RDBT | Anima

v1.0: I think it's time to release v1.0. I've migrated to the krea2 model (never imagined that krea2 would be my next choice...). Fine-tuning the anima model is really fun.

I also uploaded int8 version for ComfyUI hardware int8 (labeled as fp8).

About 8/16 step distillation:

• 8-step has higher stability. (standard "turbo" model?).

• 16-step (same as previous versions) has higher diversity and more dynamic details, less sloppy but less stable, more small errors. (Creative also means chaotic. But I still prefer this one because anime model needs a little bit chaotic)

• FYI: comparison images are uploaded as 16-step version showcase images.

• FYI: for reference, official anima turbo is 4-step distillation, means highest stability and lowest diversity.

RDBT [Anima]

This is a finetuned model with 10k high aesthetic images paired with natural language captions from LLM. Then distilled to further improve quality and stability. Dataset does not contain any shiny plastic glossy AI image.

It's not overfitted and doesn't have a default style. I use it as a clean starting point to stack more style LoRAs. I can stack whatever I want and get exactly what I stacked.

See this page for update log.

For advanced users: The RDBT model is trained as LoRA natively. See this page for original LoRA, update more frequently.

This model is based on:

• prefix with ym: AnimaYume (hf link) (civitai link).

• prefix with b,p: Anima pretrained (hf link)

Sharing merges using this model is not allowed. This "restriction" won't affect anyone. It's only aimed at those who steal others' models to sell.

If someone is selling this model as their own, I'm happy to list them here so everyone knows.

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".

Usage:

Settings:

CFG scale: 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.

Steps: 16+

Prompt:

Always specify style, or use a style LoRA. Otherwise, you will get random/mixed style. This is a feature, not a bug. This model does not provide overfitted default style.

Quality tags:

It's recommended to omit ALL quality tags. The fine-tuning dataset has higher quality than "masterpiece". Thus they don't have noticeable effects. Omitting those redundant tokens allows LLM to pay more attention on other words

Training settings

All captions are NL from Google Gemini.

Optimizer: adamw, constant lr 0.00002, weight decay 0.1, batch size 16.

LoRA rank/alpha 24.

Timesteps shift 3.

Block 0-2 and adaln linear layers are skipped.