Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Australian sovereign-LLM cooperative — building in the open; contact for collaboration"

Simple video crop and stitch nodes

Multimodal prompt generator nodes for ComfyUI, designed to generate prompts for QwenImageEdit and Wan2.2. Supports local LLM / local GGUF models (Qwen2.5-VL, Qwen3-VL, Qwen3.5 and Qwen3.6) and Qwen…

ComfyUI nodes to save/load latents of wan video

ComfyUI nodes for MOVA (OpenMOSS) synchronized video+audio generation

An Video-to-Video (V2V) workflow adapted from LTX-2_ICLoRA_Distilled, integrated with Qwen image editing, featuring toggle switches for control options.

VFX & Video Utilities for ComfyUI

Video Analysis, Scene Capture and Prompt Generation AIO

ComfyUI, a self-developed collection of custom nodes for video processing, covers editing, splicing, transcoding, and transitions, catering to practical workflows.

Build visual workflows by chaining blocks together — prompt generation, ComfyUI workflows, video upscaling, and more — all running on RunPod serverless GPUs

Nodes I vibecode as I need them or ideas come to me, plus adaptations of abandoned/unsupported nodes. Covers video workflows, image I/O, and utilities; built for WanVideo, AnimateDiff, RIFE, and Flux.

ComfyUi workflow for video face restoration

video face liquefaction

ComfyUI-SeedVR2_VideoUpscaler

MCP server for ComfyUI - Enables AI assistants to generate images, video, audio, and 3D

AI background replacement workflow for video using ComfyUI. Supports full or selective BG replacement with camera-aware consistency via Uni3C. Designed for previs, fast-turn shots, and client-appro…

All-in-one ComfyUI workflow for pro-level results. Output: IMG (done) / VIDEO (in queue) / AUDIO (done) / 3D (in queue). Designed for quality, flexibility, and creative freedom.

Intelligent FFMPEG agent node for ComfyUI - transforms natural language video editing prompts into automated video transformations

This repository provides ComfyUI custom nodes to run WAN Video-As-Prompt (VAP).

A custom node for ComfyUI that allows users to overlay text on images/Videos with support for custom fonts, effects and style.

ComfyUI nodes for QwenVL models. Image caption, OCR, object boxes, and video summary. Works with Qwen2.5-VL and Qwen3-VL. 4-bit and 8-bit support.

A streamlined toolkit for creating cinematic multi-shot long videos from sequential keyframes and prompts.

Custom nodes for ComfyUI in order to expose AI workflows to external applications (particularly image, video and audio editors) so workflows can be integrated as plugins

Node-based video editing template

Crop and stich nodes for smooth bounding box video masking in ComfyUI.