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。

人工智能在电影制作领域的应用探究——以分镜头脚本生成工具为例

随着人工智能技术的发展与应用,以Midjourney、Stable Diffusion为代表的人工智能(Artificial Intelligence,AI)图像生产工具凭借其高效率、低成本、易学习等特点,在图像绘画领域体现出较强竞争力。分镜头脚本的绘制与设计是电影前期制作的重要环节,本文着重研究将人工智能生成内容(Artificial Intelligence Generated Content,AIGC)技术应用到电影分镜头脚本的绘制当中,通过比较AIGC生成的分镜头脚本与人类创作的差异,探讨AIGC在提高创作效率、内容创新性等方面的潜在优势,此外,还将探讨AIGC技术在数字电影制作上所面临的挑战,如创造性和情感表达的限制,以及与人类创作者的合作模式,以探索实现人工智能领域分镜头脚本生成的新的可能性。

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Make-A-Video到Sora:AI视频生成技术的进步与挑战

随着人工智能技术的飞速发展,AI视频生成技术已成为研究和应用的热点。从Meta的MakeA-Video, Runway AI的Runway Gen-2,Stability AI的Stable Video Diffusion,到Google的Lumiere,再到OpenAI的Sora,每一个模型的推出都不仅代表了AI视频生成技术的进步,也带来了新的挑战。回顾了这些关键AI视频模型的原理和特点,并对比它们之间的优势和不足,探讨了AI视频生成技术面临的主要挑战,展望了未来的发展方向。

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。

Exploring the Latest Applications of OpenAI and ChatGPT: An In-Depth Survey

OpenAI and ChatGPT, as state-of-the-art languagemodels driven by cutting-edge artificial intelligence technology,have gained widespread adoption across diverse industries. In the realm of computer vision, these models havebeen employed for intricate tasks including object recognition, image generation, and image processing, leveragingtheir advanced capabilities to fuel transformative breakthroughs. Within the gaming industry, they have foundutility in crafting virtual characters and generating plots and dialogues, thereby enabling immersive and interactiveplayer experiences. Furthermore, these models have been harnessed in the realm of medical diagnosis, providinginvaluable insights and support to healthcare professionals in the realmof disease detection. The principal objectiveof this paper is to offer a comprehensive overview of OpenAI, OpenAI Gym, ChatGPT, DALL E, stable diffusion,the pre-trained clip model, and other pertinent models in various domains, encompassing CLIP Text-to-Image,education, medical imaging, computer vision, social influence, natural language processing, software development,coding assistance, and Chatbot, among others. Particular emphasis will be placed on comparative analysis andexamination of popular text-to-image and text-to-video models under diverse stimuli, shedding light on thecurrent research landscape, emerging trends, and existing challenges within the domains of OpenAI and ChatGPT.Through a rigorous literature review, this paper aims to deliver a professional and insightful overview of theadvancements, potentials, and limitations of these pioneering language models.

Rising utilization of stable isotopes in tree rings for climate change and forest ecology

Analyses of stable isotopes(C,O,H)in tree rings are increasingly important cross-disciplinary programs.The rapid development in this field documented in an increasing number of publications requires a comprehensive review.This study includes a bibliometric analysis-based review to better understand research trends in tree ring stable isotope research.Overall,1475 publications were selected from the Web of Science Core Collection for 1974-2023.The findings are that:(1)numbers of annual publications and citations increased since 1974.From 1974 to 1980,there were around two relevant publications per year.However,from 2020 to 2022,this rose sharply to 109 publications per year.Likewise,average article citations were less than four per year before 1990,but were around four per article per year after 2000;(2)the major subjects using tree ring stable isotopes include forestry,geosciences,and environmental sciences,contributing to 42.5%of the total during 1974-2023;(3)the top three most productive institutions are the Chinese Academy of Sciences(423),the Swiss Federal Institute for Forest,Snow and Landscape Research(227),and the University of Arizona(204).These achievements result from strong collaborations;(4)review papers,for example,(Dawson et al.,Annu Rev Ecol Syst 33:507-559,2002)and(McCarroll and Loader,Quat Sci Rev 23:771-801,2004),are among the most cited,with more than 1000 citations;(5)tree ring stable isotope studies mainly focus on climatology and ecology,with atmospheric CO_(2) one of the most popular topics.Since 2010,precipitation and drought have received increasing attention.Based on this analysis,the research stages,key findings,debated issues,limitations and direc-tions for future research are summarized.This study serves as an important attempt to understand the progress on the use of stable isotopes in tree rings,providing scientific guid-ance for young researchers in this field.

