Would appreciate comments, posts, reviews, and requests
if you'd like to pay for a commission or just send a dollar or two -> PAYPAL or Kofi
a Lora for an ass support pose.
0.6 - 1.0
recommended to highres. fix with my other Loras upscaling also seems to help. (so if a generation is slightly off instead of altering prompt or changing seed try upscaling)
recommended width = 512 height = 768
recommended tags: ass_support
optional tags: from_behind, from_below
V7: This version I got rid off all variants and it is strictly 2 handed ass_support, also added a few dozen images.
WITH OBJECT:
it is a bit hit or miss, the items i used were the ones in the dataset, not sure how well other items will work.
I would appreciate any feedback, images you make with my loras, and requests in the comments.
haven't tested in conjunction with this Lora Grabbing own Ass | Stable Diffusion LORA | Civitai
think V5 is undertrained and the characters from the dataset may be baked in
also V5 requires LoCon and Lycoris extension to work
Description
Epoch 14 of the same version as V3
FAQ
Comments (7)
Please, people need to stop adding trigger words to singular concepts for crying out loud.
Please explain, do you mean a single LORA shouldn't have a weird, impossible-to-guess trigger word, since once this page goes down, nobody will be able to use it? And that the trigger word should be more generic?
Or something else?
Actually, trigger words are a great thing. because of two reasons:
1. if you have a trigger word you can put that in the negative prompt while putting the lora itself in the negative prompt won't have any effect.
2. it allows for using advanced methods such as invoking the Lora after a certain number of steps like so: "apple [triggerword:20]" which tries to apply the style of the Lora to the apple only after step 19.
I'm confused, you mean you guys don't have a massive Google Sheets doc with every model you've downloaded, organized by type, with suggested settings, positive/negative trigger words, and a link to the model on CivitAI? ... No? ...Just me?
A easy way to fix this is by naming the lora this way: "triggerword - LoraName"
In the case of my Rage unleashed lora i have named it: "r1ge - AnimeRage" where r1ge is the trigger word.
I'm not sure that's better, the problem is having a LORA in your list, and not knowing what to type without coming to Civitai to look it up, or even knowing if there is a trigger word. Don't think an agreed-upon trigger format is going to help that, if anything, just cause issues with improper spacing ruining it's implementation, since there's no way to confirm the trigger word is being applied either, outside of guessing due to the output.
Edit, not really edit, I just reread it, sue me: I finally get what you mean, the triggerword is part of the NAME.
I retract my above rant, and I think you have the right of it. Might get bulky, as I've seen some LORAs with multiple costume variations which all have lists of trigger words for each costume. But other than that, it's easily done.
@namelessoptimist Yeah, what I do is copy everything from the post to my own excel sheet, so I have all the trigger words next to a link to the post and the name of the Lora that's all on my own, so even if CivitAI went down entirely, I could still use my Lora lol