Related papers: oboro: Text-to-Image Synthesis on Limited Data usi…
Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to classes with subtle appearance differences while rejecting images of unknown classes. A recent trend in OSR shows the benefit of generative models to…
Textual content in images is crucial in e-commerce sectors, particularly in marketing campaigns, product imaging, advertising, and the entertainment industry. Current text-to-image (T2I) generation diffusion models, though proficient at…
The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces…
Recent advancements in text-to-image diffusion models have shown remarkable creative capabilities with textual prompts, but generating personalized instances based on specific subjects, known as subject-driven generation, remains…
Zero-shot and few-shot learning aim to improve generalization to unseen concepts, which are promising in many realistic scenarios. Due to the lack of data in unseen domain, relation modeling between seen and unseen domains is vital for…
Recent advancements in image generative foundation models have prioritized quality improvements but often at the cost of increased computational complexity and inference latency. To address this critical trade-off, we introduce HiDream-I1,…
Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both. One effective solution to address the limitation is few-shot generative model adaption. However, the…
Diffusion Transformer (DiT) architectures have significantly advanced Text-to-Image (T2I) generation but suffer from prohibitive computational costs and deployment barriers. To address these challenges, we propose an efficient compression…
Image generation has achieved remarkable progress with the development of large-scale text-to-image models, especially diffusion-based models. However, generating human images with plausible details, such as faces or hands, remains…
Recently, video generation has achieved significant rapid development based on superior text-to-image generation techniques. In this work, we propose a high fidelity framework for image-to-video generation, named AtomoVideo. Based on…
Recent years have witnessed remarkable progress in image generation task, where users can create visually astonishing images with high-quality. However, existing text-to-image diffusion models are proficient in generating concrete concepts…
We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modeling to handle inputs…
A novel accelerated mobile edge generation (MEG) framework is proposed for generating high-resolution images on mobile devices. Exploiting a large-scale latent diffusion model (LDM) distributed across edge server (ES) and user equipment…
We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method is based on progressive object-level…
Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-quality and diverse synthesis of images from a given text prompt. However, these models lack the ability to mimic the appearance of subjects in a…
Effective connectivity estimation plays a crucial role in understanding the interactions and information flow between different brain regions. However, the functional time series used for estimating effective connectivity is derived from…
Diffusion models excel at image generation. Recent studies have shown that these models not only generate high-quality images but also encode text-image alignment information through attention maps or loss functions. This information is…
Recent advancements in large scale text-to-image models have opened new possibilities for guiding the creation of images through human-devised natural language. However, while prior literature has primarily focused on the generation of…
Diffusion-based text-to-image (T2I) models have made remarkable progress in generating photorealistic and semantically rich images. However, when the target concepts lie in low-density regions of the training distribution, these models…
Optical illusion hidden picture is an interesting visual perceptual phenomenon where an image is cleverly integrated into another picture in a way that is not immediately obvious to the viewer. Established on the off-the-shelf text-to-image…