@gemba (dlfms75) 2026-2025 Style

Initial.The LoRA was trained on 100 images from 2025 and 2026.The dataset consists of:<ul><li><code>year 2026</code>: 39 images</li><li><code>year 2025</code>: 61 images</li></ul>To encourage the LoRA to learn a wider variety of compositions, similar images, such as alternate costume versions, were limited to a maximum of two per set.dim32/alpha32, CAME, UNet LR 3e-05, cosine 900 steps, 100 images (1024²)

Files with SHA256: 01873627896c6648fe0d762a14826a97adf7e1dfd45910c6fe577ef5e217577a