GAN与Diffusion在传统纹样设计中的实验研究

传统纹样是中国优秀传统文化的重要组成部分,传统人工设计已经无法满足纹样的现代设计需求,生成式AI为传统纹样设计提供了新的设计路径和方法。文章将生成式AI应用于传统纹样设计中,通过适配实验优选基于GAN的Style GAN和基于Diffusion的Stable Diffusion两种主流图像生成模型进行实验,采用技术分析与艺术分析相结合,对实验结果进行多角度、多维度对比分析,为设计师选择生成设计方法提供参照。实验结果表明,两个模型均能满足基本的艺术设计需求。Style GAN模型生成的纹样图像更接近真实图像的分布,具有更高的图像质量和多样性;Stable Diffusion模型能较好地传承传统纹样的基因,艺术性与创造性兼具,更加符合传统纹样的艺术设计需求。

ControlNet插件在AI生成图像中的控制应用分析

运用AI绘图工具Stable Diffusion生成图像的过程中,虽然可以用提示词来描述画面,但生成图像的不确定性很大。为了生成满意的图像,可以使用Stable Diffusion的插件ControlNet对图像生成进行控制。本文分析了用ControlNet对图像生成过程的控制方法,并运用该方法在具体案例中实现了在生成图像过程中对画面构图的控制。

AIGC视野下的浙北民居风格研究路径初探

文章以Stable Diffusion为工具,以通过机器学习特定建筑风格图像并输出结果的方式,尝试对浙北民居的建筑风格在AIGC视野下的研究路径进行探索。文章建立了浙北民居与现代住宅图像的数据集并进行训练,得到该语境下的浙北民居风格模型,接着通过批量单独生成与混合生成,对生成的结果进行分类统计。最终发现了该模型在建筑风格模拟方面具有不同于人类直觉判断的抽象提取能力,进而概括了该类工具下生成结果的可能性与局限性。

从特征辨识到图像生成:基于AIGC范式的苗族服饰设计

苗族服饰是中国民族服饰体系中重要的组成部分,在商品化发展中开辟了广阔的市场,但产品同质化现象将阻碍民族文化的进一步发展,人工智能生成内容(AIGC)的发展为传统服饰设计提供了新的可能。文章基于苗族服饰现代化的需要,通过搭建多模型组合流程,为苗族服饰成衣化设计提供灵感样本。实验结果表明,以服饰辨识性为基础,采用Lora训练方式,仅需少量样本即可实现苗族服饰特征在Stable Diffusion生成内容中的迁移。将深度学习引入非遗服饰现代化的进程中,旨在助力非遗服饰朝着成衣化、多样化、大众化方向发展,以数字化方式推动民族服饰转型升级。

基于美学梯度法的人工智能风格化绘画系统

当前Stable diffusion等人工智能绘画模型在绘画时难以直接控制图像风格,同时风格模型训练仅针对单种风格。针对该问题,提出了一种基于美学梯度法的人工智能风格化绘画系统,以实现多种图像风格的控制和融合,并提供更加便捷的图像创作体验。收集并分析网络用户数据,结合问卷得到用户对图像风格的感性需求;根据感性需求收集各风格图像数据得到对应的风格图像训练集。使用梯度下降算法计算风格化文本编码器的权重,实现生成图像风格化的效果。通过可用性测试对比用户对该系统与传统人工智能绘画系统产出图像的风格满意程度,结果表明:人工智能风格化绘画系统的平均满意度相较传统人工智能绘画系统提升23%,表明人工智能风格化绘画系统在图像风格生成上具有更好的效果,可满足用户对图像风格的需求。该人工智能风格化绘画系统可以更便捷地实现图像风格调整,允许用户直观选择不同风格的权重,便捷使用一种或多种风格,能够有效满足用户对图像风格设计的需求。

基于Stable Diffusion的虚拟人形象预设计的应用与研究

对当前AIGC在虚拟形象预设计方面的现状及影响进行了分析和探讨。以Stable Diffusion为例,详细介绍了工程构建和实现,对相关模块的作用、运行环境、使用方法及其指令等多个方面进行了综合叙述、分析和探讨,针对使用不同采样方法、不同采样参数及不同训练模型生成图片效果的优劣进行了说明及展示。随后,通过项目实例,完整地展示了人物形象预设计的过程。最后,对AIGC等新技术可能带来的社会影响进行了预测和总结。

