Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising

• URL: http://arxiv.org/abs/2412.05628v1
• Date: Sat, 07 Dec 2024 11:52:41 GMT
• Title: Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
• Authors: Gongfan Fang, Xinyin Ma, Xinchao Wang,
• Abstract summary: We introduce Remix-DiT, a novel method to enhance output quality at a low cost. The goal of Remix-DiT is to craft N diffusion experts for different denoising timesteps, yet without the need for expensive training of N independent models. Experiments conducted on the ImageNet dataset demonstrate that Remix-DiT achieves promising results.
• Score: 57.857534644932194
• License:
• Abstract: Transformer-based diffusion models have achieved significant advancements across a variety of generative tasks. However, producing high-quality outputs typically necessitates large transformer models, which result in substantial training and inference overhead. In this work, we investigate an alternative approach involving multiple experts for denoising, and introduce Remix-DiT, a novel method designed to enhance output quality at a low cost. The goal of Remix-DiT is to craft N diffusion experts for different denoising timesteps, yet without the need for expensive training of N independent models. To achieve this, Remix-DiT employs K basis models (where K < N) and utilizes learnable mixing coefficients to adaptively craft expert models. This design offers two significant advantages: first, although the total model size is increased, the model produced by the mixing operation shares the same architecture as a plain model, making the overall model as efficient as a standard diffusion transformer. Second, the learnable mixing adaptively allocates model capacity across timesteps, thereby effectively improving generation quality. Experiments conducted on the ImageNet dataset demonstrate that Remix-DiT achieves promising results compared to standard diffusion transformers and other multiple-expert methods. The code is available at https://github.com/VainF/Remix-DiT.

Related papers

• ConvMixFormer- A Resource-efficient Convolution Mixer for Transformer-based Dynamic Hand Gesture Recognition [5.311735227179715]
  We explore and devise a novel ConvMixFormer architecture for dynamic hand gestures. The proposed method is evaluated on NVidia Dynamic Hand Gesture and Briareo datasets. Our model has achieved state-of-the-art results on single and multimodal inputs.
  arXiv  Detail & Related papers  (2024-11-11T16:45:18Z)
• One-Step Diffusion Distillation through Score Implicit Matching [74.91234358410281]
  We present Score Implicit Matching (SIM) a new approach to distilling pre-trained diffusion models into single-step generator models. SIM shows strong empirical performances for one-step generators. By applying SIM to a leading transformer-based diffusion model, we distill a single-step generator for text-to-image generation.
  arXiv  Detail & Related papers  (2024-10-22T08:17:20Z)
• TerDiT: Ternary Diffusion Models with Transformers [83.94829676057692]
  TerDiT is a quantization-aware training scheme for ternary diffusion models with transformers. We focus on the ternarization of DiT networks and scale model sizes from 600M to 4.2B.
  arXiv  Detail & Related papers  (2024-05-23T17:57:24Z)
• BEND: Bagging Deep Learning Training Based on Efficient Neural Network Diffusion [56.9358325168226]
  We propose a Bagging deep learning training algorithm based on Efficient Neural network Diffusion (BEND) Our approach is simple but effective, first using multiple trained model weights and biases as inputs to train autoencoder and latent diffusion model. Our proposed BEND algorithm can consistently outperform the mean and median accuracies of both the original trained model and the diffused model.
  arXiv  Detail & Related papers  (2024-03-23T08:40:38Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training. It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models. While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• One-Step Diffusion Distillation via Deep Equilibrium Models [64.11782639697883]
  We introduce a simple yet effective means of distilling diffusion models directly from initial noise to the resulting image. Our method enables fully offline training with just noise/image pairs from the diffusion model. We demonstrate that the DEQ architecture is crucial to this capability, as GET matches a $5times$ larger ViT in terms of FID scores.
  arXiv  Detail & Related papers  (2023-12-12T07:28:40Z)
• LayoutDM: Transformer-based Diffusion Model for Layout Generation [0.6445605125467572]
  Transformer-based diffusion model (DDPM) is proposed to generate high-quality images. Transformer-based conditional Layout Denoiser is proposed to generate samples from noised layout data. Our method outperforms state-of-the-art generative models in terms of quality and diversity.
  arXiv  Detail & Related papers  (2023-05-04T05:51:35Z)

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.