Sign In

xuesong

0

Updated: Apr 16, 2024

style

Download

1 variant available

SafeTensor

54.76 MB

Verified:

Type
LoRA
Stats

51

0

Reviews
Published

Apr 16, 2024

Base Model

SDXL 1.0

Hash
AutoV2
6C99931D96
default creator card background decoration
Followers - 46

46

Likes - 414

414

Holiday 2023: 5 lights
00074-497046773.jpeg

xuesong lora

Training with 50 iterations and 40 epochs, each comprising 3000 steps.

Since the loss is generally below 0.1 and the fitting degree is high, the weights can be reduced to a range of {0.5-0.8}.

I usually train using the anything model, which enhances realism significantly.