Sign In

FinalCut (SDXL)

168

1.4k

4.5k

41

Verified:

SafeTensor

Type

Checkpoint Trained

Stats

661

1.3k

1.7k

Reviews

Published

Aug 16, 2025

Base Model

SDXL 1.0

Training

Steps: 100,000
Epochs: 10

Usage Tips

Clip Skip: 2

Hash

AutoV2
B334ED89C3
SDXL Training Contest Participant
Felldude's Avatar

Felldude

FinalCut (SDXL)

I put 50k toward the 13GB being hosted next week

Onsite Recommend Settings, 16 Steps, CFG 5, DPM++ 2M

High Rez Fix, Image to Image at 0.7-0.8 remove fixed seed.

Do not use 20yo or 20 year old as Llama was used for image captioning. MILF was added. Use of Old is like using GILF

  • 13GB model has better general prompt adherence, while the 8GB model is focused on skin detail and anatomy text prompting.

  • Full FP32 Training

  • 8GB model Mixed BF16/FP16/FP32 storage ensures highest accuracy while reducing model size.

  • All cover example images shown natively at 1024x1536, however this model will benefit greatly from 1280x1920 image to image up-scaling at 0.7 and has been trained for such.