ARFlow: Autogressive Flow with Hybrid Linear Attention
- URL: http://arxiv.org/abs/2501.16085v1
- Date: Mon, 27 Jan 2025 14:33:27 GMT
- Title: ARFlow: Autogressive Flow with Hybrid Linear Attention
- Authors: Mude Hui, Rui-Jie Zhu, Songlin Yang, Yu Zhang, Zirui Wang, Yuyin Zhou, Jason Eshraghian, Cihang Xie,
- Abstract summary: Flow models are effective at progressively generating realistic images.
They struggle to capture long-range dependencies during the generation process.
We propose integrating autoregressive modeling into flow models.
- Score: 48.707933347079894
- License:
- Abstract: Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single corrupted image. To address this limitation, we propose integrating autoregressive modeling -- known for its excellence in modeling complex, high-dimensional joint probability distributions -- into flow models. During training, at each step, we construct causally-ordered sequences by sampling multiple images from the same semantic category and applying different levels of noise, where images with higher noise levels serve as causal predecessors to those with lower noise levels. This design enables the model to learn broader category-level variations while maintaining proper causal relationships in the flow process. During generation, the model autoregressively conditions the previously generated images from earlier denoising steps, forming a contextual and coherent generation trajectory. Additionally, we design a customized hybrid linear attention mechanism tailored to our modeling approach to enhance computational efficiency. Our approach, termed ARFlow, under 400k training steps, achieves 14.08 FID scores on ImageNet at 128 * 128 without classifier-free guidance, reaching 4.34 FID with classifier-free guidance 1.5, significantly outperforming the previous flow-based model SiT's 9.17 FID. Extensive ablation studies demonstrate the effectiveness of our modeling strategy and chunk-wise attention design.
Related papers
- Randomized Autoregressive Visual Generation [26.195148077398223]
This paper presents Randomized AutoRegressive modeling (RAR) for visual generation.
RAR sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks.
On the ImageNet-256 benchmark, RAR achieves an FID score of 1.48, not only surpassing prior state-the-art autoregressive image generators but also outperforming leading diffusion-based and masked transformer-based methods.
arXiv Detail & Related papers (2024-11-01T17:59:58Z) - Fast constrained sampling in pre-trained diffusion models [77.21486516041391]
Diffusion models have dominated the field of large, generative image models.
We propose an algorithm for fast-constrained sampling in large pre-trained diffusion models.
arXiv Detail & Related papers (2024-10-24T14:52:38Z) - Active Generation for Image Classification [45.93535669217115]
We propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model.
With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation.
arXiv Detail & Related papers (2024-03-11T08:45:31Z) - Scaling Rectified Flow Transformers for High-Resolution Image Synthesis [22.11487736315616]
Rectified flow is a recent generative model formulation that connects data and noise in a straight line.
We improve existing noise sampling techniques for training rectified flow models by biasing them towards perceptually relevant scales.
We present a novel transformer-based architecture for text-to-image generation that uses separate weights for the two modalities.
arXiv Detail & Related papers (2024-03-05T18:45:39Z) - Blue noise for diffusion models [50.99852321110366]
We introduce a novel and general class of diffusion models taking correlated noise within and across images into account.
Our framework allows introducing correlation across images within a single mini-batch to improve gradient flow.
We perform both qualitative and quantitative evaluations on a variety of datasets using our method.
arXiv Detail & Related papers (2024-02-07T14:59:25Z) - Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image Attenuation [53.04220377034574]
We propose incorporating an analytical image attenuation process into the forward diffusion process for high-quality (un)conditioned image generation.
Our method represents the forward image-to-noise mapping as simultaneous textitimage-to-zero mapping and textitzero-to-noise mapping.
We have conducted experiments on unconditioned image generation, textite.g., CIFAR-10 and CelebA-HQ-256, and image-conditioned downstream tasks such as super-resolution, saliency detection, edge detection, and image inpainting.
arXiv Detail & Related papers (2023-06-23T18:08:00Z) - On Distillation of Guided Diffusion Models [94.95228078141626]
We propose an approach to distilling classifier-free guided diffusion models into models that are fast to sample from.
For standard diffusion models trained on the pixelspace, our approach is able to generate images visually comparable to that of the original model.
For diffusion models trained on the latent-space (e.g., Stable Diffusion), our approach is able to generate high-fidelity images using as few as 1 to 4 denoising steps.
arXiv Detail & Related papers (2022-10-06T18:03:56Z) - Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR)
Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data.
We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
arXiv Detail & Related papers (2020-04-08T09:07:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.