Pith. sign in

REVIEW 7 cited by

Designing a Better Asymmetric VQGAN for StableDiffusion

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.04632 v1 pith:HNPZY7Z7 submitted 2023-06-07 cs.CV cs.GR

classification cs.CVcs.GR
keywords vqganasymmetricimageeditingstablediffusioninpaintingdecoderencoder
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Aligned Stable Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

    cs.CV 2026-01 conditional novelty 6.0 of 10

    ASUKA uses MAE priors and a harmonization VAE decoder to reduce hallucinated objects and color shifts in latent diffusion inpainting.

  2. XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

    cs.RO 2025-11 unverdicted novelty 6.0 of 10

    XR-1 introduces Unified Vision-Motion Codes learned by dual-branch VQ-VAE and applies them in a three-stage training pipeline to outperform prior VLA models on 120+ real-world manipulation tasks across six robot embodiments.

  3. CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CompSlider learns to synthesize image-conditioning latents from multiple attribute sliders at once, aiming for more disentangled and structure-preserving multi-attribute control in text-to-image generation.

  4. LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text to Image Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A latent-space scaling framework that replaces pixel-space upscaling with a trainable latent upsampler and noise compensation, yielding faster high-resolution text-to-image generation.

  5. UniLDiff: Unlocking the Power of Diffusion Priors for All-in-One Image Restoration

    cs.CV 2025-07 conditional novelty 5.0 of 10

    UniLDiff combines degradation-aware attention fusion with a detail-aware expert decoder to achieve state-of-the-art perceptual quality on unified image restoration benchmarks.

  6. PromptArtisan: Multi-instruction Image Editing in Single Pass with Complete Attention Control

    cs.CV 2025-02 conditional novelty 5.0 of 10

    PromptArtisan applies multiple mask-prompt edits to an image in one diffusion pass using cross-attention and self-attention control on InstructPix2Pix.

  7. Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

    cs.CV 2026-07 reject novelty 4.0 of 10

    DDR-SR routes each real-world low-resolution image to one of two diffusion experts based on a high-frequency-loss difficulty score, using a low-compression VAE for hard images and a high-compression VAE for easy image...

Pith tools