Related papers: Reflective Flow Sampling Enhancement
The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images. Although performs well for simple texts, the models may get confused when faced with complex texts that contain…
We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models. Rather than merely mode-seeking, our method achieves sampling by "pulling back" the dynamics of the…
Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recently in this setting due to their impressive performances and…
Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.g., in domains such as images and videos. Their success has attracted growing interest in applying them to language modeling. Unlike their…
Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…
Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…
Recent advances in text-to-image synthesis largely benefit from sophisticated sampling strategies and classifier-free guidance (CFG) to ensure high-quality generation. However, CFG's reliance on two forward passes, especially when combined…
The computational burden of the iterative sampling process remains a major challenge in diffusion-based Low-Light Image Enhancement (LLIE). Current acceleration methods, whether training-based or training-free, often lead to significant…
Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved for continuous modalities, including…
We introduce Reflectance Diffusion, a new neural text-to-texture model capable of generating high-fidelity SVBRDF maps from textual descriptions. Our method leverages a tandem neural approach, consisting of two modules, to accurately model…
We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-point-inspired iterative approach to invert real-world images,…
RGB-to-RAW reconstruction, or the reverse modeling of a camera Image Signal Processing (ISP) pipeline, aims to recover high-fidelity RAW data from RGB images. Despite notable progress, existing learning-based methods typically treat this…
Diffusion models have emerged as the leading approach for text-to-image generation. However, their iterative sampling process, which gradually morphs random noise into coherent images, introduces significant latency that limits their…
Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…
Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by…
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…
We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation-based method that explicitly models the discrepancy between…
Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies the latter paradigm, combining a learned continuous motion latent space with a diffusion-based…
Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models still has two main problems: (i) GRPO-style fixed per-prompt…
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of…