Config-Presets VS improved-aesthetic-predictor

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.

Perhaps you could use an "aesthetic-evaluator": https://github.com/christophschuhmann/improved-aesthetic-predictor (probably not SoTA but it works)

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

stable-diffusion-v1-2: Resumed from stable-diffusion-v1-1. 515,000 steps at resolution 512x512 on "laion-improved-aesthetics" (a subset of laion2B-en, filtered to images with an original size >= 512x512, estimated aesthetics score > 5.0, and an estimated watermark probability < 0.5. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an improved aesthetics estimator).

The data used for fine-tuning has come from a random sample of 56k Danbooru images, which were filtered based on CLIP Aesthetic Scoring where only images with an aesthetic score greater than 6.0 were used.

All they've said is they randomly picked 56,000 images that had an aesthetic score greater than 6.0. The score is created by this model. https://github.com/christophschuhmann/improved-aesthetic-predictor

Does anyone know how you could combine a model like Aesthetic Score Predictor with stable diffusion? They used this model to filter training images by score. Iit seems like a lot of people just tune their prompt to make images more aesthetic, by adding certain words.