FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
Best Kromoss ComfyUI Workflow for 16 GB GPUs: INT8 + 8-Step DMD2 LoRA Setup
Best Way to Run Recursive Flint Locally on a 16 GB GPU (NVFP4 + MoE Offload Guide)
Best MiniMax H3 GGUF Workflow in ComfyUI (Q4_K_M + Q2_K, First/Last Frame, 16 GB, Free JSON)
ChatGPT Chrome Extension Guide: Chat vs Work Mode, Setup, Permissions and Safety
Kimi K3.1 Pro: Specs, Benchmarks, Open Weights Date and Can You Run It Locally?
PHP2Shell WordPress Fix: Check and Patch the AI-Found PHP Flaw (CVE-2026-109618)
ComfyUI-RMBG 3.3: Canvas Studio, Video Background Removal and New Matting Models
MOSS-Image Edit LoRA in ComfyUI: Edit Photos With Text and Up to 4 Reference Images
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
Best Kromoss ComfyUI Workflow for 16 GB GPUs: INT8 + 8-Step DMD2 LoRA Setup
Set up Kromoss in ComfyUI on a 16 GB GPU: which INT8 files to grab, the 8-step DMD2 LoRA settings, 50-step mode, GGUF option and fixes for common…
The reading list
Latest stories
Best Way to Run Recursive Flint Locally on a 16 GB GPU (NVFP4 + MoE Offload Guide)
Run Recursive Flint locally on a 16 GB GPU: the best quant for RTX 50-series (NVFP4), llama.cpp –n-cpu-moe offload math, context settings…
Best MiniMax H3 GGUF Workflow in ComfyUI (Q4_K_M + Q2_K, First/Last Frame, 16 GB, Free JSON)
My MiniMax H3 GGUF workflow for ComfyUI: Q4_K_M FL2VA + Q2_K encoder on a 16 GB RTX 5080, exact settings, real speed…
ChatGPT Chrome Extension Guide: Chat vs Work Mode, Setup, Permissions and Safety
The ChatGPT Chrome extension now reads and controls your tabs. How to install and connect it, Chat vs Work mode, which site…
Kimi K3.1 Pro: Specs, Benchmarks, Open Weights Date and Can You Run It Locally?
Kimi K3.1 Pro is Moonshot’s 2.8T open-weight model that rivals Claude Opus 5.5. Specs, benchmarks, $2/$10 pricing, API example, the November open…
PHP2Shell WordPress Fix: Check and Patch the AI-Found PHP Flaw (CVE-2026-109618)
PHP2Shell (CVE-2026-109618, CVE-2026-109619) lets one request take over a PHP server. How to check your WordPress PHP version, the fixed versions, patch…
ComfyUI-RMBG 3.3: Canvas Studio, Video Background Removal and New Matting Models
ComfyUI-RMBG 3.3 adds a Canvas compositing node, VRMBG video background removal, FeyNoBg hair matting and box segmentation. Install steps, exact model folders,…
MOSS-Image Edit LoRA in ComfyUI: Edit Photos With Text and Up to 4 Reference Images
The MOSS-Image Edit LoRA adds instruction-based photo editing to MOSS-Image in ComfyUI: outfits, colours, lighting, seasons and style, with up to four…
Hy-Nomas in ComfyUI: Run Tencent’s Interactive World Model With WASD Controls
Hy-Nomas is Tencent Hunyuan’s open interactive world model: 720p, 24 fps video you steer turn by turn with text and camera moves.…
MiniMax H3 Extender in ComfyUI: Turn 1 Reference Image Into Multiple Connected Clips (Free Workflow)
Use the MiniMax H3 Extender node in ComfyUI to turn one or more reference images into several connected clips with the same…
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.