Comic Image Generation Based on Diffusion Models

With the rapid development of the digital entertainment industry, the demand for efficient comic image generation is increasing, especially in areas such as animation production, game design, and personalized content creation. High-quality and automated generation techniques have become essential. However, traditional comic image generation methods rely on manual drawing or basic image processing, making it difficult to achieve both rich details and automation, thus limiting creative flexibility and productivity. To address these challenges, this paper proposes a novel comic image generation model based on diffusion models—Hand-Drawn Comic Diffusion Model (HD-CDM). By learning complex image distributions, HD-CDM progressively refines noisy images to generate comics with intricate line work, vibrant colors, and distinctive artistic styles, significantly improving both quality and efficiency while reducing reliance on manual labor and computational resources. Furthermore, this paper constructs a diverse comic-style image dataset, providing a solid foundation for model training and evaluation, thereby advancing research in this field. Experimental results demonstrate that compared to existing comic image generation models, HD-CDM achieves superior performance in terms of image realism, stylistic consistency, and creative diversity, offering a novel solution for automated comic image generation. In the field of comic creation, it helps artists to quickly generate sketches or concept drawings; for non-professional comic creators, it lowers the threshold of comic creation. They can enter a simple text description or select a specific art style to quickly generate comic images with professional standards, thus making it easier for them to participate in the creation of comics.