Stable multi-electron reaction stimulated by W doping VS_(4)for enhancing magnesium storage performance

Rechargeable magnesium batteries(RMBs)hold promise for offering higher volumetric energy density and safety features,attracting increasing research interest as the next post lithium-ion batteries.Developing high performance cathode material by inducing multi-electron reaction process as well as maintaining structural stability is the key to the development and application of RMBs.Herein,multielectron reaction occurred in VS_(4)by simple W doping strategy.W doping induces valence of partial V as V^(2+)and V^(3+)in VS_(4)structure,and then stimulates electrochemical reaction involving multi-electrons in 0.5%W-V-S.The flower-like microsphere morphology as well as rich S vacancies is also modulated by W doping to neutralize structure change in such multi-electron reaction process.The fabricated 0.5%W-V-S delivers higher specific capacity(149.3 m A h g^(-1)at 50 m A g^(-1),which is 1.6 times higher than that of VS_(4)),superior rate capability(76 mA h g^(-1)at 1000 mA g^(-1)),and stable cycling performance(1500cycles with capacity retention ratio of 93.8%).Besides that,pesudocapaticance-like contribution analysis as well as galvanostatic intermittent titration technique(GITT)further confirms the enhanced Mg^(2+)storage kinetics during such multi-electron involved electrochemical reaction process.Such discovery provides new insights into the designing of multi-electron reaction process in cathode as well as neutralizing structural change during such reaction for realizing superior electrochemical performance in energy storage devices.

Effects of thinning and understory removal on water use efficiency of Pinus massoniana:evidence from photosynthetic capacity and stable carbon isotope analyses

Understanding the relationship between forest management and water use efficiency(WUE)is important for evaluating forest adaptability to climate change.However,the effects of thinning and understory removal on WUE and its key controlling processes are not well understood,which limits our comprehension of the physiological mechanisms of various management practices.In this study,four forest management measures(no thinning:NT;understory removal:UR;light thinning:LT;and heavy thinning:HT)were carried out in Pinus massoniana plantations in a subtropical region of China.Photosynthetic capacity and needle stable carbon isotope composition(δ^(13)C)were measured to assess instantaneous water use efficiency(WUE_(inst))and long-term water use efficiency(WUE_(i)).Multiple regression models and structural equation modelling(SEM)identified the effects of soil properties and physiological performances on WUE_(inst)and WUE_(i).The results show that WUE_(inst)values among the four treatments were insignificant.However,compared with the NT stand(35.8μmol·mol^(-1)),WUE_(i)values significantly increased to 41.7μmol·mol^(-1)in the UR,50.1μmol·mol^(-1)in the LT and 46.6μmol·mol^(-1)in HT treatments,largely explained by photosynthetic capacity and soil water content.Understory removal did not change physiological performance(needle water potential and photosynthetic capacity).Thinning increased the net photosynthetic rate(A_n)but not stomatal conductance(g_s)or predawn needle water potential(ψ_(pd)),implying that the improvement in water use efficiency for thinned stands was largely driven by radiation interception than by soil water availability.In general,thinning may be an appropriate management measure to promote P.massoniana WUE to cope with seasonal droughts under future extreme climates.

