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
Tessera in ComfyUI: Upscale MiniMax H3 Video to 4K and 8K (Install, Files, Settings and Real Render Times)
Tessera upscales MiniMax H3 clips to 2K, 4K or 8K tile by tile without out-of-memory errors. Install steps, model files and folders,…
Qwen-Image 2.1 Lightning v2 RL: 4-Step Setup, Files, VRAM and ComfyUI Status (2026)
Qwen-Image 2.1 Lightning v2 RL makes images in 4 steps. Here are the files, a working Diffusers script, VRAM needs, the ComfyUI…
Gemini Omni 1.2 Flash: 15-Second AI Video at $0.07/s (Pricing, How to Use, Limits)
Google’s Gemini Omni 1.2 Flash makes 3-15 second videos with audio for $0.07 per second at 720p, 30% less than 1.1. Every…
ERNIE 5.5 Flash Base: Baidu’s 280B Open-Weights Base Model (Specs, Benchmarks, Hardware, Licence)
Baidu released ERNIE 5.5 Flash Base on 5 November 2026: a 280B MoE base model with 14B active, FP8 and BF16 weights,…
CUDA Out of Memory Fix (2026): torch.OutOfMemoryError in PyTorch, ComfyUI, Ollama and LoRA Training
“CUDA out of memory. Tried to allocate…” explained in plain English, with fixes that actually work in PyTorch scripts, ComfyUI, Ollama, llama.cpp,…
Windows 11 AI Features in Paint, Photos, Notepad and Snipping Tool (2026): What Works on Your PC and How to Use It
A practical guide to the AI tools built into Windows 11’s own apps: Paint Cocreator, Image Creator, generative erase, sticker generator and…
Gemini in Gmail Guide (November 2026): Help Me Write, AI Overviews, AI Inbox, Gmail Live and How to Turn It Off
What Gemini can do in Gmail right now: free Help Me Write, Suggested Replies and thread summaries, plus Proofread, inbox Q&A, AI…
Best Laptop for Local AI and LLMs (November 2026): MacBook Pro M5 Max vs RTX 5090 Laptop vs Ryzen AI Max+ 395
Which laptop actually runs local LLMs and image models well in 2026? Memory size and bandwidth explained, picks by budget (MacBook Pro…
Google Photos AI Features (2026 Guide): Help Me Edit, Ask Photos, Nano Banana Restyle, Photo to Video and Wardrobe
Every AI feature in Google Photos as of November 2026: edit by asking with your voice, Nano Banana restyles, Ask Photos search,…
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.