FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
LongCat-2.5 Open Weights: Meituan’s 1.6T MIT Model, Benchmarks, API Price and Hardware
Claude Sheets, Whiteboards and Meetings: What They Do, Plans and How to Use Them (2026)
ComfyUI API Guide: Run Workflows From Python (Prompt, WebSocket, Images)
LM Studio Not Loading Models? How to Fix “Failed to Load Model” and Search Errors
ComfyUI Inpainting Not Working? Every Cause and Fix (SD, SDXL and Flux Fill)
Seedream 5.5 Guide: 100-Round Editing, Transparent PNGs, Pricing and How to Use It (2026)
Claude Fable 5.2 and Mythos 5.2: Price, Benchmarks, Plan Access and How to Use Them (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
LongCat-2.5 Open Weights: Meituan’s 1.6T MIT Model, Benchmarks, API Price and Hardware
Meituan released LongCat-2.5 weights under MIT on 9 Nov 2026: 1.6T MoE, ~48B active, vision and video. Specs, vendor benchmarks, $0.30/$1.20 API, Claude Code setup and self-hosting needs.
The reading list
Latest stories
Claude Code on the Web (2026): Setup, Cloud Environments, Teleport and Limits
How to use Claude Code on the web at claude.ai/code: connect GitHub, run parallel cloud tasks from your browser or phone, set…
How to Install Claude Code on Windows, Mac and Linux (2026): No Node.js Needed, Update and Fix Errors
Install Claude Code in one command on Windows, macOS, Linux or WSL, learn when you still need Node.js 22, how updates and…
Claude Code Pricing (November 2026): Pro vs Max vs Ultra vs API, and What You Really Pay
Every Claude Code price in one place: Pro $20, Max $100, Ultra $200, Team seats and API rates for Opus 5.5, Sonnet…
Unlimited OCR 2: Run Baidu’s 3B Long-PDF OCR Model Locally (VRAM, GGUF, SGLang, Benchmarks)
Baidu’s MIT-licensed Unlimited OCR 2 parses 100-300 page PDFs in one pass. Benchmarks, VRAM needs, and step-by-step local setup with transformers, SGLang…
GPT-6 Cyber: OpenAI’s First “Critical” Security Model (Benchmarks, Daybreak Access, What It Found)
OpenAI’s GPT-6 Cyber found 81 high-severity Firefox bugs and built 948 Linux kernel exploits. Every benchmark, the Critical rating, Daybreak Blue vs…
Open WebUI + Ollama Setup Guide (2026): Docker, Python, Connect Models and Fix Errors
Install Open WebUI with Docker or Python, connect it to Ollama, turn on document chat, web search and tools, and fix the…
ComfyUI Multi-GPU Guide (2026): Native CFG Split, ComfyUI-MultiGPU, Two Instances and Real Speed-Ups
How to use two or more GPUs in ComfyUI: the new native MultiGPU CFG Split node, ComfyUI-MultiGPU DisTorch2 for big models, one…
LM Studio MCP, Plugins and Agent Mode (2026): mcp.json Setup, Best Tool Models and Bionic Explained
How to add MCP servers to LM Studio with copy-paste mcp.json examples, which models call tools reliably, what plugins do, and what…
Claude Code Router Guide (2026): Use Claude Code With DeepSeek, OpenRouter, Gemini and Ollama
How to install and set up Claude Code Router v3 to run Claude Code on DeepSeek, OpenRouter, Gemini or local Ollama models,…
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.