The Enhancement of Advanced Text-to-Image Diffusion Generation Models: A Review
Abstract
Text-to-Image (T2I) generation with Diffusion Models (DMs) has drawn considerable attention recently because of their extraordinary performance and huge potential. However, DMs still have some unsolved problems, e.g., computational complexity, less scalability or concept misalignment. This review focuses on discussing the advanced methods developed to enhance the T2I Diffusion Models. The works mentioned have been categorised into three major classes: Prompt Augmentation is about the preliminary works; Fine-grained Alignment is focused on attempts during the phase of training and Model Interpretability mainly discusses the research on improving the model’s explainability.
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.