Custom ComfyUI node providing visual 2D canvas controls, aspect ratio locking, and presets for AI generation models.
Manage image and video aspect ratios, scaling factors, and model presets directly inside ComfyUI workflows.
ResolutionMaster is a custom node for ComfyUI that gives you direct, visual control over image and video generation dimensions. It is built for AI creators and video editors who need precise aspect ratios, target resolutions, and model-specific constraints for architectures like Flux, SDXL, and WAN. You should use it if you want to eliminate guesswork when calculating output dimensions and rescale factors.
The node adds an interactive 2D canvas with real-time resolution previewing, aspect ratio locking, and snap-to-grid controls to your node graph. It provides targeted scaling by megapixels or standard resolutions alongside pre-configured profiles for Flux, SDXL, Qwen-Image, and WAN video models. Instead of altering pixel data directly, it outputs calculated dimension and rescale values into your sampler, checkpoint, or image resizing nodes.
It suits ComfyUI users generating AI images or video clips who require exact canvas sizes, model-matched resolutions, or automatic dimension matching from reference inputs. It is less suitable for general video editors who do not use ComfyUI node graphs or who expect an all-in-one image processing engine. If you only perform standard video editing outside node-based AI workflows, this tool will not fit your setup.
Visually pick image dimensions using drag controls with real-time megapixels, p-value, and aspect ratio displays.
Enforce optimal resolution steps and pixel boundaries for Flux, SDXL, Krea 2, and WAN video models.
Scale dimensions by multiplier, target standard P-resolutions, or match precise megapixel counts.
Automatically read connected reference image sizes and fit or resize them to matching workflow presets.
ResolutionMaster is completely free under the MIT license. Your only cost comes from operating the underlying ComfyUI environment and hardware required to generate your media.
880 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
No, it calculates exact width, height, and scale values which you then route into ComfyUI sampler or image resize nodes.
Yes, it includes presets and rules tuned specifically for WAN video models operating between 320p and 820p.
You can declare new model profiles and presets inside the frontend JavaScript files as outlined in the documentation.
See Zekai first in Google