相关论文: AnimeAdapter: Fine-grained and Consistent Zero-sho…

We propose a learning based method for generating new animations of a cartoon character given a few example images. Our method is designed to learn from a traditionally animated sequence, where each frame is drawn by an artist, and thus the…

Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on.…

Diffusion models are increasingly popular for generative tasks, including personalized composition of subjects and styles. While diffusion models can generate user-specified subjects performing text-guided actions in custom styles, they…

Face editing methods, essential for tasks like virtual avatars, digital human synthesis and identity preservation, have traditionally been built upon GAN-based techniques, while recent focus has shifted to diffusion-based models due to…

Even though large-scale text-to-image generative models show promising performance in synthesizing high-quality images, applying these models directly to image editing remains a significant challenge. This challenge is further amplified in…

Diffusion models conditioned on identity embeddings enable the generation of synthetic face images that consistently preserve identity across multiple samples. Recent work has shown that introducing an additional negative condition through…

We propose EditCrafter, a high-resolution image editing method that operates without tuning, leveraging pretrained text-to-image (T2I) diffusion models to process images at resolutions significantly exceeding those used during training.…

While text-driven diffusion models demonstrate remarkable performance in image editing, the critical components of their text embeddings remain underexplored. The ambiguity and entanglement of these embeddings pose challenges for precise…

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…

The emergence of generative AI and controllable diffusion has made image-to-image synthesis increasingly practical and efficient. However, when input images exhibit low entropy and sparse, the inherent characteristics of diffusion models…

Personalized image generation with text-to-image diffusion models generates unseen images based on reference image content. Zero-shot adapter methods such as IP-Adapter and OminiControl are especially interesting because they do not require…

We report Zero123++, an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view. To take full advantage of pretrained 2D generative priors, we develop various conditioning and training…

Recently, text-to-image models have been thriving. Despite their powerful generative capacity, our research has uncovered a lack of robustness in this generation process. Specifically, the introduction of small perturbations to the text…

Visual storytelling with diffusion models has made impressive strides in maintaining character consistency across narrative scenes. However, a critical gap remains: while these methods ensure a character remains consistent across scenes,…

Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is…

In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When…

We present a methodology for conditional control of human shape and pose in pretrained text-to-image diffusion models using a 3D human parametric model (SMPL). Fine-tuning these diffusion models to adhere to new conditions requires large…

The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP…

Recent advances in diffusion-based text-to-video models, particularly those built on the diffusion transformer architecture, have achieved remarkable progress in generating high-quality and temporally coherent videos. However, transferring…

SmartAvatar is a vision-language-agent-driven framework for generating fully rigged, animation-ready 3D human avatars from a single photo or textual prompt. While diffusion-based methods have made progress in general 3D object generation,…