相关论文: HybridStitch: Pixel and Timestep Level Model Stitc…

Generative modeling is widely regarded as one of the most essential problems in today's AI community, with text-to-image generation having gained unprecedented real-world impacts. Among various approaches, diffusion models have achieved…

In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in generating accurate and style-consistent textual and visual…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures,…

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

Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results,…

Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks such as image enhancement, restoration, editing, and compositing. However, their widespread adoption…

Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…

Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled…

Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint…

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of…

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score…

In today's age of social media and marketing, copyright issues can be a major roadblock to the free sharing of images. Generative AI models have made it possible to create high-quality images, but concerns about copyright infringement are a…

Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new…

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses…

Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making…

The Stable Diffusion Model (SDM) is a popular and efficient text-to-image (t2i) generation and image-to-image (i2i) generation model. Although there have been some attempts to reduce sampling steps, model distillation, and network…

This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference…

Applying diffusion models to image-to-image translation (I2I) has recently received increasing attention due to its practical applications. Previous attempts inject information from the source image into each denoising step for an iterative…