LoRA of Bloody Personas
I'm creating Dreambooths, LyCORIS, and LORAs. Here is my base model Serenity: https://civarchive.com/models/110426
I upload 2-3 times a week, however, I write down suggestions all the time. If you want to see someone made into a model just leave a comment :)
Suggestions left on my donation page ( https://www.buymeacoffee.com/malcolmrey ) are taken with the highest priority and you will be able to enjoy them way before they get released here. (I also accept custom requests)
The reason is that I can't keep up with uploading and the models are being made pretty much all the time :-)
As mentioned, via the donation page I accept custom requests, so feel free to engage with me there, I will answer all your questions :)
Description
FAQ
Comments (19)
A bloody mess... and one of my favorite Models ! :)
Deserves a star !
This Model is also very useful for creating some amazing fashion photography scenes.
Thank you! :)
thank you! :) You're the best!
You are welcome :-)
now it makes sense why my pictures didn't get blood before....hope this works, this would be amazing! i wanted to recreate some Scenes from Hostel and Saw, but it would just not work without this.....will update after testing
can't wait to see the results! :)
this website is so f*cking brocken, i can not even publish the pictures i made with this lora, what a shit
try a bit later, sometimes there are just slower moments
@malcolmrey i tried it 4 times in the past days and idk why but i can not publish anything. there stays always at least one tag is missing, but i alredy have 5 tags chosen. it also saves, but i just can not publish anything of it. reather on my own page or here in the gallery......watch them on my website: https://spinangelo.jimdofree.com/ai-art-stable-diffusion/
@spin137 I love those generations, great stuff! :)
I would love to see blood that looks like a vampire has been feeding. Blood dribbling from the mouth, blood dribbling down the chin and onto the chest etc.
I can't find a decent model or lora that can do the delicate touch of blood. It's usually all or nothing, or deformed lips.
Are you willing to prepare a dataset? Then we could train it :-)
ps. have you tried lowering the strength?
How many images would you need just out of curiosity?
I have trouble getting just the mouth and chest blood to show up without blood falling from the brow and eyes. Lowering the strength hasn't helped yet. If I mess around with strengths it usually either deforms the mouth or makes the blood disappear.
@CaptainKokomo well, for people I usually go with 20-25 images.
For concepts I tend to go with more, those blood models used around 50-60.
@malcolmrey I am happy to find try and find the images and I guess they need tag files too?
where do you want me to send them?
@CaptainKokomo no need for tagging,
usually google drive works best, but you can make for example an imgur album with them :)
this is coming up as an XL Lycoris for me
Interesting, it was definitely trained as SDXL Lora.
Still, it works, right?
Would it be ok to ask for this in ZIT?