Hydraulic properties and drought response of a tropical bamboo (Cephalostachyum pergracile)

Bamboo plants are an essential component of tropical ecosystems,yet their vulnerability to climate extremes,such as drought,is poorly understood due to limited knowledge of their hydraulic properties.Cephalostachyum pergracile,a commonly used tropical bamboo species,exhibited a substantially higher mortality rate than other co-occurring bamboos during a severe drought event in 2019,but the underlying mechanisms remain unclear.This study investigated the leaf and stem hydraulic traits related to drought responses,including leaf-stem embolism resistance(P50leaf;P50stem) estimated using optical and X-ray microtomography methods,leaf pressure-volume and water-releasing curves.Additionally,we investigated the seasonal water potentials,native embolism level(PLC) and xylem water source using stable isotope.We found that C.pergracile exhibited strong resistance to embolism,showing low P50leaf,P50stem,and turgor loss point,despite its rapid leaf water loss.Interestingly,its leaves displayed greater resistance to embolism than its stem,suggesting a lack of effective hydraulic vulnerability segmentation(HVS) to protect the stem from excessive xylem tension.During the dry season,approximately 49% of the water was absorbed from the upper 20-cm-deep soil layer.Consequently,significant diurnal variation in leaf water potentials and an increase in midday PLC from 5.87±2.33% in the wet season to 12.87±4.09%in the dry season were observed.In summary,this study demonstrated that the rapid leaf water loss,high reliance on surface water,and a lack of effective HVS in C.pergracile accelerated water depletion and increased xylem embolism even in the typical dry season,which may explain its high mortality rate during extreme drought events in 2019.

Comparison of isotope-based linear and Bayesian mixing models in determining moisture recycling ratio

Stable water isotopes are natural tracers quantifying the contribution of moisture recycling to local precipitation,i.e.,the moisture recycling ratio,but various isotope-based models usually lead to different results,which affects the accuracy of local moisture recycling.In this study,a total of 18 stations from four typical areas in China were selected to compare the performance of isotope-based linear and Bayesian mixing models and to determine local moisture recycling ratio.Among the three vapor sources including advection,transpiration,and surface evaporation,the advection vapor usually played a dominant role,and the contribution of surface evaporation was less than that of transpiration.When the abnormal values were ignored,the arithmetic averages of differences between isotope-based linear and the Bayesian mixing models were 0.9%for transpiration,0.2%for surface evaporation,and–1.1%for advection,respectively,and the medians were 0.5%,0.2%,and–0.8%,respectively.The importance of transpiration was slightly less for most cases when the Bayesian mixing model was applied,and the contribution of advection was relatively larger.The Bayesian mixing model was found to perform better in determining an efficient solution since linear model sometimes resulted in negative contribution ratios.Sensitivity test with two isotope scenarios indicated that the Bayesian model had a relatively low sensitivity to the changes in isotope input,and it was important to accurately estimate the isotopes in precipitation vapor.Generally,the Bayesian mixing model should be recommended instead of a linear model.The findings are useful for understanding the performance of isotope-based linear and Bayesian mixing models under various climate backgrounds.

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。

Software Defect Prediction Method Based on Stable Learning

The purpose of software defect prediction is to identify defect-prone code modules to assist software quality assurance teams with the appropriate allocation of resources and labor.In previous software defect prediction studies,transfer learning was effective in solving the problem of inconsistent project data distribution.However,target projects often lack sufficient data,which affects the performance of the transfer learning model.In addition,the presence of uncorrelated features between projects can decrease the prediction accuracy of the transfer learning model.To address these problems,this article propose a software defect prediction method based on stable learning(SDP-SL)that combines code visualization techniques and residual networks.This method first transforms code files into code images using code visualization techniques and then constructs a defect prediction model based on these code images.During the model training process,target project data are not required as prior knowledge.Following the principles of stable learning,this paper dynamically adjusted the weights of source project samples to eliminate dependencies between features,thereby capturing the“invariance mechanism”within the data.This approach explores the genuine relationship between code defect features and labels,thereby enhancing defect prediction performance.To evaluate the performance of SDP-SL,this article conducted comparative experiments on 10 open-source projects in the PROMISE dataset.The experimental results demonstrated that in terms of the F-measure,the proposed SDP-SL method outperformed other within-project defect prediction methods by 2.11%-44.03%.In cross-project defect prediction,the SDP-SL method provided an improvement of 5.89%-25.46% in prediction performance compared to other cross-project defect prediction methods.Therefore,SDP-SL can effectively enhance within-and cross-project defect predictions.

