Guided, specialized, and creative: Advancing generative AI for image and video synthesis
Abstract
Generative modeling has undergone a rapid transformation in recent years, driven by advances in deep learning architectures. Diffusion models and generative adversarial networks (GANs) have expanded the creative possibilities of artificial intelligence, enabling unprecedented control and quality in image and video synthesis. However, challenges emerge — such as adapting generators to novel domains, personalized and high-fidelity image and video synthesis, and fostering genuine creativity beyond conventional outputs. This dissertation aims to address these gaps. First, we present a diffusion-guided domain adaptation method enabling GANs to shift to novel domains from text prompts without target-domain data. Second, we present a tuning-free multimodal LLM adapter for zero-shot personalized image generation from a single reference image. Third, we extend our focus to the temporal dimension and decouple human motion planning from video rendering to produce temporally consistent, realistic human-centric videos. Finally, we develop a creativity-oriented diffusion framework that enhances the novelty of generated results. Together, these works advance adaptability, personalization, temporal fidelity, and creative capacity in generative modeling, a progression toward more adaptable, specialized, and creative AI systems.
Read the paper
Related studies
- Learning from First-Generation Qualitative Approaches in the IS Discipline: An Evolutionary View and Some Implications for Authors and Evaluators (PART 1/2)
- Commentary on the clinical and preclinical dosage limits of interstitially administered magnetic fluids for therapeutic hyperthermia based on current practice and efficacy models
- Prosthesis: New Technological Opportunities and Innovative Biomedical Devices
- The history and future of neural modeling for cochlear implants
- Ryanodine receptors: waking up from refractoriness
- Novel Transgenic Rabbit Model Sheds Light on the Puzzling Role of Matrix Metalloproteinase-12 in Atherosclerosis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.