Related papers: AMO Sampler: Enhancing Text Rendering with Oversho…
Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest,…
Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This computational burden primarily arises from the quadratic…
Flow matching has recently emerged as a principled framework for learning continuous-time transport maps, enabling efficient ODE-based sampling without relying on stochastic diffusion processes. While generative modeling has shown promise…
Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…
Diffusion-based text-to-image generation models have significantly advanced the field of art content synthesis. However, current portrait stylization methods generally require either model fine-tuning based on examples or the employment of…
We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map. Our architecture is based on a transformer with a novel attention mechanism.…
Despite the recent advances in large-scale diffusion models, little progress has been made on the layout-to-image (L2I) synthesis task. Current L2I models either suffer from poor editability via text or weak alignment between the generated…
Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditioning when operating in an extremely low-step regime. In this…
Recent advancements in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational demands, limiting practical deployment. While recent methods…
By lifting the pre-trained 2D diffusion models into Neural Radiance Fields (NeRFs), text-to-3D generation methods have made great progress. Many state-of-the-art approaches usually apply score distillation sampling (SDS) to optimize the…
The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…
Existing two-stream models, such as CLIP, encode images and text through independent representations, showing good performance while ensuring retrieval speed, have attracted attention from industry and academia. However, the single…
The denoising process of diffusion models can be interpreted as an approximate projection of noisy samples onto the data manifold. Moreover, the noise level in these samples approximates their distance to the underlying manifold. Building…
Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compelling images. However, the imperative of achieving a seamless…
Recent advancements in text-guided diffusion models have unlocked powerful image manipulation capabilities. However, applying these methods to real images necessitates the inversion of the images into the domain of the pretrained diffusion…
Recent progress in text-to-3D generation has been achieved through the utilization of score distillation methods: they make use of the pre-trained text-to-image (T2I) diffusion models by distilling via the diffusion model training…
Class imbalance significantly impacts the performance of multi-label classifiers. Oversampling is one of the most popular approaches, as it augments instances associated with less frequent labels to balance the class distribution. Existing…
Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluation. Fast generation therefore requires using a small fixed evaluation budget…
Flow matching models (FMs) have revolutionized text-to-image (T2I) generation, with reinforcement learning (RL) serving as a critical post-training strategy for alignment with reward objectives. In this research, we show that current RL…
As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on…