Papers › Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

4 Sep 2023arXiv:2309.03350archive 2025-07-28

Jiayan Teng, Wendi Zheng, Ming Ding, Wenyi Hong, Jianqiao Wangni, Zhuoyi Yang, Jie Tang

Diffusion models achieved great success in image synthesis, but still face challenges in high-resolution generation. Through the lens of discrete cosine transformation, we find the main reason is that \emph{the same noise level on a higher resolution results in a higher Signal-to-Noise Ratio in the frequency domain}. In this work, we present Relay Diffusion Model (RDM), which transfers a low-resolution image or noise into an equivalent high-resolution one for diffusion model via blurring diffusion and block noise. Therefore, the diffusion process can continue seamlessly in any new resolution or model without restarting from pure noise or low-resolution conditioning. RDM achieves state-of-the-art FID on CelebA-HQ and sFID on ImageNet 256×256, surpassing previous works such as ADM, LDM and DiT by a large margin. All the codes and checkpoints are open-sourced at \url{https://github.com/THUDM/RelayDiffusion}.

PaperPDFConference PDFCodeCode 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="2309.03350")

Code

Syntology Ran 12 of 17 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 3 ran · honoured contract; 3 ran · our draft was wrong; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 17 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.

THUDM/RelayDiffusion officialmentioned in papermentioned on GitHubpytorchApache-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

17 samples harvested; 12 ran; 3 honoured the contract we drafted; 5 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 · honoured contract
3ran · our draft was wrong
2ran · fixture could not drive it
4ran
5unverified

Licence: 0 of the 17 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 THUDM/RelayDiffusion. “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_fid_from_inception_stats THUDM/RelayDiffusion/evaluate.py official repository ran · honoured contract Apache-2.0 (permissive) · 45e941764344e7f3 · report
constant THUDM/RelayDiffusion/torch_utils/misc.py official repository ran Apache-2.0 (permissive) · 6d32f9cf6f29b386 · report
dct THUDM/RelayDiffusion/blurring.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · a480f97ef83e404c · report
file_ext THUDM/RelayDiffusion/dataset_tool.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a2b45afa097b55b6 · report
format_time THUDM/RelayDiffusion/dnnlib/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 674eca7b9e1b6439 · report
format_time_brief THUDM/RelayDiffusion/dnnlib/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 32af001972a0699f · report
maybe_min THUDM/RelayDiffusion/dataset_tool.py official repository ran · honoured contract Apache-2.0 (permissive) · dd1dc700e87f36cc · report
parse_int_list THUDM/RelayDiffusion/generate_imagenet.py official repository ran · honoured contract Apache-2.0 (permissive) · cacd4f6ec202d9b4 · report
parse_tuple THUDM/RelayDiffusion/dataset_tool.py official repository ran Apache-2.0 (permissive) · 07b21b35ecb4815c · report
rearrange THUDM/RelayDiffusion/blurring.py official repository ran fingerprinted Apache-2.0 (permissive) · a229189b8d4631c3 · report
reverse_rearrange THUDM/RelayDiffusion/blurring.py official repository ran Apache-2.0 (permissive) · f1c09017a55ef395 · report
weight_init THUDM/RelayDiffusion/training/networks.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · d41a4250066bce93 · report
ask_yes_no THUDM/RelayDiffusion/dnnlib/util.py official repository unverified Apache-2.0 (permissive) · 9d31d2c4cd16bb2d · report
edm_sampler THUDM/RelayDiffusion/generate_imagenet.py official repository unverified Apache-2.0 (permissive) · 00ad7cd5515a96f8 · report
is_persistent THUDM/RelayDiffusion/torch_utils/persistence.py official repository unverified Apache-2.0 (permissive) · e8b31ffccfa05efc · report
params_and_buffers THUDM/RelayDiffusion/torch_utils/misc.py official repository unverified Apache-2.0 (permissive) · b5ae713738eb4d27 · report
profiled_function THUDM/RelayDiffusion/torch_utils/misc.py official repository unverified Apache-2.0 (permissive) · f4664bbb3c2df6e0 · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CelebA-HQ 256x256 RDM FID 3.15 #1 of 19 Archive leaderboard report
Image Generation CelebA-HQ 256x256 RDM Precision 0.77 #1 of 19 Archive leaderboard report
Image Generation CelebA-HQ 256x256 RDM Recall 0.55 #1 of 19 Archive leaderboard report
Image Generation ImageNet 256x256 RDM FID 1.99 #48 of 94 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

Diffusion

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