Sign In

Attack on Titan Season 4 LoRA

64
577
9
Verified:
SafeTensor
Type
LoRA
Stats
577
Reviews
Published
Mar 7, 2023
Base Model
SD 1.5
Training Images
Download
Hash
AutoV2
4B5906B06B
default creator card background decoration
Vermath's Avatar
Vermath

Creating these models takes time, money, and effort and it's great when that effort is rewarded. If you really like it you can buy me a coffee ā˜•.

If you like this model please consider checking out some of my other projects. I've made LoRAs to emulate the style of Super Crooks, Fullmetal Alchemist, Death Note, Spider-Man: Into the Spider-Verse, Cyberpunk: Edgerunners, Trigun: Stampede, Attack on Titan Season 1, and Chainsaw Man.

This is Just a LORA that emulates the style of the show. Depending on the subject you're trying to create, you'll need to play around with the strength. 0.65 strength seems to work best. All these images were created with Deliberate as the model. X-formers is on. This model is a bit horny when you ask for full body. Be sure to include negative prompts to tamp down on that if you don't want it.

As with all my models the training data is attached. Use this data however you like. I only ask that if you utilize the images I've collected you credit both me and the artists who created them.

I trained it on around 14,000 still images from the show, so it's quite good at emulating the style. No need to give it a particularly lengthy prompt these images were generated with really simple prompts.

This LORA mixes well with others as well. So if you want a trained character/person in the Attack on Titan Season 4 style that's possible. If you have any questions, comments, or concerns feel free to send me a message. I'm happy to chat about my methodology.