Learn by Building
Each tutorial walks you through a real task from start to finish. Pick a track below and follow along — no prior AI experience required for the beginner track.
Track 1: Get Started
No terminal, no config files, no prior experience needed. Install Thumper-Run, pick an app, and see results in minutes.
First Image
Generate a 1024×1024 AI image with ComfyUI and SDXL
Prerequisites: Thumper-Run installed, 6+ GB VRAM recommended
Start Tutorial →First Chatbot
Chat with a local LLM using Open WebUI and Ollama
Prerequisites: Thumper-Run installed
Start Tutorial →First Music Track
Generate a 30-second music track with ACE-Step
Prerequisites: Thumper-Run installed, 8+ GB VRAM recommended
Start Tutorial →First Video
Generate a short AI video clip with LTX-Video
Prerequisites: Thumper-Run installed, 10+ GB VRAM
Start Tutorial →First Agent Task
Use the AI assistant to find, install, and launch an app
Prerequisites: Thumper-Run installed
Start Tutorial →Track 2: Build
Ready to ship your own apps? Learn how to write manifests that package AI tools for the catalog, with GPU patches, model dependencies, and install scripts.
App Manifest
Write a .thumper.yaml to package an AI app
Prerequisites: Completed a beginner tutorial, text editor
Start Tutorial →Model Pack
Create .model.yaml + .pack.yaml to bundle models
Prerequisites: Completed App Manifest tutorial
Start Tutorial →Custom ComfyUI Node
Build and package a custom ComfyUI node from scratch
Prerequisites: Python, completed First Image tutorial
Start Tutorial →Train Your First LoRA
Fine-tune an image model on your art style with Kohya SS
Prerequisites: 12+ GB VRAM, 15-50 training images
Start Tutorial →Fine-Tune a Chatbot
Train a domain-specific LLM with QLoRA using LLaMA-Factory
Prerequisites: 12+ GB VRAM, 100+ training examples in JSON
Start Tutorial →Vibe Coding
Generate and edit code, workflows, and configs with the agent
Prerequisites: Completed First Agent Task, one app installed
Start Tutorial →