Zen Ink Wash Sumi-e
Last Update：2025-03-14 12:30:44
Search History
Explore
FAILED
Home
Special content provided by the community
Special content provided by the community
FAILED
Inspiration
Share Your Brilliant Creations
Share Your Brilliant Creations
FAILED
AI Apps
Free and High-quality AI App
Free and High-quality AI App
FAILED
AI Characters
Immersive AI Character Interaction
Immersive AI Character Interaction
FAILED
Models
Various Powerful AI Models
Various Powerful AI Models
FAILED
AI Video
Create Videos Using AI with Ease
Create Videos Using AI with Ease
FAILED
LoRA Training
Customize Your AI Model Style
Customize Your AI Model Style
FAILED
ComfyUI
Simplify Your AI Creation Process
Simplify Your AI Creation Process
FAILED
AI Audio
Generate Realistic Audio Content Using AI Magic
Generate Realistic Audio Content Using AI Magic
Swift AI
Train
Official
Community
Flux Image to Image
Flux Image to Image
Flux Text to Image (Speed-Enhanced)
Flux Text to Image (Speed-Enhanced)
Ghibli AI Image Generator
Ghibli AI Image Generator
Anime to Real
Anime to Real
AI Muscle Generator
AI Muscle Generator
AI Breast Expansion
AI Breast Expansion
AI Bikini Generator
AI Bikini Generator
The model produces nice effects in the 0.4 - 1.5 strength range.
I personally love using 1.5 strength on the Flux Dev GGUF Q4 and 1.2 on the regular Dev model.
You can safely use strength 2 and still get decent, though more abstract, results.
I strongly recommend using the keywords "monochrome, greyscale, black and white" if you want a classical Sumi-e effect. Without them, the LoRA can still create a beautiful "Ink Wash" style.
If you're using a low-end machine with 6/8 GB of VRAM, check out my guide:
https://civitai.com/articles/6846/running-flux-on-68-gb-vram-using-comfyui
All images in the Showcase Gallery were created using this workflow and the Flux Q4 Dev model on a machine with 8GB VRAM:
https://civitai.com/models/658639/super-simple-gguf-quantized-flux-lora-workflow