Attenuates OpenAI/ChatGPT source micro-grid patterns before a direct 1:1 image is used as an ETUR source or Flux2 reference. This is a pre-processing node, not…

About TBG Enhanced Tiled Upscaler and Refiner Pro! We at TBG Think. Build. Generate. Pro AI upscaling & image enrichment are excited to make our TBG Enhanced Tiled Upscaler and Refiner Pro available to you for free non-commercial use. We believe in empowering creators and innovators, which is why anything you create or generate using our software

TBG_Enhanced Tiled Upscaler & Refiner FLUX PRO

image

high_freq_reduce

low_freq_radius

Generate_Difference_Image

Attenuates OpenAI/ChatGPT source micro-grid patterns before a direct 1:1 image is used as an ETUR source or Flux2 reference. This is a pre-processing node, not a final blur/sharpen pass.

Name	Type	Default	Description
image	IMAGE		Direct 1:1 OpenAI/ChatGPT source image to clean before using it as an ETUR source/reference. This targets the measured embedded high-frequency micro-grid/checker pattern; it is not intended for already-upscaled, resampled, or final generated output images.
high_freq_reduce	FLOAT	0.250–1	How much detected source micro-grid pattern to reduce. Start at 0.20-0.35 for direct OpenAI images; high values can remove real pores/freckles or create flat skin.
low_freq_radius	FLOAT	1281–256	Width of the measured source-grid frequency detector. Existing workflows can keep 128; the actual correction is tightly capped to avoid dark spots and pixelation.
Generate_Difference_Image	BOOLEAN	false	When enabled, the second output shows only the exaggerated micro-grid difference map with a Photoshop-style curve: 0->0, 1->253, 255->255.

Name	Type	Description
image	IMAGE	—
difference_image	IMAGE	—

AI Source Pattern Cleanup

Inputs (4)

Outputs (2)