ussoewwin

ComfyUI-QwenImageLoraLoader. LoRA Loader & Diffsynth ControlNet Loader for Nunchaku Qwen Image & Nunchaku Z-Image Turbo

ComfyUI-DistorchMemoryManager. ComfyUI-VRAM-Manager is an independent memory management custom node for ComfyUI. Provides Distorch memory management functionality for efficient GPU/CPU memory handling. Supports purging of SeedVR2, Qwen3-VL, and Nunchaku models (FLUX/Z-Image/Qwen-Image). Includes Model Patch Memory Cleaner.

ComfyUI-NunchakuFluxLoraStacker. Nunchaku FLUX LoRA Stacker with dynamic UI control

ComfyUI-nunchaku-unofficial-loader. HSWQ fp8e4m3 Loader, Upscaler, detailer, however, Those nodes are also compatible with HSWQ, as well as the more common FP8E4M3 models.

Stable-Diffusion-WebUI-Forge-Nunchaku. Fixed Forge to run Nunchaku with LoRA Loader and ControlNet.

Hybrid-Sensitivity-Weighted-Quantization. HSWQ is a novel FP8 E4M3 quantization method that combines sensitivity analysis and importance-weighted histogram optimization, achieving superior quality compared to naive uniform quantization while maintaining standard loader compatibility.

comfyui-sdnq-splited. Nodes for loading and running SDNQ quantized models in ComfyUI

ADetailer_without_mediapipe. ADetailer with Python 3.13 support using InsightFace instead of MediaPipe