Linkage between precipitation isotopes and water vapor sources in the monsoon margin:Evidence from arid areas of Northwest China

The isotope composition in precipitation has been widely considered as a tracer of monsoon activity.Compared with the coastal region,the monsoon margin usually has limited precipitation with large fluctuation and is usually sensitive to climate change.The water resource management in the monsoon margin should be better planned by understanding the composition of precipitation isotope and its influencing factors.In this study,the precipitation samples were collected at five sampling sites(Baiyin City,Kongtong District,Maqu County,Wudu District,and Yinchuan City)of the monsoon margin in the northwest of China in 2022 to analyze the characteristics of stable hydrogen(δD)and oxygen(δ18O)isotopes.We analyzed the impact of meteorological factors(temperature,precipitation,and relative humidity)on the composition of precipitation isotope at daily level by regression analysis,utilized the Hybrid Single-Particle Lagrangian Integrated Trajectory(HYSPLIT)-based backward trajectory model to simulate the air mass trajectory of precipitation events,and adopted the potential source contribution function(PSCF)and concentration weighted trajectory(CWT)to analyze the water vapor sources.The results showed that compared with the global meteoric water line(GMWL),the slope of the local meteoric water line(LMWL;δD=7.34δ^(18)O-1.16)was lower,indicating the existence of strong regional evaporation in the study area.Temperature significantly contributed toδ18O value,while relative humidity had a significant negative effect onδ18O value.Through the backward trajectory analysis,we found eight primary locations that were responsible for the water vapor sources of precipitation in the study area,of which moisture from the Indian Ocean to South China Sea(ITSC)and the western continental(CW)had the greatest influence on precipitation in the study area.The hydrogen and oxygen isotopes in precipitation are significantly influenced by the sources and transportation paths of air mass.In addition,the results of PSCF and CWT analysis showed that the water vapor source areas were primarily distributed in the south and northwest direction of the study area.

Observer-based robust high-order fully actuated attitude autopilot design for spinning glide-guided projectiles

This paper investigates the design of an attitude autopilot for a dual-channel controlled spinning glideguided projectile(SGGP),addressing model uncertainties and external disturbances.Based on fixed-time stable theory,a disturbance observer with integral sliding mode and adaptive techniques is proposed to mitigate total disturbance effects,irrespective of initial conditions.By introducing an error integral signal,the dynamics of the SGGP are transformed into two separate second-order fully actuated systems.Subsequently,employing the high-order fully actuated approach and a parametric approach,the nonlinear dynamics of the SGGP are recast into a constant linear closed-loop system,ensuring that the projectile's attitude asymptotically tracks the given goal with the desired eigenstructure.Under the proposed composite control framework,the ultimately uniformly bounded stability of the closed-loop system is rigorously demonstrated via the Lyapunov method.Validation of the effectiveness of the proposed attitude autopilot design is provided through extensive numerical simulations.

A low-profile metamaterial absorber with ultrawideband reflectionless and wide-angular stability

An ultrawideband reflectionless metamaterial absorber(MA)is proposed by replacing the metallic ground with the complementary split-ring resonator(CSRR)structure.The proposed MA exhibits-10 d B reflectivity spectrum from 1 GHz to 20 GHz,which maintains more than 90%absorption from 1.5 GHz to20 GHz.Furthermore,it achieves angle stability for TE and TM polarization at oblique incident angles up to 40°and 65°,respectively.To achieve broadband absorption spectrum,we have adopted a single-layer high-impedance surface(HIS)loaded with a double-layer magnetic material(MM)structure.To further realize the RCS reduction into a lower frequency range,we have employed the scattering cancellation technology into the traditional metallic ground.Finally,we have fabricated a sample exhibiting the 10 d B RCS reduction from 1 GHz to 20 GHz with a thickness of 10 mm.Measurement and simulation results confirm that the proposed MA exhibits excellent comprehensive performance,making it suitable for many practical applications.

