Cartoondiff: Training-free Cartoon Image Generation with Diffusion Transformer Models
This addresses the need for efficient cartoon image generation for users in creative and media fields, offering a training-free method that is incremental over existing techniques.
The paper tackles the problem of image cartoonization without requiring model retraining by introducing CartoonDiff, a training-free sampling approach using diffusion transformer models that decomposes the reverse process into semantic and detail generation phases and normalizes high-frequency signals, achieving competitive results in experiments.
Image cartoonization has attracted significant interest in the field of image generation. However, most of the existing image cartoonization techniques require re-training models using images of cartoon style. In this paper, we present CartoonDiff, a novel training-free sampling approach which generates image cartoonization using diffusion transformer models. Specifically, we decompose the reverse process of diffusion models into the semantic generation phase and the detail generation phase. Furthermore, we implement the image cartoonization process by normalizing high-frequency signal of the noisy image in specific denoising steps. CartoonDiff doesn't require any additional reference images, complex model designs, or the tedious adjustment of multiple parameters. Extensive experimental results show the powerful ability of our CartoonDiff. The project page is available at: https://cartoondiff.github.io/