Generative AI

Wan 2.2 Image-to-Video on 8GB VRAM: Best ComfyUI Settings (10 Min)

Tested settings for Wan 2.2 image-to-video in ComfyUI on an 8GB GPU: Q8_0 model, 14 steps and --fast make a clean 5-second video in about 10 minutes. Workflow included.
Generative AI

Free VRAM Used by Ollama and AivisSpeech for Image Generation (8GB GPU)

Idle Ollama models and GPU text-to-speech quietly hold 4GB+ of VRAM. Unload Ollama with ollama stop and run AivisSpeech on the CPU; measured timings on an 8GB GPU.
Generative AI

Free Local AI Character Chat with Voice and Pictures on 8GB VRAM

Chat out loud with an AI character that also draws the scene, all local and free: Ollama, AivisSpeech and ComfyUI tied together by one PowerShell script, on 8GB VRAM.
Generative AI

Make a Talking AI VTuber from One Image, Locally on 8GB VRAM

Turn a single character image into a lip-syncing, expressive AI VTuber that answers by voice, all running locally: Mesh Avatar Studio, Ollama and AivisSpeech on 8GB VRAM.
Claude

Use Claude Max API Credits with the Agent SDK: A Claude Code-Like Chat

Max plan API credits don't work in interactive Claude Code, but they do with the Agent SDK and a Console API key. Here is my browser chat built on it, full code included.
Claude Code

Claude Code Approval Notifier: A Desktop Pet That Jumps to the Tab

A free Windows desktop pet that tells you when Claude Code is waiting for approval and jumps to that Windows Terminal or VS Code tab on click. No hooks needed.
Claude Code

Local AI Dashboard for Windows: Start/Stop Ollama & ComfyUI, See VRAM

A free Node.js dashboard that shows which local AI services (Ollama, ComfyUI, TTS) are running and what uses your VRAM, with start/stop buttons. No npm install.
スポンサーリンク