Related papers: 1.58-bit FLUX
We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel…
Although contemporary text-to-image generation models have achieved remarkable breakthroughs in producing visually appealing images, their capacity to generate precise and flexible typographic elements, especially non-Latin alphabets,…
Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing a unified tokenizer. However, existing tokenizers face a…
Stable Diffusion XL (SDXL) has become the best open source text-to-image model (T2I) for its versatility and top-notch image quality. Efficiently addressing the computational demands of SDXL models is crucial for wider reach and…
In the domain of image generation, latent-based generative models occupy a dominant status; however, these models rely heavily on image tokenizer. To meet modeling requirements, autoregressive models possessing the characteristics of…
We introduce a novel and uniform framework for quantum pixel representations that overarches many of the most popular representations proposed in the recent literature, such as (I)FRQI, (I)NEQR, MCRQI, and (I)NCQI. The proposed QPIXL…
Recent image generation schemes typically capture image distribution in a pre-constructed latent space relying on a frozen image tokenizer. Though the performance of tokenizer plays an essential role to the successful generation, its…
Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally…
Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years. Although these image synthesis methods produce visually appealing results, they frequently exhibit spelling errors…
This work aims to improve the efficiency of text-to-image diffusion models. While diffusion models use computationally expensive UNet-based denoising operations in every generation step, we identify that not all operations are equally…
1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LLMs from scratch, failing to fully leverage pre-trained models. This results in high training…
We propose a measurement-based model for fault-tolerant quantum computation that can be realised with one-dimensional cluster states and fusion measurements only; basic resources that are readily available with scalable photonic hardware.…
Rectified Flow text-to-image models surpass diffusion models in image quality and text alignment, but adapting ReFlow for real-image editing remains challenging. We propose a new real-image editing method for ReFlow by analyzing the…
Text-to-image diffusion models have demonstrated remarkable capabilities in transforming textual prompts into coherent images, yet the computational cost of their inference remains a persistent challenge. To address this issue, we present…
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…
Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding…
Optical super-resolution microscopy is a key technology for structural biology that offers high imaging contrast and live-cell compatibility. Minimal (fluorescence) photons flux microscopy, or MINFLUX, is an emerging super-resolution…
Diffusion models have shown unprecedented success in the task of text-to-image generation. While these models are capable of generating high-quality and realistic images, the complexity of sequential denoising has raised societal concerns…
Recent advancements in diffusion-based generative image editing have sparked a profound revolution, reshaping the landscape of image outpainting and inpainting tasks. Despite these strides, the field grapples with inherent challenges,…
Deep neural networks (DNNs) are ubiquitous in computer vision and natural language processing, but suffer from high inference cost. This problem can be addressed by quantization, which consists in converting floating point operations into a…