# Designing a Better Asymmetric VQGAN for StableDiffusion

arXiv: https://arxiv.org/abs/2306.04632 · HTML: https://mlsanity.com/paper/2306.04632/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 40 of its 42 references that are in the map.
- First posted on arXiv 7 Jun 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 40)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)

## Built on by (most cited first, 30 of 45)

- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models](https://mlsanity.com/paper/2410.10733/) (2024)
- [EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling](https://mlsanity.com/paper/2502.09509/) (2025)
- [RealFill: Reference-Driven Generation for Authentic Image Completion](https://mlsanity.com/paper/2309.16668/) (2023)
- [Restructuring Vector Quantization with the Rotation Trick](https://mlsanity.com/paper/2410.06424/) (2024)
- [Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration](https://mlsanity.com/paper/2312.02918/) (2023)
- [DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space](https://mlsanity.com/paper/2508.00413/) (2025)
- [A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis](https://mlsanity.com/paper/2409.08947/) (2024)
- [Attention Distillation: A Unified Approach to Visual Characteristics Transfer](https://mlsanity.com/paper/2502.20235/) (2025)
- [MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing](https://mlsanity.com/paper/2408.08000/) (2024)
- [Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting](https://mlsanity.com/paper/2404.19758/) (2024)
- [LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models](https://mlsanity.com/paper/2405.14477/) (2024)
- [Boosting Latent Diffusion with Perceptual Objectives](https://mlsanity.com/paper/2411.04873/) (2024)
- [Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency](https://mlsanity.com/paper/2312.04831/) (2023)
- [Lazy Diffusion Transformer for Interactive Image Editing](https://mlsanity.com/paper/2404.12382/) (2024)
- [Epsilon-VAE: Denoising as Visual Decoding](https://mlsanity.com/paper/2410.04081/) (2024)
- [ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion](https://mlsanity.com/paper/2410.08168/) (2024)
- [Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution](https://mlsanity.com/paper/2401.00877/) (2023)
- [Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration](https://mlsanity.com/paper/2407.03636/) (2024)
- [MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration](https://mlsanity.com/paper/2407.10833/) (2024)
- [XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations](https://mlsanity.com/paper/2511.02776/) (2025)
- [Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach](https://mlsanity.com/paper/2310.12004/) (2023)
- [Entropy Rectifying Guidance for Diffusion and Flow Models](https://mlsanity.com/paper/2504.13987/) (2025)
- [Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective](https://mlsanity.com/paper/2511.22249/) (2025)
- [MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance](https://mlsanity.com/paper/2503.14944/) (2025)
- [GeoRemover: Removing Objects and Their Causal Visual Artifacts](https://mlsanity.com/paper/2509.18538/) (2025)
- [LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal](https://mlsanity.com/paper/2510.15868/) (2025)
- [DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignment](https://mlsanity.com/paper/2603.22125/) (2026)
- [DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick](https://mlsanity.com/paper/2509.26469/) (2025)
- [DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation](https://mlsanity.com/paper/2502.11897/) (2025)

## Abstract (arXiv)

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 urlhttps://github.com/buxiangzhiren/AsymmetricVQGAN.