Peter Neill

Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5

Klein 9B LoRA Studio — train, profile, repair, and extract Flux 2 Klein 9B LoRAs

Improved ReferenceLatent for ComfyUI — per-image strength, timestep gating, MediaPipe auto-masks, 1-4 image inputs. Works with Flux, Klein, Lumina, Wan, Hunyuan, Qwen-Image.

One-click tidy-by-role for ComfyUI workflows. Loaders / encoders / samplers / decoders / outputs each get their own column or row, with optional colour-coded groups. Width-aware. Connections preserved.

Split FLUX.2 and LTX 2.3 across two GPUs (LAN or same-machine) — NVENC compresses activations live on the wire. Icarus (ComfyUI node) + Daedalus (back-half server).

Click-to-refine + smart inpaint sampler node for ComfyUI (FLUX 2 Klein). One node: generate, then click / paint / drag to refine, or do location-guided whole-image edits.

A ComfyUI custom node that collapses generate plus inpaint into one box. Click, paint, or drag on the node preview to refine regions of an image, tuned for FLUX 2 Klein.

A ComfyUI node pack that implements FreeLong (NeurIPS 2024) spectral blending for Wan 2.2 video generation

Advanced FLUX LoRA manipulation toolkit with GUI interface

Use the GPU's idle NVENC silicon to multiply the effective bandwidth of every PCIe wire on the board

ComfyUI node for WAN I2V control with built-in person/face mask generation using MediaPipe

Load a folder of images one at a time into ComfyUI — a fresh image on every Queue. Natural sort, filetype picker (png/jpg/webp/.../all), reverse, subfolders, Reset/Prev/Next.

Load images from your clipboard directly into ComfyUI. "It looks like you're trying to load an image. Would you like help with that?"

ComfyUI LoRA loader with bookmarks, trigger words, and fzf-style fuzzy search. Stop scrolling 1000-LoRA dropdowns.

ComfyUI mode that highlights every node by graph distance from the one you click — direct neighbours red, then orange / yellow / green / blue / violet. Focus slider darkens the further bands so you can dial in to one neighbourhood ring at a time.

No description.

Extract a LoRA from the difference between two MODEL objects in ComfyUI. Capture chained edits (LoRAs, layer scaling, merges, IP-Adapter, patches) as a single distributable .safetensors file.

Fetch images from 8 daily / random sources straight into ComfyUI: Bing Daily, NASA APOD, Wikimedia POTD, Unsplash, Pexels, Lorem Picsum, random Dog/Cat.

A persistent drop zone for loading ComfyUI workflows from images or .json — reliable alternative to built-in drag-and-drop, with crash-recovery snapshots, recents, favorites, paste and append.

ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.

A place where all wallpapers can be found .... magic!!!