FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
llama-server Guide (2026): Run llama.cpp as a Local OpenAI-Compatible API
Ollama Context Length: How to Check and Increase num_ctx (2026)
ComfyUI Black Image Fix: Every Cause and the Exact Fix (2026)
How to Cancel Gemini Subscription (Google AI Pro): Web, Android, iPhone and Refunds (2026)
Text Generation WebUI Guide (2026): Install oobabooga TextGen, Models and API
InvokeAI Guide (2026): Install Invoke, VRAM Needs, Models and the Canvas
Aider Guide (2026): AI Pair Programming in Your Terminal With Claude, GPT or Ollama
SillyTavern Guide (2026): Install, Connect Ollama or KoboldCpp and Create Characters
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

llama-server Guide (2026): Run llama.cpp as a Local OpenAI-Compatible API
Install and run llama.cpp’s llama-server on Windows, Mac and Linux: key flags, –fit memory, GPU layers, the OpenAI-compatible API, router mode, Docker and fixes.
The reading list
Latest stories

MiniMax H3 ComfyUI reference to image: Consistent Character Workflow (Free JSON)
Turn MiniMax H3 ref2va into a still-image workflow with length 5 and ImageFromBatch. Includes tested settings, honest limitations, and a free API-format…

Best Local AI Video Models in 2026: Text-to-Video, Image-to-Video and Reference-to-Video
An evidence-linked practical countdown of local video model families, including text, image and reference workflows, hardware trade-offs and licensing cautions.
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.