Related papers: SwiftDiffusion: Efficient Diffusion Model Serving …

Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis. Recent research has introduced tuning methods that make subtle adjustments to the original models, yielding…

As scaling laws in generative AI push performance, they also simultaneously concentrate the development of these models among actors with large computational resources. With a focus on text-to-image (T2I) generative models, we aim to…

Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further…

Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment,…

Creating graphic layouts is a fundamental step in graphic designs. In this work, we present a novel generative model named LayoutDiffusion for automatic layout generation. As layout is typically represented as a sequence of discrete tokens,…

Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person has a different appearance e.g. pose, face, and clothing,…

Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts in a sequential…

Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency. However, such fine-tuned models are not robust; they often fail to compose with concepts of pretrained…

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Diffusion models excel in many generative modeling tasks, notably in creating images from text prompts, a task referred to as text-to-image (T2I) generation. Despite the ability to generate high-quality images, these models often replicate…

Diffusion Transformer (DiT), an emerging diffusion model for image generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs stem from the static inference…

Diffusion models demonstrate remarkable capabilities in capturing complex data distributions and have achieved compelling results in many generative tasks. While they have recently been extended to dense prediction tasks such as depth…

Diffusion Transformers (DiTs) have demonstrated exceptional capabilities in text-to-image synthesis. However, in the domain of controllable text-to-image generation using DiTs, most existing methods still rely on the ControlNet paradigm…

Diffusion models have revolutionized generative AI, with their inherent capacity to generate highly realistic state-of-the-art synthetic data. However, these models employ an iterative denoising process over computationally intensive layers…

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based…

Text-to-image generation has witnessed significant progress with the advent of diffusion models. Despite the ability to generate photorealistic images, current text-to-image diffusion models still often struggle to accurately interpret and…

In the visual spatial understanding (VSU) area, spatial image-to-text (SI2T) and spatial text-to-image (ST2I) are two fundamental tasks that appear in dual form. Existing methods for standalone SI2T or ST2I perform imperfectly in spatial…

Large-scale text-guided image diffusion models have shown astonishing results in text-to-image (T2I) generation. However, applying these models to synthesize textures for 3D geometries remains challenging due to the domain gap between 2D…

Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video…

Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles.…