Illustrious: an Open Advanced Illustration Model

TL;DR

Illustrious is an open-source text-to-image anime generation model that achieves high resolution, dynamic colors, and detailed character depiction through innovative training techniques and multi-level captioning.

Contribution

The paper introduces novel training strategies, higher resolution capabilities, and refined captioning methods to significantly improve anime image generation quality.

Findings

Achieves state-of-the-art anime image quality

Handles images over 20MP with high detail

Outperforms existing illustration models

Abstract

In this work, we share the insights for achieving state-of-the-art quality in our text-to-image anime image generative model, called Illustrious. To achieve high resolution, dynamic color range images, and high restoration ability, we focus on three critical approaches for model improvement. First, we delve into the significance of the batch size and dropout control, which enables faster learning of controllable token based concept activations. Second, we increase the training resolution of images, affecting the accurate depiction of character anatomy in much higher resolution, extending its generation capability over 20MP with proper methods. Finally, we propose the refined multi-level captions, covering all tags and various natural language captions as a critical factor for model development. Through extensive analysis and experiments, Illustrious demonstrates state-of-the-art performance in terms of animation style, outperforming widely-used models in illustration domains, propelling easier customization and personalization with nature of open source. We plan to publicly release updated Illustrious model series sequentially as well as sustainable plans for improvements.