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
V5-25
Added Support for Flux GGUF Models, designed for lower vram configurations e.g. 6-12GB (like mine!), as Flux Full Fat strains on 12GB and really needs 24GB. GGUF models are also faster (and many on CIvitAI). Updated the User Guide and included some useful links to articles explaining Flux Full Fat and GGUF Models (including where to get the models etc.) as well as PDF copies of them in the zip file.
V5 Notes below (for anyone who missed the previous version):
Massive Update, as a consequence of which the workflow has been renamed. Added support for basic (schnell/fp8) and full fat flux (dev/fp16) alongslde the existing SDXL, with a model selector, which automatically reconfigures the sampler paths etc. Added selectable landscape / portrait aspect ratios (which can be changed), which automatically reconfigures the upscale parameters. Updated User Guide, and possibly some other sh*t that I forgot.