This LoRA model has been trained on Kohya SS based on Akabur artstyle on Autism Mix SDXL checkpoint. As Akabur used different artsyle for its games, obtained graphics is mostly a mix of those original artstyles. This LoRA model could be use for graphic representation of women.
Note : While the training dataset includes works created by Akabur without direct authorization, this LoRA model's design ensures full compliance with copyright laws. This is achieved through a transformative training process that abstracts and generalizes Akabur artistic style rather than replicating specific copyrighted works. As a result, this LoRA model is able to generate innovative and original content inspired by Akabur artistic influences, while remaining within the boundaries of legal and ethical standards.
Description
FAQ
Comments (7)
Nice, love Akabur games. Have you seen Innocent witches? Its a sequel game for Witch Trainer, made by other developers. Has pretty similar style and ton of new arts and characters for your dataset. Hope you will like it
Innocent witches artstyle is effectively really similar to Witch Trainer style. Lead artist of Sad Crab company is Siserg (https://www.patreon.com/siserg/overview). And yes, It would surely be possible to train a Lora model on its artstyle and on Innocent witches artworks. I will add this to my todo list.
@GTsuya_Studio yeah, you can even merge 2 styles together for a bigger dataset
@Rating_Agent After creating the Siserg LoRA model, yes, I could try to mix it with the Akabur one.
Here is the Valerii Siserg artstyle LoRA model : https://civitai.com/models/906997
@Rating_Agent Here is the mixed LoRA model : https://civitai.com/models/910132
@GTsuya_Studio You are awesome!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.