Designing a Better Asymmetric VQGAN for StableDiffusion

• URL: http://arxiv.org/abs/2306.04632v1
• Date: Wed, 7 Jun 2023 17:56:02 GMT
• Title: Designing a Better Asymmetric VQGAN for StableDiffusion
• Authors: Zixin Zhu and Xuelu Feng and Dongdong Chen and Jianmin Bao and Le Wang and Yinpeng Chen and Lu Yuan and Gang Hua
• Abstract summary: A revolutionary text-to-image generator, StableDiffusion, learns a diffusion model in the latent space via a VQGAN. We propose a new asymmetric VQGAN with two simple designs. It can be widely used in StableDiffusion-based inpainting and local editing methods.
• Score: 73.21783102003398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: StableDiffusion is a revolutionary text-to-image generator that is causing a stir in the world of image generation and editing. Unlike traditional methods that learn a diffusion model in pixel space, StableDiffusion learns a diffusion model in the latent space via a VQGAN, ensuring both efficiency and quality. It not only supports image generation tasks, but also enables image editing for real images, such as image inpainting and local editing. However, we have observed that the vanilla VQGAN used in StableDiffusion leads to significant information loss, causing distortion artifacts even in non-edited image regions. To this end, we propose a new asymmetric VQGAN with two simple designs. Firstly, in addition to the input from the encoder, the decoder contains a conditional branch that incorporates information from task-specific priors, such as the unmasked image region in inpainting. Secondly, the decoder is much heavier than the encoder, allowing for more detailed recovery while only slightly increasing the total inference cost. The training cost of our asymmetric VQGAN is cheap, and we only need to retrain a new asymmetric decoder while keeping the vanilla VQGAN encoder and StableDiffusion unchanged. Our asymmetric VQGAN can be widely used in StableDiffusion-based inpainting and local editing methods. Extensive experiments demonstrate that it can significantly improve the inpainting and editing performance, while maintaining the original text-to-image capability. The code is available at \url{https://github.com/buxiangzhiren/Asymmetric_VQGAN}.

Related papers

• Editable Image Elements for Controllable Synthesis [79.58148778509769]
  We propose an image representation that promotes spatial editing of input images using a diffusion model. We show the effectiveness of our representation on various image editing tasks, such as object resizing, rearrangement, dragging, de-occlusion, removal, variation, and image composition.
  arXiv  Detail & Related papers  (2024-04-24T17:59:11Z)
• CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models [57.9771859175664]
  Recent generative-prior-based methods have shown promising blind face restoration performance. Generating fine-grained facial details faithful to inputs remains a challenging problem. We introduce a diffusion-based-prior inside a VQGAN architecture that focuses on learning the distribution over uncorrupted latent embeddings.
  arXiv  Detail & Related papers  (2024-02-08T23:51:49Z)
• DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing [66.43179841884098]
  Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years. We propose DiffEditor to rectify two weaknesses in existing diffusion-based image editing. Our method can efficiently achieve state-of-the-art performance on various fine-grained image editing tasks.
  arXiv  Detail & Related papers  (2024-02-04T18:50:29Z)
• Forgedit: Text Guided Image Editing via Learning and Forgetting [17.26772361532044]
  We design a novel text-guided image editing method, named as Forgedit. First, we propose a vision-language joint optimization framework capable of reconstructing the original image in 30 seconds. Then, we propose a novel vector projection mechanism in text embedding space of Diffusion Models.
  arXiv  Detail & Related papers  (2023-09-19T12:05:26Z)
• Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization [73.52943587514386]
  Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm. We propose a novel two-stage framework: (1) Dynamic-Quantization VAE (DQ-VAE) which encodes image regions into variable-length codes based their information densities for accurate representation.
  arXiv  Detail & Related papers  (2023-05-19T14:56:05Z)
• StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN [4.7590051176368915]
  Inverting real images into StyleGAN's latent space is an extensively studied problem. Trade-off between the image reconstruction fidelity and image editing quality remains an open challenge. We present a novel image inversion framework and a training pipeline to achieve high-fidelity image inversion with high-quality editing.
  arXiv  Detail & Related papers  (2022-12-29T16:14:09Z)
• High-Fidelity Image Inpainting with GAN Inversion [23.49170140410603]
  In this paper, we propose a novel GAN inversion model for image inpainting, dubbed InvertFill. Within the encoder, the pre-modulation network leverages multi-scale structures to encode more discriminative semantics into style vectors. To reconstruct faithful and photorealistic images, a simple yet effective Soft-update Mean Latent module is designed to capture more diverse in-domain patterns that synthesize high-fidelity textures for large corruptions.
  arXiv  Detail & Related papers  (2022-08-25T03:39:24Z)
• Diffusion Autoencoders: Toward a Meaningful and Decodable Representation [1.471992435706872]
  Diffusion models (DPMs) have achieved remarkable quality in image generation that rivals GANs'. Unlike GANs, DPMs use a set of latent variables that lack semantic meaning and cannot serve as a useful representation for other tasks. This paper explores the possibility of using DPMs for representation learning and seeks to extract a meaningful and decodable representation of an input image via autoencoding.
  arXiv  Detail & Related papers  (2021-11-30T18:24:04Z)
• In-Domain GAN Inversion for Real Image Editing [56.924323432048304]
  A common practice of feeding a real image to a trained GAN generator is to invert it back to a latent code. Existing inversion methods typically focus on reconstructing the target image by pixel values yet fail to land the inverted code in the semantic domain of the original latent space. We propose an in-domain GAN inversion approach, which faithfully reconstructs the input image and ensures the inverted code to be semantically meaningful for editing.
  arXiv  Detail & Related papers  (2020-03-31T18:20:18Z)

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.