(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. Gives you the quality as it should be. From wallpaper level digital art, to 5-min sketch.
Dataset contains ~10k images, handpicked by professional amateur artists, captioned by LLM. The criteria for evaluation are not visual appeal, but the painting technique and the level of completion.
Some cover images look ridiculous; they're just for demonstration purposes for corner cases.
Useful links:
RDBT | Digital Art: Beginner friendly 16-step ckpt. Optimized for digital art style.
RDBT | Original LoRA: If you're an advanced user and want to minmaxing everything.
16-step Acc LoRA: Style friendly, less AI slop, compared to the official Turbo.
Usage:
Settings:
Base version: CFG 4 and steps 24+.
Distilled version (8s, 16s, discontinued): CFG: 1. Steps: 8 or 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:
You don't need 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?
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.
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.
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".
Description
FAQ
Comments (3)
What's the benefit of this over regular Anima? Just aesthetic?
speed
Fine-tuned checkpoints such as this generally perform better than the base model depending on what do you want to make: Realism, cartoonish, Anime style, etc. It is possible to get good results with the base Anima Preview-3 but its generally harder without adding stuff like "masterpice,best quality," and "low quality, bad hands" on the negatives, so that's why people usually look for fine-tunes to get better without having your prompts become a giant wall of text.
I have been trying this checkpoint and apart from the huge generation speed boost from generating at 1-3 cfg and 8-16 steps, it has been able to work well with an anime style Anima Preview-2 LoRA (haven't trained on Preview 3 yet) that I'm working on and it gets very nice results keeping the anime aesthetic from the LoRA with the added bonus of fast generation.