RDBT | Digital Art
Fast 16-step model with a default digital art style (aka. my taste.).
Note: model has been distilled for 4x faster generation (16 NFEs vs 60) (except the "base" version).
Use steps: 16, cfg: 1.
Do not add other "turbo" or "dmd2" LoRA.
Mixed with:
RDBT finetuned base. (10k images general finetune)
Some personal style/quality LoRAs. (Not released).
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.
v2 base
Based on RDBT v2.0 base (without distillation).
Settings: steps: 24+, cfg: 4+.
v2 preview
Based 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.
v1
RDBT v1.3 finetuned base.
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.
Description
FAQ
Comments (2)
Do you plan to upload the int8 version of v2 base?
thank you for your hard work 🙏