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
Added Attention Couple to Regional Prompting
Added Vpred support to normal T2I workflow
FAQ
Comments (6)
I dont know what it is but i cant et the FaceDetailer to work. All other detailers work, but when i run the Workflow it finishes the FaceDetailer Pipe, and then throws an error"
FaceDetailerPipe
'NoneType' object has no attribute 'data'
.. any Idea?
My guess is that you should try redownloading the detection file and replacing it, as it might have been corrupted during the initial download.
Is there some way to see the "patch notes" or differences between the versions when you update? I'm on v17 and v18 came out but whats new?
There aren't really any patch notes, I just write a very short note in the "About this version" section. For V18, the only real functional difference was the added attention couple to the regional prompting. The rest of the changes were just moving nodes and adjusting values.
I want to start by saying I love your workflows. They're really helpful.
I have a bug report for V18. Body ADetailer doesn't work in any of the workflows. They all have the same problem.
The [HandDetailer (pipe)] output goes directly to [BodyDetailer (pipe)]. It bypasses the [Edit DetailerPipe] node in the body detailer flow. The body detailer doesn't get loaded.
It's an easy fix, but a lot of people might not notice it, so I wanted to let you know.
Thanks for your hard work on these.
Thank you! I appreciate the feedback and will make sure to fix the bug in the next iteration.