library_name: diffusers
pipeline_tag: text-to-image
tags:
- art
🔥Declaration: I suggest illustrators and arts cannot be replaced by AI, although these models can accelerate design/drawing, the details, sprite-inside, visual-logics cannot be Datafication in Neural Networks.
Modill (Modern-Illustration) is a trained checkpoint to make attractive and creative illustrations/painting. I’am UI/UX designer, so I want to a model to generate some flat illustrations for both business and creative-design.
🔥Advantages: Modill is trained by 289 brilliant illustrations from different designers/illustrators. It can draw exaggerated-body characters and raster texture.
No strictly restrictions on style. The train data includes different styles, no-overfitting can generate more special outputs.
🔥Recommendations of parameters: