<h2 id="rdbt-or-digital-art">RDBT | Digital Art</h2>16-step ckpt optimized for digital anime art styles.Settings: steps: 16, cfg: 1.Mixed with:<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2356447">RDBT finetuned base</a>.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2967964/16-step-acc-lora-or-anima">RDBT 16-step acc LoRA</a>.</li><li>Some personal style/quality LoRAs. (Not released).</li></ul><hr />v3.0Based on RDBT v3.0.This should be the final release for Anima. It's time to switch to the MOSS Image. <s>(aka. the greatest anime model that has ever released).</s> Stay tuned.v2.4Based on RDBT v2.4.Strengths of merged styles/quality filters are greatly reduced. This is for better LoRA compatibility and built-in style accuracy.v2 baseBased on RDBT v2.0 base (without distillation).Settings: steps: 24+, cfg: 4+.v2 previewBased on RDBT v2.0 (preview). Compared to v1. It has a clean and consistent default effect. And much better details and more diverse due to new base.v1RDBT v1.3 finetuned base.<hr />Sharing merges using this model is not allowed. This is a free model and it will always free. This "restriction" won't affect anyone, it's only aimed at those who steal others' models, merge them, wipe all merge metadata and credits, and sell it as their own model.FYI: all my models have special trigger words and latent watermark.

RDBT | 16-step Digital Art

rdbtAnime_v2Base.safetensors

rdbt_anime_v2.0_base_anima_b1_ckpt.safetensors

Files with SHA256: a89282083a85ebd5374e603f279bc06c6f540370dd6b103a91d3cb7f12aeb9f4