Extensions/Artfat Resolution
ComfyUI Extension

Artfat Resolution

Resolution picker for low-base + upscale workflows: preset sizes, custom ratio or exact manual W×H, two upscale stages (base → mid → final), plus an empty LATENT and a live readout. Built for Krea 2 / Selfism.

By artfat-creator·Created 27 days ago·Updated 27 days ago· 1
artfat-creator/ComfyUI-Artfat-Resolution
Nodes—
On cloudLocal install
Stars1
Updated27 days ago
Readme

ComfyUI-Artfat-Resolution

A tiny, elastic resolution picker for ComfyUI built for low-base + upscale workflows (Krea 2 / Selfism), but works anywhere. Three ways to set the size, two upscale stages, and a live readout so you always know the final file size before you render.

No canvas, no dozen buttons — clean controls and a real-time readout.

Artfat Resolution node

Node: Artfat Resolution

Three modes (one size dropdown)

size dropdown

  • Preset size — pick a ready W×H (e.g. 2:3 portrait · 512×768). Beginner-friendly.
  • Custom ratio — set ratio_w:ratio_h + base short side (e.g. 3:1 banners).
  • Manual W×H — type an exact manual_w / manual_h. Not snapped — exact stays exact (e.g. 1200×400).

Two upscale stages

  • upscale_1, upscale_2 — decimal multipliers. 1.0 = off (true passthrough, no snapping).
  • Outputs the full chain: base → mid (×up1) → final (×up2) — matches a two-pass upscale pipeline, so you see the final size up front.

Other inputs

  • multiple — snap sides to 8 / 16 / 32 / 64 (16/32 safe for Krea 2 / Qwen). Ignored for the exact side in Manual mode.
  • batch_size — for the LATENT output.
  • latent_type — SD3 / Flux / Krea 2 (16ch) or SD1.5 / SDXL (4ch). Only matters if you use the latent output — match it to your model.

latent types

Outputs

width, height, mid_width, mid_height, final_width, final_height (INT), plus a ready LATENT (empty, at base size — drop your EmptyLatentImage) and an info string (512x768 -> 960x1472 -> 1920x2944, wire into a text node for a readout / filename).

The node also draws the base → mid → final chain live at the bottom.

Install

Option 1 — ComfyUI-Manager (easiest) Custom Nodes Manager → Install via Git URL → https://github.com/artfat-creator/ComfyUI-Artfat-Resolution

Option 2 — git clone

cd ComfyUI/custom_nodes
git clone https://github.com/artfat-creator/ComfyUI-Artfat-Resolution.git

Then restart ComfyUI (a browser refresh is not enough — the node registers on server start).

No extra Python dependencies — uses torch, already provided by ComfyUI.

License

MIT © artfat-creator