The-frizzy1/Qwen-Image-Edit-2509-GGUF

Qwen Image & Edit 2509 GGUF — Beginner Friendly

By: The_frizzy1 Hardware target: 4 GB VRAM (Q4_K_S) / 12 GB VRAM (Q8) CivitAI: https://civitai.com/models/2229874/qwen-image-and-edit-2509-gguf-beginner-friendly YouTube: https://www.youtube.com/@the_frizzy1

🎥 Video Explainer: https://www.youtube.com/watch?v=NPni2ulov34

---

What This Is

Lightweight ComfyUI workflow for Qwen Image on low/mid-end hardware. GGUF-quantised + optional Lightning LoRAs. Supports image generation and editing.

---

Model Downloads

Source	Link
Qwen Image Edit 2509 GGUF	https://huggingface.co/QuantStack/Qwen-Image-Edit-2509-GGUF
Qwen Image GGUF	https://huggingface.co/QuantStack/Qwen-Image-GGUF

Lightning LoRAs (optional):

• 4-step: https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V2.0.safetensors
• 8-step: https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V2.0.safetensors

Text Encoder: https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors

VAE: https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors

---

File Placement

ComfyUI/models/
├── diffusion_models/   ← Qwen GGUF file
├── loras/              ← Lightning LoRAs
├── vae/                ← qwen_image_vae.safetensors
└── text_encoders/      ← qwen_2.5_vl_7b_fp8_scaled.safetensors

---

Required Custom Nodes

Node	Link
KJNodes	https://github.com/kijai/ComfyUI-KJNodes

---

Usage

• Generation mode: Connect EmptyLatent → K-Sampler
• Editing mode: Activate all nodes except unused image inputs, connect latent → K-Sampler

---

Changelog

Version	Notes
v1.0	Initial release