This is a pixel art lora that focuses on playing nice with automated, non-AI post-processing.Recommended/Optional: It works well with the Pixel Grid Helper [<a target="_blank" rel="ugc" href="https://registry.comfy.org/publishers/molbal/nodes/comfyui-pixelgrid-helpers">ComfyUI Registry</a>] [<a target="_blank" rel="ugc" href="https://github.com/molbal/ComfyUI-PixelGridHelpers">GitHub</a>] custom nodes, which I developed specifically for this mode.Use this Lora with 0.8-1.0 strength, and always set the size to 768x768. The output will be a 128x128 image, scaled up to 768x768. Scaling it down using nearest neighbour should be fine in almost all cases. (The 'Pixel Grid: Median Fixer' node however checks each 6 by 6 square and applies the median color to all the pixels to iron out minor artifacts.)<img src="https://github.com/molbal/ComfyUI-PixelGridHelpers/raw/master/assets/pixel-grid-median-fixer.png" alt="Screenshot of the node" />Use the trigger word pixel_6x6.Example workflow with post-processing [<a rel="ugc" href="https://gist.githubusercontent.com/molbal/7eadc7ca099b2de6ab4396e8b606f099/raw/5cd645d0fc6debe7c2c24d1dee7985d4e90ea152/pixel-6x6-comfyui-workflow.json">Github</a>]:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6fae78bd-ebd1-4e15-969f-f6afc5195e87/width=525/6fae78bd-ebd1-4e15-969f-f6afc5195e87.jpeg" />

Files with SHA256: 0f0415b5cab4d46f43c8acfe58ddbdac97819baf3317f140b5f13b645286bd09