RDBT [Anima]

See the main page for more info. (ckpt version, usage ...)

See this page for update log.

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.

This is the original LoRA file. If you have the base model of the LoRA already, you can download this LoRA.

Why LoRA instead of FFT (Full Fine-Tuning)? I don't have millions of images, there is no need to FFT. A LoRA is enough.

Links to the LoRA base models:

• AnimaYume (ym) (hf link) (civitai link).

• Anima pretrained (b1,p3,p2,p1) (hf link)

Although this is a LoRA but this does NOT mean it works on arbitrary base model. Don't mismatch base models. If you don't know how LoRA works or what this means, use the ckpt version.

"Merged" model usually is NOT recommended.

• It's weights might be very messy. Probably merged different pretrained versions. A nightmare for LoRAs.

• Has overfitted AI style. Surpasses everything.

• Has turbo lora merged in. Stacking distilled models is tricky and sometimes it won't work as you expected. FYI: If model can generate image (not deformed) with CFG < 2, then it's distilled (merged turbo lora). Do not trust model page, test yourself.