ghost
Sign In

Archiveria

593
4.7k
51
Verified:
SafeTensor
Type
LoRA
Stats
1,753
Reviews
Published
Oct 22, 2023
Base Model
SD 1.5
Training
Steps: 7,500
Epochs: 1
Usage Tips
Clip Skip: 2
Trigger Words
<lora:Archiveria_yiu_v30:0.5>
Archiveria
Hash
AutoV2
D4DF145ECE
default creator card background decoration
Dima_yiu's Avatar
Dima_yiu

How to use

It is recommended to write the following tokens: architecture, building, house, blackout, slate gray, epic lighting, glow, complex details, vegetation, raw, hdr, professional photo.

Copy the prompta and parameters from the preview to this model — you will not lose.

What the model is suitable for

This model is designed to generate buildings of various styles: from Venetian classics to modern neo-modern and cyberpunk.

I trained LoRA on the Deliberate_v3 model, so it's better to work with her in pairs.

It is possible to generate at high resolutions and get a complete image, since the dataset had sources with a panorama and a wide shooting angle.

Which model works best with

It is best to use the Deliberate_v3 model, but you can combine this LoRA with other solutions focused on photorealism, model will work perfectly with them.

Links to my resources

You will find help in my telegram chat.
My Telegram channel.