FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
Meta Muse Spaces Guide: Build Custom Mini Apps by Describing Them (Setup, Ideas, Privacy)
Underdog Woof: Run the 32 MB Text-to-Speech Model Locally (Specs, Setup, Licence)
Photoshop AI Assisted Editor (2026): How to Turn It On, Every Tool, Models, Layers and Credits
Gemini in Google Sheets Guide (2026): Build Sheets, Fill With Gemini, =AI() Formulas and Limits
Intel Arc GPU for Local AI (2026): B580, B60, B70 with Ollama, LM Studio, llama.cpp and ComfyUI
RTX 5070 Ti for AI (2026): What It Runs, Speeds, Price Spike and Best Settings
Claude Plays EVE Online: Anthropic’s Project EVE Trading and Saboteur Results Explained
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
Meta Muse Spaces Guide: Build Custom Mini Apps by Describing Them (Setup, Ideas, Privacy)
Meta Muse Spaces let you build trackers, planners and games by describing them. How to create, pin and schedule Spaces, connect Gmail or Notion for live updates, 12…
The reading list
Latest stories
Underdog Woof: Run the 32 MB Text-to-Speech Model Locally (Specs, Setup, Licence)
Underdog Woof is a 32 MB English text-to-speech model that runs on one CPU thread with no GPU. Specs, vendor benchmarks, setup…
Photoshop AI Assisted Editor (2026): How to Turn It On, Every Tool, Models, Layers and Credits
Photoshop’s AI Assisted Editor (beta) explained: how to turn it on, every tool (Prompt, Markup, Fill, Remove, Expand, Upscale), which models you…
Gemini in Google Sheets Guide (2026): Build Sheets, Fill With Gemini, =AI() Formulas and Limits
How to use Gemini in Google Sheets in 2026: build whole spreadsheets from a prompt, Fill with Gemini (3,000 cells with per-cell…
Copilot in Microsoft Teams Guide (2026): Meetings, Recap, Facilitator, Meeting AI Toggle and How to Turn It Off
How to use Copilot in Microsoft Teams in 2026: meetings (during and after vs only during), the new Meeting AI toggle, Facilitator…
Intel Arc GPU for Local AI (2026): B580, B60, B70 with Ollama, LM Studio, llama.cpp and ComfyUI
Is Intel Arc good for AI in 2026? Every Arc card from B570 to the 32 GB Pro B70 with prices, what…
RTX 5070 Ti for AI (2026): What It Runs, Speeds, Price Spike and Best Settings
Is the RTX 5070 Ti good for AI? Specs, November 2026 prices ($749 MSRP vs $1,230-$1,400 now), which LLMs and ComfyUI models…
Claude Plays EVE Online: Anthropic’s Project EVE Trading and Saboteur Results Explained
Anthropic’s Project EVE put Claude in EVE Online and EVE Frontier: Fable 5 grew trading capital 43% per window, fleets built their…
Ling-3.2-flash: Ant’s Free 560B Multimodal Model (Specs, Benchmarks, API, Claude Code)
Ling-3.2-flash from Ant Ling: 560B/25B native multimodal MoE with 1M context, free API for two weeks. Specs, vendor benchmarks vs Opus 5,…
Codex vs Claude Code (November 2026): Pricing, Limits and Benchmarks
OpenAI Codex vs Claude Code compared: plans, the October 29 Codex limit changes, models, CLI and cloud, AGENTS.md vs CLAUDE.md, benchmarks 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.