<3 Please join my PATREON page, where you get additional content (for SDXL) and personal help, IF I can help you^^:
https://www.patreon.com/polyhedron_ai
*Publishing Notes:
Version 1.0 is a merge of four different custom LoRAs: one for female skin, one for female hands, one for male skin and - surprise! :D - one for male hands. (This version is 288 mb and in PickleTensor.)
Version 1.1 is a completely new-trained LoRA containing ALL above. And so it differs from the first version, which can be as good as bad. So: simply try BOTH, to get the output YOU desire. :) :-* // (This version is 144 mb and in SafeTensor.)
------------------------------------------------------------------------------------------------------
This LoRA has been trained to support realistic skin with blemishes as well as help create realistic hands for woman and for man. The model already works with simple resolutions up to 768px. It is actually not necessary to use an upscaler or sharpener ... Have fun with it. <3
Tipp: Get another LoRa for perfect eyes. (not made by me yet) Like this one:
https://huggingface.co/casque/detailed_eye-10/tree/main
Trivia: The example pics are re-made from Olivio Sarikas used on this tutorial:
Frank
Description
Version 1.0 is a merge of four different LoRAs: one for female skin, one for female hands, one for male skin and - surprise! :D - one for male hands.
Version 1.1 is a completley new-trained LoRA containing ALL above. And so it differs from the first version, which can be as good as bad. So: simply try BOTH, to get the output YOU desire. :) :-*
FAQ
Comments (20)
SafeTensor is NOW available.
Where can I find lora:detailed_eye?
Look into my description. ;)
@Polyhedron_AI Dang it, I'm so blind. :P Looked all over Civit, googled it and it's right in front of my eyes. Thanks!
cant get this working properly. every picture came out mushy. any idea what i did wrong?
Sorry for the late answer: You have to reduce the LORA weight, I guess. For example: <lora:polyhedron_xxx_xxx:0.3>
Any plans for an XL version of this?
Already done, my friend. ;) (including eyes)
where could we find that sdxl version :)
@ThricePi Look into my profile ... you got this! ;)
With this Lora all faces look the same. (weight 0.2-0.6). Unsatisfying...
Try to use an additional character LoRA or embedding to get different faces; you can merge different faces too. Use other prompts and seeds. Experiment ... ^^ Have fun.
Does thie LORA support asian skin?
This LoRA is not specially trained on asian skin, but: Give it a try. :)
is it good for asian skin?
racking my brain on how asian skin is any different than other skin. i haven't had any asians turn caucasian or vice versa with this Lora 😄
@Narz It's because AI tends to learn things that you're not intended for them to learn. I mean, how exactly are going to train for a skin lora without using some faces. Sometimes AI tends to associate other things with the one you actually intended for AI to learn.
Details
Files
polyhedron_new_skin_v1.1.safetensors
Mirrors
polyhedron_new_skin_v1.1.safetensors
features_skin.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedronNewSkinV11.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
detailed-skin.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
e2f9a468-8b11-4fef-96d7-acc33fc10c98.safetensors
4caa2b9e-c2f2-4fd5-9cad-ab2a29843f5f.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedronskin.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
polyhedron_new_skin_v1.1.safetensors
Skin-and-Hands (e2f9a468-8b11-4fef-96d7-acc33fc10c98).safetensors
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.



