Updated: May 9, 2026
base model
RDBT [Anima]
Distilled model (aka. "turbo"). 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.
See Update Log section for version info.
See this page for standalone LoRA.
Example: Original img. Original prompt.
Usage:
Settings (different from anima base model):
Steps: 8, 12 or 24. Scheduler: simple. Note: Those two settings control the timestamps during inference. I use a fixed timestamps during training. Other inference timestamps might not work.
CFG scale: 1~4. Cover images are without CFG (CFG 1). You can enable CFG (CFG >1) if you need higher prompt adherence (e.g. need higher style effect). High CFG needs "RenormCFG" node and set "renorm_cfg" to ~1.1 to avoid oversaturation.
Prompt
Specific style is required! This model does not provide a default style. You should always prompt specific style. Or use a style LoRA. Otherwise, you will get random/mixed style. This is a feature, not a bug. I use this model as a starting point to stack more style LoRA.
There are some "rough" trigger words, they are trained so they have effect, but they are not "specific style":
"digital anime illustration": common 2d anime.
"digital art", 2d art but not anime, mostly digital art. (not many samples)
"anime sketch": simplified/unfinished anime drawing. (not many samples)
FAQ: Base model built-in styles have less effect. This is a common problem for fringe content + distilled model + no cfg. You can:
Enable and use higher CFG. (2x slower)
Find/train a style LoRA.
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.
Update Logs
(TBD): v0.31:
No more green-ish, color shifting.
Second-order sampling. Should have improved quality.
Trigger words have been reclassified to avoid model learning a unified style. New:
@anime sketch: Low complexity. Rough outlines.
@digital anime illustration: Typical "anime". Clear and fine outlines. General complexity.
@digital art: More complex lighting than typical "anime" illustrations.
@cinematic digital art: More lighting effects.
As well as traditional media:
@pencil drawing and hatching
@watercolor painting
@ink wash painting: Not many samples.
@oil painting: Not many samples.
(4/27/2026): v0.29: Distillation algorithm was almost completely rewritten.
Increased diversity. Different seeds now can generate more different images. This also improved lighting range, styles and LoRA compatibility.
Better details. This version can squeeze every single pixel out of the VAE.
(4/23/2026) v0.27: Improved stability, details.
(4/18/2026) v0.25: It's based on anima p3.
Previous testing versions, see this page