@nekoshoko Style

Initial. The LoRA was trained on 100 images from 2024 through 2026.The dataset consists of:<ul><li><code>year 2026</code>: 51 images</li><li><code>year 2025</code>: 35 images</li><li><code>year 2024</code>: 14 images</li></ul>The latter half of the showcase features comparisons between this LoRA, <a target="_blank" rel="ugc" href="https://civitai.red/models/2787321/nekoshoko?modelVersionId=3192812">NekosokoStyleAnima.safetensors</a> by Ai_Corn (trigger: <code>@nekoshokostyle</code>), and no LoRA—that is, the artist's style as learned by Anima Turbo-v1.1 itself. <code>dim32/alpha32, CAME, UNet LR 3e-05, cosine 1,000 steps. 100 images (1024²)</code> 😭

Files with SHA256: 1142f34fa9c0780b038b70a4bed1910afa5b6eead25d9e43a49215045b4cfbe3