• 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.

• International journal of advanced smart convergence
• /
• 제12권2호
• /
• pp.90-95
• /
• 2023

With the rapid development of deep learning and artificial intelligence, generative models have achieved remarkable success in the field of image generation. By combining the stable diffusion method with Web UI technology, a novel solution is provided for the application of AI painting generation. The application prospects of this technology are very broad and can be applied to multiple fields, such as digital art, concept design, game development, and more. Furthermore, the platform based on Web UI facilitates user operations, making the technology more easily applicable to practical scenarios. This paper introduces the basic principles of Stable Diffusion Web UI technology. This technique utilizes the stability of diffusion processes to improve the output quality of generative models. By gradually introducing noise during the generation process, the model can generate smoother and more coherent images. Additionally, the analysis of different model types and applications within Stable Diffusion Web UI provides creators with a more comprehensive understanding, offering valuable insights for fields such as artistic creation and design.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제17권2호
• /
• pp.129-138
• /
• 2013

A spatio-temporal models as systems of ODE which describe two-species Beddington - DeAngelis type predator-prey system living in a habitat of two identical patches linked by migration is investigated. It is assumed in the model that the per capita migration rate of each species is influenced not only by its own but also by the other one's density, i.e. there is cross diffusion present. We show that a standard (self-diffusion) system may be either stable or unstable, a cross-diffusion response can stabilize an unstable standard system and destabilize a stable standard system. For the diffusively stable model, numerical studies show that at a critical value of the bifurcation parameter the system undergoes a Turing bifurcation and the cross migration response is an important factor that should not be ignored when pattern emerges.

• 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.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.23-24
• /
• 2023

가상 면접은 현대 사회에서 필수적인 기술이지만, 상호작용의 부족으로 인해 한계가 존재한다. 현실적이고 현장감 있는 가상 면접을 구현하기 위해서는 면접관을 자동으로 생성하여 다양한 상황에서의 면접을 진행할 필요가 있다. 본 논문은 Stable Diffusion 기반의 프롬프트 엔지니어링을 통해 가상 면접관 생성에 대한 연구 결과를 제시한다. 프롬프트 엔지니어링은 Stable Diffusion 모델이 생성하는 결과의 품질을 향상시킬 수 있으며 다양한 조건에 따른 실험 결과를 제시한다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회B
• /
• pp.2366-2371
• /
• 2007

Spray combustion characteristics of a conducting fuel electrospray have been studied for clean combustion technology. The multiplexing system which can retain the characteristics of the cone-jet mode is inevitable for the electrospray application. Charged micro droplets can be obtained in almost uniform size during operating the electrospray in the cone-jet mode. This experiment device set up the multiplexed grooved nozzle system with the extractor. Using the grooved nozzle, the stable cone-jet mode can be achieved at the each groove in the grooved mode. This electrospray system was applied to the diffusion combustion. It is the first step to discover the diffusion combustion characteristics of the electrospray. In case of the single grooved nozzle electrospray, the diffusion flames are occurred at each jet of grooved mode and they are quite stable. The exhaust gas analysis was indicated that there is the critical point which can make very stable diffusion combustion.

• 대한기계학회논문집B
• /
• 제31권12호
• /
• pp.979-985
• /
• 2007

Spray combustion characteristics of the conducting fuel electrospray has been studied for clean combustion technology. The electrospraying multiplexed system which can maintain the characteristics of the cone-jet mode is able to obtain charged micro droplets with high flow rate. In addition, they have monodisperse distribution during operating the electrospray in the cone-jet mode. The multiplexed grooved nozzle system with the extractor was applied to this experimental device set up. The stable grooved mode can be generated by the grooved nozzle and this electrospray system was applied to the diffusion combustion. It is the first step to discover the diffusion combustion characteristics of the electrospray, In case of the single grooved nozzle electrospray the diffusion flames are occurred at each Jet of grooved mode and they are quite stable. The exhaust gas analysis was indicated that there is the critical point which can make very stable diffusion combustion

