I made Jack Cayman. Well here's some small info about him:

"Jack Cayman is the protagonist of the video game series "MadWorld" and "Anarchy Reigns," developed by PlatinumGames. He is a large, muscular man with a distinctive appearance, characterized by his black leather outfit, cybernetic right arm, and a chainsaw attached to his arm. Jack is known for his brutal combat style, deep voice, and tough, no-nonsense attitude. He often finds himself in violent and chaotic situations, where he uses his chainsaw and fighting skills to battle enemies." --say chatGPT whatever lol

Jack Cayman is muscular man and idk why I made this. I developed this LoRA quite long time. Dataset seems really hard to come by. So, I need to processing the image.

Trigger Word

jack_cayman

Supporting Trigger Word

In this model there's some trigger word that you can use for creating JD Fenix

//WORDS

jack_cayman --> main prompt
jacket --> his armor
goggles, goggles on head --> his signature orange goggles that appear in Anarchy Reigns
short hair --> his signature short hair
white hair --> his signature white hair

//NOTES

1. This model has problem when prompting his signature jacket. It quite wonky one.
2. This model showcase mostly Jack Cayman without his cybernetic right arm.

Settings I used:

• Sampling Method:

  • DPM++ 2M SDE Karras

  • DPM++ 2M Karras

• CFG Steps: 5 - 7

• Sampling Steps: 20 - 25

• Resolution: 768x960

  • All of sample image that I use is based on 768x768 with HiRES + Fix applied and upscaled by 1.3x and denoising strength of 0.55 - 0.6 using sampler Latent, R-ESRGAN 4x, or R-ESRGAN 4x Anime 6B depending the type of image. Then I upscaled the final image 4x by using ESRGAN-4x, R-ESRGAN 4x, and R-ESRGAN 4x Anime 6B upscaler depending what kind image that I handled.

  • No inpainting, regional prompter, controlNet I use in all my sample image. All of them were built in from SD Checkpoint + Text Embedding.

• Weight: 0.6 - 0.8