Test Cases
11_Case Studies on the Use of Open-Weight AI Models in Broadcasting
12_Comprehensive Summary of Project Results
12_Report on Contributions to the Open Source Ecosystem
12_Sharing the Future Roadmap and Plans for Continued Contribution

jplee

The SceneMakerAI Team

Team Lead, SceneMakerAI Multimodal AI Pipeline

View all authors

This author has not written any posts yet.

Docs

Get Started
Architecture

Community

Hugging Face
LangChain

More

Blog
GitHub
Solbox

Copyright © 2026 SceneMakerAI · Solbox Inc. Built with Docusaurus.