FreakyJolly: AI video, ComfyUI workflows and local AI guides
How to Run MiniCPM-V 4.7 Locally: Ollama, llama.cpp and 16 GB GPU Settings
Run MiniCPM-V 4.7 (35B-A3B MoE and 1B) locally with Ollama, llama.cpp or vLLM: which GGUF quant fits your GPU, 16 GB tips, and OpenBMB’s recommended settings.
Latest stories
Train a MOSS-Image LoRA With KohakuMoss: 6 GB VRAM Guide and ComfyUI Export
How to train MOSS-Image LoRAs and LyCORIS adapters with KohakuMoss: VRAM tiers from 6 GB, install, dataset prep, config wizard, speed by GPU and exporting to ComfyUI.
Bria Fibo 2.0 in ComfyUI: Generate and Edit Images With the 8B Open Model
How to run Bria Fibo 2.0 in ComfyUI: Dev vs 4-step Edit Turbo, files and folders, settings, VGL JSON prompts, instruction, mask and multi-reference edits, and the CC…
Best MiniMax H3 Video Section Editor in ComfyUI: Re-Generate Part of a Video with Frame Infill (Free JSON)
Re-generate only part of a video with MiniMax H3 Frame Infill in ComfyUI, keep the original audio and use an optional mask. Free workflow JSON.
Mistral Large 4 Open Weights: Release Date, Specs and Hardware to Run It
Everything confirmed about Mistral Large 4 open weights: the October 31 release ETA, 1.05T MoE specs, benchmarks, pricing, license question and the hardware needed to run it locally.
Fish Audio Drama 3 Locally in ComfyUI: Run the 35B TTS on an 8 GB GPU
Run Fish Audio Drama 3, the 35B multi-speaker TTS model, locally in ComfyUI on an 8 GB GPU: RAM needs, which file to pick, install steps, script tags…
MOSS-Image in ComfyUI: Files, Settings, Layout JSON and 4-Step LoRAs
How to run OpenMOSS’s 5B MOSS-Image model in ComfyUI: which files go where, the right settings, JSON layout control with bounding boxes, and the 4-step and 8-step LoRAs.