• (9/26/2026): Distilled ckpt will not be updated. Use the new standalone acc LoRA here. After v2.4. All versions will be the "base" version (not distilled).

• Update log and version info: link.

RDBT [Anima]

A general finetuned base mode.

Dataset contains ~10k images, handpicked by professional amateur artists, captioned by latest LLM.

Some cover images look ridiculous; they're just for demonstration purposes for corner cases.

Useful links:

• RDBT | Digital Art: Beginner friendly 16-step ckpt. Has a default digital art style.

• RDBT | Original LoRA: If you're an advanced user and want to minmaxing everything.

• 16-step Acc LoRA: Still fast, but style friendly, less AI slop, compared to the official Turbo.

Usage:

Settings:

• Base version: has a suffix "base". CFG 4 and steps 24+.

• Distilled version (discontinued): CFG: 1. Steps: 16+.

Prompt:

Always specify @style in prompt, or use a style LoRA. Otherwise, you will get random/mixed style.

Unlike most finetuned models out there. This model does not have overfitted default style. Because the dataset is big enough. It's a feature not a bug (see below FAQs).

Quality tags:

Omit ALL quality tags. 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.

FAQs:

Why doesn't this model have a default style?

1. If a model has a "default" style (ignores prompt and is always active). We call it "overfitted". Technically, "default" style is not a feature, it's a bug. This means the training dataset is not big enough, and the model has lost its ability to generate other styles.

2. The goal of RDBT model is to reproduce styles, not one style, but every style, as accurate as possible. As some of you know, I use this model to aid in drawing. I need unique textures and details, instead of uniformed 2.5D AI slop style.

3. You decide what style you want, not me.

RDBT can't remove nor resist overwhelming Al slop effects

Too long, see: link.

Sharing merges using this model is not allowed.

This mode is a free and it will always be free. This "restriction" won't affect anyone. It's only aimed at those who steal others' models to sell.

Known model thieves: NukeA.I (selling this model behind paywall on tensorart).

Because he is such a jerk I wrote a story about it. Also contains a guide for trainers about "how to bake special trigger word into your model".