One AI Brain, Many Faces and Voices
Our presenter, her news-anchor self, and every character voice in our videos share infrastructure: one local LLM, swappable voices, swappable faces. The architecture that makes characters cheap.
Guides
Step-by-step guides to building your own fully-local AI companion, voice, brain, avatar and all.
Run a Private AI Image Generator on Your Own GPU (ComfyUI Starter)
Free, unlimited, private image generation at home, the ComfyUI setup we generate hundreds of images a day on, explained for a first-timer.
The Everyday Local-LLM Toolkit: PDFs, Summaries, Study Guides, and More
One local model, six daily superpowers, chat with your documents, digest long videos, summarize voice memos, build study guides, prep interviews, draft anything, all offline and private.
Train a Character LoRA: Make Your AI Character Look the Same in Every Image
The complete recipe behind our presenter’s locked identity. Dataset rules, local AI Toolkit vs cloud Civitai training, the strength dials that matter, and the four rules we paid to learn.
Use Your Home AI from Anywhere (Without Exposing It to the Internet)
Our whole stack, image generation, the LLM brain, everything, is reachable from a phone on the other side of the country, with zero open ports. Tailscale setup in fifteen minutes.
Word-Perfect Subtitles for Any Video, Free, with Local Whisper
Every caption on our channel, including karaoke-timed lyrics, comes from faster-whisper running locally. Setup, word-level timestamps, and the two tricks that fix the words it always gets wrong.
Build a Local Talking AI Avatar: The Complete Architecture
The full blueprint for a local AI companion, speech in, talking face out. Every stage can run on your own hardware; this is the map, and every stage links to a hands-on guide.
Give Your AI a Custom Voice, Cloned Locally, Running on CPU
Design a voice once, clone it forever: how we gave Aillex a warm, consistent voice with NeuTTS Air, zero GPU cost, zero per-word fees, fully offline.
Real-Time Lip-Sync with MuseTalk on an RTX 5090 (Blackwell Survival Guide)
MuseTalk generates lip-synced video faster than real time on a 5090, but getting it to BUILD on Blackwell is dependency hell. Here’s the exact recipe that works.
Run a 26B AI Brain Locally, Warm, Multimodal, and With Memory
The brain is the biggest VRAM line-item and the biggest latency trap. How we run a 26B multimodal LLM via Ollama with sub-second warm responses, persistent memory, and free screen vision.