Papers › BiDM: Pushing the Limit of Quantization for Diffusion Models

BiDM: Pushing the Limit of Quantization for Diffusion Models

8 Dec 2024arXiv:2412.05926archive 2025-07-28

Xingyu Zheng, Xianglong Liu, Yichen Bian, Xudong Ma, Yulun Zhang, Jiakai Wang, Jinyang Guo, Haotong Qin

Diffusion models (DMs) have been significantly developed and widely used in various applications due to their excellent generative qualities. However, the expensive computation and massive parameters of DMs hinder their practical use in resource-constrained scenarios. As one of the effective compression approaches, quantization allows DMs to achieve storage saving and inference acceleration by reducing bit-width while maintaining generation performance. However, as the most extreme quantization form, 1-bit binarization causes the generation performance of DMs to face severe degradation or even collapse. This paper proposes a novel method, namely BiDM, for fully binarizing weights and activations of DMs, pushing quantization to the 1-bit limit. From a temporal perspective, we introduce the Timestep-friendly Binary Structure (TBS), which uses learnable activation binarizers and cross-timestep feature connections to address the highly timestep-correlated activation features of DMs. From a spatial perspective, we propose Space Patched Distillation (SPD) to address the difficulty of matching binary features during distillation, focusing on the spatial locality of image generation tasks and noise estimation networks. As the first work to fully binarize DMs, the W1A1 BiDM on the LDM-4 model for LSUN-Bedrooms 256×256 achieves a remarkable FID of 22.74, significantly outperforming the current state-of-the-art general binarization methods with an FID of 59.44 and invalid generative samples, and achieves up to excellent 28.0 times storage and 52.7 times OPs savings. The code is available at https://github.com/Xingyu-Zheng/BiDM .

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="2412.05926")

Code

Syntology Ran 12 of 16 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · honoured contract; 6 ran · our draft was wrong; 2 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xingyu-zheng/bidm officialmentioned in paperpytorch 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

16 samples harvested; 12 ran; 2 honoured the contract we drafted; 4 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.

2ran · honoured contract
6ran · our draft was wrong
2ran · fixture could not drive it
2ran
4unverified

Licence: 16 of the 16 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 Xingyu-Zheng/BiDM. “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.

Normalize Xingyu-Zheng/BiDM/bidm-cifar/models/diffusion_bidm.py official repository ran · our draft was wrong no licence file found · pointer only · c3a6b977022957cb · report
dict2namespace xingyu-zheng/bidm/bidm-cifar/main_bidm.py official repository ran · our draft was wrong no licence file found · pointer only · bd1f17e427bf51a5 · report
get_timestep_embedding xingyu-zheng/bidm/bidm-cifar/models/diffusion_bidm.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · cb49209c125de1b4 · report
isimage xingyu-zheng/bidm/bidm-cifar/models/util_ldm.py official repository ran no licence file found · pointer only · b1368330cf0f5642 · report
ismap xingyu-zheng/bidm/bidm-cifar/models/util_ldm.py official repository ran no licence file found · pointer only · d72762b700feee6f · report
list_dir xingyu-zheng/bidm/bidm-cifar/datasets/utils.py official repository ran · our draft was wrong no licence file found · pointer only · 915e1c6c38494be9 · report
list_files xingyu-zheng/bidm/bidm-cifar/datasets/utils.py official repository ran · our draft was wrong no licence file found · pointer only · 208e196e9582a9a6 · report
make_beta_schedule xingyu-zheng/bidm/bidm-cifar/models/util_bidm.py official repository ran · honoured contract no licence file found · pointer only · 3bd7e0cdbd131fdb · report
make_ddim_sampling_parameters xingyu-zheng/bidm/bidm-cifar/models/util_bidm.py official repository ran · fixture could not drive it no licence file found · pointer only · 3ee640131c9d4362 · report
make_ddim_timesteps xingyu-zheng/bidm/bidm-cifar/models/util_bidm.py official repository ran · honoured contract no licence file found · pointer only · 0ea4e960ea54514c · report
md5_hash xingyu-zheng/bidm/bidm-cifar/functions/ckpt_util.py official repository ran · our draft was wrong no licence file found · pointer only · 07d90bd6ae1be7db · report
nonlinearity xingyu-zheng/bidm/bidm-cifar/models/diffusion_bidm.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 3137073275f8c21a · report
check_integrity xingyu-zheng/bidm/bidm-cifar/datasets/utils.py official repository unverified no licence file found · pointer only · 7345763c9b9300fb · report
get_ckpt_path xingyu-zheng/bidm/bidm-cifar/functions/ckpt_util.py official repository unverified no licence file found · pointer only · c37fc656e8bb2a80 · report
log_txt_as_img xingyu-zheng/bidm/bidm-cifar/models/util_ldm.py official repository unverified no licence file found · pointer only · f9bd2e83191afad1 · report
noise_estimation_loss xingyu-zheng/bidm/bidm-cifar/functions/losses.py official repository unverified no licence file found · pointer only · e7829cb162499d04 · report

Tasks

BinarizationImage GenerationNoise EstimationQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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