Trained on my art, just like istolemyownart and istolemyownwheat, but this time as a LORA so the filesize is much smaller and has higher quality, too bad the actual style is still the same.
tl;dr
Use istolemyownlora3.safetensors, it's the better one and gets 99% 1:1 my style, for better or worse, better than what I can do manually honestly. The other ones were trained first with less optimal settings
How to use a LORA?
Place it in "\stable-diffusion-webui\models\Lora". Don't see the folder? git pull
Load any model, preferably an anime model. All these examples are made with Meadmix, I found it gives good results but any Anything based model should work.
Use the purple icon under the generate button to bring up the LORA list or just add it to your prompt like this <lora:istolemyownlora:1>, change the number to reduce the strenght like <lora:istolemyownlora:0.5>
Combine it with other LORAs to make this style not as bad.
Examples for istolemyownlora3.safetensors (better settings, 5 repeats)
Examples for istolemyownlora2.safetensors (5 repeats)
Examples for istolemyownlora.safetensors (2 repeats)
Terms and conditions
Does this give me and everyone else the rights over your entire art and dataset and all your future artworks both made manually and with AI?
No
Can I use anything generated with this Lora for whatever I want though?
Fair use and derivative works
Can I sell your LORAs?
No
Can I merge them to another model and distribute it?
Waste of gigabytes but credit the original so people can at least download the smaller file.
Do I own that model?
No
Can I use this to impersonate you and make bad faith arguments to make MY stunning and brave anti AI argument win over your disgusting pro AI argument, chud?
roflcopter
Well your still art sucks!
Hai
- Downloads last month
- 248