~/ai-muninn
search
⌘K
❯
esc
Loading…
blog
model anatomy
github
中
~ / blog
/
tag / local-ai
❯
grep -r "#local-ai" ~/blog
6 matches
date
read
title
2026-10-09
17m
One face, eight outfits: keeping a character consistent with Qwen-Image 2.1 on an RTX 5090
#qwen-image-2.1
#image-editing
#character-consistency
#reference-image
2026-10-08
12m
FastH3 on an RTX 5090: a 5-second talking clip in under a minute, 2.9x faster than MiniMax-H3
#fasth3
#minimax-h3
#video-generation
#lip-sync
2026-10-08
13m
Kandinsky 6.0 Pro on an RTX 5090: lip-synced English dialogue works, Chinese isn't quite there yet
#kandinsky-6.0
#video-generation
#lip-sync
#text-to-video
2026-04-17
9m
[LLM 101 #6] Why Run AI on Your Own Computer? It's Not a Cheaper ChatGPT — It's a Different Tool
#llm
#local-ai
#ollama
#beginner
2026-04-07
8m
[LLM 101 #1] Ollama vs vLLM: Two Ways to Run AI on Your Own Computer
#ollama
#vllm
#llm
#local-ai
2026-03-18
5m
[AI Agent] openclaw: When the Agent Calls for Help
#ai-agent
#openclaw
#codex
#llm
← back to all posts