Qwen Image Edit Rapid AIO (4-Step) - One Click Installer & ComfyUI Workflow

Edit your images faster with the Qwen Image Edit Rapid AIO in ComfyUI. This refined Qwen variant integrates the optimized Qwen 4-Step Lighting and Detail enhancement process directly into the model—no external LoRA required. It delivers reliable results for both SFW and NSFW creative workflows while maintaining speed, quality, and flexibility.
 
Qwen Image Edit Rapid AIO is part of the Qwen2.5-VL series optimized for visual-linguistic alignment and instruction-following image tasks. The GGUF variants are quantized for local inference with low VRAM usage while still maintaining high generation fidelity. These models are fully integrated with ComfyUI bindings for editing, inpainting, and multi-prompt workflows without additional setup.
 
Preloaded Models within the Installer (Low VRAM)
 
Qwen2.5-VL-7B-Instruct-UD-Q4_K_XL.gguf (ComfyUI\models\text_encoders)
Hugging Face Link
Qwen2.5-VL-7B-Instruct-mmproj-F16.gguf (ComfyUI\models\text_encoders)
Hugging Face Link
qwen_image_vae.safetensors (ComfyUI\models\vae)
Hugging Face Link
qwen-rapid-nsfw-v7.1-Q2_K.gguf (ComfyUI\models\unet)
Hugging Face Link
2xLexicaRRDBNet_Sharp.pth Upscale model (ComfyUI\models\upscale_models)
Hugging Face Link
 
Note: The full FP16 and FP8 diffusion versions of Qwen Image Edit Rapid AIO are not bundled in the installer due to their large file sizes. Once available, they will be added to the archive. For now, the GGUF quants perform exceptionally well and are suitable for both general and artistic use.
 
Link to GGUF Quants - https://huggingface.co/Phil2Sat/Qwen-Image-Edit-Rapid-AIO-GGUF/tree/main
 
Speed
 
Generate and edit 1024×1024 images in approximately 2 minutes on an RTX 4050 with 6GB VRAM. The workflow automatically scales with your system, providing faster generation and higher resolution on GPUs like the RTX 4090 or higher-memory setups.
 
Tips for best results in ComfyUI:
Use the “Fast Group Bypass” toggle to quickly switch between model types without rebuilding chains.
For editing or NSFW content, activate the pre-included conditioning node to boost realism and lighting accuracy.
When using text prompts, keep them descriptive but concise—Qwen2.5 models interpret detailed spatial and aesthetic cues effectively.
For fast previews, run a Q2_K quant version; for final renders, switch to Q4_K or higher for fidelity.
 
System Requirements
Nvidia RTX 30XX, 40XX, or 50XX series GPU (FP16 support required; GTX 10XX/20XX not tested)
CUDA-compatible GPU (minimum 6GB VRAM; more recommended)
Windows OS
At least 40GB free storage
 
What’s Included
Portable, pre-configured ComfyUI + Qwen Image Edit Rapid AIO installation with ready-to-run workflow
Automatic download of all required custom nodes and models on first launch
Built-in modularity for bypassing, testing, and chaining GGUF and (future) diffusion variants
Streamlined interface for single-click edits, consistent lighting correction, and seamless NSFW/SFW transitions