A rened analytical model for reconstruction problems in diuse reectance spectroscopy

A rened analytical model of spatially resolved diffuse reectance with small source-detector separations(SDSs)for the in vivo skin studies is proposed.Compared to the conventional model developed by Farrell et al.,it accounts for the limited acceptance angle of the detectorber.The rened model is validated in the wide range of optical parameters by Monte Carlo simulations of skin diffuse reectance at SDSs of units of mm.Cases of uniform dermis and two-layered epidermis-dermis structures are studied.Higher accuracy of the rened model compared to the conventional one is demonstrated in the separate,constraint-free reconstruction of absorption and reduced scattering spectra of uniform dermis from the Monte Carlo simulated data.In the case of epidermis-dermis geometry,the recovered values of reduced scattering in dermis are overestimated and the recovered values of absorption are underestimated for both analytical models.Presumably,in the presence of a thin mismatched topical layer,only the effective attenuation coe±cient of the bottom layer can be accurately recovered using a diffusion theorybased analytical model while separate reconstruction of absorption and reduced scattering fails due to the inapplicability of the method of images.These-ndings require implementation of more sophisticated models of light transfer in inhomogeneous media in the recovery algorithms.

Simulation of the Ecosystem Productivity Responses to Aerosol Diffuse Radiation Fertilization Effects over the Pan-Arctic during 2001–19

The pan-Arctic is confronted with air pollution transported from lower latitudes.Observations have shown that aerosols help increase plant photosynthesis through the diffuse radiation fertilization effects(DRFEs).While such DRFEs have been explored at low to middle latitudes,the aerosol impacts on pan-Arctic ecosystems and the contributions by anthropogenic and natural emission sources remain less quantified.Here,we perform regional simulations at 0.2o×0.2ousing a well-validated vegetation model(Yale Interactive terrestrial Biosphere,YIBs)in combination with multi-source of observations to quantify the impacts of aerosol DRFEs on the net primary productivity(NPP)in the pan-Arctic during 2001-19.Results show that aerosol DRFEs increase pan-Arctic NPP by 2.19 Pg C(12.8%)yr^(-1)under clear-sky conditions,in which natural and anthropogenic sources contribute to 8.9% and 3.9%,respectively.Under all-sky conditions,such DRFEs are largely dampened by cloud to only 0.26 Pg C(1.24%)yr^(-1),with contributions of 0.65% by natural and 0.59% by anthropogenic species.Natural aerosols cause a positive NPP trend of 0.022% yr^(-1)following the increased fire activities in the pan-Arctic.In contrast,anthropogenic aerosols induce a negative trend of-0.01% yr^(-1)due to reduced emissions from the middle latitudes.Such trends in aerosol DRFEs show a turning point in the year of 2007 with more positive NPP trends by natural aerosols but negative NPP trends by anthropogenic aerosols thereafter.Though affected by modeling uncertainties,this study suggests a likely increasing impact of aerosols on terrestrial ecosystems in the pan-Arctic under global warming.

Boron-doped high-entropy oxide toward high-rate and long-cycle layered cathodes for wide-temperature sodium-ion batteries

03-type layered metal oxides hold great promise for sodium-ion batteries cathodes owing to their energy density advantage.However,the severe irreversible phase transition and sluggish Na^(+)diffusion kinetics pose significant challenges to achieve high-performance layered cathodes.Herein,a boron-doped03-type high entropy oxide Na(Fe_(0.2)Co_(0.15)Cu_(0.05)Ni_(0.2)Mn_(0.2)Ti_(0.2))B_(0.02)O_(2)(NFCCNMT-B_(0.02))is designed and the covalent B-O bonds with high entropy configuration ensure a robust layered structure.The obtained cathode NFCCNMT-B_(0.02)exhibits impressive cycling performance(capacity retention of 95%and 82%after100 cycles and 300 cycles at 1 and 10 C,respectively)and outstanding rate capability(capacity of 83 mAh g^(-1)at 10 C).Furthermore,the NFCCNMT-B_(0.02)demonstrates a superior wide-temperature performance,maintaining the same capacity level(113,4 mAh g^(-1)@-20℃,121 mAh g^(-1)@25℃,and 119 mAh g^(-1)@60℃)and superior cycle stability(90%capacity retention after 100 cycles at 1 C at-20℃).The high-entropy configuration design with boron doping strategy contributes to the excellent sodium-ion storage performance.The high-entropy configuration design effectively suppresses irreversible phase transitions accompanied by small volume changes(ΔV=0.65 A3).B ions doping expands the Na layer distance and enlarges the P3 phase region,thereby enhancing Na^(+)diffusion kinetics.This work offers valuable insights into design of high-performance layered cathodes for sodium-ion batteries operating across a wide temperature.

