FIRST OF ALL: I ASK THAT IF YOU USE MY LORA, PLEASE DO NOT PUBLISH NSFW CONTENT THAT IS DAMAGING, ABUSIVE, DEGRADING, INSULTING, HUMILIATING, OR OFFENSIVE TO HUMAN DIGNITY. I DID NOT CREATE MY LORAS FOR PEOPLE TO DO SUCH THINGS. PLEASE, BE RESPECTFUL.
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
This new model aims to adopt an artistic style characterized by the addition of artistic qualities such as bold brushstrokes and ink; or in the case of the "Illustrious" models, it seeks to enhance their ability to adopt various types of Ink Art imagery. The LoRa is capable of generating images similar to the sample images with relative ease.
IMPORTANT: This model has been trained with several types of ink art, covering themes ranging from "kawaii" to more formal styles like traditional art, and even modern visual art. It does not have a specific trigger word but instead allows for multiple options. You can use whichever words you prefer to adopt the aesthetic you want, just be careful not to overload the prompt or write contradictory words. This does not mean that you cannot use several trigger words in the same message; in fact, it is recommended that you do use several in order to achieve more interesting results. (It is recommended to place the trigger words not only at the end, but it's better to place them little by little along the prompt).
NOTE: Feel free to try out this LoRa as much as you like, and if you wish, you are totally free to write your opinions and recommendations in the comments. It would be greatly appreciated.
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Suggested Specifications:
Image size: 768x1152. If you use an Upscaler and want to save credits, you can use the image size of 512x768 at a 2x resolution (this gives good quality and is relatively cheap in credits).
Sampling Steps: 20 to 25.
VAE: Automatic.
Sampling Method: Euler A or Euler; both in "normal" mode (you can use any sampler you prefer, just make sure to use the TA information table for the best results).
CFG Scale: 7 to 10.
Upscaler: R-ESRGAN 4x+ Anime6B.
AD Detailer: Optional, based on your preference.
Base Model: The LoRa has been tested with various checkpoints, but it has been noted that each one has unique characteristics that influence the final product. If you want to create silhouette images, it is recommended to use "Soul Shine Anime EX | FuturEvoLab." On the other hand, if you want to get anime-oriented images with ink finishes or draw traditional Asian-style images, you can use "Nova Anime XL - Illustrious v2.0." Additionally, if you want to experiment, you can use other checkpoints. (In any case, you are free to use the base model you prefer).
Extra (IMPORTANT): This LoRa will only work if you specify the type of ink art you want (e.g., brushstrokes, ink drops, sumi-e, colored ink, monochrome ink, etc.).
Please, I ask that you do not attempt to use the images generated with the style of this LoRa to create "copies" of it. Creating this LoRa took time and resources, and it has been difficult to train. It may not be the best LoRa in the world, but I just ask for a little respect 😥. Thank you for understanding.
Well, lastly, I hope this model helps you create the images you want and that you enjoy it. If you have any questions, feel free to write in the comments.