Trained with an experimental "double sided depth" technique using Perceptual LoRA Toolkit. This conditions the training on both a depth reference and a custom perceptual depth loss.
This is preliminary version of a depth control LoKR for Klein 9b is trained on 550 images. It should be able to handle a good range of scenarios requiring only short prompt guidance for things like specific clothing, setting, etc. It is trained entirely on humans, so it knows anatomy and poses decently well. It should also be able to handle non-human subjects to a point.
Use at strength 0.3 - 1.3 depending on how closely you want to match the reference. I recommend starting at 1.
The images in the gallery have Comfy workflows embedded with nodes that will create depth maps from images you provide.
You may optionally add a background removal node if you have images with backgrounds that enter the depth map.