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
AMD GPU for AI in 2026: ROCm on Windows and Linux, Ollama, LM Studio and ComfyUI Setup (RX 9070 XT, 7900 XTX, R9700)
Can you use an AMD Radeon GPU for local AI in 2026? Which cards ROCm 7.2.1 supports on Windows and Linux, how…
How to Run ComfyUI on RunPod (2026): Official Template, Network Volume, Model Folders and Costs
Step-by-step RunPod ComfyUI setup for November 2026: pick the right GPU, create a network volume ($0.07/GB/month), deploy the official ComfyUI or Blackwell…
iOS 27.2 Siri Update: Memory of Past Chats, 5 New Languages, Excluded Apps and How to Use Them
iOS 27.2 is the biggest Siri AI update since launch: Siri now remembers past conversations, reads more personal context, speaks French, Japanese,…
RTX 5090 vs RTX 5080 for AI (November 2026): VRAM, Speed, Real Prices and Is Two 5080s Better?
RTX 5090 or RTX 5080 for local LLMs, ComfyUI image and video generation? Specs, memory bandwidth, what fits in 32 GB vs…
Google Colab Free GPU Limits (November 2026): T4 Hours, Compute Units, Pro vs Pro+ and the Best Free Alternatives
How much free GPU time Google Colab really gives you in 2026, what compute units buy on T4, L4, A100, H100 and…
How to Check GPU VRAM and Usage on Windows, Linux and Mac (2026): Task Manager, nvidia-smi and AI Tools
Find out how much VRAM your graphics card has and how much is in use right now, on Windows, Linux and macOS.…
Circle to Search Guide (2026): How to Use It, Scam Check, Translate, Try On and Fix It Not Working
Everything Circle to Search can do in November 2026: multi-object search with Gemini 3, scam check for texts, scroll and translate, Find…
How to Turn Off Meta AI on WhatsApp, Instagram and Facebook (November 2026): Every Setting That Works
Meta AI can’t be uninstalled, but you can mute it, block it from chats with Advanced Chat Privacy, delete its stored data…
50 Facebook Page Ideas, Names and Reels Ideas (2026) + a Free Claude Skill That Plans Your First 30 Days
50 Facebook page ideas, page name formulas, 60 post and Reel ideas, Meta’s 2025 originality rules, current monetisation programs, and a free…
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.