• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.563-564
• /
• 2023

Midjourney and Stable Diffusion are two popular AI-generated image programs nowadays. With AI's outstanding image-generation capabilities, everyone can create artistic paintings in just a few minutes. Therefore, "Comparison of differences between AI-generated images using Midjourney and Stable Diffusion" will help see each program's advantages and assist the users in identifying the tool suitable for their needs.

• 천문학회보
• /
• 제46권1호
• /
• pp.60.2-60.2
• /
• 2021

In this study, we determinate the differential emission measure(DEM) of solar corona using three SDO/AIA EUV channel images and three AI-generated ones. To generate the AI-generated images, we apply a deep learning model based on multi-layer perceptrons by assuming that all pixels in solar EUV images are independent of one another. For the input data, we use three SDO/AIA EUV channels (171, 193, and 211). For the target data, we use other three SDO/AIA EUV channels (94, 131, and 335). We train the model using 358 pairs of SDO/AIA EUV images at every 00:00 UT in 2011. We use SDO/AIA pixels within 1.2 solar radii to consider not only the solar disk but also above the limb. We apply our model to several brightening patches and loops in SDO/AIA images for the determination of DEMs. Our main results from this study are as follows. First, our model successfully generates three solar EUV channel images using the other three channel images. Second, the noises in the AI-generated EUV channel images are greatly reduced compared to the original target ones. Third, the estimated DEMs using three SDO/AIA images and three AI-generated ones are similar to those using three SDO/AIA images and three stacked (50 frames) ones. These results imply that our deep learning model is able to analyze temperature response functions of SDO/AIA channel images, showing a sufficient possibility that AI-generated data can be used for multi-wavelength studies of various scientific fields. SDO: Solar Dynamics Observatory AIA: Atmospheric Imaging Assembly EUV: Extreme Ultra Violet DEM: Diffrential Emission Measure

• 천문학회보
• /
• 제44권1호
• /
• pp.81.2-81.2
• /
• 2019

We develop an image-to-image translation model, which is a popular deep learning method based on conditional Generative Adversarial Networks (cGANs), to generate solar magnetograms and EUV images from sunspot drawings. For this, we train the model using pairs of sunspot drawings from Mount Wilson Observatory (MWO) and their corresponding SDO/HMI magnetograms and SDO/AIA EUV images (512 by 512) from January 2012 to September 2014. We test the model by comparing pairs of actual SDO images (magnetogram and EUV images) and the corresponding AI-generated ones from October to December in 2014. Our results show that bipolar structures and coronal loop structures of AI-generated images are consistent with those of the original ones. We find that their unsigned magnetic fluxes well correlate with those of the original ones with a good correlation coefficient of 0.86. We also obtain pixel-to-pixel correlations EUV images and AI-generated ones. The average correlations of 92 test samples for several SDO lines are very good: 0.88 for AIA 211, 0.87 for AIA 1600 and 0.93 for AIA 1700. These facts imply that AI-generated EUV images quite similar to AIA ones. Applying this model to the Galileo sunspot drawings in 1612, we generate HMI-like magnetograms and AIA-like EUV images of the sunspots. This application will be used to generate solar images using historical sunspot drawings.

• International Journal of Advanced Culture Technology
• /
• 제11권2호
• /
• pp.403-408
• /
• 2023

The widespread discussion of AI-generated content, fueled by the emergence of consumer applications like ChatGPT and Midjourney, has attracted significant attention. Among various AI applications, AI painting has gained popularity due to its mature technology, user-friendly nature, and excellent output quality, resulting in a rapid growth in user numbers. Midjourney and Stable Diffusion are two of the most widely used AI painting tools by users. In this study, the author adopts a perspective that represents the general public and utilizes case studies and comparative analysis to summarize the distinctive features and differences between Midjourney and Stable Diffusion in the context of AI character illustration. The aim is to provide informative material forthose interested in AI painting and lay a solid foundation for further in-depth research on AI-generated content. The research findings indicate that both software can generate excellent character images but with distinct features.

• 천문학회보
• /
• 제44권1호
• /
• pp.82.3-82.3
• /
• 2019

In this study, we generate future full disk magnetograms in 12, 24, 36 and 48 hours advance from SDO/HMI images using deep learning. To perform this generation, we apply the convolutional generative adversarial network (cGAN) algorithm to a series of SDO/HMI magnetograms. We use SDO/HMI data from 2011 to 2016 for training four models. The models make AI-generated images for 2017 HMI data and compare them with the actual HMI magnetograms for evaluation. The AI-generated images by each model are very similar to the actual images. The average correlation coefficient between the two images for about 600 data sets are about 0.85 for four models. We are examining hundreds of active regions for more detail comparison. In the future we will use pix2pix HD and video2video translation networks for image prediction.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.130-135
• /
• 2024

The Stable diffsuion AI tool is popular among designers because of its flexible and powerful image generation capabilities. However, due to the diversity of its AI models, it needs to spend a lot of time testing different AI models in the face of different design plans, so choosing a suitable general AI model has become a big problem at present. In this paper, by comparing the AI images generated by two different Stable diffsuion models, the advantages and disadvantages of each model are analyzed from the aspects of the matching degree of the AI image and the prompt, the color composition and light composition of the image, and the general AI model that the generated AI image has an aesthetic sense is analyzed, and the designer does not need to take cumbersome steps. A satisfactory AI image can be obtained. The results show that Playground V2.5 model can be used as a general AI model, which has both aesthetic and design sense in various style design requirements. As a result, content designers can focus more on creative content development, and expect more groundbreaking technologies to merge generative AI with content design.

