Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models

TL;DR

Diffutoon introduces a diffusion model-based method for high-resolution, editable toon shading that produces consistent, detailed anime-style videos and allows content editing through prompts, surpassing existing approaches.

Contribution

The paper presents Diffutoon, a novel diffusion model approach for high-resolution, consistent, and editable toon shading in videos, addressing key challenges in stylization and content editing.

Findings

Diffutoon achieves superior visual quality and consistency in anime-style video stylization.

It enables content editing via prompts with high fidelity.

Quantitative and human evaluations confirm its effectiveness.

Abstract

Toon shading is a type of non-photorealistic rendering task of animation. Its primary purpose is to render objects with a flat and stylized appearance. As diffusion models have ascended to the forefront of image synthesis methodologies, this paper delves into an innovative form of toon shading based on diffusion models, aiming to directly render photorealistic videos into anime styles. In video stylization, extant methods encounter persistent challenges, notably in maintaining consistency and achieving high visual quality. In this paper, we model the toon shading problem as four subproblems: stylization, consistency enhancement, structure guidance, and colorization. To address the challenges in video stylization, we propose an effective toon shading approach called \textit{Diffutoon}. Diffutoon is capable of rendering remarkably detailed, high-resolution, and extended-duration videos in anime style. It can also edit the content according to prompts via an additional branch. The efficacy of Diffutoon is evaluated through quantitive metrics and human evaluation. Notably, Diffutoon surpasses both open-source and closed-source baseline approaches in our experiments. Our work is accompanied by the release of both the source code and example videos on Github (Project page: https://ecnu-cilab.github.io/DiffutoonProjectPage/).