Qwen Image Edit - Fast 4 Step ComfyUI Workflow & One Click Windows Installer

Run the Qwen Image Edit model with the fast 4-Step Lightning LoRA for High Quality generations in less than a minute and 40 seconds locally.
Run the Qwen Image Edit model with the fast 4-Step Lightning LoRA for High Quality generations in less than a minute and 40 seconds locally. Qwen Image Edit is a cutting-edge AI image editing model built on the robust 20B Qwen-Image foundation, supporting highly accurate semantic and appearance edits—including object manipulation and precise text rendering. The 4-Step Lightning LoRA workflow accelerates results without sacrificing quality, making it ideal for smooth, creative edits even on low VRAM GPUs. With the custom ComfyUI workflow and a one-click Windows installer, setup becomes seamless—so users can focus on instantly generating high-resolution images with advanced control and easy configuration.
 
Preloaded Models within the Installer (Low VRAM)
Qwen_Image_Edit-Q3_K_S.gguf (ComfyUI\models\unet)
Downloaded from: QuantStack/Qwen-Image-Edit-GGUF
Qwen2.5-VL-7B-Instruct-Q4_0.gguf (ComfyUI\models\text_encoders)
Downloaded from: unsloth/Qwen2.5-VL-7B-Instruct-GGUF
Qwen2.5-VL-7B-Instruct-mmproj-F16.gguf (ComfyUI\models\text_encoders)
Downloaded from: unsloth/Qwen2.5-VL-7B-Instruct-GGUF
qwen_image_vae.safetensors (ComfyUI\models\vae)
Downloaded from: Comfy-Org/Qwen-Image_ComfyUI
Qwen-Image-Lightning-4steps-V1.0.safetensors (ComfyUI\models\loras)
Downloaded from: lightx2v/Qwen-Image-Lightning
2xLexicaRRDBNet_Sharp.pth (ComfyUI\models\upscale_models)
Downloaded from: Thelocallab/2xLexicaRRDBNet_Sharp
 
The standard Qwen Image Edit 20B diffusion models (FP16 and FP8) are not packaged with the installer, but you can download them directly from the Comfy Org Hugging Face repository and add them to your ComfyUI/models/diffusion_models folder:
Comfy Org Qwen Image Edit Diffusion Models
 
Speed:
Generate 1024 x 1024 resolution images in a minute and 30 seconds on an RTX 4050 with 6GB VRAM. Faster performance is possible on higher-end GPUs.
 
System Requirements:
Nvidia RTX 30XX, 40XX, or 50XX series GPU (FP16 support required; GTX 10XX/20XX not tested)
CUDA-compatible GPU with at least 4–6 GB VRAM
Windows OS
At least 40 GB free storage
 
What’s Included:
Portable ComfyUI Windows Installer, pre-configured for Qwen Image Edit Image to Image
Custom workflow supporting image-to-image image editing
Automatic downloads for all required nodes and models
 
Usage Notes:
Upload up to two input images, then enter a detailed prompt describing the specific interaction, transformation, or relationship you want to see between the images in the generated result. Be as clear as possible about which elements to modify, preserve, or combine, and specify how the items should relate or interact within the scene for best results.
 
Support and More Information
Community Support: For troubleshooting or to connect with other users, join the Discord server.