Type
LORA
Publish Time
2024-09-24
Base Model
SDXL 1.0
Trigger Words
koson
Copy
Version Introduction
V1 uses autotagged images



Experimental LoRA to capture the style of Ohara Koson's brush paintings. Because the original paintings were done on unbleached paper / silk, you likely won't get a white background.
Lower CFG scale <7 and medium weights around 0.6 appear to be the best balance (depending on subject matter), otherwise the image takes on a distorted / overly processed look
V1 uses autotagged images
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
