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
Viggle Remake in ComfyUI: Reshoot Any Video With MiniMax H3 (12-16 GB Setup Guide)
Use Viggle Remake’s Swap and Edit LoRAs for MiniMax H3 in ComfyUI: files, install commands, int8/GGUF picks for 12-24 GB GPUs, settings,…
NitroFusion2 in ComfyUI: 1-Step Z-Image-Turbo Files, Settings and Low-VRAM Quants
Run NitroFusion2, the 1-2 step Z-Image-Turbo distill, in ComfyUI: exact files and folders, 1-step and 2-step settings, int8/GGUF quants by VRAM, and…
Best Mixamo Alternatives in 2026: Auto Rig Characters With Fingers, Face and Hair
Mixamo still rigs humanoid bodies for free, but it stops there. The best Mixamo alternatives in 2026 for face expressions, hair bones,…
How to Make a 3D VTuber Model From One Image (Face Expressions, Hair Bones, No Modelling)
Turn one character drawing into a rigged 3D VTuber-style model with blink, smile and talk expressions and hair bones, without modelling or…
Nemotron 3.5 Transcribe: Run NVIDIA’s Open 40-Language Speech Model Locally (GGUF, VRAM, Setup)
NVIDIA’s open Nemotron 3.5 Transcribe turns up to an hour of audio into text in 40 languages with speakers, timestamps and translation.…
Image to 3D Online: Turn One Picture Into an Animated 3D Model (GLB, No GPU)
Turn one image into a textured GLB 3D model in your browser, then rig and animate it in the same run. Which…
Claude Personal Finance Guide: Link Your Bank, What Claude Sees, Privacy and Limits (Nov 2026)
Claude can now read your US bank accounts through Plaid. Who gets Personal Finance, step-by-step setup, what Claude can and cannot see,…
H3 Dials in ComfyUI: 14 KB Sliders for MiniMax H3 Motion and Mood (Setup Guide)
H3 Dials turns prompt pairs into 14 KB sliders for MiniMax H3 motion, mood and style. Every dial file, install folders, strengths,…
Ripple-65B Preview: Specs, Benchmarks, Price and How to Run It Locally
Ripple-65B Preview from Ricursive: a 65B dense Apache 2.0 coding model. Benchmarks, $0.20/$0.60 API price, GGUF sizes, llama.cpp, DGX Spark setup and…
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.