RedRayz/Any Anima (for LoRA training)
Modified Anima Base for LoRA training. It reduces unintended style changes(color/contrast shift) and improves precision. Designed for character or concept LoRA without style. Not tested for style Note: This model is not suitable for image generation. The model tends to generate ugly images. LoRA学習用のAnimaです。 意図しない画風の変化(色/コントラストのずれ)を軽減し、精度も改善します。 画風を含まないキャラクターまたはコンセプトLoRA向けです。 なお、データセットの画風の偏りが大きいと画風変化が増加します。 注意: このモデルは画像生成に適していません。モデルは醜い画像を生成する傾向があります。 Recommended training params Discrete Flow Shift: 1.5 LLM Adapter LR: 0 Timestep Sampling: Sigmoid(logit_normal) or Shift Train diffusion model on
| Author / organization | RedRayz |
|---|---|
| Downloads | 2.2K (as reported by Civitai) |
| Likes | 176 |
| Task | text-to-image |
| Created | 11 June 2026 |
| Last updated at source | — |
More from RedRayz
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.