Sign In

Krea2 FinalCut **Update** FP16 Version with 95% less "Wet Skin"

Download

1 variant available

fp16 SafeTensor

krea2_finalcut_turbo_V2_fp16.safetensors

Half precision, best balance • 23.88 GB

Verified:

Type
Checkpoint Trained
Stats

103

Reviews
Published

Aug 29, 2026

Base Model

Krea 2

Hash
AutoV2
35C8DDA833
default creator card background decoration
Reactions - 67715

67.7K

Downloads - 625805

625.8K

Generations - 4992225

5M

Krea 2 Training Contest Community Winner

License:

Krea2_00008_.png

Krea2 FinalCut

FP16

FP16 version has 95% reduction in wet skin and improved overall. For those who can use it, this is the best overall choice. Up to 2440x1440 native latent size.

Universal v2

Universal FP8 is my custom blockwise quantization that requires no metadata and should work for most users if Convrot is causing you issues. Convrot still has slightly better performance and should be used if possible.

V2 vs V1

While only marginally larger 13.8GB vs 12.2GB this training sees a massive seed to seed error reduction. Gradient Energy, Sharpness, Edge Density near equal. However a amazing 12.2% more unique RGB colors, in median average test.

  • INT8 Convrot is recommended for most users.

  • Official Comfy FP8 or INT8 Convrot scaling/quantization if not using universal

  • 100's of hours training.


SFW Image Comparison

NSFW Image Comparison