**The 100% Offline, Serverless Metadata Viewer for AI Images.**

Robust Speech Recognition via Large-Scale Weak Supervision

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

A custom ComfyUI node for models/clips fp8 converter

A repo to quantize diffusion models directly in ComfyUI

Windows graphical interface for yt-dlp, designed as a simple YouTube downloader

Official SeedVR2 Video Upscaler for ComfyUI