ComfyUI-QwenEdit-Urbanism-by-UGA
Offline text-driven image editing for urban and architectural workflows using open-source Qwen-Image-Edit model in GGUF format with custom ComfyUI nodes for batch and…
🏙️ ComfyUI-QwenEdit-Urbanism-by-UGA
Qwen Image Edit for Urbanism brings localized, text-driven image editing to urban and architectural workflows using the open-source Qwen-Image-Edit model in GGUF format. All processing runs fully offline — no API, no cloud — making it ideal for architects, planners, and researchers who need privacy, reproducibility, and full visual control.
🧠 1. Qwen Image Edit for Urbanism : Comfy Pipelines
| Version | Description | Tutorial | |----------|--------------|-----------| | v1.0 | Basic Qwen Image Edit workflow for single-image editing. Adapts automatically to input ratio and size. | v1.0 Tutorial → | | v1.1 | Adds image editing from a reference image and advanced sampling capabilities for complex scenes. | v1.1 Tutorial → | | v1.2 | Add sequential & Batch Edits | v1.2 Tutorial → | | v1.3 | Add editing with a Mask and a reference image and/or prompt | v1.3 Tutorial → |
Download the Workflows
Right-click any link above and choose “Save link as…” to download the workflow file. Then, open ComfyUI → File → Load → Workflow, and select the downloaded .json file to load it into your workspace.
| Version | Workflow File |
|---|---|
| v1.0 | Download Qwen-Edit-UGA-v1.0.json |
| v1.1 | Download Gwen-Edit-UGA-v1.1.json |
| v1.2 | Download Gwen-Edit-UGA-v1.2.json |
| v1.3 | Download Gwen-Edit-UGA-v1.3.json |
⚙️ 2. Custom Nodes
Custom nodes developed for urban image processing and automation within ComfyUI.
| Node Name | Function | Description | |------------|-----------|--------------| | 🎲 Random Image Selector | Randomly selects one image among several inputs each run. | For stochastic rendering. | | 🔁 Sequential Image Loader | Loads each connected image in order across executions. | For batch processing. | | 🖼️ Stateful Image Collector | Stores and display the processed outputs from each run into six persistent slots. | For preview. |
🧩 Installation
- Download and install ComfyUI
- Open the desired workflow and install the required models. Follow the Qwen-Edit-UGA tutorials to download and place the necessary checkpoints, VAE, CLIP, and other model files inside your ComfyUI/models directory.
- Add custom nodes (required from v1.2). Navigate to your ComfyUI directory: ComfyUI/custom_nodes/
- Clone or download our repository and put the QwenUrbanismNodes folder in your custom_nodes directory https://github.com/perezjoan/ComfyUI-QwenEdit-Urbanism-by-UGA.git
- Restart ComfyUI.
The nodes will appear under image/sequence and image/random categories.
🧩 Credits
Developed by Urban Geo Analytics (UGA)
Based on open-source work by QuantStack, ComfyUI, and Qwen Image Edit contributors.
🪪 License