Effect of sodium nitroprusside on the microrheological properties of red blood cells in different media

Red blood cell(RBC)aggregation as well as their deformation significantly affects blood microrheology.These processes depend on various factors,one of which is concentration of the nitric oxide,one of the main signaling molecule in the bloodstream.The purpose of this study was to investigate the effect of nitric oxide on the microrheological properties of red blood cells(RBCs)in RBC samples of various media after the addition of nitric oxide donor sodium nitroprusside in vitro.Microrheological properties were measured using laser aggregometer and ektacytometer based on diffuse light scattering and diffraction of laser light on a suspension of RBCs,respectively.The study found that heparin-stabilized blood showed increased RBC aggregation and deformation with sodium nitroprusside concentrations of 100,and 200M,while EDTA-stabilized blood showed slightly decreased aggregation and unchanged deformation.With washed RBCs in dextran solution,the addition of sodium nitroprusside(in the concentrations of 100,and 200M)resulted in decreased aggregation and increased deformation.These-ndings aid in our understanding of nitric oxide's effect on RBC microrheological properties.

Microstructure and thermal properties of dissimilar M300–CuCr1Zr alloys by multi-material laser-based powder bed fusion

Multi-material laser-based powder bed fusion (PBF-LB) allows manufacturing of parts with 3-dimensional gradient and additional functionality in a single step. This research focuses on the combination of thermally-conductive CuCr1Zr with hard M300 tool steel.Two interface configurations of M300 on CuCr1Zr and CuCr1Zr on M300 were investigated. Ultra-fine grains form at the interface due to the low mutual solubility of Cu and steel. The material mixing zone size is dependent on the configurations and tunable in the range of0.1–0.3 mm by introducing a separate set of parameters for the interface layers. Microcracks and pores mainly occur in the transition zone.Regardless of these defects, the thermal diffusivity of bimetallic parts with 50vol% of CuCr1Zr significantly increases by 70%–150%compared to pure M300. The thermal diffusivity of CuCr1Zr and the hardness of M300 steel can be enhanced simultaneously by applying the aging heat treatment.

Construction of Dynamic Alloy Interfaces for Uniform Li Deposition in Li-Metal Batteries

It is well accepted that a lithiophilic interface can effectively regulate Li deposition behaviors,but the influence of the lithiophilic interface is gradually diminished upon continuous Li deposition that completely isolates Li from the lithiophilic metals.Herein,we perform in-depth studies on the creation of dynamic alloy interfaces upon Li deposition,arising from the exceptionally high diffusion coefficient of Hg in the amalgam solid solution.As a comparison,other metals such as Au,Ag,and Zn have typical diffusion coefficients of 10-20 orders of magnitude lower than that of Hg in the similar solid solution phases.This difference induces compact Li deposition pattern with an amalgam substrate even with a high areal capacity of 55 mAh cm^(-2).This finding provides new insight into the rational design of Li anode substrate for the stable cycling of Li metal batteries.

Value of multiple models of diffusion-weighted imaging to predict hepatic lymph node metastases in colorectal liver metastases patients

