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
OpenRouter Guide (November 2026): Free Models, Rate Limits, 5.5% Fee, BYOK and How to Use It
OpenRouter explained for November 2026: one API key for 600+ models, the 5.5% credit fee, free tier limits (20 RPM, 50 or…
Is Gemini CLI Still Free? Gemini CLI vs Antigravity CLI in November 2026 (Limits, Install and Migration)
Google moved consumer Gemini CLI users to Antigravity CLI on June 18, 2026. Here is who can still use Gemini CLI, the…
Claude Skills Guide (2026): How to Create, Upload and Use SKILL.md in Claude.ai, Claude Code and the API
A practical guide to Claude Agent Skills in 2026: what they are, SKILL.md format and limits, how to upload a skill to…
Qwen Image Edit 2509 vs 2511 vs 2512 vs 2.1: Which Qwen Image Model to Use in ComfyUI (2026)
Qwen-Image-Edit 2509, Edit 2511, Qwen-Image 2512 and Qwen-Image 2.1 compared: what each one does, licences, file names, text encoders, VRAM, reference images,…
Claude Code Commands Cheat Sheet (November 2026): Slash Commands, Shortcuts, CLI Flags and Config Files
Every Claude Code command that matters in November 2026 (v2.1.30x): install, slash commands, keyboard shortcuts, CLI flags, permission modes, model aliases, effort…
What Is fal.ai? Pricing, GPU Rates and Models Explained After Its $16B Valuation (November 2026)
fal.ai just raised $1.3 billion at a $16 billion valuation. Here is what fal is, its per-image and per-second model prices, GPU…
44% of Famous LLM Findings Have Expired: Stanford’s Shelf-Life Study Explained (Hallucinated Citations, Lost in the Middle, Sycophancy)
Stanford retested 50 widely cited LLM claims on 20 models from July 2024 to September 2026. 44% expired, 34% weakened, only 22%…
Run GLM-4.7-Flash Locally (2026): Ollama, llama.cpp, VRAM Table and Is GLM-5.3-Flash Worth the Upgrade?
How to run Z.ai’s GLM-4.7-Flash (30B-A3B MoE) on 12 to 24 GB GPUs with Ollama, llama.cpp and LM Studio, the right GGUF…
GPT-6 Astra Designed a Hardware Device in Under a Week: What OpenAI Showed and What It Means for Makers
OpenAI says GPT-6 Astra designed the enclosure, PCB, firmware and interface of a Codex talk-to device in under a week. Here are…
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.