Related papers: StyleSSP: Sampling StartPoint Enhancement for Trai…

Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…

In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs). SFT advocates for the fine-tuning of DDPM samplers through…

3D asset generation plays a pivotal role in fields such as gaming and virtual reality, enabling the rapid synthesis of high-fidelity 3D objects from a single or multiple images. Building on this capability, enabling style-controllable…

With the incorporation of the UNet architecture, diffusion probabilistic models have become a dominant force in image generation tasks. One key design in UNet is the skip connections between the encoder and decoder blocks. Although skip…

Diffusion models demonstrate impressive image generation performance with text guidance. Inspired by the learning process of diffusion, existing images can be edited according to text by DDIM inversion. However, the vanilla DDIM inversion…

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…

The rapid advancement in visual generation, particularly the emergence of pre-trained text-to-image and text-to-video models, has catalyzed growing interest in training-free video editing research. Mirroring training-free image editing…

Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfer modules to transfer the style statistics to the content…

Centred on content modification and style preservation, Scene Text Editing (STE) remains a challenging task despite considerable progress in text-to-image synthesis and text-driven image manipulation recently. GAN-based STE methods…

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 pre-trained on billions of image-text pairs have recently enabled 3D content creation by optimizing a randomly initialized differentiable 3D representation with score distillation. However, the optimization…

Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak…

Although recent text-to-image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style-Prompting Guidance (SPG), a…

Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

Modern diffusion models have set the state-of-the-art in AI image generation. Their success is due, in part, to training on Internet-scale data which often includes copyrighted work. This prompts questions about the extent to which these…

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely…

Text style transfer without parallel data has achieved some practical success. However, in the scenario where less data is available, these methods may yield poor performance. In this paper, we examine domain adaptation for text style…

Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain…

Stylized text-to-image generation focuses on creating images from textual descriptions while adhering to a style specified by a few reference images. However, subtle style variations within different reference images can hinder the model…