[Release] ComfyUI DiffAid Patches — inference-time adaptive interaction denoising for rectified text-to-image generation

I just released ComfyUI DiffAid Patches Also available via ComfyUI-Manager. This repo is based on ideas from: Binglei Li, Mengping Yang, Zhiyu Tan, Junping Zhang, Hao Li Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation arXi:2602.13585, 2026 The core idea in Diff-Aid is to improve text-image interaction during denoising in a targeted way, instead of relying on a single static conditioning strength everywhere.