Papers › Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free

Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free

31 May 2025arXiv:2506.00433archive 2025-07-28

Luigi Sigillo, Shengfeng He, Danilo Comminiello

High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a lightweight framework that enables any latent diffusion model to scale to ultra-high-resolution image generation (2K to 4K) for free. LWD introduces three key components: (1) a scale-consistent variational autoencoder objective that enhances the spectral fidelity of latent representations; (2) wavelet energy maps that identify and localize detail-rich spatial regions within the latent space; and (3) a time-dependent masking strategy that focuses denoising supervision on high-frequency components during training. LWD requires no architectural modifications and incurs no additional computational overhead. Despite its simplicity, it consistently improves perceptual quality and reduces FID in ultra-high-resolution image synthesis, outperforming strong baseline models. These results highlight the effectiveness of frequency-aware, signal-driven supervision as a principled and efficient approach for high-resolution generative modeling.

PaperPDFCode 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="2506.00433")

Code

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

By repository: found in paper text by Syntology: 10 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

LuigiSigillo/LatentWaveletDiffusion found in paper text by SyntologyApache-2.0 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; 2 ran; 0 honoured the contract we drafted; 8 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.

1ran · violated contract
1ran · our draft was wrong
8unverified

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 LuigiSigillo/LatentWaveletDiffusion. “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.

calculate_shift LuigiSigillo/LatentWaveletDiffusion/src/pipeline_flux.py found in paper text by Syntology ran · violated contract Apache-2.0 (permissive) · 4e3ad3679e5c37b2 · report
retrieve_timesteps LuigiSigillo/LatentWaveletDiffusion/src/pipeline_flux.py found in paper text by Syntology ran · our draft was wrong Apache-2.0 (permissive) · 0b56680ee1708fee · report
compute_wavelet_attention LuigiSigillo/LatentWaveletDiffusion/src/new_wav_attn_maps.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 6fe1dccb17235788 · report
decode_and_save LuigiSigillo/LatentWaveletDiffusion/src/train_2k.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 23e116cc74ff473e · report
get_mask LuigiSigillo/LatentWaveletDiffusion/src/new_wav_attn_maps.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 75ac92003acbbee0 · report
get_mask_batch LuigiSigillo/LatentWaveletDiffusion/src/new_wav_attn_maps.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 5a6018313fb2afd6 · report
parse_args LuigiSigillo/LatentWaveletDiffusion/src/train_2k.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 589fc02804855db7 · report
parse_args LuigiSigillo/LatentWaveletDiffusion/src/train_4k.py found in paper text by Syntology unverified Apache-2.0 (permissive) · a548e14c1a574df6 · report
parse_args LuigiSigillo/LatentWaveletDiffusion/src/helpers/cache_latent_codes.py found in paper text by Syntology unverified Apache-2.0 (permissive) · a5ae6bb2816685a3 · report
resize LuigiSigillo/LatentWaveletDiffusion/src/helpers/cache_latent_codes.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 35767eedf8ca0430 · report

Tasks

2k4kComputational EfficiencyDenoisingImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionLatent Diffusion Model

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