Diffusion Product Quantization

• URL: http://arxiv.org/abs/2411.12306v1
• Date: Tue, 19 Nov 2024 07:47:37 GMT
• Title: Diffusion Product Quantization
• Authors: Jie Shao, Hanxiao Zhang, Jianxin Wu,
• Abstract summary: We explore the quantization of diffusion models in extreme compression regimes to reduce model size while maintaining performance. We apply our compression method to the DiT model on ImageNet and consistently outperform other quantization approaches.
• Score: 18.32568431229839
• License:
• Abstract: In this work, we explore the quantization of diffusion models in extreme compression regimes to reduce model size while maintaining performance. We begin by investigating classical vector quantization but find that diffusion models are particularly susceptible to quantization error, with the codebook size limiting generation quality. To address this, we introduce product quantization, which offers improved reconstruction precision and larger capacity -- crucial for preserving the generative capabilities of diffusion models. Furthermore, we propose a method to compress the codebook by evaluating the importance of each vector and removing redundancy, ensuring the model size remaining within the desired range. We also introduce an end-to-end calibration approach that adjusts assignments during the forward pass and optimizes the codebook using the DDPM loss. By compressing the model to as low as 1 bit (resulting in over 24 times reduction in model size), we achieve a balance between compression and quality. We apply our compression method to the DiT model on ImageNet and consistently outperform other quantization approaches, demonstrating competitive generative performance.

Related papers

• Pushing the Limits of Large Language Model Quantization via the Linearity Theorem [71.3332971315821]
  We present a "line theoremarity" establishing a direct relationship between the layer-wise $ell$ reconstruction error and the model perplexity increase due to quantization. This insight enables two novel applications: (1) a simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, dubbed HIGGS, and (2) an optimal solution to the problem of finding non-uniform per-layer quantization levels.
  arXiv  Detail & Related papers  (2024-11-26T15:35:44Z)
• Timestep-Aware Correction for Quantized Diffusion Models [28.265582848911574]
  We propose a timestep-aware correction method for quantized diffusion model, which dynamically corrects the quantization error. By leveraging the proposed method in low-precision diffusion models, substantial enhancement of output quality could be achieved with only negligible overhead.
  arXiv  Detail & Related papers  (2024-07-04T13:22:31Z)
• BitsFusion: 1.99 bits Weight Quantization of Diffusion Model [43.11229823281721]
  We develop a novel weight quantization method that quantizes the UNet from Stable Diffusion v1.5 to 1.99 bits, achieving a model with 7.9X smaller size. We extensively evaluate our quantized model across various benchmark datasets and through human evaluation to demonstrate its superior generation quality.
  arXiv  Detail & Related papers  (2024-06-06T17:59:23Z)
• Lossy Image Compression with Foundation Diffusion Models [10.407650300093923]
  In this work we formulate the removal of quantization error as a denoising task, using diffusion to recover lost information in the transmitted image latent. Our approach allows us to perform less than 10% of the full diffusion generative process and requires no architectural changes to the diffusion model.
  arXiv  Detail & Related papers  (2024-04-12T16:23:42Z)
• QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning [52.157939524815866]
  In this paper, we empirically unravel three properties in quantized diffusion models that compromise the efficacy of current methods. We identify two critical types of quantized layers: those holding vital temporal information and those sensitive to reduced bit-width. Our method is evaluated over three high-resolution image generation tasks and achieves state-of-the-art performance under various bit-width settings.
  arXiv  Detail & Related papers  (2024-02-06T03:39:44Z)
• Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing [49.800746112114375]
  We propose a novel post-training quantization method (Progressive and Relaxing) for text-to-image diffusion models. We are the first to achieve quantization for Stable Diffusion XL while maintaining the performance.
  arXiv  Detail & Related papers  (2023-11-10T09:10:09Z)
• Towards Accurate Post-training Quantization for Diffusion Models [73.19871905102545]
  We propose an accurate data-free post-training quantization framework of diffusion models (ADP-DM) for efficient image generation. Our method outperforms the state-of-the-art post-training quantization of diffusion model by a sizable margin with similar computational cost.
  arXiv  Detail & Related papers  (2023-05-30T04:00:35Z)
• Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
  We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
  arXiv  Detail & Related papers  (2023-05-11T17:55:25Z)
• OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization [32.60139548889592]
  We propose a novel One-shot Pruning-Quantization (OPQ) in this paper. OPQ analytically solves the compression allocation with pre-trained weight parameters only. We propose a unified channel-wise quantization method that enforces all channels of each layer to share a common codebook.
  arXiv  Detail & Related papers  (2022-05-23T09:05:25Z)
• Training with Quantization Noise for Extreme Model Compression [57.51832088938618]
  We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator. In this paper, we extend this approach to work beyond int8 fixed-point quantization with extreme compression methods.
  arXiv  Detail & Related papers  (2020-04-15T20:10:53Z)

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.