Workflow for XL/Illustrious/NoobAI Models
Any feedback would be appreciated.
See the Article for a Guide:
https://civarchive.com/articles/17339 (probably doesn't work rn)
https://civarchive.com/articles/17339
Key Features:
LoRA
TIPO Prompting
Detail Enhancers
ControlNet Upscale
IPAdapter
HiresFix
OpenPose
Wildcards
ControlNET
Color Match
FBCNN
Regional Prompting
Inpaint
Outpaint
Workflows included:
🟥Advanced: comprehensive text to image workflow
🟨Basic: more basic version of the Standard workflow
🟦Standard: more basic version of the Advanced workflow
🟩Detailer: detailing previously generated or existing images
Experiment and enjoy!
Description
About this version
Update from V24→V25
(This is not an exhaustive changelog)
General:
General improvements and bug fixes
Adjusted default values
T2I:
Added CFGZeroStar
Changed the how the conditioning/prompt was handled to be less obfuscated
Basic:
Added LoRA Manager
FAQ
Comments (5)
Hello) in Detailer wf for some reason, my image generation stops at the Face Detailer step. I can't figure out why. 4 identical pictures fall into tmp dir. hmmm. may be someone know where i do mistake?((
The detector for faces isn't included by default. Follow the linked article.
NB! Loaded the Basic wf, two nodes missing - Lora Loader and TriggerWord Toggle. Installing those missing nodes means installing ComfyUI LoRA Manager by Will Maio, which on restart crawls your checkpoints and loras folders, creating a metadata JSON file for each file found within.
Is this considered a good or a bad thing? Like what does this .json file do?
@Greyvein Depends on you. Some people do not like unexpected code running on their machines. As to the usefulness of the JSON files, ask Will Maio.