tags:
- stable-diffusion
- text-to-image
license: creativeml-openrail-m
v1.1: xivcine-style-1-1.ckpt
token/class: xivcine style
If using the newer version of this model, use "xivcine style" in your prompt. The following images were made with a generic prompt like "portrait, xivcine style, action pose, [hyper realistic], colorful background, bokeh, detailed, cinematic, 3d octane render, 4k, concept art, trending on artstation"
Faces will trend toward the following style with a nonspecific prompt:
Armor styles can be tweaked effectively with variations in X/Y plots:
Landscapes will trend toward the following style with a nonspecific prompt:
Merging with other checkpoints can produce entirely unique styles while maintaining an ornate armor style:
These are examples of how elements combine in various mergers:
Future updates will be aimed at training specific pieces of armor, etc. The intent is to create gposes in the style of FFXIV trailers.
v1.0: xivcine_person_v1.ckpt
token/class: xivcine person
This is my first attempt at any of this. It is far from a finished model, but it makes some cool landscapes.
The class should probably be "style" or something, but I kept screwing up the process. So it's person for now.
The images below were prompted with the standard "cinematic, colorful background, concept art, dramatic lighting, high detail, highly detailed, hyper realistic, intricate, intricate sharp details, octane render, smooth, studio lighting, trending on artstation" plus forest or castle.
