LOGO HOOKE - IngĂ©nierie et maĂźtrise d'Ɠuvre

How to Install Qwen-Image-Edit_ComfyUI on Copilot+ PC with Native FP4 Offline Setup

Docker offers the quickest path to setting up this model locally.

Follow the step-by-step instructions below.

Hands-free setup: the system self-downloads the heavy model files.

The smart installation system will instantly find the perfect configuration for your specific hardware.

🔐 Hash sum: 7d48d1f3b0ec31a7144e5a4f5f80efa4 | 📅 Last update: 2026-06-27



  • Processor: 6-core 3.5 GHz minimum required
  • RAM: fast 5600MHz+ required to avoid memory bottlenecks
  • Disk Space:70 GB free space for full FP16 weights storage
  • Graphics: TensorRT-LLM / vLLM inference engine compatible chip

The Qwen-Image-Edit_ComfyUI model leverages a state‑of‑the‑art diffusion framework to deliver precise image editing capabilities directly within the ComfyUI environment. It supports high‑resolution outputs and enables operations such as object removal, inpainting, and style transfer with minimal latency. A conditional guidance mechanism ensures semantic consistency across edited regions, preserving the original context while applying modifications. The architecture employs a dual‑encoder design that combines a vision encoder for detailed feature extraction and a text encoder for contextual understanding. Users can integrate the model into existing node‑based workflows without extensive retraining, making advanced editing accessible to both developers and artists. Below is a quick comparison of key performance metrics that highlight its efficiency and quality relative to similar tools.

Metric Value
Resolution 2048×2048
Inference Time ~120ms
PSNR 38.5 dB