FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
How to Move From ChatGPT to Claude: Import Memory, Chats and Custom GPTs (2026)
How to Use Cursor AI: Beginner’s Guide to Cursor 3, Agent, Rules and Pricing (2026)
How to Run Ollama in Docker With GPU (NVIDIA, AMD) + Open WebUI Compose (2026)
How to Do Image to Video in ComfyUI: Wan 2.2, MiniMax H3 and LTX-2.5 (2026)
Qwen3.5-4B 3D Coder and GLB 3D Coder: Make 3D Scenes and Godot Game Assets Locally From a Prompt
Qwen-Image-Edit 2511 in ComfyUI: Normal and Lightning 4-Step Setup (2026)
Qwen-Image 2.1 GGUF in ComfyUI: Run Normal and Turbo on 8 GB and 12 GB GPUs (2026)
The world of AI. Explained.
A clearer view of artificial intelligence.
Hands-on guides for ComfyUI workflows, AI video, image editing and running models locally — tested, with every file path and setting written down.
- Lead story
How to Move From ChatGPT to Claude: Import Memory, Chats and Custom GPTs (2026)
Switch from ChatGPT to Claude without starting over: export your ChatGPT data, import memory into Claude, move custom instructions, rebuild GPTs as Projects and cancel safely.
The reading list
Latest stories
How to Use Cursor AI: Beginner’s Guide to Cursor 3, Agent, Rules and Pricing (2026)
Learn Cursor AI step by step: install, Tab, Ctrl+K, Agent and Plan modes, rules and AGENTS.md, MCP, cloud agents, the new X…
How to Run Ollama in Docker With GPU (NVIDIA, AMD) + Open WebUI Compose (2026)
Run Ollama in Docker step by step: CPU, NVIDIA GPU with the Container Toolkit, AMD ROCm and Vulkan, Windows WSL2, a Docker…
How to Do Image to Video in ComfyUI: Wan 2.2, MiniMax H3 and LTX-2.5 (2026)
Turn any photo into a video in ComfyUI: pick the right model for your GPU, every file and folder for Wan 2.2,…
Qwen3.5-4B 3D Coder and GLB 3D Coder: Make 3D Scenes and Godot Game Assets Locally From a Prompt
Two Apache 2.0 Qwen3.5-4B fine-tunes write Three.js 3D scenes and exportable GLB game assets from a text prompt. Files, VRAM, Ollama, llama.cpp…
Google’s Smartwatch AI Spots High Blood Pressure Without a Cuff: Nature Study, Numbers and What You Can Use Today
Google Research’s smartwatch AI caught 65.8% of hypertension cases vs 55.3% for an office check in a 196-person Nature study. How it…
Qwen-Image-Edit 2511 in ComfyUI: Normal and Lightning 4-Step Setup (2026)
Set up Qwen-Image-Edit 2511 in ComfyUI with the normal 40-step model and the Lightning 4-step LoRA: files, folders, nodes, settings, GGUF and…
Qwen-Image 2.1 GGUF in ComfyUI: Run Normal and Turbo on 8 GB and 12 GB GPUs (2026)
Run Qwen-Image 2.1 and its 8-step Turbo mode on 8 GB and 12 GB GPUs in ComfyUI: the GGUF node that works,…
NVFP4 vs MXFP4 in llama.cpp: Which FP4 GGUF to Use on RTX 50, RTX 40 and Mac (2026)
NVFP4 and MXFP4 explained: specs, which GPUs run each, llama.cpp builds, benchmarks vs Q4_K_M, how to run and convert, Ollama and LM…
Plenio 1.5 in ComfyUI: Free Local AI Song Generator That Sings Your Own Lyrics
Plenio 1.5 turns ComfyUI into a local song studio with YuE2 or MiniMax Music 3. Install, every model file and folder, VRAM,…
How every guide is built
Copy the command. Drop the file. Run the graph.
Each ComfyUI guide follows the same shape, so you can skim straight to what you need.
- Step 1InstallNode packs and exact download commands.
- Step 2Files & pathsEvery model folder in one table.
- Step 3SettingsStarting values that work on consumer GPUs.
- Step 4TroubleshootKnown errors and the fix for each.
New models land fast. Get the working setup first.
Follow FreakyJolly in any feed reader to get every new guide the moment it goes live.