AnimeDiffusion: Anime Diffusion Colorization

Being essential in animation creation, colorizing anime line drawings is usually a tedious and time-consuming manual task. Reference-based line drawing colorization provides an intuitive way to automatically colorize target line drawings using reference images. The prevailing approaches are based on generative adversarial networks (GANs), yet these methods still cannot generate high-quality results comparable to manually-colored ones. In this paper, a new AnimeDiffusion approach is proposed via hybrid diffusions for the automatic colorization of anime face line drawings. This is the first attempt to utilize the diffusion model for reference-based colorization, which demands a high level of control over the image synthesis process. To do so, a hybrid end-to-end training strategy is designed, including phase 1 for training diffusion model with classifier-free guidance and phase 2 for efficiently updating color tone with a target reference colored image. The model learns denoising and structure-capturing ability in phase 1, and in phase 2, the model learns more accurate color information. Utilizing our hybrid training strategy, the network convergence speed is accelerated, and the colorization performance is improved. Our AnimeDiffusion generates colorization results with semantic correspondence and color consistency. In addition, the model has a certain generalization performance for line drawings of different line styles. To train and evaluate colorization methods, an anime face line drawing colorization benchmark dataset, containing 31,696 training data and 579 testing data, is introduced and shared. Extensive experiments and user studies have demonstrated that our proposed AnimeDiffusion outperforms state-of-the-art GAN-based methods and another diffusion-based model, both quantitatively and qualitatively.

Sex-divergent expression of cytochrome P450 and SIRTUIN 1-7 proteins in toxicity evaluation of a benzimidazole-derived epigenetic modulator in mice

Efforts in precision medicine to combat aberrant epigenome have led to the development of epigenetic targeting drugs. We have previously reported the capability of the BZD9L1 epigenetic modulator to impede colorectal tumour growth in vitro and in vivo through sirtuin (SIRT) inhibition. Although most benzimidazole derivatives are commonly less toxic, their effects on SIRTs and cytochrome P450 (CYP) regulations have not been explored alongside toxicity assessments. SIRTs are histone deacetylases that are crucial in maintaining metabolic homeostasis, whereas CYP is essential in drug metabolism. This study aims to determine the toxicology profile of BZD9L1 through oral acute and repeated dose toxicity evaluations, along with molecular analyses of SIRT, CYP and relevant toxicity markers through western blot and quantitative polymerase chain reaction (qPCR). BZD9L1 demonstrated no sign of acute toxicity at the limit dose (2000 mg/kg). The 28-day toxicity study highlighted the tolerability of repeated dose administration without adverse effects. BZD9L1 showed a sex-divergent regulation of hepatic SIRT1-7, CYP2A5 and CYP2D proteins. Furthermore, BZD9L1 did not induce the expression of organ injury proteins or alter the gene expression of cellular function indicators in mouse liver and kidneys, hence demonstrating, at least in part, the safety of BZD9L1 in short-term evaluations. The present study cautions for personalised strategies when employing benzimidazole-derived epigenetic therapeutics.

Body measurements of Chinese males in dynamic postures and application

It is generally accepted that there is a relationship between body dimensions, body movement and clothing wearing ease design, and yet previous research in this area has been neither sufficient nor systematic. This paper proposes a method to measure the human body in the static state and in 17 dynamic postures, so as to understand dimensional changes of different body parts during dynamic movements. Experimental work is carried out to collect 30 measurements of 10 male Chinese subjects in both static and dynamic states. Factor analysis is used to analyse body measurement data in a static state, and such key measurements describe the characteristics of different body figures. Moreover, one-way ANOVA is used to analyse how dynamic postures affect these key body measurements. Finally, an application of the research results is suggested: a dynamic block patternmaking method for high-performance clothing design.