<a target="_blank" rel="ugc" href="https://danbooru.donmai.us/artists/137693">Artist page</a>

@kagimushi / eisu (eith) Style

Initial.For v0.0.0, I used 93 training images, primarily consisting of images from 2016 through 2025 on Danbooru.Below is a comparison of the training configurations with the already-released <code>Eisu (Eith)</code><a target="_blank" rel="ugc" href="https://civitai.red/models/2773923/eisu-eith?modelVersionId=3123402"> LoRA by StellaDeCorbin</a>.Eisu (Eith): <code>dim20/alpha20, AdamW8bit, UNet LR 1e-04, cosine_with_restart[*1] 4080 steps, warmup 100, 34 images (1024²)</code>v0.0.0 (this LoRA): <code>dim32/alpha32, CAME, UNet LR 3e-05, cosine 930 steps, 93 images (1024²)</code>[*1] The number of restarts and the details of the training images used by StellaDeCorbin are unknown.

Files with SHA256: 8bd1a596b7fd827b8005ae5dd2c9ed44c95e46a4f67468c73a0a72ab4160cebd