Krea 2 [fp8/nvfp4 mixed precision]

Updated note:

the "txtfusion.projector" and surrounding layers (aka. where people are trying to remove the filter) in both nvfp4 and fp8 ckpt, are still in original bf16 precision. You don't have to worry the precision.

Krea 2 in ComfyUI mixed precision format.

Converted from official bf16 ckpt.

Compared to official fully quantized ckpt, this ckpt keeps some important layers in original bf16 format. Thus it's a little bit larger, has a little bit better precision.

For nvfp4, ckpt size is ~9.5GiB, should be good for GPU that has 12GiB VRAM, without swapping.

For scaled fp8, ckpt size is ~14.5GiB, should be good for GPU that has 16GiB VRAM, without swapping.

ComfyUI supports this format natively, you don't have to config anything.