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
Improvements and Fixes
Replaced ComfyCouple with Regional Prompting
FAQ
Comments (6)
Thank you, works like a charm. One question: In the Basic T2I WF: Where can I adjust the Lora Strength?
You just need to adjust it in the prompt e.g:
from <lora:Name_Of_LoRA> (unspecified LoRA weight)
to <lora:Name_Of_LoRA:0.75> (specified LoRA weight 0.75)
@Legendaer Thank you for the quick response. I almost thought as much but wasn't sure.
@Legendaer Sorry to bother you again but I have a question about the Clip Vision Option in the T2I workflow. Coming from A1111 I'm asking myself if this is basically an optional I2I Node? If so, how can I adjust the denoising? I've got the impression the clip Vision doesnt do much.
Hey, this works pretty well in general, but the loras I normally use with my checkpoint in another workflow causes the image to get artefacts in this one, especially if i try to switch to Eular a, which is what I normally use. What can be the reason for that?
Love it. My renders dont seem to be keeping my OpenPose poses though. it was correct after rendering initially but when it went through the detailer process the correct previews got replaced by the character standing neutrally. i did have "facing_viewer" as a tag but not sure thats strong enough of a pose to override?