What's this LoRA
This is a LoRA trained on a single image, increasing the weight tend to make the image monochrome and giving it a dark vibe. This is part of my "shot" series of lightweight LoRAs trained on single images. You need to lower the weight, otherwise all the images will look similar (check the comparison picture).
All the images in the examples have been created using my custom model (https://civarchive.com/models/24149) and this LoRA only. All the examples have been created using the hires-fix or by creating the base 512x768 image, upscaling it to 1.5 and the applying the same prompt again as img2img
All the pictures have been created using a weight between 0.6-0.8. If you want the picture to be in color, make sure to use (monochrome:1.4) in the negative prompt.
The LoRA works also on NSFW (check last examples).
Image Used
The LoRA was trained using the following image (also AI generated):
Guides
Learn how to create pictures like mine with my step-by-step tutorials:
Support
If you want to support my work, you can check out my music here:
https://inzaniak.bandcamp.com/
You can also check my AI Art accounts, where you'll find daily pictures made with my models (and previews of new ones coming):
Description
FAQ
Comments (6)
这是什么版本的ai
Dude, you might have uploaded something different lmao, check ur 1shot lora and any 1-6shot loras.
Hi! I've checked the file, and it's the correct LoRA. Am I missing something?
Hi Hello !!
I'm trying to run an experiment on the different way to tag a LoRA (specifically a 1-image-LoRA).
I used to love your work as they are extremely good and -because it's my first time doing it- I wanted to ask you about the settings you're using to create these kinds of LoRA.
If you could recommend me the most basics settings you're personnaly using I'll be very happy to run my tagging experiment ^u^
PS: sorry if this was asked you hundreds of time through social medias ^^"
Hi! You can find the basic settings on my guide here: Guide (inzaniak.github.io).
@Inzaniak Oooh yes that's perfect !! Thanks a lot ^u^