v0.27: Improved stability (might be overcooked) and details/textures.

If you want to try latest unstable version, I upload them as LoRA at here, so I won't have to upload and you won't have to download a 4gib file every time.

See Update Log section for all versions.

RDBT [Anima]

Finetuned, then distilled. It delivers faster speed and higher aesthetics with only 12 NFEs, 5x faster than base model (60 NFEs).

Sharing merges using this model is not allowed.

Usage:

Settings:

• Sampler: "euler_a" "euler" "er_sde". (from smooth to high variance)

• Steps: 8, 12 or 24. Scheduler: simple. Important: training timestamps are fixed. Other inference timestamps might not work.

• CFG scale: 1~2. Cover images are all without CFG (CFG 1). You can enable CFG (CFG >1) if you need higher prompt adherence (e.g. style is too weak).

Prompt

Prefer natural language prompt. Prompt structure: style, subject, action, background.

This model does not provide a stable default style. You should always prompt style. Or use a style LoRA. I don't like bake a strong style into the model, I prefer having choices.

There are two "rough" trigger words:

• "digital anime illustration": 2d anime.

• "digital art", 2d art but not anime, mostly digital art. (not many samples)

Quality tags:

You can omit all the quality tags. 1) The quality of training data is higher than "masterpiece". 2) Quality tags have been reinforced during distillation. Thus they don't have noticeable effects.

Same as negative tags. If you use cfg, there is no need to dump "score_1, blurry, worst quality, jpeg artifacts, extra arms,... x100 words" in your negative prompt. Those things have been distilled out.

Released models

RDBT LoRAs: Released as LoRA. For better distribution efficiency.

Update Logs

(4/23/2026) v0.27: Improved stability, details.

(4/18/2026) v0.25: It's based on anima p3.

Previous testing versions, see RDBT LoRAs