Using https://civarchive.com/models/1875016/depth-reference-fusion-lora.
The workflow lets you load any 2 images: first is the reference character, second is the pose image., It makes the pose into a depth reference, resize to your original image, you can pad the image (ie. zoom), though it will be cropped and resized keeping aspect ratio of original image.
Description
FAQ
Comments (8)
Prompt execution failed
Prompt outputs failed validation: EmptyImage: - Exception when validating inner node: tuple index out of range
??? Whats wrong?
Doesnt work properly. it seems to change outfit based on depth pose
How do you get the links to go around the nodes properly? Does it come from an extension? Sa m'intéresserais :) Merci d'avance
Error: GroundingDinoSAM2Segment (segment anything2)
Failed to get source for <function Enum._generate_next_value_ at 0x0000021869CE0AE0> using inspect.getsource
SAM2 has been having problems recently if seems. Might have to swap for Florence or REMbg to segment.
Though I could install it so far all the time, it's not the first time there's a problem with it for others.
My man, thank you very much! Working.
I was able to get the workflow to run, but for the final picture I get a blank, white image. Any thoughts?
a version that uses florence2 would be awesome