SDXL

Hakushi Mix

#Manga
Hakushi Mix - AI Model cover image
Caricato su
14 apr 2025, 03:22
Utilizzi
1.3k
Recensioni
No reviews
Passaggi di campionamento

15

Scala CFG

5

Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Recommended LoRAs

Descrizione

[Hakushi Mix by tonikakushiroi784](https://civitai.com/models/1337666?modelVersionId=1655685)

Hakushi Mix is designed to be used with various blended art styles.

"Hakushi" means "Blank Paper" The quality tags and negative prompts used in the samples are not necessarily the best or only options. Please adjust them as needed to match your preferred style.

v1.2

Merged with Illustrious v1.1. Additional adjustments were made to enhance detail and enable more delicate, refined strokes.

High-resolution output is possible for simple compositions. However, complex poses may lead to visual breakdowns such as extra limbs or duplicated figures, so avoid pushing it too far.

Support for natural language prompts has not been thoroughly tested.

Be aware that prompts emphasizing the background tend to make the main subject appear too small.

Recommended Settings:

Steps: 15~35

CFG Scale: 5~7

Sampler: Euler a / Euler / DPM++ 2M /DDIM etc

Schedule: Automatic / SGM Uniform / Simple etc

Size: 1024x1024, 832x1280, 896x1216, 1280x1280, 1024x1536, 1088x1472 etc

Additional tools: Use Hires Fix and ADetailer as needed.

Commenti

Artwork made by Hakushi Mix