Text-to-image technology enables computers to create images from text by simulating the human process of forming mental images. GAN-based text-to-image technology involves extracting features from input text; subsequently, they are combined with noise and used as input to a GAN, which generates images similar to the original images via competition between the generator and discriminator. Although images have been extensively generated from English text, text-to-image technology based on multilingualism, such as Korean, is in its developmental stage. Webtoons are digital comic formats for viewing comics online. The webtoon creation process involves story planning, content/sketching, coloring, and background drawing, all of which require human intervention, thus being time-consuming and expensive. Therefore, this study proposes a multilingual text-to-image model capable of generating webtoon images when presented with multilingual input text. The proposed model employs multilingual BERT to extract feature vectors for multiple languages and trains a DCGAN in conjunction with the images. The experimental results demonstrate that the model can generate images similar to the original images when presented with multilingual input text after training. The evaluation metrics further support these findings, as the generated images achieved an Inception score of 4.99 and an FID score of 22.21.

This study focuses on harnessing deep-learning-based text-to-image transformation techniques to help webtoon creators’ creative outputs. We converted publicly available datasets (e.g., MSCOCO) into a multimodal webtoon dataset using CartoonGAN. First, the dataset was leveraged for training contrastive language image pre-training (CLIP), a model composed of multi-lingual BERT and a Vision Transformer that learnt to associate text with images. Second, a pre-trained diffusion model was employed to generate webtoons through text and text-similar image input. The webtoon dataset comprised treatments (i.e., textual descriptions) paired with their corresponding webtoon illustrations. CLIP (operating through contrastive learning) extracted features from different data modalities and aligned similar data more closely within the same feature space while pushing dissimilar data apart. This model learnt the relationships between various modalities in multimodal data. To generate webtoons using the diffusion model, the process involved providing the CLIP features of the desired webtoon’s text with those of the most text-similar image to a pre-trained diffusion model. Experiments were conducted using both single- and continuous-text inputs to generate webtoons. In the experiments, both single-text and continuous-text inputs were used to generate webtoons, and the results showed an inception score of 7.14 when using continuous-text inputs. The text-to-image technology developed here could streamline the webtoon creation process for artists by enabling the efficient generation of webtoons based on the provided text. However, the current inability to generate webtoons from multiple sentences or images while maintaining a consistent artistic style was noted. Therefore, further research is imperative to develop a text-to-image model capable of handling multi-sentence and -lingual input while ensuring coherence in the artistic style across the generated webtoon images.

This study investigated the effects of filler metal composition and δ-ferrite characteristics on the cryogenic behavior and corrosion resistance of 316L austenitic stainless steel (STS) welds produced by gas tungsten arc welding (GTAW) using 309L and 312 filler metals (FMs). Different δ-ferrite fractions and morphologies were observed in the weld metals (WMs), with the δ-ferrite fraction being lower in the ER309L WM than in the ER312 WM. Despite its higher δ-ferrite fraction, the ER312 WM exhibited better corrosion resistance than the ER309L WM, which was primarily attributed to its higher Cr content. The ER312 weld also exhibited higher tensile strength than the ER309L weld at both 300 and 123 K, which was associated with differences in the WM microstructure, δ-ferrite characteristics, and FM composition. All welds exhibited enhanced tensile strength at 123 K, primarily due to strain-induced martensitic transformation, while deformation twinning may also have contributed to the cryogenic deformation behavior. These findings demonstrate that the cryogenic mechanical and corrosion behaviors of 316L stainless steel welds are influenced by the combined effects of filler metal composition and δ-ferrite characteristics.

Digital Image Correlation (DIC) models are directed by texture-awareness means and the guidance signal loses crucial, fine-grained detail in the process when naively downsampled to modulate the abrasive, semantic feature maps in the encoder’s deeper layers. While current state-of-the-art models like RAFT achieve high precision through iterative refinement, they, in addition, undergo significant computational latency, limiting their efficacy in real-time industrial monitoring. The proposed model makes use of a five-level U-Net backbone joined with a hierarchical decoder that creates four-channel displacement and uncertainty priors across three resolution scales (1/4, 1/2, and full scale), ensuring that the expansive path obtains geometrically founded signals to do away with the need for recurrent loops. Experimental validation on a structured dataset of 36,000 reference-deformed images shows that the proposed method offers a highly optimized accuracy-latency tradeoff. DNet-MRSP achieves a mean End-Point Error (EPE) of \(0.00302 \pm 0.00050\text { px}\), exceeding baseline designs such as Deep DIC \(\text {(EPE} = 1.97721\text { px)}\) and unconstrained optical flow models like RAFT-DIC (\(\text {EPE} = 4.42217\text { px}\)). The framework has a rapid feed-forward execution latency of \(2.23 \pm 1.70\text { ms}\), which results in an operational processing throughput of 448.3 frames per second. This profile offers a slight latency trade-off with traditional Deep DIC (\(1.75\text { ms}\)) that is totally justified by a significant leap in sub-pixel tracking accuracy.