RDBT - Anima

RDBT [Anima]

Finetuned + guidance distilled.

This is the original LoRA file. If you have the pretrained base ckpt, you can download this.

See the main page for more info. This page for update log.

Sharing merges using this model is not allowed.

Random experiment, random quality. New version != better version. Feel free to leave feedback.

Which base model should I use:

• Use the pretrained anima if you don't know where to start. This is highly recommended.

• Use "trained" base model if you feel lucky. Add different flavors.

• "Merged" base model usually is not recommended, as it's weights might be very messy, has overfitted AI style and turbo lora merged in. This LoRA might not work on such base model.

• FYI: If model can generate image (not deformed) with CFG < 3, then it's distilled. Do not trust model page, test yourself.