RDBT | Digital Art
Fast 16-step model with high aesthetics digital art style (aka. my taste.). Features: Fine outlines, strong post-processed lighting, highly detailed/realistic textures.
Note: model has been distilled for 4x faster generation (16 NFEs vs 60).
Use steps: 16, cfg: 1 (or 1~1.5 for better prompt adherence, but 2x slower). Unless it's the "base".
Do not add other "turbo" or "dmd2" LoRA.
Links:
v2.4
Based on RDBT v2.4.
Strengths of merged styles/quality filters are greatly reduced. This is for better LoRA compatibility and built-in style accuracy.
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.





