<a target="_blank" rel="ugc" href="https://twitter.com/aza_wind">Azasuke</a> style (LoRA) for <a target="_blank" rel="ugc" href="https://civarchive.com/models/66/anything-v3">Anything v3</a> compatible models and different versions. I suggest to use LoRA weight around 0.6 to obtain a good rendering.This model is an @ritcher1 request.If you like this model, please add a small review or a sample of your work to share with the others all the possibility of this model.

Azasuke style (LoRA)

Trigger : &lt;lora:azazuke:0.6&gt;

Azazuke-000081.safetensors

Azasuke - Anything V3 (LoRA)

This LoRA model has been trained on Kohya SS based on <a target="_blank" rel="ugc" href="https://x.com/aza_wind">Azasuke</a> artstyle on Anything v3.0 checkpoint. Obtained graphics are close to the original artstyle. This LoRA model could be use for anime representation of women.Note : This model is a new release of an old LoRA model that I have initialy released on my <a target="_blank" rel="ugc" href="https://subscribestar.adult/gtsuyastudio">SubscribeStar</a> account.Note : While the training dataset includes works created by <a target="_blank" rel="ugc" href="https://x.com/aza_wind">Azasuke</a> 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 <a target="_blank" rel="ugc" href="https://x.com/aza_wind">Azasuke</a> artistic style rather than replicating specific copyrighted works. As a result, this LoRA model is able to generate innovative and original content inspired by <a target="_blank" rel="ugc" href="https://x.com/aza_wind">Azasuke</a> artistic influences, while remaining within the boundaries of legal and ethical standards.

Files with SHA256: e4a6e718d0eae94f3405933bd78e2356b11c07e1bd818ce945d8cf2cc863db50