Novel Static Security and Stability Control of Power Systems Based on Artificial Emotional Lazy Q-Learning

The stability problem of power grids has become increasingly serious in recent years as the size of novel power systems increases.In order to improve and ensure the stable operation of the novel power system,this study proposes an artificial emotional lazy Q-learning method,which combines artificial emotion,lazy learning,and reinforcement learning for static security and stability analysis of power systems.Moreover,this study compares the analysis results of the proposed method with those of the small disturbance method for a stand-alone power system and verifies that the proposed lazy Q-learning method is able to effectively screen useful data for learning,and improve the static security stability of the new type of power system more effectively than the traditional proportional-integral-differential control and Q-learning methods.

Incidence, Clinical Presentation and Angiographic Findings among Patients with Coronary Artery Ectasia in Gaza

Background: Coronary artery ectasia (CAE) is a rare form of aneurysmal coronary heart disease. This condition increases risk of ischemia that leaded to stable angina pectoris and also acute coronary syndrome. Objective: To evaluate the incidence of CAE and to analyze clinical and angiographic characteristics among patients with symptomatic coronary artery disease. Methods: Retrospective trial of diagnostic coronary angiography which was performed at Alshifa hospital in Gaza, included all patients with coronary heart disease and underwent diagnostic coronary angiography from March 2014 to March 2023. We evaluate the incidence, clinical presentation and angiographic findings of patients with symptomatic coronary ectasia. Results: Of the 12,534 angiograms analyzed, CAE was found in 539 patients, an incidence of 4.3%. The mean age was 59.2 ± 11.7 years, and male gender predominate 81.8%. A 285 (52.9%) of patients found to have single ectatic vessel at their angiographic results. In two vessels 120 patients (22.3%), in three vessels 95 patients (17.6%) and in three vessel plus left main in 39 patients (7.2%). 70.9% angiograms showed pure ectasia without associated significant stenotic lesions in the same vessel. The right coronary artery (RCA) was the commonest affected vessel by ectasia. The most common presentation of patients is non ST segment elevation acute coronary syndrome. Conclusion: The incidence of coronary ectasia was 4.3%. Non ST segment elevation acute coronary syndrome was the most common clinical presenting. Only 30% of patients have additionally significant coronary artery stenosis. The majority of patients had single vessel involvement and right coronary artery was the most common involved vessel. Despite a dapper understanding of CAE in last years, there are still come critical issues about optimal treatment. Large multicenter randomized control trials are recommended to guide the clinician in the management of this complex sitting of patients.

Loggerhead Sea Turtles Hand-Reared in Captivity: Isotopic Insights into Their Inherent Dietary Variation

Stable isotope analysis is a widely used method for gathering ecological insights into the diet and feeding habitats of various species. While captive studies often limit lethal sampling and differ from wild conditions, they offer valuable insights into inherent isotopic variations among individuals, which are often assumed to reflect differences between natural populations. In the Sea Turtle Conservation Program, loggerhead turtle hatchlings from different nests were fed. Necropsies were conducted on turtles that died during this period, obtaining bone fragments for analysis. We evaluated the isotopic variation of carbon (δ13C) and nitrogen (δ15N) in bone tissue across six turtle nests (n = 66 samples) and assessed differences in Straight Carapace Length (SCL, n = 71 samples). Using SIBER and nicheROVER in R, we calculated niche width and overlap, while the simmr package determined primary prey assimilation. Despite feeding the hatchlings the same prey, we observed variations in nitrogen isotope assimilation between nests. Nests 4 and 6 had a niche width >1.8‰, indicating consistent consumption frequencies across all prey and >70% niche overlap with other nests. In contrast, nests 1 and 2 showed a narrower niche width (Mugil sp. constituted the primary diet component (>40%) across all groups. This study demonstrates how factors like competition or prey preference can influence the assimilation of diet, even when the source remains constant (inherent variation).

AI绘画在艺术创作中的应用——以Stable Diffusion为例

AI绘画是基于人工智能技术进行艺术创作的一种方法,在AI绘画中,Stable Diffusion可提供稳定、连续和高质量的图像生成。Stable Diffusion是一种基于生成对抗网络的图像生成方法,它通过不断更新图像的噪声分布,逐渐生成越来越逼真的图像。在绘画艺术创作中,Stable Diffusion能够激发创作者的灵感,帮助他们探索不同的创作风格和创作方式。与此同时,创作者仍需运用自己的审美判断力对所绘制的作品进行筛选和调整。