Death Note Lora

Just a LORA that emulates the style of the anime Death Note. Strength of 1.0 should work fine for most stuff, but lowering the strength can help if it only throws characters from the show at you. The LORA doesn't like creating people of color without lowering the strength, but is fully capable of doing so.

It does have a hard time reproducing L. I could fix this by manually captioning shots of him from the show, but that's a bit more work than I'm willing to put in. Maybe you'll be able to pull him out with a little creative prompting.

I trained it on around 5,000 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 Death Note 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.

If you really like it you can buy me a coffee, totally unnecessary, but always welcome. I do this for fun.

https://www.buymeacoffee.com/vermath