Sign In

Zekrom

103
592
4.4k
40
Verified:
SafeTensor
Type
LoRA
Stats
592
4,423
Reviews
Published
Nov 6, 2023
Base Model
SD 1.5
Training
Steps: 2,000
Epochs: 8
Usage Tips
Clip Skip: 1
Strength: 1
Trigger Words
Zekrom
Hash
AutoV2
451BD58182

Zekrom LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Has a lot of trouble with the tail, it'll take some attempts to get a passable output. Add (wings) to your prompt to get more consistent wings. If you're having issues with the LoRA, lower the strength. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on a mixed male/female dataset.