Sign In

Mercy (Overwatch) Generalbutch style - LoRa

137
789
4.3k
43
Verified:
SafeTensor
Type
LoRA
Stats
360
2,675
Reviews
Published
Mar 3, 2024
Base Model
SD 1.5
Training
Steps: 2,088
Epochs: 1
Usage Tips
Clip Skip: 2
Strength: 1
Trigger Words
mercy_\(overwatch\)
Hash
AutoV2
55F28D95C2
default creator card background decoration
lizarb's Avatar
lizarb

Greetings!

Now this is a really special one, mostly because I couldn't find any other LoRa that could replicate GB's style. What I really wanted to do was to replicate his style with any characters, but I'm still learning on how to do that properly (styles are trickier!).

Model Characteristics

For now, enjoy this instead. I might also do a version 2.0 on this but for now I'm happy enough with the results. There are a few things to keep in mind though:

  • Trigger word: mercy_\(overwatch\)

  • Use weight of 0.7 to 1. See what works best for you.

  • I'm using DarkSun v7b and RealCartoon3D v13 and got good results, so I'd recommend using checkpoints that have a Semi-Realistic style.

  • Full body shots appear to mess her face up a little, so I'd recommend using ADetailer.

  • Restore face is optional (ADetailer works way better).

  • Play around with the samplers, but I got best results with DPM++ 2M Karras and DPM++ SDE Karras.

  • Clip Skip 2 works best.

  • To avoid overfitting, I recommend using the extension Lora Block Weight

  • Hires Fix works like a charm, I recommend using R-ESRGAN as the upscaler.

Trainning

I'm relatively new to LoRa trainning so any tips for improvement are much appreciated!

  • Dataset size: 84

  • Model: DreamShaper 8

  • Buckets enabled

  • Epoch: 1

  • Repeats: 100 (good dataset) and 50 (bad dataset)

  • Total steps: 2088

I'd be happy if you guys could give me any character suggestions for my next LoRA!

Cheers.

Like my stuff? Buy me a Monster!

All my models and images will always be 100% free, don't feel obligated to donate!