Sign In
homemodelsimagesvideos3D Modelsarticlescomicschallengesupdatesshop

RDBT | Anima

Updated: Aug 26, 2026

base model

Download

1 variant available

bf16 SafeTensor

rdbt_anima_b1_v0.37.1_ckpt.safetensors

BF16, good balance • 3.89 GB

Verified:

Type
Checkpoint Trained
Stats

1,304

Reviews

(83)

Published

May 25, 2026

Base Model

Anima

Hash
AutoV2
14536A4214
default creator card background decoration
Base Model Creators position #8

#8

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

out-_00646_.webp

RDBT [Anima]

This is a general finetuned + distilled model.

Less artifacts and errors, better prompt adherence. I use the model as a clean starting point to stack more LoRAs. I can get the style exactly as it should be.

Dataset contains ~10k handpicked images. NL captions from LLM. Accurate body/hands anatomy. Does not contain any shiny plastic glossy AI image.

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

Update log and version info: link.

Original LoRA: link. For advanced users: RDBT model is trained as LoRA natively. You don't need to download this full ckpt.

My Turbo LoRA for RDBT: link. I won't recommend the official Turbo model because it's very sloppy and overwrites style LoRA. I made my own.

Links to base model:

For those who don't want to stack style LoRAs and is looking for a out-of-the-box ckpt with high aesthetic style: RDBT | Anime, based on RDBT, and optimized for high quality digital art.

Usage:

Settings:

  • CFG: 1~3. This model has been distilled. You can disable CFG (CFG 1) and run the model 2x faster. Cover images are without CFG for demonstration. "RenormCFG" node is highly recommended if CFG is enabled (CFG > 1), set "renorm_cfg" value to 1.1.

  • Steps: 16+

  • Sampler: Euler (best diversity), Euler a/er_sde etc. (better stability)

  • Res: 1MP

Prompt:

Always specify style in prompt, or use a style LoRA. Otherwise, you will get random/mixed style. This is a feature, not a bug. This model does NOT have overfitted default style (which ignores prompt and is always active).

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.

FAQ:

About distillation:

Compared to the official turbo model, my distillation has very high diversity (seed, style diversity, etc.), and is more compatible with style LoRAs (it won't add a quality filter which changes/overwrites the style drastically).

I didn't name it "turbo" because the unwritten definition of "turbo" model is 8-step + aesthetic RL + many black magic. My distillation is just a basic distillation that mimics what the original model would generate. A real "turbo" model is too much for me.

Why not bake a default style?

If a model has a default style, this means whether you prompted it or not, the style is always active. This is called "overfitted", this not a feature, it's a bug.

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).

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