SD-Chad VS Config-Presets

I'm not familiar with nodeGPT but if it's an LLM like most, and if it can accept images, then it's usually ok at identifying parts of an image, things like style, content etc. What it's not good at is rating it, for that you need what's usually called an ascetic scorer, which some are ok, the one that comes to mind first is https://github.com/grexzen/SD-Chad there are others but I can't remember them off the top of my head. This could be used as your critic module I suppose.

"Calculates aesthetic score for generated images using CLIP+MLP Aesthetic Score Predictor based on Chad Scorer "

You can use the Config-Presets extension to save settings for pretty much anything and reload them from a dropdown menu.

You can use the Config-Presets extension which you can install from within webui. You'll want to create a new preset for your adetailer settings and add all the fields that you'd like to reuse before saving it.

XYZ plot combined with Agent Scheduler to queue tasks, and Config Presets to set the XYZ plot values.

You can use a simple extension like Config Presets to accomplish this.

There is this one too: Zyin055/Config-Presets: Extension for Automatic1111 (github.com)

Config Presets uses a config .json file to set some of the fields in txt2img and img2img.

And a QoL extension I love is Config_Presets that makes loading settings a one-touch affair. I have presets defined for aspect ratio, sampling method, etc to save a lot of clicking

Edit ui-config.json, or use an extension like Config Presets.