A simple and editable resolution preset selector node for ComfyUI.
This custom node lets you quickly select common image or video resolutions from a dropdown list, or define your own manual resolution.
Presets are stored in a separate resolutions.json file that you can freely edit.
The node also generates an Empty Latent (1×4×H/8×W/8), so you can plug it directly instead of an Empty Latent Image node.
- ✅ Dropdown list of predefined image/video resolutions
- ✅ Easy manual input via “Custom (manual input)” option
- ✅ External
resolutions.jsonfile — editable at runtime - ✅ Works with Reload Custom Nodes (no restart)
- ✅ Clean output:
(width, height)for direct wiring toEmpty Latent Image,WANVideo, etc.
ComfyUI/custom_nodes/
└── ResolutionSelector/
├── init.py
├── ResolutionSelector.py
└── resolutions.json
- Go to your ComfyUI
custom_nodesfolder. - Clone this repository:
git clone https://github.com/dodemedexter/ComfyUI-ResolutionSelector.git
Find it under the Utilities category:
Utilities → Resolution Selector
Select a preset (e.g. WAN - 9:16 HD [544x960 portrait])
Connect the outputs:
(width, height) → Empty Latent Image
The list of resolutions is stored in resolutions.json. You can edit this file freely to add, rename, or remove entries.
Example:
{
"IMAGE 1:1 [1024x1024 square]": {"width": 1024, "height": 1024},
"WAN - 9:16 HD [544x960 portrait]": {"width": 544, "height": 960},
"Custom (manual input)": {"width": 512, "height": 512}
}
After editing, just click Reload Custom Nodes in ComfyUI Manager — no need to restart.
None. This node uses only the standard ComfyUI API and the Python standard library.
This project is released under the MIT License


