My workflow for SDXL models. It is a bit messy but functional. Has the following high level features:
Text to Image and Image to Image from multiple sources
I2I can be from random Danbooru posts, image file, image folder, URL, or video with optional autotagging.
Wildcard support
Randomized orientation and image ratio
Prompt list to create a series of images from a file
Batch or single image generation
Multiple detailers with support for detailing of background characters and faces and NSFW areas
Uses a mix of LCM and standard samplers to speed up generation
Description
Fixed a number of issues:
The size and orient group was not right. Should be good now. No longer tied to the SDXL Aspect Ratio group when there is an image input. There is a dedicated image input settings for the short length and ratio override.
I had issues with LCM detailers and skin tone so there is an option to toggle LCM off and use a regular detailer.
Added a image blur group on the input image to help clear any styles from the input image.
Added multiple seeded wildcard input blocks. The output can be enabled or disabled based on the Prompt List count.
Added a SAM3 detector for logos to enhance the watermark/logo removal