DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

• URL: http://arxiv.org/abs/2405.18428v1
• Date: Tue, 28 May 2024 17:59:33 GMT
• Title: DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
• Authors: Lianghui Zhu, Zilong Huang, Bencheng Liao, Jun Hao Liew, Hanshu Yan, Jiashi Feng, Xinggang Wang,
• Abstract summary: We introduce Diffusion Gated Linear Attention Transformers (DiG), a simple, adoptable solution with minimal parameter overhead, following the Diffusion Transformers (DiT) design. In addition to better performance than DiT, DiG-S/2 exhibits $2.5times$ higher training speed than DiT-S/2 and saves $75.7%$ memory resolution $179times 1792$. With the same model size, DiG-XL/2 is $4.2times$ faster than the recent Mamba-based diffusion model at a $1024$ resolution, and is $1.8times$ faster than DiT with FlashAttention-2
• Score: 82.24166963631949
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with scalability and quadratic complexity efficiency. In this paper, we aim to leverage the long sequence modeling capability of Gated Linear Attention (GLA) Transformers, expanding its applicability to diffusion models. We introduce Diffusion Gated Linear Attention Transformers (DiG), a simple, adoptable solution with minimal parameter overhead, following the DiT design, but offering superior efficiency and effectiveness. In addition to better performance than DiT, DiG-S/2 exhibits $2.5\times$ higher training speed than DiT-S/2 and saves $75.7\%$ GPU memory at a resolution of $1792 \times 1792$. Moreover, we analyze the scalability of DiG across a variety of computational complexity. DiG models, with increased depth/width or augmentation of input tokens, consistently exhibit decreasing FID. We further compare DiG with other subquadratic-time diffusion models. With the same model size, DiG-XL/2 is $4.2\times$ faster than the recent Mamba-based diffusion model at a $1024$ resolution, and is $1.8\times$ faster than DiT with CUDA-optimized FlashAttention-2 under the $2048$ resolution. All these results demonstrate its superior efficiency among the latest diffusion models. Code is released at https://github.com/hustvl/DiG.

Related papers

• Dynamic Diffusion Transformer [67.13876021157887]
  Diffusion Transformer (DiT) has demonstrated superior performance but suffers from substantial computational costs. We propose Dynamic Diffusion Transformer (DyDiT), an architecture that dynamically adjusts its computation along both timestep and spatial dimensions during generation. With 3% additional fine-tuning, our method reduces the FLOPs of DiT-XL by 51%, accelerates generation by 1.73, and achieves a competitive FID score of 2.07 on ImageNet.
  arXiv  Detail & Related papers  (2024-10-04T14:14:28Z)
• LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba [54.85262314960038]
  Local Attentional Mamba blocks capture both global contexts and local details with linear complexity. Our model exhibits exceptional scalability and surpasses the performance of DiT across various model scales on ImageNet at 256x256 resolution. Compared to state-of-the-art diffusion models on ImageNet 256x256 and 512x512, our largest model presents notable advantages, such as a reduction of up to 62% GFLOPs.
  arXiv  Detail & Related papers  (2024-08-05T16:39:39Z)
• $Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers [13.433352602762511]
  We propose an overall training-free inference acceleration framework $Delta$-DiT. $Delta$-DiT uses a designed cache mechanism to accelerate the rear DiT blocks in the early sampling stages and the front DiT blocks in the later stages. Experiments on PIXART-$alpha$ and DiT-XL demonstrate that the $Delta$-DiT can achieve a $1.6times$ speedup on the 20-step generation.
  arXiv  Detail & Related papers  (2024-06-03T09:10:44Z)
• DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis [56.849285913695184]
  Diffusion Mamba (DiM) is a sequence model for efficient high-resolution image synthesis. DiM architecture achieves inference-time efficiency for high-resolution images. Experiments demonstrate the effectiveness and efficiency of our DiM.
  arXiv  Detail & Related papers  (2024-05-23T06:53:18Z)
• DiffiT: Diffusion Vision Transformers for Image Generation [88.08529836125399]
  Vision Transformer (ViT) has demonstrated strong modeling capabilities and scalability, especially for recognition tasks. We study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT) DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency.
  arXiv  Detail & Related papers  (2023-12-04T18:57:01Z)
• Scalable Diffusion Models with Transformers [18.903245758902834]
  We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We find that DiTs with higher Gflops -- through increased transformer depth/width or increased number of input tokens -- consistently have lower FID.
  arXiv  Detail & Related papers  (2022-12-19T18:59:58Z)
• SDM: Spatial Diffusion Model for Large Hole Image Inpainting [106.90795513361498]
  We present a novel spatial diffusion model (SDM) that uses a few iterations to gradually deliver informative pixels to the entire image. Also, thanks to the proposed decoupled probabilistic modeling and spatial diffusion scheme, our method achieves high-quality large-hole completion.
  arXiv  Detail & Related papers  (2022-12-06T13:30:18Z)

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.