tags:
- stable-diffusion
- text-to-image
license: creativeml-openrail-m
v1.1: xivcine-style-1-1.ckpt
token/class: xivcine style
All training images are from the trailers of the critically acclaimed MMORPG Final Fantasy XIV, which has a free trial that includes the entirety of A Realm Reborn AND the award-winning Heavensward expansion up to level 60 with no restrictions on playtime. Sign up, and enjoy Eorzea today! https://secure.square-enix.com/account/app/svc/ffxivregister?lng=en-gb. This model hopes to replicate that style. (Use recruitment code D8PE6VFZ if you like my model and decide to play the game. /smile)
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 this style with a non-specific prompt:
Armor styles can be tweaked effectively with variations in X/Y plots:
Landscapes will trend toward this style with a non-specific 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 model is just for fun. It makes deep fried images with bright colors and cool lights if you want it to, but it won't listen to your prompts very well.
The images below were prompted with a generic prompt like "xivcine person, 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.
License
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
- You can't use the model to deliberately produce nor share illegal or harmful outputs or content
- The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
- You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here