Kani Biimu Style LoRA for AnimaAn artist-style LoRA trained for Anima Base 1.0, based on mature-period artworks associated with Kani Biimu.The LoRA mainly captures the overall illustration treatment, including facial rendering, eye design, linework, coloring, shading, and character presentation, while keeping character identity, clothing, pose, composition, and background reasonably controllable through normal prompts.Trigger: <code>@kanibiimuaf2020</code>Recommended LoRA strength: <code>0.8–1.0</code> Lower values can be used for a lighter style influence.Training information<ul><li>Base model: Anima Base 1.0</li><li>LoRA: Rank 32 / Alpha 32</li><li>Training resolution: 1024</li><li>Optimizer: ProdigyPlusScheduleFree</li><li>Text encoder / LLM adapter: frozen</li><li>Training images: 319</li><li>Validation images: 32</li><li>Released checkpoint: 2200 steps</li></ul>UsageUse the trigger together with ordinary Anima/Danbooru-style tags or natural-language prompts. Character, outfit, pose, expression, composition, and background should generally be described normally rather than relying on the LoRA itself.

Kani Biimu Style(mostly after 2020)

About this versionThis is the first public baseline release. It provides a reasonably stable reproduction of the target style and normal prompt usability, but it is not intended to be the final version. Some loss of style consistency can still occur in highly complicated scenes or unusually demanding prompts.

Files with SHA256: 63dea4da7a137aad717c6453bb49f29071d907132e60f050bd75b68b20e1bef4