Related papers: Inverse Bridge Matching Distillation

Inverse Bridge Matching Distillation

URL: http://arxiv.org/abs/2502.01362v1
Date: Mon, 03 Feb 2025 13:56:03 GMT
Title: Inverse Bridge Matching Distillation
Authors: Nikita Gushchin, David Li, Daniil Selikhanovych, Evgeny Burnaev, Dmitry Baranchuk, Alexander Korotin,
Abstract summary: Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. We propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice. We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks.
Score: 69.479483488685
License:
Abstract: Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern diffusion and flow models, DBMs suffer from the problem of slow inference. To address it, we propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice. Unlike previously developed DBM distillation techniques, the proposed method can distill both conditional and unconditional types of DBMs, distill models in a one-step generator, and use only the corrupted images for training. We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks, and show that our distillation technique allows us to accelerate the inference of DBMs from 4x to 100x and even provide better generation quality than used teacher model depending on particular setup.

Related papers

One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation [60.54811860967658]
FluxSR is a novel one-step diffusion Real-ISR based on flow matching models. First, we introduce Flow Trajectory Distillation (FTD) to distill a multi-step flow matching model into a one-step Real-ISR. Second, to improve image realism and address high-frequency artifact issues in generated images, we propose TV-LPIPS as a perceptual loss.
arXiv Detail & Related papers (2025-02-04T04:11:29Z)
An Ordinary Differential Equation Sampler with Stochastic Start for Diffusion Bridge Models [13.00429687431982]
Diffusion bridge models initialize the generative process from corrupted images instead of pure Gaussian noise. Existing diffusion bridge models often rely on Differential Equation samplers, which result in slower inference speed. We propose a high-order ODE sampler with a start for diffusion bridge models. Our method is fully compatible with pretrained diffusion bridge models and requires no additional training.
arXiv Detail & Related papers (2024-12-28T03:32:26Z)
Relational Diffusion Distillation for Efficient Image Generation [27.127061578093674]
Diffusion model's high delay hinders its wide application in edge devices with scarce computing resources. We propose Diffusion Distillation (RDD), a novel distillation method tailored specifically for distilling diffusion models. Our proposed RDD leads to 1.47 FID decrease under 1 sampling step compared to state-of-the-art diffusion distillation methods and achieving 256x speed-up.
arXiv Detail & Related papers (2024-10-10T07:40:51Z)
One Step Diffusion-based Super-Resolution with Time-Aware Distillation [60.262651082672235]
Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. Recent techniques have been devised to enhance the sampling efficiency of diffusion-based SR models via knowledge distillation. We propose a time-aware diffusion distillation method, named TAD-SR, to accomplish effective and efficient image super-resolution.
arXiv Detail & Related papers (2024-08-14T11:47:22Z)
EM Distillation for One-step Diffusion Models [65.57766773137068]
We propose a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of quality. We develop a reparametrized sampling scheme and a noise cancellation technique that together stabilizes the distillation process.
arXiv Detail & Related papers (2024-05-27T05:55:22Z)
Distilling Diffusion Models into Conditional GANs [90.76040478677609]
We distill a complex multistep diffusion model into a single-step conditional GAN student model. For efficient regression loss, we propose E-LatentLPIPS, a perceptual loss operating directly in diffusion model's latent space. We demonstrate that our one-step generator outperforms cutting-edge one-step diffusion distillation models.
arXiv Detail & Related papers (2024-05-09T17:59:40Z)
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation [24.236841051249243]
Distillation methods aim to shift the model from many-shot to single-step inference. We introduce Latent Adversarial Diffusion Distillation (LADD), a novel distillation approach overcoming the limitations of ADD. In contrast to pixel-based ADD, LADD utilizes generative features from pretrained latent diffusion models.
arXiv Detail & Related papers (2024-03-18T17:51:43Z)
Aligning Logits Generatively for Principled Black-Box Knowledge Distillation [49.43567344782207]
Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server. We formalize a two-step workflow consisting of deprivatization and distillation. We propose a new method Mapping-Emulation KD (MEKD) that distills a black-box cumbersome model into a lightweight one.
arXiv Detail & Related papers (2022-05-21T02:38:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.