FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
Qwen3.5-4B 3D Coder and GLB 3D Coder: Make 3D Scenes and Godot Game Assets Locally From a Prompt
Qwen-Image-Edit 2511 in ComfyUI: Normal and Lightning 4-Step Setup (2026)
Qwen-Image 2.1 GGUF in ComfyUI: Run Normal and Turbo on 8 GB and 12 GB GPUs (2026)
NVFP4 vs MXFP4 in llama.cpp: Which FP4 GGUF to Use on RTX 50, RTX 40 and Mac (2026)
Plenio 1.5 in ComfyUI: Free Local AI Song Generator That Sings Your Own Lyrics
Idol Turbo in ComfyUI: Image to 3D Gaussian Splat in 5 Steps
Krea 3 Explained: Multi-Image Editing, Pricing, Benchmarks and the ComfyUI Node
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
Qwen3.5-4B 3D Coder and GLB 3D Coder: Make 3D Scenes and Godot Game Assets Locally From a Prompt
Two Apache 2.0 Qwen3.5-4B fine-tunes write Three.js 3D scenes and exportable GLB game assets from a text prompt. Files, VRAM, Ollama, llama.cpp and LM Studio setup, the exact…
The reading list
Latest stories
MiniMax H3 Out of Memory in ComfyUI: 16 GB GPU Fixes That Work
Fix MiniMax H3 out of memory in ComfyUI on 16 GB GPUs: tested settings for model load, Qwen text encoder, sampler and…
Local Background Removal: Best Practices with U2NETP on CPU
A tested local U2NETP CPU workflow with an original teapot fixture, transparent PNG checks, real edge analysis, and reusable scripts. Includes the…
Add Sound Effects and a Music Climax to a Short Without Re-encoding the Video
Build a licensed sound-effects library and music reveal with FFmpeg and Python while preserving video. Includes tested scripts, four CC0 samples and…
Best MiniMax H3 Reference-to-Video Workflow for ComfyUI (Consistent Characters, 16 GB, Free JSON)
My MiniMax H3 reference-to-video ComfyUI workflow for consistent characters on 16 GB: ref2va, 6-step Turbo, RIFE 72 fps + 1080p finish. Free…
Best MiniMax H3 Image-to-Video Workflow for ComfyUI (First/Last Frame, 16 GB, Free JSON)
The MiniMax H3 image-to-video and first/last-frame ComfyUI workflow I run on a 16 GB RTX 5080: 6-step Turbo, synced audio, free JSON.
Best MiniMax H3 Text-to-Video Workflow for ComfyUI (16 GB VRAM, Free JSON)
MiniMax H3 T2V on 16 GB: every file (qwen3vl_4b_int4_convrot, mmh3-4b-ClipProj-v3.1-mlp) with size and folder, and which pack has MiniMaxH3TurboSampler.
ComfyUI Pixal3D Workflow: Image to 3D with a Real Example
Free ComfyUI Pixal3D + TRELLIS.2 workflow: trellis_2_int8_convrot (5.25 GB), dino_v3_L_naf_fp32 and every model file with folder and download link.
Voicebox Tutorial: Free Local AI Voice Generation on Windows
Set up Voicebox on Windows, choose the right local text-to-speech engine, create a voiceover, and explore authorized voice cloning, expressive delivery, and…
MiniMax H3 ComfyUI reference to image: Consistent Character Workflow (Free JSON)
Turn MiniMax H3 ref2va into a still-image workflow with length 5 and ImageFromBatch. Includes tested settings, honest limitations, and a free API-format…
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.