n8n workflow for automated ComfyUI video generation using Flux and WAN 2.2

ComfyUI custom nodes for Dots TTS text-to-speech generation, voice cloning, and Whisper transcription with support for 24 officially benchmarked languages. Includes auto-downloading FP32/BF16 model…

Mantice — Procedural ambient/sacred drone generator with FM synthesis, granular clouds, spatial panning, and real-time browser UI. The breath behind the drone.

ComfyUI-AI-Photography-Toolkit

Automated setup scripts for ComfyUI with Flux and WAN 2.2 models on vast.ai

A variety of custom ComfyUI nodes and workflows

Some music tools in ComfyUI

opencode-browser is a browser automation plugin for OpenCode with live visual feedback and persistent sessions.

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

simple concept map diagram editor

SaaS-ready boilerplate. BetterAuth + multi-tenant + Resend + R2 already wired (Stripe on the roadmap). Bun, Hono, React 19, TanStack, Drizzle, Postgres. Clean Architecture + pragmatic DDD. Fourteen…

LLM inference in C/C++

Run bash actions in Saltcorn

an engine sound generator written in JavaScript using the Web Audio API

Bridging Godot and Blender

This is a fork of the awesome idb library, which adds the ability to sync an IndexedDB database with a remote REST API.

[CVPR 2026 Highlight] MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator

Bootstrap 5 layout with LLM-generated CSS overlay

[CVPR 2026 Highlight] GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering

Secure, self-hosted HLS streaming with token-based access written in Python.

Secure document & video sharing with analytics

Code repo for EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation

Perfect Green Screen Keys

ComfyUI-CorridorKey is a ComfyUI custom node package that exposes a native CorridorKey inference node for four-pass CorridorKey processing inside ComfyUI.

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Hypernetworks that update LLMs to remember factual information

Generative Motion Latent Flow Matching for Audio-driven Talking Portrait