Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 18 of 18 for “"DALL-E"”.
-
Sesgos de la inteligencia artificial en la representación visual de los pueblos indígenas amazónicos
… por dos plataformas de Inteligencia Artificial, DALL-E y Runway, sobre la representación de los pueblos indígenas amazónicos para identificar sesgos en ellas. Se analizó 400 imágenes en los campos referidos a la cantidad de personas, género, rango de edad, espacio geográfico donde se ubican y las …
-
Sad and dreamy there : exploring nostalgia, narrative, and family histories through experimental video : an exegesis presented in partial fulfillment of the requirements for the postgraduate degree of Master of Fine Arts at Massey University, Wellington, New Zealand
… Artificial Intelligence (AI) engines such as DALL-E. The sound includes cloning of my father’s voice through the AI engine at Eleven Labs. Combining the authentic and the inauthentic, history and falsehood, I am evoking an interior psychological space where memories are faulty or even wholly …
-
Minds, Brains and Autonomous Human-Like Embodied AI Physical Drawing Machines for Generating Architectural Design Concepts
… DNN-based image generative approach, such as DALL-E 2, creating DALL-E 2-BraccioV4. The latter can process can be thought to bear parallels with human architectural designers’ externalising their generated design ideas in their <i>visual mental imagery via traditional physical hand …
-
COLLABORATIVE INTELLIGENCE: THE FUTURE ROLE OF ARTIFICIAL INTELLIGENCE IN BUSINESS CREATIVITY
… providing immediate feedback. AI programs like Dall-E and ChatGPT can augment human creativity, offering new perspectives and approaches that enhance the ideation phase. However, AI-generated content often requires human intervention to ensure accuracy and clarity, highlighting the importance of …
-
We’re cooked : creative responses to generative AI and atmospheres of technocapitalism on Twitter
… 2022, generative AI art tools such as OpenAI’s DALL-E (January 2021), Hugging Face’s Craiyon (April 2022), and Midjourney (July 2022), were steadily gaining popularity. However, the release of OpenAI’s AI text-based tool, ChatGPT, in November 2022 brought many new eyes to the world of generative …
-
Quantitative and Qualitative Analysis of Text-to-Image models
… text-to-image models, namely Stable Diffusion, DALL-E Mini, Lafite, and Ernie-ViLG. I assess their performance in generating accurate images of human faces, groups, and specified numbers of objects, using both Frechet Inception Distance (FID) scores and R-precision as my evaluation metrics. …
-
Auditing imbalance and bias in deep neural networks for multimedia content analytics
… in large visual-linguistic models like CLIP, DALL-E and Stable Diffusion. Traditional bias measures, focusing on accuracy, were found inadequate for capturing the extent of bias in multimodal vision models. Techniques from NLP were adapted to create metrics to capture bias in multiple …
-
Three Degrees of Representation: How GenAI Filters, Retrieves, and Remixes Lesbian Film Data
… with image and text generators (in this case, DALL-E 3 and ChatGPT-5) builds on established methods of algorithm auditing. An analysis of the AI-generated data reveals the homogenizing drift and the biases inherent in “the coded gaze” (Buolumwini). Furthermore, the featured data comparisons and …
-
Evaluation of three text-to-image Gen AI models
… ορίζουμε τα τρία προς αξιολόγηση μοντέλα (DALL-E 2, Stable Diffusion, Pix-Art-α) και τις τρεις υπερπαράμετρους που χρησιμοποιούμε για την αξιολόγηση τους: κείμενο (prompt), πλάτος (width) και ύψος (height). Στην παράμετρο κειμένου εκχωρούνται τιμές από το πρωτόκολλο αναφοράς (benchmark) που …
-
The protection of AI-generated works under European copyright law : toward adoption of a neighbouring rights approach
… capacities, thanks to generative models such as DALL-E and Midjourney, and sometimes even win awards with these works. These intelligent technologies – incorporated by many into their creative endeavours – throw into question the boundaries of copyright law, built as it is upon human creativity. …
-
AdaptPrompt with Diffusion Set: A Unified Framework for Generalizable Deepfake Detection
… available tools such as Stable Diffusion and DALL-E pose immediate challenges to existing detection techniques. Diffusion models generate photorealistic and high-resolution content with less observable or detectable artifacts and are, therefore, more difficult to detect using traditional …
-
Generatyvus dirbtinis intelektas Lietuvos žiniasklaidoje: žiniasklaidos darbuotojų požiūris /
… artificial intelligence tools like „ChatGPT“, „DALL-E“ and „Midjourney“ become more advanced and accessible, they raise profound implications for the field of journalism and its role in democratic society. Journalism has long served as a bulwark against the proliferation of misinformation, …
-
Ataques adversarios en redes neuronales: análisis de transferabilidad y generación de imágenes adversarias mediante modelos difusos
… complejas o generar código de programación. Dall E 2 genera imágenes de alta resolución respondiendo a complejos prompts, desde dibujos animados a todo tipo de representaciones realistas. Existen otros tipos de modelos, quizás menos mediáticos, que también han alcanzado resultados notables. …
-
Process Mining over Conversational Data
… από το ευρύ κοινό. Εφαρμογές όπως το ChatGPT, το Dall-E, το Bard, και άλλα χρησιμοποιούνται από όλο και περισσότερα άτομα ημερησίως. Άλλες εφαρμογές τεχνητής νοημοσύνης κάνουν χρήση επεξεργασίας της φυσικής γλώσσας, επεξεργασίας εικόνων, ή κατάταξης περιεχομένου πολυμέσων για διαφημιστικούς …
-
Multimodal Foundation Models through the Lens of Security: Robust Deepfake Detection and Adversarial Resilience
… Text-to-Image (T2I) generation models like DALL-E and Stable Diffusion, which create highly realistic images from simple text prompts. Additionally, Multimodal Large Language Models (MLLMs) such as LLaMA and ChatGPT integrate visual and textual data to generate informative responses. Vision …
-
Towards Securing Quantized Deep Learning
… Artificial Intelligence (AI) models such as DALL-E, Stable Diffusion, and Midjourney. While larger models remain a significant trend, there is a counter-trend towards small models, often referred to as Tiny Machine Learning (TinyML). These smaller models cater to on-device inference tasks, …
-
Hallucinations in Large Foundation Models: Characterization, Quantification, Detection, Avoidance, and Mitigation
… Large Foundation Models (LFMs), like GPT and DALL-E, are accessible to the general public, enabling individuals to efficiently produce high-quality creative content on a large scale. For example, in healthcare, GenAI models help in drug discovery and medical imaging analysis, while in …
-
Designer Robots: An early look at applications for Artificial Intelligence Visualization Software in Landscape Architecture
Due to rapid technological changes, artificial intelligence (AI) driven graphic software appears to be the next frontier in creating digital imagery, though little is known on the potential of artificial intelligence for rendering landscape architecture graphics. The objective of this study is to …