This page contains RDBT full model, in fp16 and fp8. Also a fp8 "anima preview", just for convenience.
RDBT [fp16 + fp8]
Finetuned anima. More info: https://civarchive.com/models/2364703
Beware: it needs different settings. Read the docs above!
FYI:
It was trained as a fp32 LoRA. If you already have the "preview" anima base model, you can just download and load the LoRA.
This fp16 model just merged that fp32 LoRA, and mathematically has tiny little bit higher precision than bf16.
preview [fp8]:
fp8 anima preview
About fp8 models:
Quantized fp8 models in ComfyUI format.
Model file contains calibrated metadata for hardware fp8 linear. If you GPU supports it (aka. rtx 4000 and later), ComfyUI will use hardware fp8 automatically, which might (blame Nvidia) be a little bit faster. More about ComfyUI fp8, see ComfyUI docs TensorCoreFP8Layout.
Just ignore ComfyUI log warnings about tons of keys not loaded. Its a small bug in ComfyUI, it checked wrong keys. Those keys are metadata and they are loaded.