BACKGROUND About 10%-31% of colorectal liver metastases(CRLM)patients would concomitantly show hepatic lymph node metastases(LNM),which was considered as sign of poor biological behavior and a relative contraindication for liver resection.Up to now,there’s still lack of reliable preoperative methods to assess the status of hepatic lymph nodes in patients with CRLM,except for pathology examination of lymph node after resection.AIM To compare the ability of mono-exponential,bi-exponential,and stretchedexponential diffusion-weighted imaging(DWI)models in distinguishing between benign and malignant hepatic lymph nodes in patients with CRLM who received neoadjuvant chemotherapy prior to surgery.METHODS In this retrospective study,97 CRLM patients with pathologically confirmed hepatic lymph node status underwent magnetic resonance imaging,including DWI with ten b values before and after chemotherapy.Various parameters,such as the apparent diffusion coefficient from the mono-exponential model,and the true diffusion coefficient,the pseudo-diffusion coefficient,and the perfusion fraction derived from the intravoxel incoherent motion model,along with distributed diffusion coefficient(DDC)andαfrom the stretched-exponential model(SEM),were measured.The parameters before and after chemotherapy were compared between positive and negative hepatic lymph node groups.A nomogram was constructed to predict the hepatic lymph node status.The reliability and agreement of the measurements were assessed using the coefficient of variation and intraclass correlation coefficient.RESULTS Multivariate analysis revealed that the pre-treatment DDC value and the short diameter of the largest lymph node after treatment were independent predictors of metastatic hepatic lymph nodes.A nomogram combining these two factors demonstrated excellent performance in distinguishing between benign and malignant lymph nodes in CRLM patients,with an area under the curve of 0.873.Furthermore,parameters from SEM showed substantial repeatability.CONCLUSION The developed nomogram,incorporating the pre-treatment DDC and the short axis of the largest lymph node,can be used to predict the presence of hepatic LNM in CRLM patients undergoing chemotherapy before surgery.This nomogram was proven to be more valuable,exhibiting superior diagnostic performance compared to quantitative parameters derived from multiple b values of DWI.The nomogram can serve as a preoperative assessment tool for determining the status of hepatic lymph nodes and aiding in the decision-making process for surgical treatment in CRLM patients.

Effect of Cosmic Plasma on the Observation of Supernovae Ia

In observational cosmology,a supernova la is used as a standard candle in order to extend the Hubble diagram to a higher redshift range.Astrophysicists found that the observed brightness of high redshift supernovae la is dimmer than expected.This dimming effect is considered observational evidence for the existence of dark energy in the universe.It should be noted that this conclusion is based on an assumption that the mass density of the cosmic plasma is very small.Therefore,the dimming effect caused by the Compton scattering of free electrons in cosmic plasma can be neglected.X-ray observations suggest that the mass density of the cosmic plasma may be very large.In theory,the observed dimming effect of high redshift supernovae Ia may be caused by the Compton scattering of free electrons in the cosmic plasma.In this paper it will be shown that this idea is reasonable.Therefore,there is no need to introduce the confusing concept of dark energy into cosmology.

General laws of funding for scientific citations:how citations change in funded and unfunded research between basic and applied sciences

Purpose:The goal of this study is to analyze the relationship between funded and unfunded papers and their citations in both basic and applied sciences.Design/methodology/approach:A power law model analyzes the relationship between research funding and citations of papers using 831,337 documents recorded in the Web of Science database.Findings:The original results reveal general characteristics of the diffusion of science in research fields:a)Funded articles receive higher citations compared to unfunded papers in journals;b)Funded articles exhibit a super-linear growth in citations,surpassing the increase seen in unfunded articles.This finding reveals a higher diffusion of scientific knowledge in funded articles.Moreover,c)funded articles in both basic and applied sciences demonstrate a similar expected change in citations,equivalent to about 1.23%,when the number of funded papers increases by 1%in journals.This result suggests,for the first time,that funding effect of scientific research is an invariant driver,irrespective of the nature of the basic or applied sciences.Originality/value:This evidence suggests empirical laws of funding for scientific citations that explain the importance of robust funding mechanisms for achieving impactful research outcomes in science and society.These findings here also highlight that funding for scientific research is a critical driving force in supporting citations and the dissemination of scientific knowledge in recorded documents in both basic and applied sciences.Practical implications:This comprehensive result provides a holistic view of the relationship between funding and citation performance in science to guide policymakers and R&D managers with science policies by directing funding to research in promoting the scientific development and higher diffusion of results for the progress of human society.

Glymphatic function and its influencing factors in different glucose metabolism states

