See-Krea2

Plain INT8, per-channel scaled — 13.2 GB. Same size as the ConvRot build, slightly faster, slightly less accurate.This is Genesis-int8_convrot without the rotation step. No activation rotation at inference means a little less work per matrix multiply.The cost shows up unevenly: 1.55 % average weight deviation, but it ranges from 0.9 % on well-behaved layers up to 3.1 % on the ones with strong outliers. ConvRot exists precisely to flatten that spread.Runs on: any GPU with a working INT8 path. Pick this if: throughput matters more to you than the last bit of fidelity, or if your ComfyUI build does not handle ConvRot INT8. Otherwise take Genesis-int8_convrot — same size, better numbers.Settings: 8 steps · CFG 1.0 · euler · simple · ~1 MP.

See-Krea2-Genesis_int8.safetensors

Genesis-int8

Genesis-V2

Text Encoders

Genesis-int4_convrot

Genesis-nvfp4

Genesis-int8_convrot

Genesis-fp8_scaled

Genesis-BF16

Files with SHA256: 13f65046798878ebfd5c71e4f6a60dc13d4fbbbbfd0bc0cd515210a8f456168c