File size: 931 Bytes
8e84b6e
 
 
e4f736a
 
8e84b6e
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
---
tags:
- stable-diffusion
license: apache-2.0
pipeline_tag: text-to-image
---

# SD1.5-NAI-Character-Lora-1024

Re-train of a majority of my existing character loras (some of you may be familiar with my posts on [CivitAI](https://civitai.com/user/DocShotgun)) at 1024 resolution and with slightly different hyperparameters. The previews folder contains example images generated with each lora, each containing embedded generation info. The higher training resolution seems to capture smaller outfit details better, although this is no guarantee that these perform any better than my existing loras/locons posted.

Training was done using manually-gathered datasets, and [Derrian Distro's training scripts](https://github.com/derrian-distro/LoRA_Easy_Training_Scripts).

These are provided as-is, and YMMV. The user is responsible for any outputs produced using these loras, and outputs may vary depending on the base model used.