BACKGROUND Dysfunction of the glymphatic system in the brain in different stages of altered glucose metabolism and its influencing factors are not well characterized.AIM To investigate the function of the glymphatic system and its clinical correlates in patients with different glucose metabolism states,the present study employed diffusion tensor imaging along the perivascular space(DTI-ALPS)index.METHODS Sample size was calculated using the pwr package in R software.This crosssectional study enrolled 22 patients with normal glucose metabolism(NGM),20 patients with prediabetes,and 22 patients with type 2 diabetes mellitus(T2DM).A 3.0T magnetic resonance imaging was used to evaluate the function of the glymphatic system.The mini-mental state examination(MMSE)was used to assess general cognitive function.The DTI-ALPS index of bilateral basal ganglia and the mean DTI-ALPS index was calculated.Further,the correlation between DTI-ALPS and clinical features was assessed.RESULTS The left-side,right-side,and mean DTI-ALPS index in the T2DM group were significantly lower than that in the NGM group.The right-side DTI-ALPS and mean DTI-ALPS index in the T2DM group were significantly lower than those in the prediabetes group.DTI-ALPS index lateralization was not observed.The MMSE score in the T2DM group was significantly lower than that in the NGM and prediabetes group.After controlling for sex,the left-side DTI-ALPS and mean DTI-ALPS index in the prediabetes group were positively correlated with 2-hour postprandial blood glucose level;the left-side DTI-ALPS index was negatively correlated with total cholesterol and low-density lipoprotein level.The right-side DTI-ALPS and mean DTI-ALPS index were negatively correlated with the glycosylated hemoglobin level and waist-to-hip ratio in the prediabetes group.The left-side,right-side,and mean DTI-ALPS index in the T2DM group were positively correlated with height.The left-side and mean DTIALPS index in the T2DM group were negatively correlated with high-density lipoprotein levels.CONCLUSION Cerebral glymphatic system dysfunction may mainly occur in the T2DM stage.Various clinical variables were found to affect the DTI-ALPS index in different glucose metabolism states.This study enhances our understanding of the pathophysiology of diabetic brain damage and provides some potential biological evidence for its early diagnosis.

基于提示词优化的AIGC汉长安城遗址儿童绘本应用研究

以汉长安城遗址中椒房殿为测试对象,探究和优化Stable Diffusion中的提示词输入策略生成椒房殿复原设想图,并且依据该输入逻辑制作出儿童绘本素材图。研究将AI绘画、汉文化和儿童绘本创新性的融合,对于AI艺术应用和儿童美育教育实践具有可供参考的推广价值。

基于生成式AI的人工智能在建筑设计中的应用探究

近两年间人工智能(AI)相关技术逐步由顶端智能产业下放,走进越来越多诸如建筑等传统行业中。把握住与新型技术相结合的机会是建筑设计领域一种可探索的道路。文章将以生成式AI为例,从应用领域、应用模式、方案生成等视角,探究人工智能在建筑方案设计领域可以为建筑师提供的参考和帮助,并提出其中的缺陷与局限性,为今后人工智能在建筑设计领域更加深入、系统地应用提供参考。

Diffuseness effect and radial basis function network for optimizing α decay calculations

A radial basis function network(RBFN)approach is adopted for the first time to optimize the calculation of$\alpha$decay half-life in the generalized liquid drop model(GLDM),while concurrently incorporating the surface diffuseness effect.The calculations presented herein agree closely with the experimental half-lives for 68 superheavy nuclei(SHN),achieving a remarkable reduction of 40%in the root-mean-square(rms)deviations of half-lives.Furthermore,using the RBFN method,the half-lives for four SHN isotopes,252-288Rf,272-310Fl,286-316119,and 292-318120,are predicted using the improved GLDM with the diffuseness correction and the decay energies from WS4 and FRDM as inputs.Therefore,we conclude that the diffuseness effect should be embodied in the proximity energy.Moreover,increased application of neural network methods in nuclear reaction studies is encouraged.

Spatial sensitivity to absorption changes for various near-infrared spectroscopy methods:A compendium review

This compendium review focuses on the spatial distribution of sensitivity to localized absorption changes in optically diffuse media,particularly for measurements relevant to near-infrared spectroscopy.The three temporal domains,continuous wave,frequency domain,and time domain,each obtain different optical data types whose changes may be related to effective homogeneous changes in the absorption coefficient.Sensitivity is the relationship between a localized perturbation and the recovered effective homogeneous absorption change.Therefore,spatial sensitivity maps representing the perturbation location can be generated for the numerous optical data types in the three temporal domains.The review first presents a history of the past 30 years of work investigating this sensitivity in optically diffuse media.These works are experimental and theoretical,presenting one-,two-,and three-dimensional sensitivity maps for different Near-Infrared Spectroscopy methods,domains,and data types.Following this history,we present a compendium of sensitivity maps organized by temporal domain and then data type.This compendium provides a valuable tool to compare the spatial sensitivity of various measurement methods and parameters in one document.Methods for one to generate these maps are provided in Appendix A,including the code.This historical review and comprehensive sensitivity map compendium provides a single source researchers may use to visualize,investigate,compare,and generate sensitivity to localized absorption change maps.