General Reminder: Each of these versions is a completely different model - check version info for usage instructions and example images as a baseline.
Does pretty much what it says on the tin - this is a collection of LoRAs that produce images consistent with giantess foot fetish. As I've trained more, "giantess feet" is a bit of a broad umbrella - more specialized models will likely be put in their own LoRA pages. This will remain a collection mostly focused on people under or between giantess feet. Generally tested so that weight 1.0 is optimal (though tacking on other LoRAs usually requires you reduce the weight, as do some checkpoints that are less amenable to LoRAs), generally supports anime and toon-style checkpoints.
UPDATE: I've been in the process of retraining a bunch of these for illustrious, as I find that it is far more stylistically stable and prompt adhering than Pony 6. Any of my illustrious versions are a significant improvement over the Pony versions, so much so that the older ones might as well be deprecated (not Pony's fault necessarily - I'm also better at this than I was when I trained those, but it is why I'm not bothering to retrain those at least until there's an improved Pony model). There is also a decent amount of cross-compatibility between illustrious and pony LoRAs, so if you have a favorite pony checkpoint, you're probably better off trying the illustrious version instead.
Completed:
Underfoot POV: Images in which the viewer is beneath a giantess' feet
UF_tiny: Images in which a tiny person is under a giantess' feet (size scale - tiny person roughly the size of her foot or smaller)
UF_mini: Same, but with more of an 'amazon' size scale where the tiny person is less than half the giantess' height, but larger than her foot
Imminent stomp (illustrious): Images in which a tiny person is under a giantess' foot, usually with the implication that she is about to step on them.
Between feet (illustrious): Images in which a tiny person is pressed between a giantess' feet.
In progress:
between toes: self-explanatory - will see how well this comes out
under toes: same as above
Similar models:
GTS feet bondage: Images in which a tiny person (or the viewer) is bound to a giant woman's foot. Tied, leashed, or taped.
Sock/shoe entrapment (WIP): This is what I actually started out wanting to do, but it proved trickier than I expected. I've revamped some of these datasets and will start retraining once the last two versions for this model are done.
GTS Foot worship (WIP): I've attempted models like this and had trouble making something that works. It's tricky because it's nearly impossible to prompt poses for two different subjects simultaneously. The tiny subject is also often at the low end of what can be resolved without upscaling and careful inpainting. I think the approach is to create something where the prompt mostly poses the giantess and the model just knows what the worshipper should do, but that requires some very granular training of specialized models.
Deprecated
under_foot_mini (pony), under_foot_tiny, under_foot, gtsFeetPOV, : just use the illustrious versions above.
imminent stomp, between feet (pony): hopefully the illustrious version is out soon
2.1,2.0,1.0: Don't use these. Ever. I didn't know what I was doing.
Description
This is a general prompt that is mostly for solo shots putting the viewer in interaction with a character's feet. While I generally had giantess content in mind, it's also a pretty reliable general foot pic generator.
Like the others, this uses a combination of booru tags and natural language prompt. Use the example images to get started, but the general concepts are
pov: imminent stomp by giantess (looking up at someone with a foot raised, as if about to stomp)
pov: giantess presents feet (generally someone in a seated position showing off their feet)
pov: looking up at seated giantess (looking up at someone seated above the viewer with their legs dangling suggestively) "pov: seated giantess presents feet" combined with "from below" might give the same results, possibly even more reliably, but I'm not sure.
pov: under giantess toes (extremely unreliable, but will sometimes frame the image to imply that you are looking at them through a gap in their toes. Often doesn't work and when it does, it tends to look really bizarre, but it's there)
Then add booru tags to add details. Specify footwear, setting, character, etc. Also as usual include the standard pony tags - score_9, score_8_up, etc. I generally also put realistic and cg render in the negative tags.
I think this has the highest success rate of anything I've made, owing to the large training set and simple composition, but there are a couple known issues.
1) It really likes bare feet and sometimes you have to fight with it to get socks or shoes. In general, I've had luck with (socks:1.5), (shoes:1.5), etc.
2) As usual with SD, the prompts are more suggestion than command, so a little bit of randomness is to be expected.