Do not use these styles on other SDXL models, they are trained specifically for Pony Diffusion V6 XL!
This is another experiment to get LoRAs for Pony XL V6 to copy the style of specific models
Unlike One Image Style these styles are much more stable, similar to Not Artists styles
LoRA trained on images created by Me using SD WebUI Forge and Kohya HRFix
The previews were generated without using ADetailer
LoRAs without Trigger Words!
Recommended LoRA Strength: 1 (Strength can be reduced to 0.7 below this value I do not recommend it)
Original Models
Repeats: 10
Epoch: 4
Image Count: 64
Network Rank: 16
Network Alpha: 8
Batch size: 1
Clip skip: 1
Training steps: 2560
Resolution: 768x1024
Train Resolution: 1024x1024
Model: ponyDiffusionV6XL_v6
WD14 Captioning: SmilingWolf/wd-v1-4-convnextv2-tagger-v2
Recommended LoRA Strength: [0.7-1]
A darker version with clearer faces
1. Права на репостнутые модели принадлежат оригинальным создателям.
2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить
