RDBT Anime

RDBT finetuned base model (https://civitai.red/models/2356447) + additional style LoRAs.

Settings: steps: 16+, cfg: 1, scheduler simple:, sampler: euler (highest diversity) or er_sdr (estimated 3rd order, lower diversity but better stability),

Omit ALL quality tags. You don't need those. The fine-tuning dataset has higher quality than "masterpiece". Thus quality tags don't have effects. Omitting those redundant tokens allows LLM to pay more attention on other words.

Built-in style trigger words: @digital art

v2

RDBT v2.0 finetuned base (preview), and 1 private style LoRA. Compared to v1. It has a clean and consistent default effect. And much better details and more diverse due to new base.

v1

RDBT v1.3 finetuned base, and some private LoRAs.

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.