Not satisfied with current state of feet models on Stable Diffusion, I set out to train one based on content available that has feet in the frame(s), but not as the primary focus on the photo. This model helps with more photorealistic details on feet and often emphasizes particular positions that are probably well known by foot fetish lovers. Captioned with BLIP.
On its own, it sometimes will impose a stylistic look (gold, vintage pinup type of feel), but merges excellently with other models. Mixing with chillout, Realistic Vision have given me lots of fun results. Still loads of training and input data work I could do so this is just the start.
Made some good content with it? Why not post them? :)
Description
First release
FAQ
Comments (12)
We will watch your model with great interest!
hell yea
Hi, I am wondering how you are mixing this with other models when you distribute it as checkpoint and not as lora... anything I am missing here technically I guess?
by making a new model merging the two together I'm guessing
Yes, with model merge tab, weighted sum. Mixing a little of Realistic Vision, chill out mix, or whatever in creates models that keep the feet effect but get some novel DNA from the other ones in there as well. You can see in some of the model names on the example images what it looks like when you make such a merge.
Also, i want to post LoRa version eventually. I just didn't figure out how to make one yet.
Did you know why so many men like feet? Bing it up, but it's because the part of the brain that relates to the wang is DIRECTLY beside the part that relates to feet. It's true.
I'm leaning into it and encourage everyone else to do the same
FINALLLY!!! Can't believe SD has been out for like a year and we don't have a single actual feet model that is not x9999 zoomed on feet, simply includes feet.
This is exactly what we need!! Please keep working on it!!
hell yea my thoughts exactly brother
can you do a lora of this?
thank you for this