Sign In

jianlan

9

90

70

3

Updated: Feb 27, 2024

concept

Verified:

SafeTensor

Type

LoRA

Stats

90

70

Reviews

Published

Feb 27, 2024

Base Model

SDXL 1.0

Training

Steps: 20
Epochs: 10

Trigger Words

flower

Hash

AutoV2
D6D1DD73C0
default creator card background decoration
Holiday 2023: 5 lights
arcgua's Avatar

arcgua

jianlan 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.

Striving to upload two models daily.