FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model

• URL: http://arxiv.org/abs/2410.13925v1
• Date: Thu, 17 Oct 2024 15:51:49 GMT
• Title: FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
• Authors: ZiDong Wang, Zeyu Lu, Di Huang, Cai Zhou, Wanli Ouyang, and Lei Bai,
• Abstract summary: We present the textbfFlexible Vision Transformer (FiT), a transformer architecture specifically designed for generating images with textitunrestricted resolutions and aspect ratios FiTv2 exhibits $2times$ convergence speed of FiT, when incorporating advanced training-free extrapolation techniques. Comprehensive experiments demonstrate the exceptional performance of FiTv2 across a broad range of resolutions.
• Score: 76.84519526283083
• License:
• Abstract: \textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To address this limitation, we conceptualize images as sequences of tokens with dynamic sizes, rather than traditional methods that perceive images as fixed-resolution grids. This perspective enables a flexible training strategy that seamlessly accommodates various aspect ratios during both training and inference, thus promoting resolution generalization and eliminating biases introduced by image cropping. On this basis, we present the \textbf{Flexible Vision Transformer} (FiT), a transformer architecture specifically designed for generating images with \textit{unrestricted resolutions and aspect ratios}. We further upgrade the FiT to FiTv2 with several innovative designs, includingthe Query-Key vector normalization, the AdaLN-LoRA module, a rectified flow scheduler, and a Logit-Normal sampler. Enhanced by a meticulously adjusted network structure, FiTv2 exhibits $2\times$ convergence speed of FiT. When incorporating advanced training-free extrapolation techniques, FiTv2 demonstrates remarkable adaptability in both resolution extrapolation and diverse resolution generation. Additionally, our exploration of the scalability of the FiTv2 model reveals that larger models exhibit better computational efficiency. Furthermore, we introduce an efficient post-training strategy to adapt a pre-trained model for the high-resolution generation. Comprehensive experiments demonstrate the exceptional performance of FiTv2 across a broad range of resolutions. We have released all the codes and models at \url{https://github.com/whlzy/FiT} to promote the exploration of diffusion transformer models for arbitrary-resolution image generation.

Related papers

• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation [19.65838242227773]
  This paper contributes a novel, concise, and efficient approach that adapts pre-trained large-scale text-to-image (T2I) diffusion model to the image-to-image (I2I) paradigm in a plug-and-play manner. Our method allows flexible control over both guiding factor and guiding intensity of the reference image simply by tuning the type and bandwidth of the substituted frequency band.
  arXiv  Detail & Related papers  (2024-08-02T04:13:38Z)
• Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models [26.926712014346432]
  This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Our method's efficacy is demonstrated on the class-conditional ImageNet generation benchmark, setting new state-of-the-art FID scores of 1.70 on ImageNet 256 x 256 and 2.89 on ImageNet 512 x 512.
  arXiv  Detail & Related papers  (2024-06-13T17:59:58Z)
• FiT: Flexible Vision Transformer for Diffusion Model [81.85667773832279]
  We present a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. Unlike traditional methods that perceive images as static-resolution grids, FiT conceptualizes images as sequences of dynamically-sized tokens. Comprehensive experiments demonstrate the exceptional performance of FiT across a broad range of resolutions.
  arXiv  Detail & Related papers  (2024-02-19T18:59:07Z)
• I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models [80.32562822058924]
  Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos.
  arXiv  Detail & Related papers  (2023-12-27T19:11:50Z)
• Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks [53.67497327319569]
  We introduce a novel neural rendering technique to solve image-to-3D from a single view. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
  arXiv  Detail & Related papers  (2023-12-24T08:42:37Z)
• Multi-Context Dual Hyper-Prior Neural Image Compression [10.349258638494137]
  We propose a Transformer-based nonlinear transform to efficiently capture both local and global information from the input image. We also introduce a novel entropy model that incorporates two different hyperpriors to model cross-channel and spatial dependencies of the latent representation. Our experiments show that our proposed framework performs better than the state-of-the-art methods in terms of rate-distortion performance.
  arXiv  Detail & Related papers  (2023-09-19T17:44:44Z)
• Diverse Image Inpainting with Bidirectional and Autoregressive Transformers [55.21000775547243]
  We propose BAT-Fill, an image inpainting framework with a novel bidirectional autoregressive transformer (BAT) BAT-Fill inherits the merits of transformers and CNNs in a two-stage manner, which allows to generate high-resolution contents without being constrained by the quadratic complexity of attention in transformers.
  arXiv  Detail & Related papers  (2021-04-26T03:52:27Z)

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.