Papers › Designing a Better Asymmetric VQGAN for StableDiffusion

Designing a Better Asymmetric VQGAN for StableDiffusion

7 Jun 2023arXiv:2306.04632archive 2025-07-28

Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua

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}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.04632")

Code

Syntology Ran 8 of 10 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · violated contract; 3 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

buxiangzhiren/asymmetric_vqgan officialmentioned in papermentioned on GitHubpytorchMIT report
Fantasy-Studio/Paint-by-Example mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 8 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · violated contract
3ran · our draft was wrong
2ran
2unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from buxiangzhiren/asymmetric_vqgan. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

always buxiangzhiren/asymmetric_vqgan/ldm/modules/x_transformer.py official repository ran · our draft was wrong MIT (permissive) · fe5dd5258046898c · report
chunk buxiangzhiren/asymmetric_vqgan/txt2img.py official repository ran · our draft was wrong MIT (permissive) · 8241c0562bc710fd · report
default buxiangzhiren/asymmetric_vqgan/ldm/modules/attention.py official repository ran · violated contract MIT (permissive) · 424012cb37b31172 · report
exists buxiangzhiren/asymmetric_vqgan/ldm/modules/attention.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
isimage buxiangzhiren/asymmetric_vqgan/ldm/util.py official repository ran MIT (permissive) · b1368330cf0f5642 · report
ismap buxiangzhiren/asymmetric_vqgan/ldm/util.py official repository ran MIT (permissive) · d72762b700feee6f · report
numpy_to_pil buxiangzhiren/asymmetric_vqgan/inpaint_st.py official repository ran · violated contract MIT (permissive) · 1e63d588563eb90a · report
uniq buxiangzhiren/asymmetric_vqgan/ldm/modules/attention.py official repository ran · our draft was wrong MIT (permissive) · 9a299fe5ae09e407 · report
download_models buxiangzhiren/asymmetric_vqgan/notebook_helpers.py official repository unverified MIT (permissive) · 4533e43e06a12dc5 · report
log_txt_as_img buxiangzhiren/asymmetric_vqgan/ldm/util.py official repository unverified MIT (permissive) · f9bd2e83191afad1 · report

Tasks

DecoderImage GenerationImage Inpainting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionInpainting

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections