Skip to content
BytePlusBytePlusBytePlus ModelArk for ComfyUI

Image Quality Enhance

Template
Image Quality Enhance, in the ComfyUI template browser under BytePlus
Workflow file
Image Quality Enhance.json
BytePlus nodes
Image Quality Enhance
Keys needed
AI MediaKit API key
Also uses
Compare Images, Load Image, Save Image (built into ComfyUI)

What it makes

Section titled “What it makes”

A sharper, larger copy of a picture. The template loads an image (the ComfyUI logo) and enhances it to twice its width and height. It saves the result and also sets up a before-and-after comparison.

The workflow

Section titled “The workflow”
Load Image feeding Image Quality Enhance, whose outputs go to Save Enhanced Image and to both inputs of Compare Images
Four nodes: Load Image, Image Quality Enhance, Save Enhanced Image and Compare Images.
  1. Load Image supplies the picture to improve.
  2. Image Quality Enhance runs with tool_version set to standard, output_size set to multiple and multiple at 2.00. The image_url input is empty because the image comes from the socket.
  3. Save Enhanced Image writes the enhanced picture to BytePlus/Image/enhanced.
  4. Compare Images receives the original output as image_a and the enhanced image as image_b. The original output is the input resized to the enhanced size, so the slider lines up. Compare Images shows its slider in Nodes 2.0 only; Classic Canvas shows a note instead.

Run it

Section titled “Run it”
  1. Add your AI MediaKit API key in Settings → BytePlus if you have not yet (API keys). This is a separate key from the ModelArk key.
  2. Log in to your Comfy.org account in ComfyUI. A connected image is uploaded to Comfy.org storage first, because AI MediaKit only takes links.
  3. Open the template browser and choose Image Quality Enhance under BytePlus.
  4. Press Run. The enhanced picture appears in Save Enhanced Image.

Settings worth changing

Section titled “Settings worth changing”
  • Image: pick your own picture in Load Image. To skip the Comfy.org upload, leave the socket empty and paste a public link into image_url.
  • tool_version: standard is fast clean-up for thumbnails, UGC and OCR input. professional and max add richer texture and have a generative_enhance_mode choice. Prices differ per version.
  • multiple: the scale factor, 1 to 8 with standard, up to 30 with professional and max.
  • output_size: switch to target size to set a width and height in pixels instead of a factor.

Example result

Section titled “Example result”
The enhanced ComfyUI logo in Save Enhanced Image: a yellow ring above the word ComfyUI on a purple gradient
Example result.

Time and cost

Section titled “Time and cost”

AI MediaKit bills each enhanced image, and the price depends on tool_version. Running again with an unchanged workflow reuses ComfyUI’s cached result and does not bill.

Section titled “Related”