• 한국BIM학회 논문집
• /
• 제14권2호
• /
• pp.13-24
• /
• 2024

This research suggests a novel visualization approach utilizing Generative AI to render photorealistic architectural alternatives images in the early design phase. Photorealistic rendering intuitively describes alternatives and facilitates clear communication between stakeholders. Nevertheless, the conventional rendering process, utilizing 3D modelling and rendering engines, demands sophisticate model and processing time. In this context, the paper suggests a rendering approach employing the text-to-image method aimed at generating a broader range of intuitive and relevant reference images. Additionally, it employs an Text-to-Image method focused on producing a diverse array of alternatives reflecting architects' styles when visualizing the exteriors of residential buildings from the mass model images. To achieve this, fine-tuning for architects' styles was conducted using the Low-Rank Adaptation (LoRA) method. This approach, supported by fine-tuned models, allows not only single style-applied alternatives, but also the fusion of two or more styles to generate new alternatives. Using the proposed approach, we generated more than 15,000 meaningful images, with each image taking only about 5 seconds to produce. This demonstrates that the Generative AI-based visualization approach significantly reduces the labour and time required in conventional visualization processes, holding significant potential for transforming abstract ideas into tangible images, even in the early stages of design.

• 천문학회보
• /
• 제46권1호
• /
• pp.41.1-41.1
• /
• 2021

We generate solar magnetograms and EUV images from Galileo sunspot drawings using a deep learning model based on conditional generative adversarial networks. We train the model using pairs of sunspot drawing from Mount Wilson Observatory (MWO) and their corresponding magnetogram (or UV/EUV images) from 2011 to 2015 except for every June and December by the SDO (Solar Dynamic Observatory) satellite. We evaluate the model by comparing pairs of actual magnetogram (or UV/EUV images) and the corresponding AI-generated one in June and December. Our results show that bipolar structures of the AI-generated magnetograms are consistent with those of the original ones and their unsigned magnetic fluxes (or intensities) are well consistent with those of the original ones. Applying this model to the Galileo sunspot drawings in 1612, we generate HMI-like magnetograms and AIA-like EUV images of the sunspots. We hope that the EUV intensities can be used for estimating solar EUV irradiance at long-term historical times.

• 문화기술의 융합
• /
• 제10권5호
• /
• pp.397-406
• /
• 2024

오늘날 현대 패션디자인 분야에서는 새로운 디자인 도구로써 AI가 적극적으로 활용되고 있으며 디자이너와 AI와의 협업이라는 새로운 패러다임을 견인하게 되었다. 본 연구는 인간 디자이너와 AI와의 협업을 통한 융합적 패션디자인 개발 방법에 관한 연구이다. 본 연구의 목적은 패션 도식화를 AI 생성 프로그램 미드저니에 사용하여 생성한 패션디자인 이미지의 시각적, 조형적 특징과 변화를 분석함으로써 패션디자인 개발에 있어 AI 이미지 생성 프로그램 활용에 대한 이해와 활용 방법의 확장을 꾀하는 데 있다. 본 연구의 결과는 다음과 같다. 첫째, 미드저니는 이미지 생성 시 명령어보다는 사용한 기존 이미지의 특징에 더 의존적인 특성이 있다. 또한 의상과 이미지 배경 사이에서 절충적 상호작용을 통하여 디자인을 분산하여 응용하는 방식으로 새로운 이미지를 생성하며 명령어에 패션 아이템 명칭을 배제하면 더욱 다양한 아이디어를 얻을 수 있는 이미지를 생성할 수 있다. 둘째, 미드저니는 색상 생성에 있어서 초기에는 패션 도식화에 사용된 색상으로 의상 색을 표현하고 점차 다양한 색상 계열로 확장하며 이미지 배경도 색상 생성의 대상으로 인식한다. 셋째, 미드저니가 이미지 생성 시 색상과 디자인 사이에서 일종의 절충적 상관관계가 있으며 이에 따라 이미지 배경과 의상 색을 특정하여 제한하면 더욱 다양하게 발전된 패션디자인 이미지를 생성할수 있다.

• 문화기술의 융합
• /
• 제10권2호
• /
• pp.465-470
• /
• 2024

인공지능(Artificial Intelligence, AI) 기반 이미지 생성 기술의 발달로 다양한 이미지가 생성되고 있으며, 이를 정확하게 판별하는 기술이 필요하다. 생성된 이미지 데이터의 양에는 한계가 있으며, 한정된 데이터로 높은 성능을 내기 위해 본 연구에서는 전이 학습(Transfer Learning)을 활용한 생성 이미지를 판별하는 모델을 제안한다. ImageNet 데이터 셋으로 사전학습 된 모델을 입력 데이터 셋인 CIFAKE 데이터 셋에 그대로 적용하여 학습의 시간 비용을 줄인 후, 3개의 은닉층과 1개의 출력층을 더해 모델을 튜닝한다. 모델링 결과, 최종 레이어를 조정한 모델의 성능이 높아짐을 확인하였다. 딥러닝에서 전이 학습을 통해 학습한 후 출력층과 가까운 레이어를 데이터의 특성에 맞게 추가 및 조정하는 과정을 통해 적은 이미지 데이터로 인한 학습 정확도 이슈를 줄이고 생성된 이미지 판별을 할수 있다는 데 의의가 있다.