G

generative-ai

Personal ComfyUI fork (upstream: github.com/comfyanonymous/ComfyUI, GPL-3.0) with a fully local Wan 2.2 + Z-Image Turbo image/video setup tuned for 8 GB VRAM on WSL2: setup scripts, a model downloader, and ready-to-load workflows.

Official UmeAiRT production workflow library. Offers 40+ highly optimized visual pipelines for FLUX, SDXL, LTXV, Qwen, and WAN architectures.

Official implementations of "Latent Diffusion Models for Attribute-Preserving Image Anonymization" and "Harnessing Foundation Models for Image Anonymization".

[2025] Autonomous Claude Code plugin with pattern learning and skill auto-selection. Features 27 specialized agents across 4 collaborative groups, quality control automation, and intelligent task execution without human approval at each step.