Papers › Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and...

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization

13 Jun 2024arXiv:2406.09416archive 2025-07-28

Qihao Liu, Zhanpeng Zeng, Ju He, Qihang Yu, Xiaohui Shen, Liang-Chieh Chen

This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Diffusion models have gained prominence for their effectiveness in high-fidelity image generation. While conventional approaches rely on convolutional U-Net architectures, recent Transformer-based designs have demonstrated superior performance and scalability. However, Transformer architectures, which tokenize input data (via "patchification"), face a trade-off between visual fidelity and computational complexity due to the quadratic nature of self-attention operations concerning token length. While larger patch sizes enable attention computation efficiency, they struggle to capture fine-grained visual details, leading to image distortions. To address this challenge, we propose augmenting the Diffusion model with the Multi-Resolution network (DiMR), a framework that refines features across multiple resolutions, progressively enhancing detail from low to high resolution. Additionally, we introduce Time-Dependent Layer Normalization (TD-LN), a parameter-efficient approach that incorporates time-dependent parameters into layer normalization to inject time information and achieve superior performance. Our method's efficacy is demonstrated on the class-conditional ImageNet generation benchmark, where DiMR-XL variants outperform prior diffusion models, setting new state-of-the-art FID scores of 1.70 on ImageNet 256 x 256 and 2.89 on ImageNet 512 x 512. Project page: https://qihao067.github.io/projects/DiMR

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 13 ran (5 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

qihao067/DiMR officialmentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 13 ran (8 instrument-failed) · 3 unverified 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: 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran · our draft was wrong
5ran
3unverified

Licence: 6 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from qihao067/DiMR. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

qihao067/DiMR official repository 16 samples, 13 ran (8 instrument-failed) · 3 unverified
Normalize in 154 papers libs/autoencoder.py ran · our draft was wrong Apache-2.0 (permissive) · 9fcdaa6e423e8aa7 · report fixture: signature in_channels:int/0/int, num_groups:int/0/int · returned GroupNorm · level recorded 2026-09-22
center_crop in 48 papers datasets.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · f057bf3471d77c43 · report fixture: signature width:int/0/int, height:int/0/int, img:ndarray/3/int · returned ndarray · level recorded 2026-09-24
center_crop_arr in 79 papers datasets.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · f8b4a29a52612a41 · report fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned ndarray · level recorded 2026-09-25
centers libs/core/axial_rope.py ran Apache-2.0 (permissive) · d29a52dd74b2322a · report fixture: signature start:float/0/float, stop:float/0/float, num:int/0/int, dtype:dtype/0/?, device:device/0/? · returned Tensor · level recorded 2026-09-24
dct2str utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 507ea4bd829ac4b0 · report fixture: signature dct:dict/0/? · returned str · level recorded 2026-09-25
get_optimizer in 228 papers utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 7328f4d3c151e58b · report fixture: signature params:generator/0/?, name:str/0/str · returned Adam · level recorded 2026-09-25
get_sde sde.py ran · our draft was wrong Apache-2.0 (permissive) · d35a53bdb646eb7c · report fixture: signature name:str/0/str, beta_min:float/0/float, beta_max:float/0/float · returned VPSDE · level recorded 2026-09-24
interpolate_fn in 42 papers dpm_solver.py ran fingerprinted Apache-2.0 (permissive) · 86c7877e164664bc · report fixture: signature x:Tensor/2/float, xp:Tensor/2/float, yp:Tensor/2/float · returned Tensor · level recorded 2026-09-24
model_wrapper in 37 papers dpm_solver.py ran Apache-2.0 (permissive) · ace7da590f4070e0 · report fixture: signature model:callable/0/?, noise_schedule:NoiseSchedule/0/?, is_cond_classifier:bool/0/bool, classifier_fn:callable/0/?, classifier_scale:float/0/float, time_input_type:str/0/str, total_N:int/0/int, model_kwargs:dict/0/?, is_deis:bool/0/bool · returned function · level recorded 2026-09-24
mos sde.py ran Apache-2.0 (permissive) · 02c82bdf3494ea71 · report fixture: signature a:Tensor/3/float, start_dim:int/0/int · returned Tensor · level recorded 2026-09-24
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
libs/autoencoder.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
random_crop_arr in 41 papers datasets.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 05d1f95a391c0ec3 · report fixture: signature pil_image:Image/0/?, image_size:int/0/int, min_crop_frac:float/0/float, max_crop_frac:float/0/float · returned ndarray · level recorded 2026-09-24
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
libs/core/axial_rope.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a098b5566baeb748 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_nnet utils.py unverified Apache-2.0 (permissive) · 673862e6d1280a4b · report
make_attn in 22 papers libs/autoencoder.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · f97adc1ae5efb785 · report
stp sde.py unverified Apache-2.0 (permissive) · 4d33c2f525f1b1c0 · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 DiMR-G/2R FID 1.63 #30 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 DiMR-XL/2R FID 1.70 #34 of 94 Archive leaderboard report
Image Generation ImageNet 512x512 DiMR-XL/3R FID 2.89 #38 of 52 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEConcatenated Skip ConnectionConvolutionDense ConnectionsDiffusionDropoutLabel SmoothingLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerU-Net

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