RDBT | Anima2.9B

About Anima 2.9B: https://huggingface.co/Gazingstars123/Anima-2.9B

Temporary note and FAQ:

The "distillation add-on" is not a "turbo" model. The unwritten definition of "turbo" model is 8-step + aesthetic RL + many black magic. This LoRA is just a basic distillation LoRA that mimics what the original model would generate. A "turbo" model is too much for me.

You don't need to add quality tags in prompt. The finetuning dataset has higher quality than "masterpiece".

Versions:

v2 distillation addon:

It works, most of the time. Settings: CFG 1, 16 steps.

You should (probably need to) load both this add-on LoRA and the "v2" finetuned LoRA.

v2:

Finetuned LoRA.

Sharing merges using this model is not allowed. This is a free model and it will always free. This "restriction" only aimed at those fake base model creaters who steal others' models to sell.

FYI: all my models have special trigger words and latent watermark.