This workflow is designed to allow multiple prompt sets to be kept in a single workflow and then switched between easily, automatically changing the ReActor face swap image (if switched on) and output filename prefix. A detailed User Guide is included in the zip file.
A full set of wildcards specifically designed for use with this workflow can be found here:
ComfyUI Wildcard Pack
This workflow has the following features:
Support for SDXL, Flux Basic (Schnell/FP8), Flux Full Fat (Dev/FP16) and GGUF (Lower VRAM) Models
Selectable or Random - Portrait / Landscape Aspect Ratio (automatically adjusts upscale to suit)
8 Selectable or Random Switchable input prompt sets, each with:
2 Positive wildcard prompt boxes
ReActor face swap image loader
Output filename prefix
8 Selectable or Random Image Style Prompts
Shared negative prompt
Lora loader (4 for SDXL, 1 for Flux)
Reactor face swapper (switchable)
Face Detailer (switchable, mainly for SDXL and Flux Basic)
Simple upscaler (fast)
Image cropper for removing text at the bottom of an image (X pixels)
Image save with full MetaData
Description
Further improved integration of clothing into style prompts, by inserting the clothing wildcard text into the style prompt, by replacing "##" characters in the style prompt text with the clothing wildcard text. This further ensures styles do not override the clothing... ho hum... now include my ComfyUI Wildcard Pack in the zip file... Updated User Guide... added another yellow highlighted bit for people upgrading from versions prior to 9....
Version 9 notes for those who missed it...
Major Update. In previous versions style prompts, which describe the style of the image and clothing, generally had the effect of overriding the clothes descriptions included in the main prompt sets, so the amount and type of clothes in the final image often varied from what was wanted. In this version the description of the amount and type of clothing has been moved to the style prompts area into its own wildcard prompt box. By doing this it allows the clothing to be weighted and encoded in with the style prompts separately from the encoding of the main image prompts, this resolves the above issue. However this is only really effective if you are using wildcards for clothing, as otherwise you would need to change this prompt manually every time you want different clothing. Hence this version is called "Pro" because it is really only for people using wildcards, as this workflow is specifically designed for them, and as well all know Pro's use wildcards ;-) Updated User Guide - Read yellow highlighted sections if you have used previous version, to catch up with the changes.