• 한국연소학회지
• /
• 제15권3호
• /
• pp.74-81
• /
• 2010

In this study, soot formation characteristics on the instability of laminar diffusion flames were investigated experimentally using a concentric co-flow burner. When a small amount of air was supplied through an inner nozzle, a stable propane laminar diffusion flame became unstable and began to oscillate mainly due to the dilution effect. The increase of air flow rate transformed an oscillating non-sooting flame into a stable nonsooting flame. When the air flow rate was continuously increased an inner flame was formed and the flame was changed to an oscillating sooting flame, an oscillating non-sooting flame and finally a stable non-sooting hollow flame. When the air flow rate was decreased, a non-sooting hollow flame was eventually changed back to a stable non-sooting flame. The presence of an inner flame, however, altered the soot formation characteristics of a flame. More soot production was observed with the presence of an inner flame. The increased or decreased soot formation/oxidation rates, the radiation heat loss, and the heating effect of inner flames are most likely to be responsible for the observed instability of laminar diffusion flames.

• 한국구조물진단유지관리공학회 논문집
• /
• 제28권4호
• /
• pp.55-61
• /
• 2024

최근 들어 노후화된 콘크리트 구조물의 비중이 점차 늘어나는 추세다. 이는 대다수의 구조물이 기대수명에 근접하고 있기 때문이다. 이 같은 구조물은 정확한 점검과 지속적인 관리가 필수적으로 요구되며, 철저한 점검이 이루어지지 않을 경우 본래의 기능과 성능이 저하되어 안전사고로 이어질 수 있음은 자명한 사실이다. 따라서 딥러닝과 컴퓨터 비전을 이용한 객관적인 점검 기술에 대한 연구가 활발하기 이뤄지고 있다. 특히 고해상도는 미세한 균열뿐만 아니라 박락과 철근 노출까지 정확하게 관찰할 수 있으며, 딥러닝을 통해서 자동화 탐지가 가능하다는 장점이 있다. 딥러닝은 다양하고 다수의 훈련 데이터가 있어야지만 높은 탐지 성능을 보장할 수 있지만, 콘크리트의 표면 손상은 비정상 장면으로 일반적으로 촬영하여 확보할 수 있는 데이터가 아니므로 훈련 데이터의 수는 부족할 수밖에 없다. 이러한 한계를 극복하기 위해서 이 연구에서는 stable diffusion을 통해 균열, 박락, 철근 노출을 포함하고 있는 콘크리트 표면 손상 영상을 생성하는 방법을 제안했다. 이는 문자열과 영상이 쌍을 이룬 데이터로 새로운 손상 영상을 합성하는 방법이다. 이를 위해서 총 678장의 훈련 데이터 세트를 구축했고, low rank adaptation을 통해서 fine-tuning을 수행했다. 이때 stable diffusion의 세 가지 기저 모델에 따른 생성 영상의 품질을 비교했다. 결과적으로 가장 다양하고 고품질의 콘크리트 손상 영상을 합성하는 방법을 완성했다. 이 연구는 향후 데이터 부족 문제 해결에 기여하여 딥러닝 기반 손상 탐지 알고리즘의 정확도 향상에 긍정적인 영향을 미칠 것으로 기대한다.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.1-14
• /
• 2024

While text-to-image models have made remarkable progress in image synthesis, certain models, particularly generative diffusion models, have exhibited a noticeable bias to- wards generating images related to the culture of some developing countries. This paper introduces an empirical investigation aimed at mitigating the bias of image generative model. We achieve this by incorporating symbols representing Saudi culture into a stable diffusion model using the Dreambooth technique. CLIP score metric is used to assess the outcomes in this study. This paper also explores the impact of varying parameters for instance the quantity of training images and the learning rate. The findings reveal a substantial reduction in bias-related concerns and propose an innovative metric for evaluating cultural relevance.