Download
2 variants available
fp8 SafeTensor
uwumerge_checkpoint_v2_fp8.safetensors
8-bit, smaller file (pruned) • 3.31 GB
Verified: 6 months ago
SafeTensor
fp8
uwumerge_checkpoint_v2_fp8.safetensors
8-bit, smaller file (pruned)
Verified: 6 months ago
3500 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
6.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
(55)
Feb 14, 2026
v2.0 is built on the new improved uwustyle v4.0.
I think this version has more personality and depth.
This version also handles CFG above >7.0 better :)
Show more

2130 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
5320 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
License:
Illustrious LicenseFurry/feral checkpoint with a default style influenced by my uwustyle LoRa, emphasizing strong outlines and colors, but still being flexible.
Fast versions are optimized for low CFG and 6-12 step generation. I use a blend of DMD2 and SDXL-Flash that I think preserves the style well, but there will still be differences from base versions.
FP8 pruned model stores the UNet and CLIP models in FP8, but the VAE in FP16. This reduces the byte size by almost half in return for a slight quality loss, but most likely won't support hardware-accelerated FP8 inference (so it won't generate faster).
Due to the contrast & saturation enhancement of the VAE, I personally use vaemix v6 (or similar anime/toon VAE) for the hires-fix step to avoid the excessive contrast and color "burn" that can sometimes happen.
